CN117974348A - Wisdom agricultural thing networking monitoring system - Google Patents
Wisdom agricultural thing networking monitoring system Download PDFInfo
- Publication number
- CN117974348A CN117974348A CN202410384776.1A CN202410384776A CN117974348A CN 117974348 A CN117974348 A CN 117974348A CN 202410384776 A CN202410384776 A CN 202410384776A CN 117974348 A CN117974348 A CN 117974348A
- Authority
- CN
- China
- Prior art keywords
- model
- factors
- crop growth
- growth condition
- crops
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 24
- 230000006855 networking Effects 0.000 title claims description 3
- 230000004044 response Effects 0.000 claims abstract description 43
- 238000004458 analytical method Methods 0.000 claims abstract description 34
- 238000000034 method Methods 0.000 claims abstract description 18
- 239000000654 additive Substances 0.000 claims abstract description 17
- 230000000996 additive effect Effects 0.000 claims abstract description 17
- 238000012360 testing method Methods 0.000 claims description 19
- 230000003993 interaction Effects 0.000 claims description 18
- 201000010099 disease Diseases 0.000 claims description 15
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 15
- 239000002689 soil Substances 0.000 claims description 12
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 claims description 10
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 9
- 238000003973 irrigation Methods 0.000 claims description 8
- 230000002262 irrigation Effects 0.000 claims description 8
- 241000607479 Yersinia pestis Species 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 7
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 229910002092 carbon dioxide Inorganic materials 0.000 claims description 5
- 239000001569 carbon dioxide Substances 0.000 claims description 5
- 238000005286 illumination Methods 0.000 claims description 5
- 229930002875 chlorophyll Natural products 0.000 claims description 3
- 235000019804 chlorophyll Nutrition 0.000 claims description 3
- ATNHDLDRLWWWCB-AENOIHSZSA-M chlorophyll a Chemical compound C1([C@@H](C(=O)OC)C(=O)C2=C3C)=C2N2C3=CC(C(CC)=C3C)=[N+]4C3=CC3=C(C=C)C(C)=C5N3[Mg-2]42[N+]2=C1[C@@H](CCC(=O)OC\C=C(/C)CCC[C@H](C)CCC[C@H](C)CCCC(C)C)[C@H](C)C2=C5 ATNHDLDRLWWWCB-AENOIHSZSA-M 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims description 3
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims description 3
- 238000010187 selection method Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims description 2
- 230000000694 effects Effects 0.000 description 7
- 230000008859 change Effects 0.000 description 4
- 238000009499 grossing Methods 0.000 description 4
- 239000003621 irrigation water Substances 0.000 description 4
- 241000238631 Hexapoda Species 0.000 description 3
- 238000012271 agricultural production Methods 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 3
- 230000002452 interceptive effect Effects 0.000 description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000002301 combined effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000000611 regression analysis Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 241000894006 Bacteria Species 0.000 description 1
- 241000233866 Fungi Species 0.000 description 1
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 1
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 230000035558 fertility Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 229910001385 heavy metal Inorganic materials 0.000 description 1
- 230000009916 joint effect Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 239000005416 organic matter Substances 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 229910052698 phosphorus Inorganic materials 0.000 description 1
- 239000011574 phosphorus Substances 0.000 description 1
- 230000029553 photosynthesis Effects 0.000 description 1
- 238000010672 photosynthesis Methods 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
- 229910052700 potassium Inorganic materials 0.000 description 1
- 239000011591 potassium Substances 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 235000013619 trace mineral Nutrition 0.000 description 1
- 239000011573 trace mineral Substances 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an intelligent agriculture internet of things monitoring system, which collects influence factor data of crops in a historical period and corresponding crop growth condition data thereof; the method comprises the steps of taking influence factor data as an interpretation variable and crop growth condition data as a response variable, and constructing a redundancy analysis model to identify key influence factors; the key influence factors are taken as interpretation variables, crop growth condition data are taken as response variables, and a generalized additive model is constructed to quantify the response relation between the key influence factors and the crop growth conditions; and finally, inputting the real-time monitored influence factor data into a generalized additive model to predict the growth condition of crops, and adjusting and supervising the influence factors of the crops by combining the expected growth condition of the crops. The invention solves the problem that the influence factors are difficult to effectively monitor and manage according to the preference of crops because the response of the crops to the influence factors influencing the growth is unknown.
Description
Technical Field
The invention belongs to the technical field of agricultural Internet of things, and relates to an intelligent agricultural Internet of things monitoring system.
Background
In the world today, rapid development of technology has profoundly affected industries, and the agricultural field is no exception. With the continuous existence of challenges such as population growth and resource shortage, the traditional agricultural method faces a plurality of problems including resource waste, environmental pollution, and increased labor cost. In order to solve the problems, intelligent agriculture is gradually rising, and new vitality is injected into agricultural production by means of advanced technologies such as Internet of things, big data analysis and artificial intelligence. The intelligent agriculture provides more accurate agricultural production guidance for farmers through real-time monitoring and management of farmland environment and crop growth conditions.
At present, most of intelligent agriculture is used for monitoring influencing factors influencing crop growth, including weather, soil physicochemical indexes, water quality, plant diseases and insect pests, irrigation and the like. However, since the response of crops to influencing factors that influence their growth is unknown, it is difficult to effectively monitor and manage the influencing factors according to the preferences of crops.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides an intelligent agriculture Internet of things monitoring system.
The aim of the invention can be achieved by the following technical scheme:
The application provides an intelligent agriculture internet of things monitoring system, which comprises an information acquisition module, an information analysis module and an information decision module, wherein the information acquisition module, the information analysis module and the information decision module are in communication connection, and the intelligent agriculture internet of things monitoring system comprises the following components:
The information acquisition module is used for acquiring influence factor data of the monitored crops, wherein the influence factor data comprises weather, soil physicochemical indexes, water quality, illumination intensity, carbon dioxide concentration, pest and disease conditions, spore disease conditions and irrigation conditions;
The information analysis module is used for inputting the collected influence factor data into a preset information analysis unit and predicting the growth condition of crops;
The information decision module is used for adjusting and supervising the influence factors of the crops according to the predicted crop growth conditions and the expectations of the crop growth conditions;
further, the preset information analysis unit includes the following construction steps:
s1, data collection: collecting influence factor data of crops in a historical period and corresponding crop growth condition data thereof, wherein the crop growth condition data comprise growth states and growth trends;
s2, identifying key influence factors: the method comprises the steps of taking influence factor data as an explanatory variable, taking corresponding crop growth condition data as a response variable, constructing a redundancy analysis model, and identifying key influence factors which have obvious influence on the crop growth condition;
S3, determining the response of the crop growth condition to key influence factors: and constructing a generalized additive model by taking the key influence factors as explanatory variables and crop growth condition data as response variables, and quantifying the response relation between the key influence factors and the crop growth conditions.
Further, in step S1, the growth state includes plant height, stem thickness, leaf area, chlorophyll content, and fruit size;
further, in step S1, the growth trend includes a growth rate, a leaf color, and a leaf morphology.
Further, in step S2, the redundancy analysis model is constructed, and the key influencing factors having significant influence on the growth condition of the crops are identified, which includes the following steps:
S21, determining a model variable: determining an interpretation variable and a response variable of the constructed model, wherein the influence factor data is used as the interpretation variable, and the corresponding crop growth condition data is used as the response variable;
S22, model test: checking the significance of the whole model and the first axis of the model by utilizing Monte Carlo displacement test, and when the significance exists in the whole model and the first axis of the model, checking the model;
S23, identifying key influence factors: and drawing a sequencing graph according to the scores of the variables in the sequencing axis, and determining key influence factors according to the included angle between the influence factor data and the crop growth condition data in the graph.
Further, in step S3, the building a generalized additive model includes the following steps:
S31, single factor significance test: checking significance of influences of all key influence factors on the crop growth conditions by establishing a model between a single key influence factor and crop growth condition data, and finally eliminating key influence factors with insignificant modeling results;
S32, sorting importance of key influence factors: ranking the importance of the single factors including key influencing factors and their interaction terms by comparing all AIC values passing through the single factor checking model;
S33, determining a final model: adopting a forward selection method, adding single factors comprising key influence factors and interaction items thereof into the model one by one according to importance ranking, stopping adding the single factors when the AIC value of the model added with the single factors is not reduced any more, and determining a final model;
S34, checking model performance: the new data set is input into the final model, and the predictive performance of the final model on the new data set is evaluated by adopting the decision coefficients.
Further, in step S31, the single factor significance test indicates that the modeling result is not significant when the p value of the model between the single key influencing factor and the crop growth condition data is greater than 0.05.
Further, in step S31, the single factor significance test further tests the significance of the interaction term formed by the key influencing factors on the modeling of the crop growth condition data.
Further, in step S34, the decision coefficient is calculated as follows:
,
Wherein y i is the actual measurement value of the dataset response variable; z i is the predicted value of the dataset response variable; an average value of actual measurement values of the data set; n is the number of samples.
The invention has the beneficial effects that:
The method comprises the steps of collecting influence factor data of crops in a historical period and corresponding crop growth condition data; the method comprises the steps of taking influence factor data as an interpretation variable and crop growth condition data as a response variable, and constructing a redundancy analysis model to identify key influence factors; the key influence factors are taken as interpretation variables, crop growth condition data are taken as response variables, and a generalized additive model is constructed to quantify the response relation between the key influence factors and the crop growth conditions; and finally, inputting the real-time monitored influence factor data into a generalized additive model to predict the growth condition of crops, and adjusting and supervising the influence factors of the crops by combining the expected growth condition of the crops. The invention solves the problem that the influence factors are difficult to effectively monitor and manage according to the preference of crops because the response of the crops to the influence factors influencing the growth is unknown.
Drawings
The present invention is further described below with reference to the accompanying drawings for the convenience of understanding by those skilled in the art.
Fig. 1 is a block diagram of an intelligent agriculture internet of things monitoring system in the invention.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention for achieving the intended purpose, the following detailed description will refer to the specific implementation, structure, characteristics and effects according to the present invention with reference to the accompanying drawings and preferred embodiments.
Referring to fig. 1, the application provides an intelligent agriculture internet of things monitoring system, which comprises an information acquisition module, an information analysis module and an information decision module, wherein the information acquisition module, the information analysis module and the information decision module are in communication connection, and the intelligent agriculture internet of things monitoring system comprises:
The information acquisition module is used for acquiring influence factor data of the monitored crops, wherein the influence factor data comprises weather, soil physicochemical indexes, water quality, illumination intensity, carbon dioxide concentration, pest and disease conditions, spore disease conditions and irrigation conditions;
In this embodiment, for the collected and monitored crop influencing factors, including the meteorological, soil physicochemical index, water quality, illumination intensity, carbon dioxide concentration, pest and disease condition, spore disease condition and irrigation condition, the following method may be adopted to collect and analyze data:
(1) Weather data: various weather information such as temperature, humidity, precipitation, wind speed and the like is acquired through weather station data, weather sensors or weather service providers, and the data can help analyze the influence of weather adaptability and weather change of crop growth on crop yield;
(2) Physical and chemical indexes of soil: soil samples are required to be collected and subjected to laboratory analysis, and indexes such as soil pH value, organic matter content, nitrogen, phosphorus, potassium content, trace elements and the like are included, and can reflect soil nutrient level, soil structure and fertility status, so that important influences are exerted on crop growth and yield;
(3) Water quality data: the method is crucial to the water quality detection of an irrigation water source, and the water quality analysis including the pH value, the dissolved oxygen content, the conductivity, the heavy metal content and the like is carried out by collecting an irrigation water sample, so that the proper irrigation water quality can effectively ensure the health of crop growth.
(4) Illumination intensity and carbon dioxide concentration: is closely related to photosynthesis of crops, and directly affects the growth and the yield of the crops.
(5) Pest and spore disease conditions: the farmland is checked regularly, the occurrence condition, the type and the degree of the plant diseases and insect pests are recorded, and the insect monitor, the disease recognition equipment and the like can be used for monitoring in real time, so that prevention and control measures are adopted timely, and the safe growth of crops is ensured; spore disease is a plant disease caused by fungi or bacteria, and the plant is caused to have symptoms of different degrees such as leaf withering, spotting, browning and the like through the propagation of spores on the surface or inside of the plant, so that the condition of the spore disease is found in time, and effective prevention and control measures are taken, so that the method has important significance for protecting healthy growth of the plant and reducing yield loss.
(6) Irrigation conditions: the soil moisture and irrigation water quantity are monitored by using equipment such as a moisture sensor and a liquid level sensor, the soil moisture condition and irrigation condition are known in real time, the irrigation strategy is convenient to adjust, and the water is required for the full growth of crops.
The information analysis module is used for inputting the collected influence factor data into a preset information analysis unit and predicting the growth condition of crops;
In this embodiment, the information analysis module is a core part of intelligent agricultural monitoring, and through influence factors and crop growth condition data sets in a historical period, the information analysis unit is trained offline, and finally the trained information analysis unit is applied to analysis of crop influence factor data, including key influence factor analysis, influence factor suitable range analysis and the like, so that the crop influence factors and the crop growth conditions can be monitored in real time.
Further, the preset information analysis unit includes the following construction steps:
s1, data collection: collecting influence factor data of crops in a historical period and corresponding crop growth condition data thereof, wherein the crop growth condition data comprise growth states and growth trends;
In the embodiment, the growth state of the crops is various indexes of quantifying the growth condition according to the growth characteristics and physiological processes of the crops, including plant height, stem thickness, leaf area, chlorophyll content, fruit size and the like; the growth trend may describe the overall growth of the crop, including growth rate, leaf color, leaf morphology, and the like.
S2, identifying key influence factors: the method comprises the steps of taking influence factor data as an explanatory variable, taking corresponding crop growth condition data as a response variable, constructing a redundancy analysis model, and identifying key influence factors which have obvious influence on the crop growth condition;
In this embodiment, the redundancy analysis (RDA) model is a multiple regression analysis model based on reduced-dimension ordering analysis, and is applicable to a scenario of multiple interpretation variables and response variables. The RDA model uses arrows to represent variables, and the angles of the arrows can represent the correlation between the variables (the smaller the angle of the arrows is, the stronger the correlation is), while the projected length of the arrows on the RDA axis is used to represent the importance of the variables. In this embodiment, the RDA model is constructed by using the influence factor data as an explanatory variable and the corresponding crop growth condition data as a response variable. And finally, the key influencing factors which have obvious influence on the growth condition of crops can be identified by utilizing the included angle relation among the variables.
Further, in step S2, the redundancy analysis model is constructed, and the key influencing factors having significant influence on the growth condition of the crops are identified, which includes the following steps:
S21, determining a model variable: determining an interpretation variable and a response variable of the constructed model, wherein the influence factor data is used as the interpretation variable, and the corresponding crop growth condition data is used as the response variable;
S22, model test: checking the significance of the whole model and the first axis of the model by utilizing Monte Carlo displacement test, and when the significance exists in the whole model and the first axis of the model, checking the model;
S23, identifying key influence factors: and drawing a sequencing graph according to the scores of the variables in the sequencing axis, and determining key influence factors according to the included angle between the influence factor data and the crop growth condition data in the graph.
It should be noted that, in step S23, in addition to the manner of using the angle between the impact factor data and the crop growth condition data, the correlation coefficient of the scores of the impact factor data and the crop growth condition data in the sorting axis may be directly calculated, so that the impact factor data with higher correlation may be used to determine the key impact factor.
S3, determining the response of the crop growth condition to key influence factors: and constructing a generalized additive model by taking the key influence factors as explanatory variables and crop growth condition data as response variables, and quantifying the response relation between the key influence factors and the crop growth conditions.
In this embodiment, since a plurality of key influencing factors are introduced, they have an influence of a superposition effect on the growth condition of crops, the influence is often difficult to quantify, and since a nonlinear relationship exists between the key influencing factors and the growth condition of crops, the difficulty of constructing the relationship between the key influencing factors and the growth condition of crops is greatly increased. Therefore, the method provided by the application can be used for quantifying the nonlinear relation between the two by constructing the generalized additive model and the influence of a plurality of key influence factors, so that the accuracy of crop monitoring is improved. The generalized additive model is a multivariate statistical model, which is a framework based on a generalized linear model, but unlike the generalized linear model, the generalized additive model allows the relationship between an independent variable (an explanatory variable) and a dependent variable (a response variable) to be nonlinear, and models the nonlinear relationship by a smoothing function instead of assuming a linear relationship. The core idea of the generalized additive model is to split the argument into multiple components and model each component by applying a smoothing function. These components may be continuous variables, categorical variables, or interactive terms. By superimposing the effects of these components, the response relationship between the overall dependent variable and independent variable is obtained. In modeling, common smoothing functions include spline functions, B-spline functions, and local polynomials. These smoothing functions may be estimated by least squares methods, maximum likelihood estimation, or probability distribution based methods.
Further, in step S3, the building a generalized additive model includes the following steps:
S31, single factor significance test: checking significance of influences of all key influence factors on the crop growth conditions by establishing a model between a single key influence factor and crop growth condition data, and finally eliminating key influence factors with insignificant modeling results;
In this embodiment, the screening of factors that have a significant impact on crop growth can be facilitated by modeling a single key impact factor against crop growth data and performing a significance test on all factors. In the model analysis process, if the coefficient significance of some influence factors is not high, namely, the coefficient significance does not have a significant influence on explaining the change of the crop growth condition, the model can be eliminated, so that the simplicity and the interpretation of the model are improved. The method is helpful for eliminating factors which contribute less to the prediction capability of the model, so that the model is more refined and effective. By gradually eliminating the key influence factors which are not obvious, a more accurate and concise model can be obtained, so that the change of the growth condition of crops can be better explained. The screening method can reduce the complexity of the model, improve the prediction accuracy and the interpretation of the model, and help to better guide agricultural production practice and decision making.
It should be noted that in statistics, p-values are typically used to judge the significance of individual variables in the model. The p value represents the probability that a statistic or more extreme case is observed, with the original assumption being true. In general, if the p-value of a variable is less than a set significance level (typically set to 0.05), we can reject the original hypothesis, considering that the variable has a significant impact on the outcome; conversely, if the p-value is greater than the significance level, we accept the original assumption that the variable is not considered significant to the outcome. Thus, the first and second substrates are bonded together,
Further, in step S31, the single factor significance test indicates that the modeling result is not significant when the p value of the model between the single key influencing factor and the crop growth condition data is greater than 0.05.
Further, in step S31, the single factor significance test further tests the significance of the interaction term formed by the key influencing factors on the modeling of the crop growth condition data.
In this embodiment, the interaction term formed by the key influencing factors can be regarded as a single factor, and the interaction term refers to a new variable artificially constructed for describing the interaction or effect between different variables in statistical modeling. In multiple regression analysis, the interaction term is a new variable that results from multiplying two or more independent variables. By introducing interactive terms, the joint effect between different independent variables can be captured to more fully interpret the change in the dependent variable. For example, we can model temperature and humidity as independent variables, respectively, assuming we want to study the effect of temperature and humidity on crop growth. However, if we consider that there may be a mutual influence between temperature and humidity, we can introduce a temperature and humidity interaction term, i.e. temperature times humidity, to take into account their combined effect. Therefore, the complex relation among different factors can be better captured by introducing interaction items, and the accuracy and the interpretation of the model are improved. In addition, by introducing interactive terms, the interaction among a plurality of factors can be considered simultaneously under the condition of not adding additional factors, and the expression capacity of the model can be improved. The interaction term can help us to better understand the combined effect between factors, find out the influence of different factors on the growth condition of crops, and help to improve the prediction capability of the model.
S32, sorting importance of key influence factors: ranking the importance of the single factors including key influencing factors and their interaction terms by comparing all AIC values passing through the single factor checking model;
in this embodiment, AIC (red pool information criterion) values are used to compare goodness of fit between different models. The AIC value combines the log likelihood function value of the model and the number of model parameters, and gives a comprehensive measurement index through a simple mathematical formula, so that the model fitting goodness and complexity can be balanced when the model is selected. In practical applications, the model with the smallest AIC value is usually selected as the best model.
The calculation formula of AIC is: aic=2×ln (L) +2×k, where L represents the maximum likelihood function value of the model and k represents the number of parameters of the model. The smaller AIC value represents the better fitting effect of the model on the data, meanwhile, the complexity of the model is considered, and the problem of overfitting is avoided. Therefore, the application introduces AIC values to rank the importance of key influencing factors and their interaction terms, smaller AIC values being more important.
S33, determining a final model: adopting a forward selection method, adding single factors comprising key influence factors and interaction items thereof into the model one by one according to importance ranking, stopping adding the single factors when the AIC value of the model added with the single factors is not reduced any more, and determining a final model;
S34, checking model performance: the new data set is input into the final model, and the predictive performance of the final model on the new data set is evaluated by adopting the decision coefficients.
Further, in step S34, the decision coefficient is calculated as follows:
,
Wherein y i is the actual measurement value of the dataset response variable; z i is the predicted value of the dataset response variable; an average value of actual measurement values of the data set; n is the number of samples.
The information decision module is used for adjusting and supervising the influence factors of the crops according to the predicted crop growth conditions and the expectations of the crop growth conditions.
In this embodiment, after the generalized additive model of the key impact factors and the crop growth conditions is constructed, a response relation curve between the key impact factors and the crop growth conditions can be output through a mapping program, and the impact factors can be adjusted according to the expected crop growth condition results based on the response relation curve of the final model.
The invention has the beneficial effects that:
The method comprises the steps of collecting influence factor data of crops in a historical period and corresponding crop growth condition data; the method comprises the steps of taking influence factor data as an interpretation variable and crop growth condition data as a response variable, and constructing a redundancy analysis model to identify key influence factors; the key influence factors are taken as interpretation variables, crop growth condition data are taken as response variables, and a generalized additive model is constructed to quantify the response relation between the key influence factors and the crop growth conditions; and finally, inputting the real-time monitored influence factor data into a generalized additive model to predict the growth condition of crops, and adjusting and supervising the influence factors of the crops by combining the expected growth condition of the crops. The invention solves the problem that the influence factors are difficult to effectively monitor and manage according to the preference of crops because the response of the crops to the influence factors influencing the growth is unknown.
The present invention is not limited to the above embodiments, but is capable of modification and variation in detail, and other modifications and variations can be made by those skilled in the art without departing from the scope of the present invention.
Claims (9)
1. Wisdom agricultural thing networking monitoring system, its characterized in that: the system comprises an information acquisition module, an information analysis module and an information decision module, wherein the information acquisition module, the information analysis module and the information decision module are in communication connection, and the system comprises the following components:
the information acquisition module is used for acquiring the influence factor data of the monitored crops;
The information analysis module is used for inputting the collected influence factor data into a preset information analysis unit and predicting the growth condition of crops;
The information decision module is used for adjusting and supervising the influence factors of the crops according to the predicted crop growth conditions and the expectations of the crop growth conditions;
The preset information analysis unit comprises the following construction steps:
s1, data collection: collecting influence factor data of crops in a historical period and corresponding crop growth condition data thereof, wherein the crop growth condition data comprise growth states and growth trends;
s2, identifying key influence factors: the method comprises the steps of taking influence factor data as an explanatory variable, taking corresponding crop growth condition data as a response variable, constructing a redundancy analysis model, and identifying key influence factors which have obvious influence on the crop growth condition;
S3, determining the response of the crop growth condition to key influence factors: and constructing a generalized additive model by taking the key influence factors as explanatory variables and crop growth condition data as response variables, and quantifying the response relation between the key influence factors and the crop growth conditions.
2. The intelligent agriculture internet of things monitoring system of claim 1, wherein: the influence factor data of the crops comprise weather, soil physical and chemical indexes, water quality, illumination intensity, carbon dioxide concentration, pest and disease conditions, spore disease conditions and irrigation conditions.
3. The intelligent agriculture internet of things monitoring system of claim 1, wherein: in step S1, the growth state includes plant height, stem thickness, leaf area, chlorophyll content, and fruit size.
4. The intelligent agriculture internet of things monitoring system of claim 1, wherein: in step S1, the growth trend includes growth rate, leaf color and leaf morphology.
5. The intelligent agriculture internet of things monitoring system of claim 1, wherein: in step S2, the redundancy analysis model is constructed, and key influencing factors having significant influence on the growth condition of crops are identified, including the following steps:
S21, determining a model variable: determining an interpretation variable and a response variable of the constructed model, wherein the influence factor data is used as the interpretation variable, and the corresponding crop growth condition data is used as the response variable;
S22, model test: checking the significance of the whole model and the first axis of the model by utilizing Monte Carlo displacement test, and when the significance exists in the whole model and the first axis of the model, checking the model;
S23, identifying key influence factors: and drawing a sequencing graph according to the scores of the variables in the sequencing axis, and determining key influence factors according to the included angle between the influence factor data and the crop growth condition data in the graph.
6. The intelligent agriculture internet of things monitoring system of claim 1, wherein: in step S3, the building a generalized additive model includes the following steps:
S31, single factor significance test: checking significance of influences of all key influence factors on the crop growth conditions by establishing a model between a single key influence factor and crop growth condition data, and finally eliminating key influence factors with insignificant modeling results;
S32, sorting importance of key influence factors: ranking the importance of the single factors including key influencing factors and their interaction terms by comparing all AIC values passing through the single factor checking model;
S33, determining a final model: adopting a forward selection method, adding single factors comprising key influence factors and interaction items thereof into the model one by one according to importance ranking, stopping adding the single factors when the AIC value of the model added with the single factors is not reduced any more, and determining a final model;
S34, checking model performance: the new data set is input into the final model, and the predictive performance of the final model on the new data set is evaluated by adopting the decision coefficients.
7. The intelligent agriculture internet of things monitoring system of claim 6, wherein: in step S31, the single factor significance test indicates that the modeling result is not significant when the p value of the model between the single key influencing factor and the crop growth condition data is greater than 0.05.
8. The intelligent agriculture internet of things monitoring system of claim 6, wherein: in step S31, the significance test of the single factor also tests the significance of the interaction term formed by the key influencing factors on the modeling of the crop growth condition data.
9. The intelligent agriculture internet of things monitoring system of claim 6, wherein: in step S34, the calculation formula of the determination coefficient is as follows:
,
Wherein y i is the actual measurement value of the dataset response variable; z i is the predicted value of the dataset response variable; an average value of actual measurement values of the data set; n is the number of samples.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410384776.1A CN117974348B (en) | 2024-04-01 | 2024-04-01 | Wisdom agricultural thing networking monitoring system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410384776.1A CN117974348B (en) | 2024-04-01 | 2024-04-01 | Wisdom agricultural thing networking monitoring system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117974348A true CN117974348A (en) | 2024-05-03 |
CN117974348B CN117974348B (en) | 2024-06-11 |
Family
ID=90853821
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410384776.1A Active CN117974348B (en) | 2024-04-01 | 2024-04-01 | Wisdom agricultural thing networking monitoring system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117974348B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118246824A (en) * | 2024-05-27 | 2024-06-25 | 中通服建设有限公司 | Economical modeling system based on BIM |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108428038A (en) * | 2018-01-23 | 2018-08-21 | 安徽大学 | Zinc content of soil analysis of Influential Factors method based on GAM models |
US20190050741A1 (en) * | 2017-08-10 | 2019-02-14 | Iteris, Inc. | Modeling and prediction of below-ground performance of agricultural biological products in precision agriculture |
JP2019046126A (en) * | 2017-09-01 | 2019-03-22 | 一般社団法人家畜改良事業団 | System to assist in controlling farms |
CN110597331A (en) * | 2019-09-30 | 2019-12-20 | 郑越 | Agricultural intelligent management system based on Internet of things |
CN110771442A (en) * | 2019-09-30 | 2020-02-11 | 大气候物联网科技(广州)有限公司 | Agricultural planting method and system based on Internet of things |
JP2020149652A (en) * | 2019-03-12 | 2020-09-17 | 株式会社アグリスマート | Learning farming system for providing optimal irrigation and fertilizer for farming |
CN116630078A (en) * | 2023-04-24 | 2023-08-22 | 未来智农(北京)科技有限公司 | Intelligent agricultural system based on Internet of things |
CN117113667A (en) * | 2023-08-21 | 2023-11-24 | 天津大学 | DOC influence factor analysis method based on RDA global fresh water system |
CN117371727A (en) * | 2023-10-23 | 2024-01-09 | 贵州师范学院 | Intelligent agricultural monitoring and planning method and system based on Internet of things |
CN117520843A (en) * | 2023-11-08 | 2024-02-06 | 中国林业科学研究院资源信息研究所 | Robust model variable screening method |
-
2024
- 2024-04-01 CN CN202410384776.1A patent/CN117974348B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190050741A1 (en) * | 2017-08-10 | 2019-02-14 | Iteris, Inc. | Modeling and prediction of below-ground performance of agricultural biological products in precision agriculture |
JP2019046126A (en) * | 2017-09-01 | 2019-03-22 | 一般社団法人家畜改良事業団 | System to assist in controlling farms |
CN108428038A (en) * | 2018-01-23 | 2018-08-21 | 安徽大学 | Zinc content of soil analysis of Influential Factors method based on GAM models |
JP2020149652A (en) * | 2019-03-12 | 2020-09-17 | 株式会社アグリスマート | Learning farming system for providing optimal irrigation and fertilizer for farming |
CN110597331A (en) * | 2019-09-30 | 2019-12-20 | 郑越 | Agricultural intelligent management system based on Internet of things |
CN110771442A (en) * | 2019-09-30 | 2020-02-11 | 大气候物联网科技(广州)有限公司 | Agricultural planting method and system based on Internet of things |
CN116630078A (en) * | 2023-04-24 | 2023-08-22 | 未来智农(北京)科技有限公司 | Intelligent agricultural system based on Internet of things |
CN117113667A (en) * | 2023-08-21 | 2023-11-24 | 天津大学 | DOC influence factor analysis method based on RDA global fresh water system |
CN117371727A (en) * | 2023-10-23 | 2024-01-09 | 贵州师范学院 | Intelligent agricultural monitoring and planning method and system based on Internet of things |
CN117520843A (en) * | 2023-11-08 | 2024-02-06 | 中国林业科学研究院资源信息研究所 | Robust model variable screening method |
Non-Patent Citations (1)
Title |
---|
董望成 等: "基于物联网的柑桔黄龙病监测防控技术研究", 现代农业装备, vol. 40, no. 3, 30 June 2019 (2019-06-30), pages 50 - 55 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118246824A (en) * | 2024-05-27 | 2024-06-25 | 中通服建设有限公司 | Economical modeling system based on BIM |
Also Published As
Publication number | Publication date |
---|---|
CN117974348B (en) | 2024-06-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112270129B (en) | Plant growth prediction method based on big data analysis | |
CN110109193A (en) | A kind of eggplant greenhouse temperature intellectualized detection device based on DRNN neural network | |
CN117322214A (en) | Crop fertilizer accurate application method and system based on neural network | |
CN111754045A (en) | Prediction system based on fruit tree growth | |
CN117114448A (en) | Agricultural production management system and method based on machine learning and Internet of things technology | |
CN118097438A (en) | Fertilizing method and system based on big data | |
CN117935081B (en) | Cultivated land change monitoring method and system based on remote sensing satellite data | |
Nyakuri et al. | IoT and AI based smart soil quality assessment for data-driven irrigation and fertilization | |
CN117114913A (en) | Intelligent agricultural data acquisition system based on big data | |
CN117893346A (en) | AI intelligent agriculture harvesting management system based on Internet of things and application thereof | |
CN117296538B (en) | Green plant maintenance method, device and system based on vegetation soil component detection | |
CN117974348B (en) | Wisdom agricultural thing networking monitoring system | |
CN116452358B (en) | Intelligent agriculture management system based on Internet of things | |
Xu et al. | [Retracted] Digital Technology Empowers Grain Supply Chain Optimization Simulation | |
CN114611804A (en) | Maize yield prediction method based on TSO-GRNN combined model | |
Nguyen-Xuan et al. | A dynamic model for temperature prediction in glass greenhouse | |
Khuwaja et al. | Sustainable Agriculture: An IoT-Based Solution for Early Disease Detection in Greenhouses | |
Khatraty et al. | Smart Digital-Twin hub Concept for Rice yield prediction and monitoring from multivariate time series data | |
Ujjainia et al. | Crop Yield Prediction using Regression Model | |
Vidhya et al. | Soil Nutrient Analysis for the Cultivation of Plants using Machine Learning Algorithms | |
CN117784290B (en) | Sudden drought early warning method and system based on Bayesian neural network | |
Dayalini et al. | Agro-Mate: A Virtual Assister to Maximize Crop Yield in Agriculture Sector | |
CN117575174B (en) | Intelligent agricultural monitoring and management system | |
CN118395735A (en) | Crop disease monitoring method and system based on Internet of things | |
Madhumathi et al. | Soil Nutrient Prediction and Crop Recommendation System |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |