CN118396482B - Climate change-oriented dynamic monitoring method for cultivated quality - Google Patents
Climate change-oriented dynamic monitoring method for cultivated quality Download PDFInfo
- Publication number
- CN118396482B CN118396482B CN202410852509.2A CN202410852509A CN118396482B CN 118396482 B CN118396482 B CN 118396482B CN 202410852509 A CN202410852509 A CN 202410852509A CN 118396482 B CN118396482 B CN 118396482B
- Authority
- CN
- China
- Prior art keywords
- quality
- cultivated
- cultivated land
- model
- data
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 92
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000013210 evaluation model Methods 0.000 claims abstract description 43
- 238000012549 training Methods 0.000 claims abstract description 26
- 238000004458 analytical method Methods 0.000 claims abstract description 12
- 230000008859 change Effects 0.000 claims abstract description 12
- 239000002689 soil Substances 0.000 claims description 59
- 238000011156 evaluation Methods 0.000 claims description 43
- 239000002245 particle Substances 0.000 claims description 32
- 238000009826 distribution Methods 0.000 claims description 16
- 210000002569 neuron Anatomy 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 7
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 6
- 238000012800 visualization Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims description 3
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 238000012806 monitoring device Methods 0.000 claims description 3
- 230000035772 mutation Effects 0.000 claims description 3
- 229910052757 nitrogen Inorganic materials 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 229910052698 phosphorus Inorganic materials 0.000 claims description 3
- 239000011574 phosphorus Substances 0.000 claims description 3
- 239000011591 potassium Substances 0.000 claims description 3
- 229910052700 potassium Inorganic materials 0.000 claims description 3
- 239000004016 soil organic matter Substances 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000012876 topography Methods 0.000 claims description 3
- 238000003971 tillage Methods 0.000 claims 1
- 230000000007 visual effect Effects 0.000 abstract description 6
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000010921 in-depth analysis Methods 0.000 abstract 1
- 230000006870 function Effects 0.000 description 7
- 230000035558 fertility Effects 0.000 description 3
- 238000001556 precipitation Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000012271 agricultural production Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
Classifications
-
- 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
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/24—Earth materials
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/24—Earth materials
- G01N33/246—Earth materials for water content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- Medicinal Chemistry (AREA)
- Analytical Chemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Environmental & Geological Engineering (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geology (AREA)
- Remote Sensing (AREA)
- Food Science & Technology (AREA)
- Biochemistry (AREA)
- Agronomy & Crop Science (AREA)
- Primary Health Care (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
Abstract
The invention relates to the technical field of dynamic monitoring of cultivated quality, in particular to a climate change-oriented dynamic monitoring method of cultivated quality, which comprises the following steps: selecting a set region as a cultivated land monitoring region, constructing a three-dimensional model of the cultivated land monitoring region, introducing the three-dimensional model into a cultivated land quality dynamic monitoring system, inputting cultivated land data and meteorological data acquired in real time into a cultivated land quality index evaluation model which completes training, acquiring a cultivated land quality analysis result of the cultivated land monitoring region, and linking the three-dimensional model of the cultivated land monitoring region and the cultivated land quality index evaluation model which completes training in the cultivated land quality dynamic monitoring system to form a cultivated land quality dynamic monitoring visual model, so as to complete dynamic display of the cultivated land quality analysis result. The invention can comprehensively cover the selected farmland monitoring area, improves the representativeness and reliability of the monitoring data, and is beneficial to in-depth analysis of influence factors and change trend of farmland quality.
Description
Technical Field
The invention relates to the technical field of dynamic monitoring of cultivated quality, in particular to a climate change-oriented dynamic monitoring method of cultivated quality.
Background
The quality of cultivated land is a key factor affecting grain production and agricultural sustainable development. The traditional farmland quality monitoring method mainly depends on manual sampling and laboratory analysis, has the defects of low monitoring frequency, poor timeliness, high cost and the like, is difficult to reflect the influence of climate change on farmland quality in time, cannot realize dynamic monitoring and early warning, causes hysteresis of farmland quality management, and influences the scientificity and effectiveness of agricultural production decisions. Based on the above, we have devised a dynamic monitoring method of the cultivated quality for climate change.
Disclosure of Invention
The invention aims to provide a climate change-oriented dynamic farmland quality monitoring method, which comprises the steps of sequentially designing a three-dimensional model and a farmland quality index evaluation model of a farmland monitoring area in a selected area, and forming a dynamic farmland quality monitoring visual model in a linkage way, so that abstract farmland quality indexes can be converted into visual and image three-dimensional visual scenes, the spatial distribution of farmland quality is clear at a glance, the selected farmland monitoring area can be covered comprehensively, the representativeness and reliability of monitoring data are improved, the spatial distribution and dynamic change of farmland quality can be displayed intuitively, the deep analysis of influence factors and change trends of farmland quality is facilitated, and visual and understandable support is provided for decision making.
The invention is realized by the following technical scheme:
a dynamic monitoring method of the cultivated quality facing climate change comprises the following steps:
Selecting a set area as a cultivated land monitoring area, constructing a three-dimensional model of the cultivated land monitoring area, and leading the three-dimensional model into a cultivated land quality dynamic monitoring system, wherein in the cultivated land monitoring area, according to the corresponding three-dimensional model of the cultivated land monitoring area and soil types, each monitoring point is distributed through gridding to cover the cultivated land monitoring area in a whole area, and each monitoring point is provided with a cultivated land index acquisition device and a meteorological monitoring device;
the system comprises a cultivation quality dynamic monitoring system, wherein a cultivation quality index evaluation model for completing training is arranged in the cultivation quality dynamic monitoring system, cultivation quality analysis results of a cultivation monitoring area are obtained by inputting cultivation data and meteorological data acquired in real time into the cultivation quality index evaluation model for completing training, and a three-dimensional model of the cultivation monitoring area and the cultivation quality index evaluation model for completing training are linked in the cultivation quality dynamic monitoring system so as to form a cultivation quality dynamic monitoring visualization model for completing dynamic display of the cultivation quality analysis results.
Optionally, the three-dimensional model of the cultivated land monitoring area is constructed by the following steps:
Collecting remote sensing image data and topographic data of a cultivated land monitoring area;
Sequentially correcting, registering and enhancing the remote sensing image data, and sequentially denoising, interpolating and smoothing the terrain data through the DEM model;
the ArcGIS module combines the preprocessed remote sensing image data and the preprocessed topography data to construct a three-dimensional model of the cultivated land monitoring area, and the three-dimensional model of the cultivated land monitoring area is output and imported into a cultivated land quality dynamic monitoring system after fine processing.
Optionally, the cultivated land index includes: soil temperature, soil humidity, soil conductivity, soil pH value, soil organic matter content, soil total nitrogen content, soil total phosphorus content, soil total potassium content and soil volume weight.
Optionally, the construction process of the arable soil quality index evaluation model is as follows:
acquiring historical climate data and historical farmland data of a set region;
After pretreatment, summarizing the historical climate data and the historical farmland data of the area according to gridding, and characterizing the historical climate data and the historical farmland data as factors of all evaluation units;
determining the weight of each factor, solving the cultivated quality index of each evaluation unit through weighted average, and dividing the cultivated quality index of each evaluation unit into a first-level cultivated quality, a second-level cultivated quality and a third-level cultivated quality through grading logic;
And constructing a cultivated quality index evaluation model by taking the space data, the historical climate data and the historical cultivated land data of the evaluation units as input features and the cultivated quality index of the evaluation units as an output target, and dividing each evaluation unit into a training set and a test set by random sampling, wherein the cultivated quality grade of each evaluation unit is used as a label of the input features.
Optionally, the grading logic specifically includes:
the cultivation quality index is divided into a first threshold value and a second threshold value;
Judging whether the cultivated land quality index of the evaluation unit is lower than a first threshold value, if so, judging that the evaluation unit is the first-level cultivated land quality, and if not, entering the next step;
And judging whether the cultivated-soil quality index of the evaluation unit is lower than a second threshold value, if so, judging that the evaluation unit is of second-grade cultivated-soil quality, and if not, judging that the evaluation unit is of third-grade cultivated-soil quality, wherein the third-grade cultivated-soil quality is larger than the second-grade cultivated-soil quality and larger than the first-grade cultivated-soil quality.
Optionally, the training process of the arable soil quality index evaluation model is as follows:
Initializing parameters of a cultivated quality index evaluation model, including: weight W and bias b;
setting the number of particles in the mixed particle swarm optimization algorithm as N, and randomly initializing each particle Position and velocity of (a)；
Each particle is provided withIs decoded into a weight W and a bias b;
calculating the set objective function as the fitness value of the particle, and judging whether the fitness value of the current particle is smaller than the individual optimal position Corresponding fitness value, if yes, updating the optimal position of the individual; If not, not updating; judging whether the fitness value of the current particle is smaller than the global optimal positionCorresponding fitness value, if yes, updating the global optimal position; If not, not updating;
updating particles At the same time as the particlePerforming crossover and mutation to optimize the position of the particles, repeating the steps until the maximum iteration number is reached, and outputting a global optimal positionAnd the corresponding weight W and the bias b are used as optimal parameters of the cultivated quality index evaluation model, and the cultivated quality index evaluation model after training is output.
Optionally, the specific calculation formula of the set objective function is:
wherein, For the objective function, W and b are weights and biases of the arable soil quality index evaluation model,For the regularization coefficient(s),The model's predictive value for the ith sample is evaluated for the cultivated quality index,For the true value of the ith sample, m is the total number of samples of the training set, L is the number of layers of the neural network,For the number of neurons of the first layer,For the weights from the ith neuron to the jth neuron in the first layer,Is an index.
Optionally, after training, the arable quality index evaluation model further sequentially goes through a posterior distribution estimation step and a prediction uncertainty estimation step, so as to quantify the uncertainty of the arable quality index evaluation model.
The technical scheme of the invention has at least the following advantages and beneficial effects:
According to the invention, the three-dimensional model and the cultivated land quality index evaluation model of the cultivated land monitoring area are sequentially designed in the selected area, and the cultivated land quality index dynamic monitoring visualization model is formed by linkage, so that the abstract cultivated land quality index can be converted into an intuitive and visual three-dimensional visualization scene, the spatial distribution of the cultivated land quality is clear at a glance, the selected cultivated land monitoring area can be covered on the whole surface, the representativeness and the reliability of monitoring data are improved, the spatial distribution and the dynamic change of the cultivated land quality can be intuitively displayed, the influence factors and the change trend of the cultivated land quality can be deeply analyzed, and the intuitive and easily understood support is provided for decision.
Drawings
FIG. 1 is a flow chart of a dynamic monitoring method for the cultivated quality facing the climate change.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Referring to fig. 1, fig. 1 is a schematic flow chart of a dynamic monitoring method for farmland quality facing climate change.
In some embodiments, a method for dynamically monitoring the quality of a climate change oriented cultivation, the method comprising the steps of:
Selecting a set area as a cultivated land monitoring area, constructing a three-dimensional model of the cultivated land monitoring area, and leading the three-dimensional model into a cultivated land quality dynamic monitoring system, wherein in the cultivated land monitoring area, according to the corresponding three-dimensional model of the cultivated land monitoring area and soil types, each monitoring point is distributed through gridding to cover the cultivated land monitoring area in a whole area, and each monitoring point is provided with a cultivated land index acquisition device and a meteorological monitoring device;
the system comprises a cultivation quality dynamic monitoring system, wherein a cultivation quality index evaluation model for completing training is arranged in the cultivation quality dynamic monitoring system, cultivation quality analysis results of a cultivation monitoring area are obtained by inputting cultivation data and meteorological data acquired in real time into the cultivation quality index evaluation model for completing training, and a three-dimensional model of the cultivation monitoring area and the cultivation quality index evaluation model for completing training are linked in the cultivation quality dynamic monitoring system so as to form a cultivation quality dynamic monitoring visualization model for completing dynamic display of the cultivation quality analysis results.
In implementation, the three-dimensional model of the cultivated land monitoring area in the embodiment is constructed by the following steps:
Collecting remote sensing image data and topographic data of a cultivated land monitoring area;
Sequentially correcting, registering and enhancing the remote sensing image data, and sequentially denoising, interpolating and smoothing the terrain data through the DEM model;
the ArcGIS module combines the preprocessed remote sensing image data and the preprocessed topography data to construct a three-dimensional model of the cultivated land monitoring area, and the three-dimensional model of the cultivated land monitoring area is output and imported into a cultivated land quality dynamic monitoring system after fine processing.
In this embodiment, the cultivated land index includes: soil temperature, soil humidity, soil conductivity, soil pH value, soil organic matter content, soil total nitrogen content, soil total phosphorus content, soil total potassium content and soil volume weight.
In the implementation process of the above embodiment, the construction process of the cultivation quality index evaluation model is as follows:
acquiring historical climate data and historical farmland data of a set region;
After pretreatment, summarizing the historical climate data and the historical farmland data of the area according to gridding, and characterizing the historical climate data and the historical farmland data as factors of all evaluation units;
determining the weight of each factor, solving the cultivated quality index of each evaluation unit through weighted average, and dividing the cultivated quality index of each evaluation unit into a first-level cultivated quality, a second-level cultivated quality and a third-level cultivated quality through grading logic;
And constructing a cultivated quality index evaluation model by taking the space data, the historical climate data and the historical cultivated land data of the evaluation units as input features and the cultivated quality index of the evaluation units as an output target, and dividing each evaluation unit into a training set and a test set by random sampling, wherein the cultivated quality grade of each evaluation unit is used as a label of the input features.
More specifically, the cultivated land indexes mainly include environmental data, fertility data and the like of cultivated land soil, the meteorological data mainly include temperature, precipitation and the like, in this embodiment, the historical climate data and the historical cultivated land data of a selected set area are cleaned, missing values and abnormal values are removed respectively, the historical climate data and the historical cultivated land data of the set area are summarized according to the three-dimensional model mode of the meshed cultivated land monitoring area, and the grid or grid representation evaluation units are used for obtaining factor values of each evaluation unit, and as an example, the weight of each factor is determined by expert scoring: the annual average temperature is 0.2, the annual precipitation is 0.2, the soil temperature is 0.1, the soil humidity is 0.1, the soil conductivity is 0.1, the soil pH value is 0.1, and the soil fertility is 0.2. By passing throughThe individual factor values are normalized, wherein,For the normalized factor value, x is the original value of this factor,AndThe minimum and maximum of this factor, respectively. Then, the cultivated quality index of each evaluation unit is calculated by a weighted average method, namely:
Wherein, 、、、、、AndRespectively the standardized annual average temperature, annual precipitation, soil temperature, soil humidity, soil conductivity, soil pH value and soil fertility,Is a cultivated quality index. It will be appreciated that if the above weights include more components, the calculation can be performed by this formulaWherein, the method comprises the steps of, wherein,As the weight of the i-th factor,Is a normalized value of the i-th factor. The cultivated-soil quality index of each evaluation unit is then divided into a first-level cultivated-soil quality, a second-level cultivated-soil quality, and a third-level cultivated-soil quality by the following classification logic.
The grading logic specifically comprises the following steps:
the cultivation quality index is divided into a first threshold value and a second threshold value;
Judging whether the cultivated land quality index of the evaluation unit is lower than a first threshold value, if so, judging that the evaluation unit is the first-level cultivated land quality, and if not, entering the next step;
And judging whether the cultivated-soil quality index of the evaluation unit is lower than a second threshold value, if so, judging that the evaluation unit is of second-grade cultivated-soil quality, and if not, judging that the evaluation unit is of third-grade cultivated-soil quality, wherein the third-grade cultivated-soil quality is larger than the second-grade cultivated-soil quality and larger than the first-grade cultivated-soil quality.
As the above example, the evaluation unit is classified into three levels according to the cultivated quality index, wherein the first threshold value is set to 0.4 and the second threshold value is set to 0.7, and thus:
First grade cultivated land quality, i.e. low quality: SQI is less than 0.4;
The second grade of cultivated land quality is medium quality, wherein SQI is more than or equal to 0.4 and less than 0.7;
the third grade of cultivated land has high quality, wherein SQI is more than or equal to 0.7.
More specifically, the spatial data of the evaluation unit includes: and evaluating longitude and latitude, altitude, gradient and slope direction of the unit. According to the method, the evaluation standard of the cultivated land quality can be definitely defined by calculating the cultivated land quality index through a weighted average method, different factors are given with different weights according to professional knowledge, and the cultivated land quality index evaluation model is helped to better understand the influence of the different factors on the cultivated land quality, so that the generalization capability of the model is improved.
In this embodiment, the training process of the cultivation quality index evaluation model is as follows:
Initializing parameters of a cultivated quality index evaluation model, including: weight W and bias b;
setting the number of particles in the mixed particle swarm optimization algorithm as N, and randomly initializing each particle Position and velocity of (a)；
Each particle is provided withIs decoded into a weight W and a bias b;
calculating the set objective function as the fitness value of the particle, and judging whether the fitness value of the current particle is smaller than the individual optimal position Corresponding fitness value, if yes, updating the optimal position of the individual; If not, not updating; judging whether the fitness value of the current particle is smaller than the global optimal positionCorresponding fitness value, if yes, updating the global optimal position; If not, not updating;
The specific calculation formula of the set objective function is as follows:
wherein, For the objective function, W and b are weights and biases of the arable soil quality index evaluation model,For the regularization coefficient(s),The model's predictive value for the ith sample is evaluated for the cultivated quality index,For the true value of the ith sample, m is the total number of samples of the training set, L is the number of layers of the neural network,For the number of neurons of the first layer,For the weights from the ith neuron to the jth neuron in the first layer,Is an index.
Updating particlesSpeed and position of (c):
wherein, 、Respectively the learning factors are respectively used for the learning factors,、Respectively random numbers between 0 and 1,In order to update the velocity of the particles,As the weight of the inertia is given,For the particle velocity before update.
For particlesPerforming crossover and mutation to optimize the position of the particles, repeating the steps until the maximum iteration number is reached, and outputting a global optimal positionAnd the corresponding weight W and the bias b are used as optimal parameters of the cultivated quality index evaluation model, and the cultivated quality index evaluation model after training is output.
Furthermore, the arable quality index evaluation model is used for quantifying the uncertainty of the arable quality index evaluation model after training is completed, and the arable quality index evaluation model also sequentially goes through a posterior distribution estimation step and a prediction uncertainty estimation step.
After obtaining the optimal model parameters, the present embodiment needs to estimate posterior distribution of parameters of the arable quality index estimation model to quantify uncertainty of the arable quality index estimation model, where the posterior distribution estimation step specifically includes:
from a priori distribution The initial parameter values are randomly sampled.
For the t-th iteration, fromMid-sampling candidate parameters。
The probability of acceptance is calculated by the following formula:
With probability Accepting candidate parameters, i.e.If not, rejecting the candidate parameters, i.e。
The iterative steps are repeated until convergence.
Wherein,To sample new candidate model parameters from the candidate parameter distribution in the t-th iterationIs a function of the probability of (1),Model parameters, which are candidates in the t-th iteration, respectively, include weightsBias and method of making same，For all of the viewing data relating to the quality of the cultivated land,For the weight parameters of the current model in the t-1 th iteration,Is the bias parameter of the current model in the t-1 th iteration.
The objective of posterior distribution estimation is to quantify uncertainty of parameters of the model for estimating the index of the cultivated quality, and through the steps, the posterior distribution of the parameters can be obtained according to the embodimentI.e. at a given dataIn the case of (a), the cultivated quality index evaluates the probability distribution of model parameters W and b, reflecting the uncertainty of the parameters.
In addition, after the posterior distribution estimation step is finished, the method generates a plurality of model prediction results by sampling posterior distribution, calculates the mean value and the variance of the prediction results, and respectively characterizes the expected value and the uncertainty of the prediction, so that the generalization capability and the reliability of the cultivated quality index estimation model on new data can be reflected.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (2)
1. The dynamic monitoring method for the farmland quality facing the climate change is characterized by comprising the following steps:
Selecting a set area as a cultivated land monitoring area, constructing a three-dimensional model of the cultivated land monitoring area, and leading the three-dimensional model into a cultivated land quality dynamic monitoring system, wherein in the cultivated land monitoring area, according to the corresponding three-dimensional model of the cultivated land monitoring area and soil types, each monitoring point is distributed through gridding to cover the cultivated land monitoring area in a whole area, and each monitoring point is provided with a cultivated land index acquisition device and a meteorological monitoring device;
The system comprises a cultivation quality dynamic monitoring system, a cultivation quality index evaluation model, a cultivation quality analysis model and a cultivation quality analysis model, wherein the cultivation quality index evaluation model is arranged in the cultivation quality dynamic monitoring system and used for finishing training, cultivation quality data and meteorological data acquired in real time are input into the cultivation quality index evaluation model which is used for finishing training, cultivation quality analysis results of a cultivation quality monitoring area are obtained, and a three-dimensional model of the cultivation quality monitoring area and the cultivation quality index evaluation model which is used for finishing training are linked in the cultivation quality dynamic monitoring system so as to form a cultivation quality dynamic monitoring visualization model, and dynamic display of the cultivation quality analysis results is finished;
the three-dimensional model of the cultivated land monitoring area is constructed by the following steps:
Collecting remote sensing image data and topographic data of a cultivated land monitoring area;
Sequentially correcting, registering and enhancing the remote sensing image data, and sequentially denoising, interpolating and smoothing the terrain data through the DEM model;
combining the preprocessed remote sensing image data and the preprocessed topography data through the ArcGIS module to construct a three-dimensional model of the cultivated land monitoring area, outputting the three-dimensional model of the cultivated land monitoring area after refinement treatment, and importing the three-dimensional model into a cultivated land quality dynamic monitoring system;
The cultivated land indexes comprise: soil temperature, soil humidity, soil conductivity, soil pH value, soil organic matter content, soil total nitrogen content, soil total phosphorus content, soil total potassium content and soil volume weight;
The construction process of the cultivation quality index evaluation model comprises the following steps:
acquiring historical climate data and historical farmland data of a set region;
After pretreatment, summarizing the historical climate data and the historical farmland data of the area according to gridding, and characterizing the historical climate data and the historical farmland data as factors of all evaluation units;
determining the weight of each factor, solving the cultivated quality index of each evaluation unit through weighted average, and dividing the cultivated quality index of each evaluation unit into a first-level cultivated quality, a second-level cultivated quality and a third-level cultivated quality through grading logic;
Using space data, historical climate data and historical cultivated land data of the evaluation units as input features, using cultivated quality indexes of the evaluation units as output targets, constructing a cultivated quality index evaluation model, and dividing each evaluation unit into a training set and a test set through random sampling, wherein cultivated quality grades of each evaluation unit are used as labels of the input features;
The grading logic specifically comprises the following steps:
the cultivation quality index is divided into a first threshold value and a second threshold value;
Judging whether the cultivated land quality index of the evaluation unit is lower than a first threshold value, if so, judging that the evaluation unit is the first-level cultivated land quality, and if not, entering the next step;
Judging whether the cultivated quality index of the evaluation unit is lower than a second threshold value, if so, judging that the evaluation unit is of second-grade cultivated land quality, and if not, judging that the evaluation unit is of third-grade cultivated land quality, wherein the third-grade cultivated land quality is larger than the second-grade cultivated land quality and larger than the first-grade cultivated land quality;
The training process of the tillage quality index evaluation model is as follows:
Initializing parameters of a cultivated quality index evaluation model, including: weight W and bias b;
setting the number of particles in the mixed particle swarm optimization algorithm as N, and randomly initializing each particle Position and velocity of (a)；
Each particle is provided withIs decoded into a weight W and a bias b;
calculating the set objective function as the fitness value of the particle, and judging whether the fitness value of the current particle is smaller than the individual optimal position Corresponding fitness value, if yes, updating the optimal position of the individual; If not, not updating; judging whether the fitness value of the current particle is smaller than the global optimal positionCorresponding fitness value, if yes, updating the global optimal position; If not, not updating;
updating particles At the same time as the particlePerforming crossover and mutation to optimize the position of the particles, repeating the steps until the maximum iteration number is reached, and outputting a global optimal positionThe corresponding weight W and the bias b are used as optimal parameters of the cultivated quality index evaluation model, and the cultivated quality index evaluation model after training is output;
The specific calculation formula of the set objective function is as follows:
wherein, For the objective function, W and b are weights and biases of the arable soil quality index evaluation model,For the regularization coefficient(s),The model's predictive value for the ith sample is evaluated for the cultivated quality index,For the true value of the ith sample, m is the total number of samples of the training set, L is the number of layers of the neural network,For the number of neurons of the first layer,For the weights from the ith neuron to the jth neuron in the first layer,Is an index.
2. The climate change-oriented dynamic monitoring method for the cultivated quality according to claim 1, wherein the cultivated quality index evaluation model is further subjected to a posterior distribution estimation step and a prediction uncertainty estimation step in sequence after training is completed, and is used for quantifying the uncertainty of the cultivated quality index evaluation model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410852509.2A CN118396482B (en) | 2024-06-28 | 2024-06-28 | Climate change-oriented dynamic monitoring method for cultivated quality |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410852509.2A CN118396482B (en) | 2024-06-28 | 2024-06-28 | Climate change-oriented dynamic monitoring method for cultivated quality |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118396482A CN118396482A (en) | 2024-07-26 |
| CN118396482B true CN118396482B (en) | 2024-08-27 |
Family
ID=91999922
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410852509.2A Active CN118396482B (en) | 2024-06-28 | 2024-06-28 | Climate change-oriented dynamic monitoring method for cultivated quality |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118396482B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118569656B (en) * | 2024-08-02 | 2024-10-22 | 山东省国土空间数据和遥感技术研究院(山东省海域动态监视监测中心) | Multi-mode monitoring data fusion-based dynamic farmland risk updating platform |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111667183A (en) * | 2020-06-08 | 2020-09-15 | 重庆市国土整治中心 | Method and system for monitoring cultivated land quality |
| AU2021100045A4 (en) * | 2021-01-05 | 2021-03-25 | Aparna, Gira Mrs | Soil health monitoring using drones and Augmented reality in agricultural Regions |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230345889A1 (en) * | 2015-02-20 | 2023-11-02 | Dtn, Llc | Modeling of soil compaction and structural capacity for field trafficability by agricultural equipment from diagnosis and prediction of soil and weather conditions associated with user-provided feedback |
| US20240049619A1 (en) * | 2020-12-23 | 2024-02-15 | Basf Agro Trademarks Gmbh | Method for determining field-or zone-specific seeding rate, depth, and time for planting a crop in an agricultural field based on multiple data inputs such as crop, field, yield, weather, and/or soil data |
| KR102486587B1 (en) * | 2021-07-09 | 2023-01-09 | 고려대학교 산학협력단 | Agricultural system meta-modeling method and agricultural meta-modeling system for climate change impact prediction |
| CN115619583A (en) * | 2022-10-19 | 2023-01-17 | 中国气象局沈阳大气环境研究所 | Construction method of composite agricultural meteorological disaster monitoring index system |
| CN116662784B (en) * | 2023-06-05 | 2023-10-27 | 云南瀚哲科技有限公司 | Method and system for monitoring cultivated quality |
-
2024
- 2024-06-28 CN CN202410852509.2A patent/CN118396482B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111667183A (en) * | 2020-06-08 | 2020-09-15 | 重庆市国土整治中心 | Method and system for monitoring cultivated land quality |
| AU2021100045A4 (en) * | 2021-01-05 | 2021-03-25 | Aparna, Gira Mrs | Soil health monitoring using drones and Augmented reality in agricultural Regions |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118396482A (en) | 2024-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113919448B (en) | Method for analyzing influence factors of carbon dioxide concentration prediction at any time-space position | |
| Feng et al. | Modeling urban growth with GIS based cellular automata and least squares SVM rules: a case study in Qingpu–Songjiang area of Shanghai, China | |
| CN101354757B (en) | Method for predicting dynamic risk and vulnerability under fine dimension | |
| CN111665575B (en) | Medium-and-long-term rainfall grading coupling forecasting method and system based on statistical power | |
| CN113902580B (en) | Historical farmland distribution reconstruction method based on random forest model | |
| CN113222316B (en) | Variation scenario simulation method based on FLUS model and biodiversity model | |
| CN111260111A (en) | Runoff forecast improvement method based on meteorological big data | |
| CN118396482B (en) | Climate change-oriented dynamic monitoring method for cultivated quality | |
| CN110826689A (en) | Method for predicting county-level unit time sequence GDP based on deep learning | |
| CN108764527B (en) | Screening method for soil organic carbon library time-space dynamic prediction optimal environment variables | |
| CN117787081A (en) | Hydrological model parameter uncertainty analysis method based on Morris and Sobol methods | |
| CN114972984B (en) | Random forest-based snow space-time analysis and prediction method | |
| CN117993305B (en) | Dynamic evaluation method for river basin land utilization and soil erosion relation | |
| Noor et al. | Prediction map of rainfall classification using random forest and inverse distance weighted (IDW) | |
| CN116110210B (en) | Data-driven landslide hazard auxiliary decision-making method in complex environment | |
| CN117010274B (en) | Intelligent early warning method for harmful elements in underground water based on integrated incremental learning | |
| JP6950647B2 (en) | Data determination device, method, and program | |
| Chao et al. | A spatio-temporal neural network learning system for city-scale carbon storage capacity estimating | |
| CN117523408A (en) | Remote sensing image residential area extraction method and system based on improved YOLOV8 | |
| CN116401962A (en) | Method for pushing optimal characteristic scheme of water quality model | |
| CN117131991A (en) | Urban rainfall prediction method and platform based on hybrid neural network | |
| CN116258279A (en) | Landslide vulnerability evaluation method and device based on comprehensive weighting | |
| CN116663404A (en) | Flood forecasting method and system coupling artificial intelligence and Bayesian theory | |
| CN113553708A (en) | Method and device for tracing key influence factors of simulation model | |
| CN113792105A (en) | Geospatial point data sampling method based on half-variogram |
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 |