WO2020047587A1 - System and method for sensor-based auto-calibration of soil-moisture levels - Google Patents
System and method for sensor-based auto-calibration of soil-moisture levels Download PDFInfo
- Publication number
- WO2020047587A1 WO2020047587A1 PCT/AU2019/050934 AU2019050934W WO2020047587A1 WO 2020047587 A1 WO2020047587 A1 WO 2020047587A1 AU 2019050934 W AU2019050934 W AU 2019050934W WO 2020047587 A1 WO2020047587 A1 WO 2020047587A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- soil
- soil moisture
- measurements
- moisture
- sensors
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 77
- 239000002689 soil Substances 0.000 claims abstract description 180
- 238000005259 measurement Methods 0.000 claims abstract description 54
- 238000010801 machine learning Methods 0.000 claims description 19
- 230000004044 response Effects 0.000 claims description 17
- 238000001035 drying Methods 0.000 claims description 9
- 238000010521 absorption reaction Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 3
- 238000002791 soaking Methods 0.000 claims description 3
- 238000003973 irrigation Methods 0.000 description 17
- 230000002262 irrigation Effects 0.000 description 17
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 8
- 238000012545 processing Methods 0.000 description 3
- 239000004927 clay Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000012010 growth Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 230000025508 response to water Effects 0.000 description 2
- 230000001932 seasonal effect Effects 0.000 description 2
- 238000006424 Flood reaction Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 238000005056 compaction Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000003673 groundwater Substances 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 230000002786 root growth Effects 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 239000005413 snowmelt Substances 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 230000005068 transpiration Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/24—Earth materials
- G01N33/246—Earth materials for water content
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01G—HORTICULTURE; CULTIVATION OF VEGETABLES, FLOWERS, RICE, FRUIT, VINES, HOPS OR SEAWEED; FORESTRY; WATERING
- A01G25/00—Watering gardens, fields, sports grounds or the like
- A01G25/16—Control of watering
- A01G25/167—Control by humidity of the soil itself or of devices simulating soil or of the atmosphere; Soil humidity sensors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N27/00—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means
- G01N27/02—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating impedance
- G01N27/04—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating impedance by investigating resistance
- G01N27/048—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating impedance by investigating resistance for determining moisture content of the material
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Definitions
- the present invention relates to monitoring of plant available water in agriculture.
- the present invention provides a method for soil moisture sensing including: determining, over a predetermined time period, a sequence of two or more soil moisture measurements from one or more sensors at one or more soil depths, the predetermined time period including one or more moisture uptake events in the soil and/or one or more moisture release events in the soil thereby determining a minimum soil moisture value and a maximum soil moisture value for the soil.
- minimum soil moisture value and a maximum soil moisture value are notional upper and lower values which may, for example correspond to“full point” and“refill point” or the like, depending on the application.
- one or more sensors are provided at one or more geographic locations defining a geographic area, thereby providing soil moisture sensing over the geographic area.
- the minimum soil moisture value is greater than or equal to a permanent wilting point (PWP).
- the maximum soil moisture value is preferably less than or equal to the field capacity of the soil.
- the predetermined time period further includes one or more of the following soil moisture response periods: an absorption below refill period (A); an absorption between refill and full period (B); a soaking/flooding period (C); a runoff period (D); a drying from wet period (E); a drying from dry period (F); or a drying below refill period (G).
- the method further includes the step of determining the rate of change of soil moisture over the predetermined time period.
- the method further includes the step of estimating which of the soil moisture response periods A-G applies to a given geographical location, at a given point in time.
- the method further includes the step of estimating the duration of time until the refill point will be reached, for one or more geographical areas.
- the method further includes the step of determining an estimate of soil moisture capacity at a geographical location based on the sequence of two or more soil moisture measurements.
- the one or more sensors may be of different type.
- the method further includes the step of using an external data source in combination with the sequence of two or more soil moisture measurements.
- the external data may include one or more of satellite data, or data from other sensors, data from existing soil models or the external data source may include for example soil moisture, rain or irrigation measurement, insolation, evapotranspiration, atmospheric moisture, wind speed, temperature and the like.
- the method further includes the step of determining the absence of, or error in the sequence of two or more measurements, at one or more depths at one or more time periods at a specific geographical location.
- the absence of, or error in one or more measurements is determined by one or more of: an error indication returned from the sensor; the sensor returning a physically implausible reading, the sensor returning a reading outside the defined measurement range of the sensor; or the sensor returning a reading inconsistent with other sensor readings proximate in soil depth, geographical location, or time.
- the method further includes the step of interpolating data in the absence of, or error in one or more measurements, at one or more depths at one or more time periods at a specific geographical location.
- the method further includes the step of determining a confidence metric of the one or more measurements at one more depths based on one or more earlier measurements. It will be appreciated that, based on the confidence metric, one or more measurements may be excluded.
- the method further includes the step of normalising the sensor soil moisture data to a nominal data range, using consistent units.
- the method further includes the step of normalising the recorded geographical location of each soil-moisture measurement to a nominal geographical location, using a specified geographical location system and datum based on a nominal geographical location.
- the method further includes the step of applying a low pass filter on the sensor soil moisture data, thereby removing variations at short time frames.
- the method further includes the step of progressively improving the accuracy of the minimum soil moisture value and the maximum soil moisture value by determining over a number of further predetermined time periods, a sequence of two or more soil moisture measurements from one or more sensors at one or more soil depths, the predetermined time period including one or more moisture uptake events in the soil and/or one or more moisture release events in the soil thereby determining a minimum soil moisture value and a maximum soil moisture value for the soil.
- the method further includes the step of recalibrating the one or more sensors, continuously or at intervals, in order to adapt to changes in soil moisture profile, thereby maintaining the accuracy of the minimum soil moisture value and the maximum soil moisture value.
- the present invention provides a system for soil moisture sensing including: one or more sensors and a controller in data communication with the one or more sensors, the controller configured to: determine, over a predetermined time period, a sequence of two or more soil moisture measurements from the one or more sensors at one or more soil depths, the predetermined time period including one or more moisture uptake events in the soil and/or one or more moisture release events in the soil thereby determining a minimum soil moisture value and a maximum soil moisture value for the soil.
- one or more machine-learning models are established and trained on one or more time sequences of soil moisture data labelled with features, including one or more of: features A to G, minimum soil moisture value, maximum soil moisture value, full point, refill point, such that the model attains a desired degree of accuracy and stability in estimating which soil-moisture response periods A to G applies at a given time, and/or estimating a minimal soil moisture value and/or a maximum soil moisture value for the soil.
- the one or more machine-learning models are used to estimate a minimal soil moisture value and/or a maximum soil moisture value for the soil based on a sequence of two or more soil moisture measurements from one or more sensors at one or more depths.
- the one or more machine-learning models are preferably used to estimate which of the soil moisture response features A to G applies to a given geographical location, at a given period of time.
- the one or more machine-learning models may take any form, and for example, a model may be provided to classify features (for example, A to G) and then feeds the output of that model (in addition to measured data, plus filtered data, plus gradient data and the like) into a further model, that ultimately calculates full and refill points.
- the one or more machine-learning models may be further used to estimate the duration of time until the refill point will be reached, for one or more geographical areas or soil moisture capacity at a geographical location based on the sequence of two or more soil moisture measurements.
- unsupervised machine learning may be used, continuously or periodically, to refine parameters of one or more of the machine learning models to improve a desired characteristic based on a sequence of soil moisture data measurements from one or more sensors at one or more depths in one or more geographical locations.
- the desired characteristic may include, but is not limited to, speed, accuracy, repeatability, stability and the like. It will further be appreciated that real-time operation, nor use of stored data is required and either could be used.
- Figure 1 is a schematic diagram illustrating the system and method of the present invention
- Figure 2 is a flow diagram illustrating the system and method of the present invention.
- Figure 3 is a chart illustrating the soil response to water
- Figure 4 is a chart illustrating the soil response to irrigation
- Figure 5 is a chart illustrating the soil response classification according to the system and method of the present invention.
- Figure 6 is a chart illustrating the soil response to irrigation utilising classification according to the system and method of the present invention. Detailed Description
- the system 100 of the present invention may run over a network 1 15 which includes one or more sensors 130A, 130B, 130C, 130D, 130E and 130F. It will be appreciated that any number of sensors may be provided over a geographical area.
- the calibration of the sensors and associated irrigation system may be controlled via one or more electronic devices 105, 110 and/or one or more controllers 120 which may be a server processing system, which may be connected to a database 125.
- the electronic devices include one or more mobile communication devices 105 and one or more personal computers (PCs) 1 10.
- the system 100 includes a networked controller 120 connected to a database 125.
- the electronic device 105, personal computer 110 and controller 120 are connected via a network 1 15 such as the internet or a mobile communications network.
- Sensors 130A, 130B, 130C, 130D, 130E and 130F may communicate with one another and then to the controller 120 to provide information regarding the soil moisture content. Communication between the sensors may take any suitable form such as via WiFi, Bluetooth and the like.
- the present invention utilises data from one or more soil moisture sensors 130A to 130F to determine the full point and refill points required for correct irrigation of crops.
- a full point is a preferred or intended target value, which may be a percentage of field capacity.
- Field capacity is an intrinsic characteristic of a particular soil system, based on soil type, topography, density and the like. Therefore, the full point may change depending on intended crop type and need not necessarily equal the field capacity. For example full point may be optimally slightly lower than field capacity in order to reduce irrigation, encourage root growth / robustness, reduce waste/run-off and the like.
- At field capacity which may be thought of as a saturation point, there is little/no oxygen in the soil and this is not a desirable state for the crop.
- refill point is, from the point of view of irrigation, the point at which crop damage/loss of growth potential is avoided but is likely higher than PWP (permanent wilting point).
- the present invention automatically determines the calibration of the full point (field capacity) and refill point of soil, through soil moisture sensing by one or more sensors 130A to 130F.
- the present invention also allows for dynamic adjustment (recalibration) of full point and refill points taking into account external factors such as soil compaction, changes in crop development, or long-term effects such as changing climate that change the moisture holding capacity of the soil.
- the present invention provides an automated approach which eliminates the requirement for manual calibration and recalibration in the field.
- calibration may be carried out on controller 120 so much of the complexity (typically provided in the sensors) is moved from the sensor hardware into the controller 120 accessible via network 115.
- this reduces the complexity of the sensors and thereby makes the overall design of the system more robust since there is no physical access required to the sensors 130A to 130F.
- the predetermined time period may be further broken down into smaller intervals also based on a water retention curve which will be further described with reference to Figures 4 to 6.
- the measurements at step 205 may be at multiple points along the sensor, that is to say, at multiple depths along the sensor in the soil or through the use of individual sensors at different depths. It will also be appreciated that the multiple sensors may be provided at geographically dispersed locations to provide soil moisture sensing over a geographic area.
- the system and method of the present invention via the controller 210 may then process a number of measurements from the sensors in particular speed of moisture uptake and moisture release, recording of the full points and refill points for irrigation purposes over a period of time, provide a correlation between the current measured soil moisture level and the time it takes to get to a full or refill point given a particular set of conditions.
- the validation may be compared against previous measurements and provided the value falls within a predetermined tolerance band, the measurement may be accepted.
- a further test at step 215 may be applied where the measurement is validated at multiple depths.
- the model may collect a sequence of measurements over a set time from the one or more sensors and generate a data set (i.e. sensor reading, time information and the like).
- a gradient may be calculated from a range of data from the data set and calculated gradients may be provided.
- the system and method of the present invention may determine based on a data set, the best full point and refill point for a particular scenario. Predictions may also be made based on historical information together with forecast predications as to how long it will take to reach a full point and a refill point.
- Collection of data may be frequent given that the sensors will be low power in that they are simple sensors not requiring significant processing power since the processing is carried out in the controller 120.
- data may be collected 24 hours a day, 7 days a week and 365 days a year which may allow for season by season comparison of data.
- the present invention can observe the effect of external factors on soil moisture uptake without the need for human intervention.
- the moisture uptake may change by soil type and may be influenced by crop water use, transpiration, temperature, wind, rainfall and irrigation, soil compression and/or geographical location-specific conditions.
- Figure 3 is a chart illustrating calibration of the moisture content in the soil in response to water over time.
- an optimal full point and refill point for the purposes of irrigation and this can depend on the type of soil. For example, there is a lower soil water capacity in sandy soil which results in a shorter period of time between a full point and a refill point compared to a clay soil where the difference between the full point and the refill point is greater (clay has a higher soil moisture capacity).
- the system and method of the present invention allows for optimisation of the calibration of important soil moisture levels in order to achieve an optimal full point and refill point for irrigation.
- Figure 4 is a chart illustrating a typical water retention curve which shows the level of moisture in the soil over time.
- the chart of Figure 4 illustrates the response of the soil to irrigation over time where typical data is returned from a soil moisture sensor is shown which was subjected to a major rain event and an extended drought.
- the chart in Figure 5 indicates an idealised“soil moisture response curve” that might occur on the occurrence of a water ingress event on very dry soil.
- a dry soil soil moisture below the refill level absorbs water (regions A and B) until it rises to the full point (saturation), where runoff (and gravitational drainage) occurs (region C, D). After region D, all gravitational water has been drained and the soil moisture curve falls again to the full point.
- the curve regions E and F represent the range of soil moisture in which plants are able to grow. Once soil moisture falls to the wilt point, crop growth ceases (although in practice it is likely above this point - depending on the crop). If soil moisture falls below the PWP, crops are unable to recover, even if supplied with adequate moisture.
- a soil moisture response curve is likely to be "noisy" in that it is not a smooth curve. Factors affecting this may include sensor accuracy, precision, measurement range and repeatability which varies by sensor type, and soil, and range of moisture measured.
- the soil moisture response curve may also be affected by: diurnal factors in that the curve differs between day and night; the fact it is not monotonic; it doesn't always fall smoothly or rise smoothly, because the inflow and outflow varies; Inflow is variable (primarily precipitation such as rain, snow, hail, frost, irrigation such as drip, spray, channelled, surface coverage and ground-water runoff events like floods, snowmelt).
- weather events are intermittent and of variable duration and intensity, delivering variable amounts of water on varying time-scales.
- Another issue with the soil moisture response curve is that outflow, primarily drainage and evapotranspiration, may change depending on hydrological pressure with change of water table; evapotranspiration changes with factors including transient weather events : wind, temperature, insolation, cloud cover, humidity, soil colour, crop presence, crop type, regrowth, leaf cover (seasonal), crop harvest, removal of nearby trees, and others.
- the soil moisture curve therefore doesn’t typically rise and fall smoothly, but varies over short timeframes (minutes to days) and trends up and down over longer timeframes (days to weeks), affected by many factors. To accommodate this variation, an error-tolerance or filtering on measurements received by the sensor may be applied.
- Each of the regions preferably corresponds to a predetermined time period upon which sensor readings are taken.
- one predetermined time period between the moisture uptake event and the moisture release event may be characterised as being between points A and G in the curve in Figure 5.
- the present invention utilises measurements of the sensors 130A to 130F at a number of points along the water retention curve and in particular between time periods including A) absorption from below the refill point, B) absorption between the refill point and full point, C) soaking and flooding, D) run off, E) drying from wet, F) drying from dry, G) drying below refill.
- These predetermined time periods may be for a particular soil category and may differ for a particular soil category and each of the time periods have a specific gradient between each other with an accepted tolerance level.
- the data returned from the sensors 130A to 130F are provided into the system and method of the present invention and measurements may be taken between time periods A through to G.
- the present invention may classify that sensor data as A, B, C, D, E, F or G.
- multi-year comparisons with the same crop type may allow measurement of the impact of climate change for example.
- the system and method of the present invention processes and captures and validates results from the sensors.
- the system and method of the present invention may further utilise statistical, algorithmic or machine-learning techniques (based on existing data or by building up its own library of data) such that the time-sequence of data which represents each period of“moisture uptake” can be identified, and the time-sequence of data which represents each period of “moisture release” can be identified corresponding to regions E and/or F of the idealised characteristic curve in Figure 5.
- the system and method of the present invention may be trained over time to determine an optimal“moisture release” based on regular sensor data over time (identifying seasonal changes and the like).
- the use of sensor readings from multiple sensors at multiple locations over a time period will be understood to enhance the machine learning aspects of the invention by providing a larger data store for training the system ultimately resulting in more accurate determination of “moisture release” for example, irrigation delivery.
- sensors are hardware agnostic and the system and method of the present invention may be provided with any particular type of sensor.
- Sensors may include, but are not limited to, capacitance-based soil moisture sensors, RF-based or TDR-based soil moisture sensors, neutron-probe (NP) detectors, or tensiometers.
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Pathology (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Biochemistry (AREA)
- Soil Sciences (AREA)
- Water Supply & Treatment (AREA)
- Environmental & Geological Engineering (AREA)
- Immunology (AREA)
- Geology (AREA)
- Remote Sensing (AREA)
- Environmental Sciences (AREA)
- Business, Economics & Management (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Analytical Chemistry (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Artificial Intelligence (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
Abstract
A method and system for soil moisture sensing is provided. The method and system includes determining, over a predetermined time period, a sequence of two or more soil moisture measurements from one or more sensors at one or more soil depths. The predetermined time period includes one or more moisture uptake events in the soil and/or one or more moisture release events in the soil to thereby determine a minimum soil moisture value and a maximum soil moisture value for the soil.
Description
SYSTEM AND METHOD FOR SENSOR-BASED AUTO-CALIBRATION OF SOIL-
MOISTURE LEVELS
Technical Field
[0001] The present invention relates to monitoring of plant available water in agriculture.
Background of Invention
[0002] When used in agriculture, data from a soil moisture sensor (or tensiometer) is analysed to determine the‘full’ and‘refill’ soil moisture levels required for optimal irrigation of crops. Historically, irrigation of crops informed by data from soil moisture sensors largely required manual calibration and recalibration of soil‘full’ and‘refill’ points over a period of time Typically an experienced individual is required to assess a sensor response to an irrigation or rain event and take note of full and refill points - essentially examining soil moisture data manually.
[0003] It would therefore be desirable to provide a system and method which alleviates or at least ameliorates one or more of the above problems.
[0004] The discussion of the background to the invention included herein including reference to documents, acts, materials, devices, articles and the like is included to explain the context of the present invention. This is not to be taken as an admission or a suggestion that any of the material referred to was published, known or part of the common general knowledge in Australia or in any other country as at the priority date of any of the claims.
Summary of Invention
[0005] According to a first aspect, the present invention provides a method for soil moisture sensing including: determining, over a predetermined time period, a sequence of two or more soil moisture measurements from one or more sensors at one or more soil depths, the predetermined time period including one or more moisture uptake events in the soil and/or one or more moisture release events in the soil thereby determining a minimum soil moisture value and a maximum soil moisture value for the soil.
[0006] It will be appreciated that minimum soil moisture value and a maximum soil moisture value are notional upper and lower values which may, for example correspond to“full point” and“refill point” or the like, depending on the application.
[0007] Preferably, one or more sensors are provided at one or more geographic locations defining a geographic area, thereby providing soil moisture sensing over the geographic area.
[0008] Preferably, the minimum soil moisture value is greater than or equal to a permanent wilting point (PWP). The maximum soil moisture value is preferably less than or equal to the field capacity of the soil. [0009] The predetermined time period further includes one or more of the following soil moisture response periods: an absorption below refill period (A); an absorption between refill and full period (B); a soaking/flooding period (C); a runoff period (D); a drying from wet period (E); a drying from dry period (F); or a drying below refill period (G). [0010] Preferably the method further includes the step of determining the rate of change of soil moisture over the predetermined time period.
[0011] Preferably the method further includes the step of estimating which of the soil moisture response periods A-G applies to a given geographical location, at a given point in time. [0012] Preferably the method further includes the step of estimating the duration of time until the refill point will be reached, for one or more geographical areas.
[0013] Preferably the method further includes the step of determining an estimate of soil moisture capacity at a geographical location based on the sequence of two or more soil moisture measurements. [0014] It will be appreciated that the one or more sensors may be of different type.
[0015] Preferably the method further includes the step of using an external data source in combination with the sequence of two or more soil moisture measurements. The external data may include one or more of satellite data, or data from other sensors, data from existing soil models or the external data source may include for
example soil moisture, rain or irrigation measurement, insolation, evapotranspiration, atmospheric moisture, wind speed, temperature and the like.
[0016] Preferably the method further includes the step of determining the absence of, or error in the sequence of two or more measurements, at one or more depths at one or more time periods at a specific geographical location. The absence of, or error in one or more measurements is determined by one or more of: an error indication returned from the sensor; the sensor returning a physically implausible reading, the sensor returning a reading outside the defined measurement range of the sensor; or the sensor returning a reading inconsistent with other sensor readings proximate in soil depth, geographical location, or time.
[0017] Preferably the method further includes the step of identifying the absence of, or error in one or more measurements, at one or more depths at one or more time periods at a specific geographical location.
[0018] Preferably the method further includes the step of interpolating data in the absence of, or error in one or more measurements, at one or more depths at one or more time periods at a specific geographical location.
[0019] Preferably the method further includes the step of determining a confidence metric of the one or more measurements at one more depths based on one or more earlier measurements. It will be appreciated that, based on the confidence metric, one or more measurements may be excluded.
[0020] Preferably the method further includes the step of normalising the sensor soil moisture data to a nominal data range, using consistent units. Preferably the method further includes the step of normalising the recorded geographical location of each soil-moisture measurement to a nominal geographical location, using a specified geographical location system and datum based on a nominal geographical location.
[0021] Preferably the method further includes the step of applying a low pass filter on the sensor soil moisture data, thereby removing variations at short time frames.
[0022] Preferably the method further includes the step of progressively improving the accuracy of the minimum soil moisture value and the maximum soil moisture value by determining over a number of further predetermined time periods, a
sequence of two or more soil moisture measurements from one or more sensors at one or more soil depths, the predetermined time period including one or more moisture uptake events in the soil and/or one or more moisture release events in the soil thereby determining a minimum soil moisture value and a maximum soil moisture value for the soil.
[0023] Preferably the method further includes the step of recalibrating the one or more sensors, continuously or at intervals, in order to adapt to changes in soil moisture profile, thereby maintaining the accuracy of the minimum soil moisture value and the maximum soil moisture value.
[0024] According to a second aspect the present invention provides a system for soil moisture sensing including: one or more sensors and a controller in data communication with the one or more sensors, the controller configured to: determine, over a predetermined time period, a sequence of two or more soil moisture measurements from the one or more sensors at one or more soil depths, the predetermined time period including one or more moisture uptake events in the soil and/or one or more moisture release events in the soil thereby determining a minimum soil moisture value and a maximum soil moisture value for the soil.
[0025] Preferably, in accordance with the first aspect of the invention, one or more machine-learning models are established and trained on one or more time sequences of soil moisture data labelled with features, including one or more of: features A to G, minimum soil moisture value, maximum soil moisture value, full point, refill point, such that the model attains a desired degree of accuracy and stability in estimating which soil-moisture response periods A to G applies at a given time, and/or estimating a minimal soil moisture value and/or a maximum soil moisture value for the soil.
[0026] Preferably, the one or more machine-learning models are used to estimate a minimal soil moisture value and/or a maximum soil moisture value for the soil based on a sequence of two or more soil moisture measurements from one or more sensors at one or more depths. The one or more machine-learning models are preferably used to estimate which of the soil moisture response features A to G applies to a given geographical location, at a given period of time.
[0027] The one or more machine-learning models may take any form, and for example, a model may be provided to classify features (for example, A to G) and then feeds the output of that model (in addition to measured data, plus filtered data, plus gradient data and the like) into a further model, that ultimately calculates full and refill points.
[0028] The one or more machine-learning models may be further used to estimate the duration of time until the refill point will be reached, for one or more geographical areas or soil moisture capacity at a geographical location based on the sequence of two or more soil moisture measurements. [0029] In an embodiment, unsupervised machine learning may be used, continuously or periodically, to refine parameters of one or more of the machine learning models to improve a desired characteristic based on a sequence of soil moisture data measurements from one or more sensors at one or more depths in one or more geographical locations. [0030] It will be appreciated that the desired characteristic may include, but is not limited to, speed, accuracy, repeatability, stability and the like. It will further be appreciated that real-time operation, nor use of stored data is required and either could be used.
[0031] Preferably, the unsupervised machine learning may be used, continuously or periodically, to improve the accuracy of classification of soil moisture measurements into features A to G or to improve the accuracy of estimation of maximum and/or minimum soil moisture values and/or full point and/or refill point.
Brief Description of Drawings
[0032] Figure 1 is a schematic diagram illustrating the system and method of the present invention;
[0033] Figure 2 is a flow diagram illustrating the system and method of the present invention;
[0034] Figure 3 is a chart illustrating the soil response to water;
[0035] Figure 4 is a chart illustrating the soil response to irrigation;
[0036] Figure 5 is a chart illustrating the soil response classification according to the system and method of the present invention; and
[0037] Figure 6 is a chart illustrating the soil response to irrigation utilising classification according to the system and method of the present invention. Detailed Description
[0038] The system 100 of the present invention may run over a network 1 15 which includes one or more sensors 130A, 130B, 130C, 130D, 130E and 130F. It will be appreciated that any number of sensors may be provided over a geographical area. The calibration of the sensors and associated irrigation system (not shown) may be controlled via one or more electronic devices 105, 110 and/or one or more controllers 120 which may be a server processing system, which may be connected to a database 125. In this example, the electronic devices include one or more mobile communication devices 105 and one or more personal computers (PCs) 1 10. The system 100 includes a networked controller 120 connected to a database 125. [0039] The electronic device 105, personal computer 110 and controller 120 are connected via a network 1 15 such as the internet or a mobile communications network.
[0040] Sensors 130A, 130B, 130C, 130D, 130E and 130F may communicate with one another and then to the controller 120 to provide information regarding the soil moisture content. Communication between the sensors may take any suitable form such as via WiFi, Bluetooth and the like.
[0041] The present invention utilises data from one or more soil moisture sensors 130A to 130F to determine the full point and refill points required for correct irrigation of crops. A full point is a preferred or intended target value, which may be a percentage of field capacity. Field capacity is an intrinsic characteristic of a particular soil system, based on soil type, topography, density and the like. Therefore, the full point may change depending on intended crop type and need not necessarily equal the field capacity. For example full point may be optimally slightly lower than field capacity in order to reduce irrigation, encourage root growth / robustness, reduce
waste/run-off and the like. At field capacity, which may be thought of as a saturation point, there is little/no oxygen in the soil and this is not a desirable state for the crop.
[0042] Similarly, refill point is, from the point of view of irrigation, the point at which crop damage/loss of growth potential is avoided but is likely higher than PWP (permanent wilting point).
[0043] The present invention automatically determines the calibration of the full point (field capacity) and refill point of soil, through soil moisture sensing by one or more sensors 130A to 130F. The present invention also allows for dynamic adjustment (recalibration) of full point and refill points taking into account external factors such as soil compaction, changes in crop development, or long-term effects such as changing climate that change the moisture holding capacity of the soil.
[0044] Advantageously the present invention provides an automated approach which eliminates the requirement for manual calibration and recalibration in the field. In a further advantage, calibration may be carried out on controller 120 so much of the complexity (typically provided in the sensors) is moved from the sensor hardware into the controller 120 accessible via network 115. Advantageously this reduces the complexity of the sensors and thereby makes the overall design of the system more robust since there is no physical access required to the sensors 130A to 130F.
[0045] The method of the present invention may be carried out via a method 200 illustrated in Figure 2, where at step 205 measurement values are taken from the one or more sensors 130A to 130F. The data collected from the sensors may be analysed over time and in particular measurements are taken over a predetermined time period. The predetermined time period may be including one or more moisture uptake events and one or more moisture release events. The moisture uptake event and moisture release events may be modelled on a water retention curve.
[0046] Further, the predetermined time period may be further broken down into smaller intervals also based on a water retention curve which will be further described with reference to Figures 4 to 6.
[0047] The measurements at step 205 may be at multiple points along the sensor, that is to say, at multiple depths along the sensor in the soil or through the use of
individual sensors at different depths. It will also be appreciated that the multiple sensors may be provided at geographically dispersed locations to provide soil moisture sensing over a geographic area. The system and method of the present invention via the controller 210 may then process a number of measurements from the sensors in particular speed of moisture uptake and moisture release, recording of the full points and refill points for irrigation purposes over a period of time, provide a correlation between the current measured soil moisture level and the time it takes to get to a full or refill point given a particular set of conditions.
[0048] Once the measurements have been taken at step 205, control then moves to step 210 in which the measurements made by the sensors 130A to 130F are validated. The validation may be compared against previous measurements and provided the value falls within a predetermined tolerance band, the measurement may be accepted. A further test at step 215 may be applied where the measurement is validated at multiple depths.
[0049] Control then moves to step 220 where the validated data set may be provided to an auto calibration model. The model may collect a sequence of measurements over a set time from the one or more sensors and generate a data set (i.e. sensor reading, time information and the like). As will be described further with reference to Figures 4 to 6, a gradient may be calculated from a range of data from the data set and calculated gradients may be provided.
[0050] As more measurements are carried out on the system more data is provided and more gradients are provided. The gradients then may be grouped into different characteristics as will be described further with reference to Figures 4 to 6.
[0051] As a result the system and method of the present invention may determine based on a data set, the best full point and refill point for a particular scenario. Predictions may also be made based on historical information together with forecast predications as to how long it will take to reach a full point and a refill point.
[0052] Collection of data may be frequent given that the sensors will be low power in that they are simple sensors not requiring significant processing power since the processing is carried out in the controller 120. For example, data may be collected 24 hours a day, 7 days a week and 365 days a year which may allow for season by
season comparison of data. Advantageously, the present invention can observe the effect of external factors on soil moisture uptake without the need for human intervention. For example, the moisture uptake may change by soil type and may be influenced by crop water use, transpiration, temperature, wind, rainfall and irrigation, soil compression and/or geographical location-specific conditions.
[0053] Figure 3 is a chart illustrating calibration of the moisture content in the soil in response to water over time. As can be seen there is an optimal full point and refill point for the purposes of irrigation and this can depend on the type of soil. For example, there is a lower soil water capacity in sandy soil which results in a shorter period of time between a full point and a refill point compared to a clay soil where the difference between the full point and the refill point is greater (clay has a higher soil moisture capacity). The system and method of the present invention allows for optimisation of the calibration of important soil moisture levels in order to achieve an optimal full point and refill point for irrigation.
[0054] Figure 4 is a chart illustrating a typical water retention curve which shows the level of moisture in the soil over time. For example the chart of Figure 4 illustrates the response of the soil to irrigation over time where typical data is returned from a soil moisture sensor is shown which was subjected to a major rain event and an extended drought.
[0055] As shown in Figure 5 there are a number of components of the water retention curve which the present invention exploits to provide predetermined time periods between moisture uptake events and moisture release events in the soil.
[0058] It will be appreciated that the chart in Figure 5 indicates an idealised“soil moisture response curve” that might occur on the occurrence of a water ingress event on very dry soil. A dry soil (soil moisture below the refill level) absorbs water (regions A and B) until it rises to the full point (saturation), where runoff (and gravitational drainage) occurs (region C, D). After region D, all gravitational water has been drained and the soil moisture curve falls again to the full point. The curve regions E and F represent the range of soil moisture in which plants are able to grow. Once soil moisture falls to the wilt point, crop growth ceases (although in practice it is likely
above this point - depending on the crop). If soil moisture falls below the PWP, crops are unable to recover, even if supplied with adequate moisture.
[0057] It will also be appreciated that a soil moisture response curve is likely to be "noisy" in that it is not a smooth curve. Factors affecting this may include sensor accuracy, precision, measurement range and repeatability which varies by sensor type, and soil, and range of moisture measured. The soil moisture response curve may also be affected by: diurnal factors in that the curve differs between day and night; the fact it is not monotonic; it doesn't always fall smoothly or rise smoothly, because the inflow and outflow varies; Inflow is variable (primarily precipitation such as rain, snow, hail, frost, irrigation such as drip, spray, channelled, surface coverage and ground-water runoff events like floods, snowmelt). Another issue is that weather events are intermittent and of variable duration and intensity, delivering variable amounts of water on varying time-scales. Another issue with the soil moisture response curve is that outflow, primarily drainage and evapotranspi ration, may change depending on hydrological pressure with change of water table; evapotranspiration changes with factors including transient weather events : wind, temperature, insolation, cloud cover, humidity, soil colour, crop presence, crop type, regrowth, leaf cover (seasonal), crop harvest, removal of nearby trees, and others.
[0058] The soil moisture curve therefore doesn’t typically rise and fall smoothly, but varies over short timeframes (minutes to days) and trends up and down over longer timeframes (days to weeks), affected by many factors. To accommodate this variation, an error-tolerance or filtering on measurements received by the sensor may be applied.
[0059] Each of the regions preferably corresponds to a predetermined time period upon which sensor readings are taken. For example, one predetermined time period between the moisture uptake event and the moisture release event may be characterised as being between points A and G in the curve in Figure 5. The present invention utilises measurements of the sensors 130A to 130F at a number of points along the water retention curve and in particular between time periods including A) absorption from below the refill point, B) absorption between the refill point and full point, C) soaking and flooding, D) run off, E) drying from wet, F) drying from dry, G) drying below refill.
[0060] These predetermined time periods may be for a particular soil category and may differ for a particular soil category and each of the time periods have a specific gradient between each other with an accepted tolerance level.
[0061] As shown in Figure 6, the data returned from the sensors 130A to 130F are provided into the system and method of the present invention and measurements may be taken between time periods A through to G. The present invention may classify that sensor data as A, B, C, D, E, F or G.
[0062] In a further example, multi-year comparisons with the same crop type may allow measurement of the impact of climate change for example.
[0063] The system and method of the present invention processes and captures and validates results from the sensors.
[0064] The system and method of the present invention may further utilise statistical, algorithmic or machine-learning techniques (based on existing data or by building up its own library of data) such that the time-sequence of data which represents each period of“moisture uptake” can be identified, and the time-sequence of data which represents each period of “moisture release” can be identified corresponding to regions E and/or F of the idealised characteristic curve in Figure 5.
[0065] The system and method of the present invention may be trained over time to determine an optimal“moisture release” based on regular sensor data over time (identifying seasonal changes and the like). The use of sensor readings from multiple sensors at multiple locations over a time period will be understood to enhance the machine learning aspects of the invention by providing a larger data store for training the system ultimately resulting in more accurate determination of “moisture release” for example, irrigation delivery.
[0066] Finally, it will be appreciated that the sensors are hardware agnostic and the system and method of the present invention may be provided with any particular type of sensor. Sensors may include, but are not limited to, capacitance-based soil moisture sensors, RF-based or TDR-based soil moisture sensors, neutron-probe (NP) detectors, or tensiometers.
Claims
1. A method for soil moisture sensing including: determining, over a predetermined time period, a sequence of two or more soil moisture measurements from one or more sensors at one or more soil depths, the predetermined time period including one or more moisture uptake events in the soil and/or one or more moisture release events in the soil thereby determining a minimum soil moisture value and a maximum soil moisture value for the soil.
2. The method of claim 1 , wherein one or more sensors are provided at one or more geographic locations defining a geographic area, thereby providing soil moisture sensing over the geographic area.
3. The method of claim 1 , wherein the minimum soil moisture value is greater than or equal to a permanent wilting point (PWP).
4. The method of claim 1 , wherein the maximum soil moisture value is less than or equal to the field capacity of the soil.
5. The method of claim 1 , wherein the predetermined time period further includes one or more of the following soil moisture response periods:
an absorption below refill period (A);
an absorption between refill and full period (B);
a soaking/flooding period (C);
a runoff period (D);
a drying from wet period (E);
a drying from dry period (F); or
a drying below refill period (G).
6. The method of any one of the preceding claims, further including the step of determining the rate of change of soil moisture over the predetermined time period.
7. The method of claim 5, wherein the method further includes the step of: estimating which of the soil moisture response periods A-G applies to a given geographical location, at a given point in time.
8. The method of claim 7, further including the step of estimating the duration of time until the refill point will be reached, for one or more geographical areas.
9. The method of any one of the preceding claims, further including the step of determining an estimate of soil moisture capacity at a geographical location based on the sequence of two or more soil moisture measurements.
10. The method of any one of the preceding claims, wherein the one or more sensors are of different type.
1 1. The method of any one of the preceding claims, further including the step of using an external data source in combination with the sequence of two or more soil moisture measurements.
12. The method of claim 1 1 , wherein the external data includes one or more of satellite data, or data from other sensors, data from existing soil models.
13. The method of any one of the preceding claims, further including the step of determining the absence of, or error in the sequence of two or more measurements, at one or more depths at one or more time periods at a specific geographical location.
14. The method of claim 13, wherein the absence of, or error in the sequence of two or more measurements is determined by one or more of: an error indication returned from the sensor; the sensor returning a physically implausible reading, the sensor returning a reading outside the defined measurement range of the sensor; or the sensor returning a reading inconsistent with other sensor readings proximate in soil depth, geographical location, or time.
15. The method of claim 13, wherein the method further includes the step of identifying the absence of, or error in the one or more measurements, at one or more depths at one or more time periods at a specific geographical location.
16. The method of claim 13, wherein the method further includes the step of interpolating data in the absence of, or error in the one or more measurements,
at one or more depths at one or more time periods at a specific geographical location.
17. The method of claim 13, wherein the method further includes the step of determining a confidence metric of the one or more measurements at one more depths based on one or more earlier measurements.
18. The method of claim 17, wherein, based on the confidence metric, one or more measurements are excluded.
19. The method of claim 1 , wherein the method further includes the step of normalising the sensor soil moisture data to a nominal data range, using consistent units.
20. The method of claim 1 , wherein the method further includes the step of normalising the recorded geographical location of each soil-moisture measurement to a nominal geographical location, using a specified geographical location system and datum based on a nominal geographical location.
21. The method of claim 1 , wherein the method further includes the step of applying a low pass filter on the sensor soil moisture data, thereby removing variations at short time frames.
22. The method of claim 1 , wherein the method further includes the step of progressively improving the accuracy of the minimum soil moisture value and the maximum soil moisture value by determining over a number of further predetermined time periods, a sequence of two or more soil moisture measurements from one or more sensors at one or more soil depths, the predetermined time period including one or more moisture uptake events in the soil and/or one or more moisture release events in the soil thereby determining a minimum soil moisture value and a maximum soil moisture value for the soil.
23. The method of claim 1 , wherein the method further includes the step of recalibrating the one or more sensors, continuously or at intervals, in order to adapt to changes in soil moisture profile, thereby maintaining the accuracy of the minimum soil moisture value and the maximum soil moisture value.
24. A system for soil moisture sensing including:
one or more sensors and a controller in data communication with the one or more sensors, the controller configured to:
determine, over a predetermined time period, a sequence of two or more soil moisture measurements from the one or more sensors at one or more soil depths, the predetermined time period including one or more moisture uptake events in the soil and/or one or more moisture release events in the soil thereby determining a minimum soil moisture value and a maximum soil moisture value for the soil.
25. The method of Claim 1 , wherein one or more machine-learning models are established and trained on one or more time sequences of soil moisture data labelled with features, including one or more of: (features A to G), minimum soil moisture value, maximum soil moisture value, full point, refill point, such that the model attains a desired degree of accuracy and stability in estimating which soil-moisture response periods A to G applies at a given time, and/or estimating a minimal soil moisture value and/or a maximum soil moisture value for the soil.
26. The method of claim 25, wherein one or more machine-learning models are used to estimate a minimal soil moisture value and/or a maximum soil moisture value for the soil based on a sequence of two or more soil moisture measurements from one or more sensors at one or more depths.
27. The method of claim 25 or 26, wherein one or more machine-learning models are used to estimate which of the soil moisture response features A to G applies to a given geographical location, at a given period of time.
28. The method of any one of claims 25 to 27, wherein one or more machine learning models are used to estimate the duration of time until the refill point will be reached, for one or more geographical areas.
29. The method of any one of claims 25 to 28, wherein one or more machine learning models are used to estimate soil moisture capacity at a geographical location based on the sequence of two or more soil moisture measurements.
30. The method of any one of claims 25 to 29, wherein unsupervised machine learning is used, continuously or periodically, to refine parameters of one or more of the machine learning models to improve a desired characteristic based on a sequence of soil moisture data measurements from one or more sensors at one or more depths in one or more geographical locations.
31. The method of claim 30, wherein unsupervised machine learning is used, continuously or periodically, to improve the accuracy of classification of soil moisture measurements into features A to G.
32. The method of claim 30, wherein unsupervised machine learning is used, continuously or periodically, to improve the accuracy of estimation of maximum and/or minimum soil moisture values and/or full point and/or refill point.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2018903282 | 2018-09-04 | ||
AU2018903282A AU2018903282A0 (en) | 2018-09-04 | System and method for sensor-based auto-calibration of soil moisture levels |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2020047587A1 true WO2020047587A1 (en) | 2020-03-12 |
Family
ID=69721506
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/AU2019/050934 WO2020047587A1 (en) | 2018-09-04 | 2019-09-03 | System and method for sensor-based auto-calibration of soil-moisture levels |
Country Status (1)
Country | Link |
---|---|
WO (1) | WO2020047587A1 (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2022125900A1 (en) * | 2020-12-10 | 2022-06-16 | Semiosbio Technologies Inc. | Method for managing crop irrigation, and system using same |
WO2022251973A1 (en) * | 2021-06-04 | 2022-12-08 | Groupe Ramo Inc. | Controlled irrigation process and system for land application of wastewater |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7203576B1 (en) * | 2004-02-09 | 2007-04-10 | Orbit Irrigation Products, Inc. | Moisture sensor timer |
US8340910B1 (en) * | 2009-02-02 | 2012-12-25 | Green Badge LLC | Method and system for monitoring soil and water resources |
US8862277B1 (en) * | 2010-02-01 | 2014-10-14 | Green Badge, LLC | Automatic efficient irrigation threshold setting |
US20170020091A1 (en) * | 2015-07-20 | 2017-01-26 | AquaSpy, Inc. | Method and System for Automated Data Analysis of Soil Moisture |
US20170311559A1 (en) * | 2014-10-31 | 2017-11-02 | Purdue Research Foundation | Moisture management & perennial crop sustainability decision system |
US20180129175A1 (en) * | 2016-11-07 | 2018-05-10 | FarmX Inc. | Systems and Methods for Soil Modeling and Automatic Irrigation Control |
WO2018107245A1 (en) * | 2016-12-16 | 2018-06-21 | The Crown In The Right Of The State Of New South Wales Acting Through The Department Of Primary Industries, An Office Of The Nsw Department Of Industry, Skills And Regional Development | Detection of environmental conditions |
AU2018200711A1 (en) * | 2017-02-01 | 2018-08-16 | Julius Industrial & Scientific Pty Ltd | Method for measurement of subterranean soil characteristics for water management purposes |
-
2019
- 2019-09-03 WO PCT/AU2019/050934 patent/WO2020047587A1/en active Application Filing
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7203576B1 (en) * | 2004-02-09 | 2007-04-10 | Orbit Irrigation Products, Inc. | Moisture sensor timer |
US8340910B1 (en) * | 2009-02-02 | 2012-12-25 | Green Badge LLC | Method and system for monitoring soil and water resources |
US8862277B1 (en) * | 2010-02-01 | 2014-10-14 | Green Badge, LLC | Automatic efficient irrigation threshold setting |
US20170311559A1 (en) * | 2014-10-31 | 2017-11-02 | Purdue Research Foundation | Moisture management & perennial crop sustainability decision system |
US20170020091A1 (en) * | 2015-07-20 | 2017-01-26 | AquaSpy, Inc. | Method and System for Automated Data Analysis of Soil Moisture |
US20180129175A1 (en) * | 2016-11-07 | 2018-05-10 | FarmX Inc. | Systems and Methods for Soil Modeling and Automatic Irrigation Control |
WO2018107245A1 (en) * | 2016-12-16 | 2018-06-21 | The Crown In The Right Of The State Of New South Wales Acting Through The Department Of Primary Industries, An Office Of The Nsw Department Of Industry, Skills And Regional Development | Detection of environmental conditions |
AU2018200711A1 (en) * | 2017-02-01 | 2018-08-16 | Julius Industrial & Scientific Pty Ltd | Method for measurement of subterranean soil characteristics for water management purposes |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2022125900A1 (en) * | 2020-12-10 | 2022-06-16 | Semiosbio Technologies Inc. | Method for managing crop irrigation, and system using same |
US12029174B2 (en) | 2020-12-10 | 2024-07-09 | Semiosbio Technologies Inc. | Method for managing crop irrigation, and system using same |
WO2022251973A1 (en) * | 2021-06-04 | 2022-12-08 | Groupe Ramo Inc. | Controlled irrigation process and system for land application of wastewater |
US11856901B2 (en) | 2021-06-04 | 2024-01-02 | Groupe Ramo Inc. | Controlled irrigation process and system for land application of wastewater |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3179319B1 (en) | Method for irrigation planning and system for its implementation | |
US11310970B2 (en) | Method of determination of water stress in a one or more plants in a crop located in the vicinity of a soil moisture sensor array and knowledge of ETo | |
US11985925B2 (en) | Method of determination of water stress in a one or more plants in a crop located in the region of a soil moisture sensor array and knowledge of ETo | |
Thompson et al. | Determination of lower limits for irrigation management using in situ assessments of apparent crop water uptake made with volumetric soil water content sensors | |
Amatya et al. | Hydrologic modeling of a drained pine plantation on poorly drained soils | |
WO2017106962A1 (en) | System and method for real-time water management | |
Abrisqueta et al. | Soil water content criteria for peach trees water stress detection during the postharvest period | |
CN111461909A (en) | Short-term prediction method for farmland evapotranspiration | |
McCarthy et al. | Experimental determination of the hydrologic components of a drained forest watershed | |
Segovia-Cardozo et al. | Detecting crop water requirement indicators in irrigated agroecosystems from soil water content profiles: An application for a citrus orchard | |
WO2020047587A1 (en) | System and method for sensor-based auto-calibration of soil-moisture levels | |
Parry et al. | Comparison of a stand-alone surface renewal method to weighing lysimetry and eddy covariance for determining vineyard evapotranspiration and vine water stress | |
Li et al. | Quantification of soil water balance components based on continuous soil moisture measurement and the Richards equation in an irrigated agricultural field of a desert oasis | |
CN114365682B (en) | Method and device for predicting soil moisture of facility cultivation and electronic equipment | |
WO2022040756A1 (en) | Refill point or target deficit for crop irrigation | |
US11805740B2 (en) | Systems and methods for monitoring and controlling crop irrigation schedules | |
JP4006098B2 (en) | Paddy field water management system, paddy field water management method, and computer-readable medium recording a program for water management of paddy field group | |
Balbis et al. | Dynamic model of soil moisture for smart irrigation systems | |
CN110432046B (en) | Intelligent irrigation system in greenhouse | |
Knox et al. | Estimating evapotranspiration by using atmometers for irrigation scheduling in a humid environment | |
CN110596345A (en) | Computing method for drought and waterlogging sharp turning standard | |
Soderquist et al. | Simulating the dependence of aspen (Populus tremuloides) on redistributed snow in a semi‐arid watershed | |
Jin et al. | Evapotranspiration of xerophytic shrub Salsola passerina and Reaumuria soongorica in an arid desert ecosystem of NW China | |
Raoof et al. | Reference Evapotranspiration Estimation Using Locally Adjusted Coefficient of Angstrom’s Radiation Model in an Arid-Cold Region | |
Mahmud et al. | Performance evaluation of class a pan coefficient models to estimate reference evapotranspiration in Mymensingh region of Bangladesh. |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 19857553 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 19857553 Country of ref document: EP Kind code of ref document: A1 |