CN113408701A - Convolutional neural network soil organic matter analysis model construction system and method - Google Patents

Convolutional neural network soil organic matter analysis model construction system and method Download PDF

Info

Publication number
CN113408701A
CN113408701A CN202110691758.4A CN202110691758A CN113408701A CN 113408701 A CN113408701 A CN 113408701A CN 202110691758 A CN202110691758 A CN 202110691758A CN 113408701 A CN113408701 A CN 113408701A
Authority
CN
China
Prior art keywords
module
soil
organic matter
model
neural network
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
Application number
CN202110691758.4A
Other languages
Chinese (zh)
Inventor
宋振强
潘拓
魏茂盛
程飞雁
张振
马明星
安晓宇
高晓东
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Harbin Space Star Data System Technology Co ltd
Original Assignee
Harbin Space Star Data System Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Harbin Space Star Data System Technology Co ltd filed Critical Harbin Space Star Data System Technology Co ltd
Priority to CN202110691758.4A priority Critical patent/CN113408701A/en
Publication of CN113408701A publication Critical patent/CN113408701A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • 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
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
    • G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
    • G16C20/70—Machine learning, data mining or chemometrics
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
    • G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
    • G16C20/90—Programming languages; Computing architectures; Database systems; Data warehousing

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computing Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Chemical & Material Sciences (AREA)
  • Crystallography & Structural Chemistry (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Image Processing (AREA)

Abstract

The invention relates to the technical field of remote sensing technology and variable fertilization, in particular to a convolutional neural network soil organic matter analysis model construction system and a method, and the system comprises a raw data sorting module, a wave band transformation module, a sensitivity analysis module, a transformed wave band analysis module, a parameter input module, a convolutional neural network construction module, a model training module, a precision evaluation module, a coarse error elimination module, a model verification module, a model storage module, a model retraining module and a result graph output module which are operated in a flow process, wherein the sensitivity analysis module is used for analyzing the sensitivity degree of a soil sample image raw wave band and a transformed wave band to soil organic matters, calibrating input wave band parameters, and guiding accurate and comprehensive fertilization through a soil organic matter analysis model of a remote sensing and convolutional neural network, so that excessive cost input caused by excessive fertilization is avoided, The environment is polluted, the soil is hardened due to too little fertilization, the growth of crops is influenced, and the land is damaged.

Description

Convolutional neural network soil organic matter analysis model construction system and method
Technical Field
The invention relates to the technical field of remote sensing technology and variable fertilization, in particular to a system and a method for constructing a convolutional neural network soil organic matter analysis model.
Background
Scientific fertilization is an effective means for preventing environmental pollution caused by over fertilization and preventing the crop growth and improving the quality of agricultural products due to insufficient soil nutrient supply caused by insufficient fertilizing amount, the scientific fertilization is based on accurately mastering the soil nutrient distribution, the traditional soil testing scheme is that a large number of detection points are utilized and are too sparse, the organic matter content of the soil of the whole farmland is measured by replacing the detection points with 'points' and 'surfaces', the 'actual field measurement' cannot be finely realized, a large amount of soil testing data needs to be collected on site, the cost of sample collection and measurement is high, a large amount of manpower and material resources are consumed, the production cost is increased, and the precision is difficult to guarantee.
With the rapid development of satellite remote sensing at home and abroad, the variety of satellite images of multispectral data and hyperspectral data is increased, and effective data support is provided for researching inversion of soil organic matter content based on the multispectral and hyperspectral data. The important influencing factor for scientific fertilization is organic matters, and because the organic matter modeling is greatly influenced by agricultural production environment factors, terrain environment, meteorological factors and the like, image data with higher time resolution and a soil organic matter inversion model are needed; the defects in the prior art are that the organic matter distribution of soil can not be rapidly collected before planting, and effective data support is provided for scientific fertilization.
Disclosure of Invention
The invention aims to provide a convolutional neural network soil organic matter analysis model construction system and a convolutional neural network soil organic matter analysis model construction method, which can be used for constructing an analysis model system, so as to solve the influence of agricultural production activities and meteorological factors, efficiently and accurately obtain soil organic matter distribution data and provide data support for scientific fertilization.
The purpose of the invention is realized by the following technical scheme:
a convolutional neural network soil organic matter analysis model construction system comprises a raw data sorting module, a wave band transformation module, a sensitivity analysis module, a transformed wave band analysis module, a parameter input module, a convolutional neural network construction module, a model training module, a precision evaluation module, a coarse error elimination module, a model verification module, a model storage module, a model retraining module and a result chart output module which are operated in a flow process.
The original data sorting module is used for carrying out diversity, conversion, encapsulation and calibration on collected soil sample data, meteorological output, topographic data and soil type data according to the data input structure requirement for constructing the convolutional neural network structure.
And the band conversion module is used for converting the collected preprocessed image bands according to a fixed formula to obtain converted bands.
And the sensitivity analysis module is used for analyzing the sensitivity of the preprocessed image wave band and the converted wave band to soil organic matters and calibrating input wave band parameters.
The parameter input module is used for establishing input parameter transformation of convolutional neural network structure model training;
the convolutional neural network construction module is responsible for constructing a convolutional neural network structure and packaging;
the precision evaluation module is used for training the precision evaluation of the convolutional neural network structure;
the coarse error elimination module eliminates obvious errors according to the precision evaluation result, and improves the training precision of the convolutional neural network structure;
the model verification module is responsible for verifying the final result precision;
the model storage module is used for storing an optimal soil organic matter inversion model;
the model retraining module is used for continuously training the stored optimal soil organic matter inversion model and further improving the precision of the soil organic matter inversion model;
and the result map output module is used for outputting the soil organic matter distribution result map of the target area according to the image coordinate system and the projection.
A convolutional neural network soil organic matter analysis model construction method comprises the following steps:
the method comprises the following steps: collecting soil samples of a target area according to the requirements of soil sample collection technical specifications, establishing a soil organic matter sample database collected on site by the soil sample collection technology, establishing a meteorological database, a topographic database and a soil type database of a sample collection time period, and performing diversity, conversion, encapsulation and calibration on the soil sample data, meteorological output, topographic data and soil type data through an original data sorting module;
further, the soil sample collection is the soil sample point collection of a target area, an equidistant sampling method is adopted to collect plough layer soil of 0-20 cm in an operation area, and a 5-division method is adopted to fully mix the soil uniformly to obtain a soil sample; acquiring longitude, latitude and elevation information of sampling points by using a GPS; after sampling is finished, the soil sample enters a laboratory for processing, and the accurate content of the soil organic matters is measured according to the measurement standard of the soil organic matters; acquiring information such as the highest temperature, the lowest temperature, the relative humidity, the rainfall and the like in a soil acquisition time period to establish a meteorological database; acquiring the gradient and the altitude of a target area to establish a terrain database; and collecting red soil, yellow brown soil, black calcium soil and the like in the target area to establish a soil type database.
Further, before crop sowing, image data during sample collection are obtained, wherein the image data comprise Landsat8OLI, Sentinel-2 and GF-5AHSI, and radiation calibration, atmospheric correction, filtering processing and resampling processing are carried out on the obtained image data by utilizing ENVI5.6 arranged in the wave band conversion module, so as to establish a remote sensing image database;
step two: performing mathematical transformation on the preprocessed image wave band through a wave band transformation module to obtain a transformation wave band;
further, the wave band change module calls two tools in commercial application software to carry out 11 mathematical transformations, wherein a bandmath tool in ENVI5.6 software is utilized to carry out reciprocal transformation, reciprocal logarithmic transformation, reciprocal transformation of logarithm and square root transformation;
using the Image derivation tool in the ENVI5.6 software, the first Derivative R ', the first Derivative of the reciprocal (1/R)', the first Derivative of the logarithm (lg) were performedR) ', first derivative of square root
Figure BDA0003127046290000031
The first derivative of the logarithm of the reciprocal (lg (1/R))' and the first derivative of the reciprocal of the logarithm (1/lg)R) The operation of' wherein R is an image sensitive band.
Step three: the sensitivity analysis module performs sensitivity analysis on the preprocessed image wave band and the converted wave band based on a soil organic matter sample database, and calibrates input wave band parameters;
furthermore, sensitivity analysis is carried out on the converted wave bands by utilizing a spearman correlation analysis algorithm based in the sensitivity analysis module, significance correlation is marked according to a report output by software, and when the output result reaches 0.05 significance level or 0.01 significance level, marking is carried out on the upper right corner of the report to show that the significance is more or extremely significant; and selecting 3-10 obvious sensitivity wave bands shown in the report as input parameters for soil organic matter inversion model training.
Step four: the parameter input module carries out parameter transformation on a soil organic matter sample database, a meteorological database, a terrain database, a soil type database and input waveband parameters;
further, integrating model training input and target parameters according to the requirement of a four-dimensional data input parameter format of the soil organic matter inversion model structure, and carrying out transformation and calibration;
step five: the convolutional neural network construction module constructs a convolutional neural network;
step six: the RMSE, R2, the positive error distribution map and the error confidence interval in the accuracy evaluation module are used for evaluating the accuracy of the model training;
further, the precision evaluation module carries out precision evaluation on the trained convolutional neural network structure, and selects the optimal convolutional neural network structure to establish a soil organic matter inversion model;
step seven: coarse error elimination module for coarse error elimination
Further, a coarse error elimination module eliminates coarse errors in the training process, and provides effective sample data for training an optimal soil organic matter inversion model;
step eight: model verification module verifies accuracy of data inverted by soil organic matter inversion model
Further, the model verification module compares and analyzes soil organic matter data predicted by the soil organic matter inversion model with actually measured data, and verifies the actual precision of the soil organic matter inversion model;
step nine: the model storage module stores an optimal soil organic matter inversion model to form a regionalized calibration soil organic matter inversion model
Further, the model storage module stores the optimal soil organic matter inversion model to complete the regionalization calibration of the soil organic matter inversion model;
step ten: the model retraining module retrains the stored optimal soil organic matter inversion model again
Further, the model retraining module retrains the stored optimal soil organic matter inversion model after further expanding the sample data to obtain a better soil organic matter inversion model;
step eleven: and the result map output module outputs the soil organic matter distribution result map of the target area according to the image coordinate system and the projection.
Further, the result graph output module outputs the soil organic matter distribution result graph of the target area according to the image coordinate system and the projection, and the result graph is used for data analysis in practical application.
The method for constructing the soil organic matter inversion model by the convolutional neural network construction module comprises the following steps of:
the method comprises the following steps: establishing a sample database input by a soil organic matter inversion model, and extracting reflectivity information of a wave band of a preprocessed image after sensitivity analysis into soil sampling point information by using a Spatial analysis tool in ArcGIS software;
step two: extracting meteorological data, topographic data and soil type data under a sampling point into soil sampling point information, inputting data of a crop soil organic matter model, taking collected soil organic matters as target data, and establishing a sample database;
step three: carrying out four-dimensional matrix change on the sample database by utilizing Python according to a designed algorithm structure;
step four: establishing a convolutional neural network by utilizing a Python language Keras library, wherein the weights of neurons on the same plane are equal, taking a four-dimensional matrix as input, and obtaining a soil organic matter inversion model through a gradient back propagation algorithm and an optimization algorithm, relu, an elu activation function, an mse loss function and mae application performance;
step five: and (3) packaging the soil organic matter inversion model by using a Python language PyQt5GUI design module.
The learning process of the convolutional neural network is as follows:
performing convolution through 96 trainable filters, 11 × 11 convolution kernels, 4 × 4 step sizes, VALID filling and unifom initialization methods, generating 96 feature mapping maps in a CNN1 layer after convolution, and pooling each group of a plurality of features in the feature mapping maps through relu or elu activation functions and maxporoling to obtain 96S 1 layers of soil organic matter feature mapping maps;
the method comprises the steps that a soil organic matter feature map is convoluted through 256 trainable filters, 11 × 11 convolution kernels, 4 × 4 step sizes, VALID filling and unifonm initialization methods, 256 feature maps are generated in a CNN2 layer after convolution, and then a plurality of features in each group in the feature map are pooled through relu or elu activation functions and maxporoling to obtain 256S 2 layers of soil organic matter feature maps;
preventing overfitting by using a dropout method, and obtaining a CNN2 layer through a full connection layer; and finally, converting the sample database into a four-dimensional matrix and inputting the four-dimensional matrix into a convolutional neural network to obtain a soil organic matter inversion model.
The system and the method for constructing the soil organic matter analysis model of the convolutional neural network have the beneficial effects that:
according to the system and the method for constructing the soil organic matter analysis model of the convolutional neural network, accurate and comprehensive fertilization can be guided through the soil organic matter analysis model of the remote sensing and convolutional neural network, so that the problems that the cost input is too large and the environment is polluted due to too much fertilization, the soil is hardened and the crop growth is influenced due to too little fertilization, and the soil is damaged are avoided.
Drawings
The invention is described in further detail below with reference to the accompanying drawings and specific embodiments.
FIG. 1 is a schematic flow chart diagram of a soil organic matter analysis model construction system according to the present invention;
FIG. 2 is a schematic diagram of a soil organic matter analysis process of the present invention;
FIG. 3 is a schematic illustration of a machine-aided in-field sampling location distribution of the present invention;
FIG. 4 is a graphical representation of the correlation coefficient of the sensitivity analysis of the present invention;
FIG. 5 is a schematic diagram of the sensitivity Sig of the present invention on both sides;
FIG. 6 is a schematic diagram of a mean square error mse evaluation graph for model training according to the present invention;
FIG. 7 is a graph of the error evaluation of the positive distribution of the model of the present invention;
FIG. 8 is a graph of the model error confidence interval evaluation of the present invention;
FIG. 9 is a graph of the model fit evaluation of the present invention;
fig. 10 is a graph of soil organic matter content distribution according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
The following describes the embodiment with reference to fig. 1 to 10, and the system for constructing a convolutional neural network soil organic matter analysis model includes an original data sorting module, a band transformation module, a sensitivity analysis module, a transformed band analysis module, a parameter input module, a convolutional neural network construction module, a model training module, a precision evaluation module, a coarse error elimination module, a model verification module, a model storage module, a model retraining module and a result graph output module which are connected in a logical sequence;
a soil organic matter analysis model construction system based on remote sensing and a convolutional neural network is characterized in that a neural network model for soil organic matter analysis is constructed through progressive parameter data combing of an original data sorting module, a wave band transformation module, a sensitivity analysis module, a parameter input module, a convolutional neural network structure module, a precision evaluation module, a coarse error elimination module, a model verification module, a model storage module, a model retraining module and an achievement map output module, and analysis results of various parameters of soil organic matters are finally achieved.
A convolutional neural network soil organic matter analysis model construction method comprises the following steps:
the method comprises the following steps: acquiring and preprocessing original data:
collecting, packaging and calibrating soil samples of a target area according to the requirements of 'technical specification for collecting soil samples', collecting soil sample points of the target area, collecting plough layer soil of 0-20 cm in an operation area by adopting an equidistant sampling method, fully mixing the soil by adopting a 5-division method, then taking 1kg of soil, wherein the sampling interval is determined according to the size of an operation range, the interval of general dry fields is 100m, and 9 points are uniformly distributed on each grid of a paddy field. And acquiring longitude, latitude and elevation information of the sampling point by using the GPS. After sampling is finished, the soil sample enters a laboratory for processing, and the accurate content of the soil organic matter is measured according to the standard of NY/1121.6-2006 soil organic matter measurement; acquiring information such as the highest temperature, the lowest temperature, the relative humidity, the rainfall and the like in a soil acquisition time period through a China meteorological network or a provincial meteorological center and meteorological satellite data to establish a meteorological database; establishing a terrain database by utilizing the slope and the altitude of a target area obtained by about 30m of Digital Elevation (DEM) data; and collecting red soil, yellow brown soil, black calcium soil and the like in a target area through a provincial plant inspection plant protection station or a local agricultural technology promotion center to establish a soil type database.
Acquiring image data including Landsat8OLI, Sentinel-2 and GF-5AHSI during sample acquisition before crop sowing, and utilizing ENVI5.6 arranged in a wave band conversion module to perform radiometric calibration, atmospheric correction, filtering processing and resampling on the acquired image data to establish a preprocessed image database.
Step two: image band conversion:
11 mathematical transformations are carried out on the sensitive wave band, and by utilizing ENVI5.6 software, the bandmath tool can carry out reciprocal transformation, reciprocal logarithmic transformation, reciprocal transformation of the logarithm and square root transformation; using the ENVI5.6 software, the Image derivation tool can perform the first Derivative (R '), the reciprocal first Derivative ((1/R)'), the logarithmic first Derivative ((lg)R) '), first derivative of square root
Figure BDA0003127046290000071
The first derivative of the logarithm of the reciprocal ((lg (1/R))'), the first derivative of the reciprocal of the logarithm ((1/lg)R) ', R is image sensitive band;
step three: and (3) sensitivity analysis:
the method comprises the steps of extracting reflectivity information of each wave band of a preprocessed image and reflectivity information of a mathematical transformation wave band into soil sampling point information by using ArcGIS software with the version of 10.1 or more and a Spatial analysis tool value-to-point function, carrying out sensitivity analysis on reflectivity values of each wave band of the image and corresponding organic matter content by using a spearman correlation analysis algorithm of a sensitivity analysis module, marking significance correlation according to a report output by the software, indicating that the upper right corner is significant by using a mark when an output result reaches a significance level of 0.05, and indicating that the upper right corner is significant by using a mark when the output result reaches the significance level of 0.01. Selecting a wave band with high sensitivity as an input parameter for training an inversion model, and generally selecting 3-10 wave bands;
step four: model training input and target parameter determination:
selecting single-waveband form input parameters (preprocessed image sensitive waveband, mathematically transformed sensitive waveband, meteorological data, topographic data and soil type) or double-waveband combination input parameters (preprocessed image sensitive waveband-mathematically transformed sensitive waveband, meteorological data, topographic data and soil type), and establishing a model sample database by taking organic matters measured in an on-site soil sample laboratory as target parameters;
step five: building a convolutional neural network model:
carrying out four-dimensional matrix change on the model sample database by utilizing Python according to a designed algorithm structure;
establishing a convolutional neural network by utilizing a Python language Keras library, wherein the weights of neurons on the same plane are equal, taking a four-dimensional matrix as input, and obtaining a soil organic matter inversion model through a gradient back propagation algorithm, an optimization algorithm, relu, an elu activation function, an mse loss function and mae application performance;
and (5) carrying out model packaging by using a Python language PyQt5GUI design module.
Preferably, the learning process of the convolutional neural network is as follows: performing convolution through 96 trainable filters, 11 × 11 convolution kernels, 4 × 4 step sizes, VALID filling and unifom initialization methods, generating 96 feature mapping maps in a CNN1 layer after convolution, and pooling each group of a plurality of features in the feature mapping maps through relu or elu activation functions and maxporoling to obtain 96S 1 layers of soil organic matter feature mapping maps; the method comprises the steps that a soil organic matter feature map is convoluted through 256 trainable filters, 11 × 11 convolution kernels, 4 × 4 step sizes, VALID filling and unifonm initialization methods, 256 feature maps are generated in a CNN2 layer after convolution, and then a plurality of features in each group in the feature map are pooled through relu or elu activation functions and maxporoling to obtain 256S 2 layers of soil organic matter feature maps; preventing overfitting by using a dropout method, and obtaining a CNN2 layer through a full connection layer; and finally, converting the sample database into a four-dimensional matrix and inputting the four-dimensional matrix into a convolutional neural network to obtain a soil organic matter inversion model.
Step six: model training and precision evaluation:
the method comprises the steps of randomly dividing sample data into three parts, namely 70% of training samples (training), 15% of verification samples (validation) and 15% of test samples (test), wherein the training samples are used for training a convolutional neural network model, and the verification samples and the test samples are used for verifying and testing the trained model, so that the stability and the accuracy of the model are guaranteed. And training by combining the quantitative relation between the input parameters and the target parameters and utilizing a convolutional neural network model to obtain the quantitative function relation between the input parameters and the target parameters, and establishing a soil organic matter inversion model.
The soil organic matter inversion method is characterized in that a spearman sensitivity analysis technology and a convolutional neural network algorithm are adopted, a Python language Keras library programming and a PyQt5 module are used for GUI design to establish a soil organic matter inversion model, a pixel-by-pixel fine analysis technology is carried out by using multiple parameters such as sensitive wave bands, sensitive wave band mathematical transformation, meteorological data, topographic data, soil type data and field soil sample acquisition data, quantitative analysis is carried out on organic matters of important nutrient elements in a soil fertilization prescription diagram, and specific characteristic points are as follows:
the characteristic points are as follows: preprocessing the acquired image data by utilizing the ENVI5.6 and above versions, and outputting reflectivity data; performing mathematical transformation on the processed image reflectivity data by using a mathematical formula;
and a second characteristic point: the sensitivity analysis module is used for completing the sensitivity analysis of satellite image waveband information, the conversion information of the satellite image waveband information and the content of soil organic matters, and a report is output;
the third characteristic point is as follows: selecting 3-10 wave bands which are most sensitive to the organic matter content of the soil as input parameters of model training by using a sensitivity analysis report of the feature point II, and improving the training precision of the model;
the feature points are four: the method comprises the steps of establishing a convolutional neural network by utilizing a Python language Keras library, enabling weights of neurons on the same plane to be equal, taking a four-dimensional matrix as input, obtaining a neural network model through a gradient back propagation algorithm and an optimization algorithm, relu, an elu activation function, a mse loss function and mae application performance, training input parameters by taking a feature point I and a feature point III as models, and completing construction of a soil organic matter inversion model by taking organic matter content analyzed by a field soil sample acquisition data laboratory as a target parameter.
In the west, with reference to fig. 1 to 10, taking a farmland in a certain province and a certain city as an example, by adopting the method of the invention, a distribution map of the organic matter content of the farmland soil is finally obtained, and the specific implementation scheme is as follows:
collecting soil samples according to local actual conditions, recording longitude and latitude coordinates and soil sample numbers of each sampling point, sending the soil samples to a professional third-party soil detection for laboratory test or collecting local soil organic matter sample data, wherein the position spread points of the organic matter sample data are shown in figure 3;
inquiring and downloading a remote sensing image, downloading GF-5 hyperspectral data in the example, wherein the resolution is 30 meters, the image time is 2019, 4 months and 16 days, carrying out radiometric calibration, atmospheric correction, filtering processing and wave band resampling processing on the image by using a wave band conversion module, and cutting by using a vector range; the sensitivity analysis model is used to obtain the sensitivity results of the preprocessed image data wave band and the organic matter content of the soil sample as shown in fig. 4 and 5. The correlation is significant at a confidence (double test) of 0.01, and significant at a confidence (double test) of 0.05;
calculating to obtain soil organic matter content grid data according to the optimized inversion model;
and exporting the grid data of the inverted soil organic matter content pixel by utilizing a grid surface-turning function in the GIS, establishing a fishing net according to an image range, exporting vector data according to pixels, and connecting through an attribute table to realize grid data vectorization.
The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.

Claims (10)

1. A convolutional neural network soil organic matter analysis model construction system is characterized in that: the system comprises an original data sorting module, a wave band transformation module, a sensitivity analysis module, a transformation wave band analysis module, a parameter input module, a convolutional neural network construction module, a model training module, a precision evaluation module, a coarse error elimination module, a model verification module, a model storage module, a model retraining module and a result chart output module which are operated in a flow manner, wherein the sensitivity analysis module is used for analyzing the sensitivity degree of a preprocessed image wave band and a transformation wave band to soil organic matters and calibrating input wave band parameters.
2. The convolutional neural network soil organic matter analysis model building system of claim 1, wherein: the original data sorting module is used for carrying out diversity, conversion, encapsulation and calibration on the collected soil sample data, meteorological output, topographic data and soil type data according to the data input structure requirement of the convolutional neural network building module.
3. The convolutional neural network soil organic matter analysis model building system of claim 1, wherein: and the band conversion module is used for converting the collected preprocessed image bands according to a fixed formula.
4. A convolutional neural network soil organic matter analysis model construction method is characterized by comprising the following steps: the method comprises the following steps:
the method comprises the following steps: the method comprises the steps that a soil sample collecting technology is used for establishing a soil organic matter sample database collected on site, a meteorological database, a topographic database and a soil type database of a sample collecting time period are established, and soil sample data, meteorological output, topographic data and soil type data are subjected to diversity, conversion, packaging and calibration through an original data sorting module;
step two: the band transformation module is used for carrying out mathematical transformation on the preprocessed image bands;
step three: the sensitivity analysis module performs sensitivity analysis on the preprocessed image wave band and the preprocessed conversion wave band based on a soil organic matter sample database, and calibrates input wave band parameters;
step four: the parameter input module carries out parameter transformation on a soil organic matter sample database, a meteorological database, a terrain database, a soil type database and input waveband parameters;
step five: the convolutional neural network construction module constructs a convolutional neural network;
step six: the precision evaluation module evaluates the training precision of the convolutional neural network model;
step seven: the coarse error elimination module is used for eliminating coarse errors;
step eight: the model verification module verifies the precision of the data inverted by the convolutional neural network model;
step nine: the model storage module stores the optimal model to form a regional calibration soil organic matter inversion model;
step ten: the model retraining module retrains the stored optimal soil organic matter inversion model again;
step eleven: and the result map output module outputs the soil organic matter distribution result map of the target area according to the image coordinate system and the projection.
5. The method for constructing the soil organic matter analysis model of the convolutional neural network as claimed in claim 4, wherein the method comprises the following steps: the soil sample collection is the soil sample point collection of a target area, and the highest temperature, the lowest temperature, the relative humidity and the rainfall information in the soil collection time period are obtained to establish a meteorological database; acquiring the gradient and the altitude of a target area to establish a terrain database; and collecting red soil, yellow brown soil and black calcium soil in the target area to establish a soil type database.
6. The method for constructing the soil organic matter analysis model of the convolutional neural network as claimed in claim 4, wherein the method comprises the following steps: the soil sample image data comprise Landsat8OLI, Sentinel-2 and GF-5AHSI, the wave band conversion module carries out radiometric calibration, atmospheric correction, filtering processing and resampling processing on the soil sample image data, and a preprocessed image database is established.
7. The method for constructing the soil organic matter analysis model of the convolutional neural network as claimed in claim 4, wherein the method comprises the following steps: and performing sensitivity analysis on the transformed wave band through a spearman correlation analysis algorithm based on the set sensitivity analysis module.
8. The method for constructing the soil organic matter analysis model of the convolutional neural network as claimed in claim 4, wherein the method comprises the following steps: and step four, integrating model training input and target parameters according to the four-dimensional data input parameter format requirement of the soil organic matter inversion model structure, and carrying out transformation and calibration.
9. The method for constructing the soil organic matter analysis model of the convolutional neural network as claimed in claim 4, wherein the method comprises the following steps: the method for constructing the soil organic matter inversion model by the convolutional neural network construction module comprises the following steps of:
the method comprises the following steps: establishing a sample database input by a model, and extracting reflectivity information of a wave band of the preprocessed image after sensitivity analysis into soil sampling point information by using a Spatial analysis tool in ArcGIS software;
step two: extracting meteorological data, topographic data and soil type data at a sampling point into soil sampling point information, inputting data of a crop soil organic matter inversion model, taking collected soil organic matters as target data, and establishing a sample database;
step three: carrying out four-dimensional matrix change on the sample database by utilizing Python according to a designed algorithm structure;
step four: establishing a convolutional neural network by utilizing a Python language Keras library, taking a four-dimensional matrix as input according to a neuron weight value on the same plane, and obtaining a soil organic matter inversion model through a gradient back propagation algorithm and an optimization algorithm, relu, an elu activation function, an mse loss function and mae application performance;
step five: and (3) packaging the soil organic matter inversion model by using a Python language PyQt5GUI design module.
10. The method for constructing the soil organic matter analysis model of the convolutional neural network as claimed in claim 9, wherein the method comprises the following steps: the learning process of the convolutional neural network is as follows:
performing convolution through 96 trainable filters, 11 × 11 convolution kernels, 4 × 4 step sizes, VALID filling and unifom initialization methods, generating 96 feature mapping maps in a CNN1 layer after convolution, and pooling each group of a plurality of features in the feature mapping maps through relu or elu activation functions and maxporoling to obtain 96S 1 layers of soil organic matter feature mapping maps;
the method comprises the steps that a soil organic matter feature map is convoluted through 256 trainable filters, 11 × 11 convolution kernels, 4 × 4 step sizes, VALID filling and unifonm initialization methods, 256 feature maps are generated in a CNN2 layer after convolution, and then a plurality of features in each group in the feature map are pooled through relu or elu activation functions and maxporoling to obtain 256S 2 layers of soil organic matter feature maps;
preventing overfitting by using a dropout method, and obtaining a CNN2 layer through a full connection layer; and finally, converting the sample database into a four-dimensional matrix and inputting the four-dimensional matrix into a convolutional neural network to obtain a soil organic matter inversion model.
CN202110691758.4A 2021-06-22 2021-06-22 Convolutional neural network soil organic matter analysis model construction system and method Pending CN113408701A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110691758.4A CN113408701A (en) 2021-06-22 2021-06-22 Convolutional neural network soil organic matter analysis model construction system and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110691758.4A CN113408701A (en) 2021-06-22 2021-06-22 Convolutional neural network soil organic matter analysis model construction system and method

Publications (1)

Publication Number Publication Date
CN113408701A true CN113408701A (en) 2021-09-17

Family

ID=77682509

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110691758.4A Pending CN113408701A (en) 2021-06-22 2021-06-22 Convolutional neural network soil organic matter analysis model construction system and method

Country Status (1)

Country Link
CN (1) CN113408701A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113984198A (en) * 2021-10-25 2022-01-28 北京航天创智科技有限公司 Short wave radiation prediction method and system based on convolutional neural network

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113984198A (en) * 2021-10-25 2022-01-28 北京航天创智科技有限公司 Short wave radiation prediction method and system based on convolutional neural network
CN113984198B (en) * 2021-10-25 2023-11-17 北京航天创智科技有限公司 Shortwave radiation prediction method and system based on convolutional neural network

Similar Documents

Publication Publication Date Title
Matsushita et al. Integrating remotely sensed data with an ecosystem model to estimate net primary productivity in East Asia
CN107527014A (en) Crops planting area RS statistics scheme of sample survey design method at county level
CN111798327A (en) Construction method and application of wheat yield calculation model based on hyperspectral image
CN110567892B (en) Summer corn nitrogen hyperspectral prediction method based on critical nitrogen concentration
CN115481368B (en) Vegetation coverage estimation method based on full remote sensing machine learning
CN116580318B (en) Soil nutrient inversion method, device, equipment and medium for crop coverage area
CN109711102A (en) A kind of crop casualty loss fast evaluation method
CN112149827A (en) System and method for constructing soil quick-acting potassium analysis model based on satellite images
CN114494882B (en) Winter wheat remote sensing identification analysis method and system based on random forest
CN113205014B (en) Time sequence data farmland extraction method based on image sharpening
Ji et al. Crop yield estimation at field scales by assimilating time series of Sentinel-2 data into a modified CASA-WOFOST coupled model
CN115561181B (en) Water quality inversion method based on unmanned aerial vehicle multispectral data
CN112836575A (en) Multi-time-sequence image rice yield estimation method based on crop phenological period
CN113177942A (en) Soybean planting area remote sensing monitoring and identifying method and device, electronic equipment and medium
Shao et al. Estimation of transpiration coefficient and aboveground biomass in maize using time-series UAV multispectral imagery
CN115759524A (en) Soil productivity grade identification method based on remote sensing image vegetation index
Park et al. Improvement of satellite-based estimation of gross primary production through optimization of meteorological parameters and high resolution land cover information at regional scale over East Asia
CN113408701A (en) Convolutional neural network soil organic matter analysis model construction system and method
CN113420875A (en) Convolutional neural network soil available phosphorus analysis model construction system and method
CN113435574A (en) Convolutional neural network soil quick-acting potassium analysis model construction system and method
CN113408700A (en) Convolutional neural network soil alkaline hydrolysis nitrogen analysis model construction system and method
CN113570273A (en) Spatial method and system for irrigation farmland statistical data
WO2023131949A1 (en) A versatile crop yield estimator
CN116773516A (en) Soil carbon content analysis system based on remote sensing data
CN112733780A (en) System and method for constructing soil available phosphorus analysis model based on satellite images

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