CN111783516A - Ploughing quality natural grade evaluation method based on deep learning - Google Patents
Ploughing quality natural grade evaluation method based on deep learning Download PDFInfo
- Publication number
- CN111783516A CN111783516A CN202010228440.8A CN202010228440A CN111783516A CN 111783516 A CN111783516 A CN 111783516A CN 202010228440 A CN202010228440 A CN 202010228440A CN 111783516 A CN111783516 A CN 111783516A
- Authority
- CN
- China
- Prior art keywords
- model
- evaluation
- quality
- deep learning
- natural
- 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.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 29
- 238000013135 deep learning Methods 0.000 title claims abstract description 14
- 238000012549 training Methods 0.000 claims abstract description 22
- 238000010606 normalization Methods 0.000 claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 16
- 238000011176 pooling Methods 0.000 claims abstract description 14
- 238000012795 verification Methods 0.000 claims abstract description 11
- 238000013136 deep learning model Methods 0.000 claims abstract description 8
- 230000006870 function Effects 0.000 claims description 15
- 238000011160 research Methods 0.000 claims description 14
- 238000012360 testing method Methods 0.000 claims description 10
- 230000001419 dependent effect Effects 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 6
- 238000013441 quality evaluation Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000004088 simulation Methods 0.000 claims 5
- 238000012545 processing Methods 0.000 claims 1
- 238000007726 management method Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Business, Economics & Management (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Computing Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Biology (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
Abstract
The invention provides a farmland quality natural grade evaluation method based on deep learning, which comprises the following steps: obtaining remote sensing image information of an area to be evaluated; calculating a vegetation normalization index of the area to be evaluated; constructing a deep learning model through the grades of the convolutional layers and the pooling layers; cutting the vegetation normalization index of the area to be researched into a fixed size according to the model characteristics, and establishing a training set and a verification set; training the deep learning model through known farmland quality natural grade data and a training set; and inputting the trained model by using the vegetation normalization index of the area to be evaluated to obtain a natural quality grade result of the evaluation area. The method can provide scientific basis for the evaluation of the nature quality of the cultivated land, and objectively and accurately evaluate the nature quality of the cultivated land.
Description
Technical Field
The invention relates to the field of land utilization planning, in particular to a ploughing quality natural grade evaluation method based on deep learning.
Background
The cultivated land is the basis of grain production, is a precious production data, and is an important guarantee for agricultural sustainable development and national grain safety. At present, the management of the cultivated land by the national natural resource department is gradually changed from the management of quantity only to the comprehensive management of three-in-one consideration of quantity, quality and ecological environment effect. Relevant departments and scientific researchers develop a large amount of land resource investigation work, and a large amount of farmland quality data are accumulated. How to effectively utilize the mass data so as to carry out fine evaluation on the quality change of cultivated land becomes a problem to be solved urgently. The traditional method for evaluating the nature grade of the cultivated land quality usually adopts an index weighting method, and has the problems of large calculated amount, low speed, insufficient accuracy and the like.
Disclosure of Invention
Aiming at the problems in the existing method, the invention provides a farmland quality evaluation method based on deep learning.
The invention provides a farmland quality natural grade evaluation method based on deep learning, which is characterized by comprising the following steps:
s1, acquiring Landsat remote sensing image information of a period to be evaluated in a research area and natural grade information of historical farmland quality in an evaluation area;
s2, acquiring Landsat remote sensing images in corresponding time periods according to the natural grade years of the quality of the historical cultivated land in the research area, and respectively calculating the monthly vegetation normalization indexes in the time period to be evaluated and the historical time period;
s3, constructing a full convolution neural network suitable for farmland quality evaluation through convolution layers and pooling layer structures; the convolution kernel of the convolution layer is N x N, N is an odd number larger than 1, the number of the convolution kernels is M, and M is an integer larger than 1; the pooling layer selects a function as maximum pooling or average pooling, and the activation function selects a modified linear unit function:
wherein f (x) is an activation function, x is an input variable, and λ is a linear rectification parameter;
s4, cutting vegetation normalization index results in the historical period of the research area according to the established deep learning network, randomly selecting cutting results from the results, constructing a training set and a verification set, inputting the bimonthly averaged vegetation normalization index as an independent variable and the natural level of the cultivated land quality as a dependent variable into a deep learning model by using the training set, and training the model; testing the evaluation precision of the model through verification, adjusting the parameters of the model according to the test result until the evaluation precision of the model reaches the preset requirement, and obtaining a deep learning model capable of realizing the natural grade evaluation of the farmland quality;
s5, inputting the normalized indexes of the bi-monthly vegetation in the time period to be evaluated of the evaluation area into the model to obtain the corresponding natural grade result of the farmland quality.
The invention has the following beneficial effects: the farmland natural quality evaluation method based on deep learning provided by the invention can quickly and accurately evaluate the farmland natural quality and the like, and is not limited by the evaluation range. The model is trained through historical evaluation data, so that the problem that artificial parameters cannot effectively embody characteristics is avoided by presetting evaluation parameters. A large amount of field work is reduced, and the conditions of farmland natural quality and the like can be acquired more quickly.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the embodiments or drawings used in the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flow chart of the method for evaluating the nature quality grade of cultivated land based on deep learning.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, the flowchart of the method for evaluating the natural grade of farmland quality based on deep learning in this embodiment specifically includes the following steps:
step S1: and acquiring Landsat remote sensing image information of a period to be evaluated in a research area and information such as natural quality of historical cultivated land in the evaluation area.
Step S2: and acquiring Landsat remote sensing images in corresponding time periods according to the natural equivalent years of the quality of the historical cultivated land in the research area, and respectively calculating the monthly vegetation normalization indexes of the time period to be evaluated and the historical time period.
Calculating the vegetation normalization index of the obtained remote sensing image of the research area by using the following formula,
the NDVI is the vegetation normalization index obtained after calculation, the NIR is near infrared band data of the remote sensing image, and the Red is Red band data of the remote sensing image.
Step S3: and constructing a full convolution neural network suitable for farmland quality evaluation through structures such as convolution layers, pooling layers and the like.
In this step, the convolution kernel size of the convolution layer is 3 × 3, the number of convolution kernels is 64, the pooling layer adopts a function as maximum pooling, and the activation function selects a modified linear unit function, the function being:
where f (x) is the activation function, x is the input variable, and λ is the linear rectification parameter.
In addition, the size of the convolution kernel can be any odd number, the number of the convolution kernels can be any integer, and the pooling method can also be an average value pooling method.
Step S4: according to the established deep learning network, cutting vegetation normalization index results in the historical period of a research area, randomly selecting cutting results from the cutting results, constructing a training set and a verification set, inputting the monthly vegetation normalization index serving as an independent variable, the natural farmland quality and the like serving as dependent variables into a deep learning model by using the training set, and training the model; and testing the evaluation precision of the model through verification, and adjusting the parameters of the model according to the test result until the evaluation precision of the model reaches the preset requirement to obtain the deep learning model capable of realizing the natural grade evaluation of the farmland quality.
Step S4 includes the following steps:
s41, randomly cutting the data of the research area into 224 × 224 pixel-size images, wherein each image comprises a dependent variable layer and 6 independent variable layers;
s42, randomly selecting 90% of the acquired image sets as training sets, and using the remaining 10% as verification sets;
s43, performing model training on the model established in the step S3 by using the training set data and taking the dependent variable as input and the natural quality grade as output; and testing the precision of the trained model by using a verification set, and adjusting the model parameters according to the test precision in the random gradient descending direction until the model precision meets the preset requirement, thereby completing the training of the model.
In the step, an accuracy evaluation function Loss of the model is constructed,
wherein M represents the number of cultivated land levels; y iscMarking an indication variable, wherein if the prediction result is the same as the actual situation, the indication variable is 1, otherwise, the indication variable is 0; p is a radical ofcThe prediction probability for class c is predicted for the model. And adjusting and optimizing the model parameters by adopting a random gradient descent method. Namely, the model parameter when Loss takes the minimum value is the final parameter.
Data from the study area was randomly sliced into 224 x 224 pixel size images. Each time, 40% of images from the training set were randomly selected as a batch of images to be input into the model process, and the learning rate was set to 1 × 10-6.
Step S5: and inputting the biennial average vegetation normalization index of the evaluation area in the period to be evaluated into the model to obtain a corresponding farmland quality natural grade result.
In addition to the above embodiments, the present invention may have other embodiments. All technical schemes of the quality evaluation of nature and the like of the cultivated land in the form of deep learning algorithm and the like fall within the protection scope required by the invention.
Claims (6)
1. A farmland quality natural grade evaluation method based on deep learning is characterized by comprising the following steps:
s1, acquiring Landsat remote sensing image information of a period to be evaluated in a research area and natural grade information of historical farmland quality in an evaluation area;
s2, acquiring Landsat remote sensing images in corresponding time periods according to the natural grade years of the quality of the historical cultivated land in the research area, and respectively calculating the monthly vegetation normalization indexes in the time period to be evaluated and the historical time period;
s3, constructing a full convolution neural network suitable for farmland quality evaluation through convolution layers and pooling layer structures; the convolution kernel of the convolution layer is N x N, N is an odd number larger than 1, the number of the convolution kernels is M, and M is an integer larger than 1; the pooling layer selects a function as maximum pooling or average pooling, and the activation function selects a modified linear unit function:
wherein f (x) is an activation function, x is an input variable, and λ is a linear rectification parameter;
s4, cutting vegetation normalization index results in the historical period of the research area according to the established deep learning network, randomly selecting cutting results from the results, constructing a training set and a verification set, inputting the bimonthly averaged vegetation normalization index as an independent variable and the natural level of the cultivated land quality as a dependent variable into a deep learning model by using the training set, and training the model; testing the evaluation precision of the model through verification, adjusting the parameters of the model according to the test result until the evaluation precision of the model reaches the preset requirement, and obtaining a deep learning model capable of realizing the natural grade evaluation of the farmland quality;
s5, inputting the normalized indexes of the bi-monthly vegetation in the time period to be evaluated of the evaluation area into the model to obtain the corresponding natural grade result of the farmland quality.
2. The KNN-based village land reclamation planning simulation method of claim 1, wherein: the S2 includes:
calculating the vegetation normalization index of the obtained remote sensing image of the research area by using the following formula,
the NDVI is the vegetation normalization index obtained after calculation, the NIR is near infrared band data of the remote sensing image, and the Red is Red band data of the remote sensing image.
3. The KNN-based village land reclamation planning simulation method of claim 1, wherein: in step S3, the convolution kernel size of the convolution layer is 3 × 3, and the number of convolution kernels is 64.
4. The KNN-based village land reclamation planning simulation method of claim 1, wherein: the step S4 includes the following steps:
s41, randomly cutting the data of the research area into 224 × 224 pixel-size images, wherein each image comprises a dependent variable layer and 6 independent variable layers;
s42, randomly selecting 90% of the acquired image sets as training sets, and using the remaining 10% as verification sets;
s43, performing model training on the model established in the step S3 by using the training set data and taking the dependent variable as input and the natural quality grade as output; and testing the precision of the trained model by using a verification set, and adjusting the model parameters according to the test precision until the model precision reaches the preset requirement, thereby completing the training of the model.
5. The KNN-based village land reclamation planning simulation method of claim 1, wherein: in step S43, adjusting and optimizing the model parameters by adopting a random gradient descent method; randomly cutting the data of the research area into 224 × 224 pixel images, randomly selecting 40% of the images from the training set as a batch of image input models for processing each time, and setting the learning rate to 1 × 10-6。
6. The KNN-based village land reclamation planning simulation method of claim 1, wherein: in the step, an accuracy evaluation function Loss of the model is constructed,
wherein M represents the number of cultivated land levels; y iscMarking an indicator variable, and if the predicted result is the same as the actual situation1 if not, 0 if not; p is a radical ofcPredicting a prediction probability for class c for the model; and adjusting and optimizing the model parameters by adopting a random gradient descent method, wherein the model parameters when the Loss takes the minimum value are final parameters.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010228440.8A CN111783516A (en) | 2020-03-27 | 2020-03-27 | Ploughing quality natural grade evaluation method based on deep learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010228440.8A CN111783516A (en) | 2020-03-27 | 2020-03-27 | Ploughing quality natural grade evaluation method based on deep learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111783516A true CN111783516A (en) | 2020-10-16 |
Family
ID=72753050
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010228440.8A Pending CN111783516A (en) | 2020-03-27 | 2020-03-27 | Ploughing quality natural grade evaluation method based on deep learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111783516A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112308047A (en) * | 2020-12-02 | 2021-02-02 | 宁夏回族自治区自然资源勘测调查院 | Method and system for monitoring cultivated land quality |
CN112330126A (en) * | 2020-10-29 | 2021-02-05 | 福州福大经纬信息科技有限公司 | Cultivated land quality grade evaluation method based on remote sensing index |
CN113222452A (en) * | 2021-05-28 | 2021-08-06 | 中国农业科学院草原研究所 | Beidou navigation-based natural grassland quality evaluation method and system and storage medium |
CN114557269A (en) * | 2022-03-21 | 2022-05-31 | 中国科学院新疆生态与地理研究所 | Method for adjusting desert river bank system based on branch of a river infiltration rotation irrigation |
CN114943900A (en) * | 2022-05-13 | 2022-08-26 | 南方海洋科学与工程广东省实验室(广州) | Marine environment quality grade evaluation method, device and medium based on deep learning |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102073869A (en) * | 2010-12-27 | 2011-05-25 | 中国农业大学 | Point location data and remote sensing image data-based regional farmland quality monitoring method |
CN106295096A (en) * | 2015-05-18 | 2017-01-04 | 中国科学院遥感与数字地球研究所 | A kind of method that remotely-sensed data is observed quality grading |
CN106682695A (en) * | 2016-12-28 | 2017-05-17 | 中国农业大学 | County cultivated land natural quality elevating method based on support vector machine |
CN107798357A (en) * | 2017-11-28 | 2018-03-13 | 南京大学 | A kind of village land used reclamation planning analogy method based on KNN |
US20190258902A1 (en) * | 2018-02-16 | 2019-08-22 | Spirent Communications, Inc. | Training A Non-Reference Video Scoring System With Full Reference Video Scores |
-
2020
- 2020-03-27 CN CN202010228440.8A patent/CN111783516A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102073869A (en) * | 2010-12-27 | 2011-05-25 | 中国农业大学 | Point location data and remote sensing image data-based regional farmland quality monitoring method |
CN106295096A (en) * | 2015-05-18 | 2017-01-04 | 中国科学院遥感与数字地球研究所 | A kind of method that remotely-sensed data is observed quality grading |
CN106682695A (en) * | 2016-12-28 | 2017-05-17 | 中国农业大学 | County cultivated land natural quality elevating method based on support vector machine |
CN107798357A (en) * | 2017-11-28 | 2018-03-13 | 南京大学 | A kind of village land used reclamation planning analogy method based on KNN |
US20190258902A1 (en) * | 2018-02-16 | 2019-08-22 | Spirent Communications, Inc. | Training A Non-Reference Video Scoring System With Full Reference Video Scores |
Non-Patent Citations (3)
Title |
---|
DHARUMARAJAN, S.等: "Spatial prediction of major soil properties using Random Forest techniques - A case study in semi-arid tropics of South India", 《GEODERMA REGIONAL》, vol. 1, pages 154 - 162 * |
HO TONG MINH, DINH等: "Deep Recurrent Neural Networks for Winter Vegetation Quality Mapping via Multitemporal SAR Sentinel-1", 《IEEE GEOSCIENCE AND REMOTE SENSING LETTERS》, vol. 15, no. 3, pages 464 - 468 * |
曹毅: "基于NDVI指数的骆马湖水生植被分级研究", 《环境监测管理与技术》, vol. 26, no. 2, pages 30 - 32 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112330126A (en) * | 2020-10-29 | 2021-02-05 | 福州福大经纬信息科技有限公司 | Cultivated land quality grade evaluation method based on remote sensing index |
CN112308047A (en) * | 2020-12-02 | 2021-02-02 | 宁夏回族自治区自然资源勘测调查院 | Method and system for monitoring cultivated land quality |
CN112308047B (en) * | 2020-12-02 | 2022-06-17 | 宁夏回族自治区自然资源勘测调查院 | Method and system for monitoring cultivated land quality |
CN113222452A (en) * | 2021-05-28 | 2021-08-06 | 中国农业科学院草原研究所 | Beidou navigation-based natural grassland quality evaluation method and system and storage medium |
CN113222452B (en) * | 2021-05-28 | 2024-07-05 | 中国农业科学院草原研究所 | Natural grass quality evaluation method, system and storage medium based on Beidou navigation |
CN114557269A (en) * | 2022-03-21 | 2022-05-31 | 中国科学院新疆生态与地理研究所 | Method for adjusting desert river bank system based on branch of a river infiltration rotation irrigation |
CN114943900A (en) * | 2022-05-13 | 2022-08-26 | 南方海洋科学与工程广东省实验室(广州) | Marine environment quality grade evaluation method, device and medium based on deep learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111783516A (en) | Ploughing quality natural grade evaluation method based on deep learning | |
CN108549954A (en) | Risk model training method, risk identification method, device, equipment and medium | |
CN110378070A (en) | Based on PSO-SVR and the united Prediction of Displacement in Landslide method of DES | |
CN106600595A (en) | Human body characteristic dimension automatic measuring method based on artificial intelligence algorithm | |
Jalalkamali | Using of hybrid fuzzy models to predict spatiotemporal groundwater quality parameters | |
CN107203810A (en) | A kind of precipitation Forecasting Methodology based on depth network | |
CN108920427B (en) | Dynamic estimation method for time-varying parameters of monthly scale hydrological model | |
CN102651053A (en) | Evaluation method of debris flow disaster risk based on Bayesian network model | |
CN109408773B (en) | Automatic screening method for indexes of ecological health diagnosis | |
CN108520345A (en) | Evaluation for cultivated-land method and system based on GA-BP neural network models | |
CN109858180B (en) | Regional crop water consumption space pattern optimization design method | |
CN109115992A (en) | A kind of agricultural land soil health assessment system | |
CN109064039A (en) | A kind of agricultural land soil health assessment method | |
CN107871133A (en) | The recognition methods of the optimization method, pavement disease of rim detection network and system | |
CN106529458A (en) | Deep neural network space spectrum classification method for high-spectral image | |
CN110414088B (en) | Space fuzzy evaluation method for suitability of birds-involved habitat by combining hydrodynamic model | |
CN109657940A (en) | Based on fish in response to determining that Migration system restores the method for factor priority | |
CN116777079A (en) | Desertification intrusion disaster prediction method based on Bayesian interlayer structure model | |
CN109272144B (en) | BPNN-based prediction method for NDVI (normalized difference of variance) in northern grassland area of China | |
WO2016067070A1 (en) | System and method for solving spatiotemporal-based problems | |
CN104572900B (en) | The properties and characteristicses system of selection that a kind of crop breeding is evaluated | |
CN116341391A (en) | Precipitation prediction method based on STPM-XGBoost model | |
CN115510991A (en) | Sunlight greenhouse aphid early warning method based on 1DCNN-LSTM multi-source information fusion model | |
CN110033187B (en) | Index data acquisition method based on environmental data | |
CN113379326A (en) | Power grid disaster emergency drilling management system based on deep neural network |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20201016 |
|
WD01 | Invention patent application deemed withdrawn after publication |