CN117114176A - Land utilization change prediction method and system based on data analysis and machine learning - Google Patents
Land utilization change prediction method and system based on data analysis and machine learning Download PDFInfo
- Publication number
- CN117114176A CN117114176A CN202311023749.3A CN202311023749A CN117114176A CN 117114176 A CN117114176 A CN 117114176A CN 202311023749 A CN202311023749 A CN 202311023749A CN 117114176 A CN117114176 A CN 117114176A
- Authority
- CN
- China
- Prior art keywords
- land
- data
- change
- prediction
- machine learning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000008859 change Effects 0.000 title claims abstract description 75
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000010801 machine learning Methods 0.000 title claims abstract description 34
- 238000007405 data analysis Methods 0.000 title claims abstract description 19
- 238000012546 transfer Methods 0.000 claims abstract description 48
- 238000004088 simulation Methods 0.000 claims abstract description 30
- 239000011159 matrix material Substances 0.000 claims abstract description 28
- 238000012549 training Methods 0.000 claims abstract description 14
- 238000007781 pre-processing Methods 0.000 claims abstract description 13
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 4
- 238000004458 analytical method Methods 0.000 claims description 14
- 238000011156 evaluation Methods 0.000 claims description 10
- 239000010410 layer Substances 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000012795 verification Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000009826 distribution Methods 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 claims description 4
- 230000007704 transition Effects 0.000 claims description 4
- 238000011282 treatment Methods 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000011160 research Methods 0.000 claims description 3
- 239000002356 single layer Substances 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000009966 trimming Methods 0.000 claims description 3
- 238000011161 development Methods 0.000 description 7
- 230000018109 developmental process Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000009736 wetting Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- 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
- G06Q10/067—Enterprise or organisation modelling
-
- 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
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Analysis (AREA)
- Primary Health Care (AREA)
- Probability & Statistics with Applications (AREA)
- Algebra (AREA)
- Artificial Intelligence (AREA)
- Computational Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a land use change prediction method and a system based on data analysis and machine learning, wherein the land use change prediction method comprises the following steps: (1) collecting data and constructing a data set; (2) Determining a classification standard of land utilization types, and preprocessing data; (3) calculating a land use transfer matrix; (4) Constructing a land use change prediction model based on a CA-Markov model according to land use transfer change and land use change driving factors through a machine learning algorithm; (5) Model training is carried out, and future land utilization changes are predicted through the trained model. According to the invention, the prediction model is constructed and the machine learning training is carried out, so that the precision of land utilization change simulation prediction is improved, the change trend and mode of land utilization can be accurately predicted, and a scientific basis is provided for land resource management and decision making.
Description
Technical Field
The invention relates to a land utilization change prediction technology, in particular to a method and a system for predicting the land utilization change of a river basin based on data analysis and machine learning.
Background
Urban and urban expansion will lead to land conversion from natural uses such as agriculture, forests or barren lands to construction land as the population increases, which is one of the major drivers leading to land utilization changes. Effective management of land resources is critical to achieving sustainable development. The balance between various uses in agriculture, forestry, mining, industry and urban development needs to be achieved by predicting land use changes. Predicting land use changes may help assess the potential impact of different projects and developments on the environment. By simulating future land use patterns, potential environmental risks and challenges can be better appreciated. With the development of remote sensing and GIS technologies, the acquisition and processing of spatial data becomes more convenient and efficient. The techniques can provide a large amount of land utilization and land coverage information, and provide important data support for land utilization change prediction methods. With the improvement of computing power and the development of machine learning technology, researchers can develop more complex and accurate land utilization change prediction models. The models can be combined with various data sources such as historical land utilization data, socioeconomic data, remote sensing images and the like, so that the prediction accuracy is improved. The application of the land utilization change prediction method can provide scientific basis for decision makers and promote sustainable land management and urban and rural development. However, the combination of the existing prediction model technology such as a CA model and a GIS, MCES, maxent, SLEUTH model has the problems of weak space-time synchronization simulation capability, strong correlation among cell conversion, large influence on simulation precision by various factors, difficulty in reflecting land type change fluctuation, complex growth and the like.
Disclosure of Invention
The invention aims to: the invention aims to provide a land utilization change prediction method capable of accurately predicting the change trend and mode of land utilization based on data analysis and machine learning; the invention also provides a land utilization change prediction system based on data analysis and machine learning.
The technical scheme is as follows: the land utilization change prediction method based on data analysis and machine learning comprises the following steps:
(1) Collecting data and constructing a data set;
(2) Determining a classification standard of land utilization types, and preprocessing data;
(3) Calculating a land use transfer matrix;
(4) Constructing a land use change prediction model based on a CA-Markov model according to land use transfer change and land use change driving factors through a machine learning algorithm;
(5) Model training is carried out, and future land utilization changes are predicted through the trained model.
Further, in step (1), the collected data includes image data, geographical elevation data and road data of the predicted area land utilization.
Further, the step (2) includes the steps of:
(21) Determining a classification standard of land utilization types according to the attribute of the data source, the land classification standard, the actual condition of a prediction area and the prediction target requirement;
(22) Converting the unified data coordinate system of the raster data into the same projection coordinate system, and overlapping the trimming data range with the research area to ensure that the raster numbers of all raster data are equal;
(23) And determining the resolution of the raster data according to the size of the predicted area, the model operation time and the calculation precision.
Further, the step (3) includes the steps of:
(31) After grid reclassification, grid surface turning, vector fusion and intersection treatment are carried out, land use transfer change is calculated by a grid calculator, and a land use transfer matrix S is obtained ij :
Wherein: s is S ij Representing the area or probability of the i-th land type being converted into the j-th land type, and representing the area or probability of the land type not being converted when i=j; i=1, 2, …, n; j=1, 2, …, n; n is the number of land types.
Further, the step (4) includes the following steps:
(41) Selecting a driving factor influencing land utilization change, and performing data rasterization;
(42) Carrying out superposition statistical analysis on the driving factor image and land utilization data, and determining the relation between the distribution of each land utilization type and the driving factor;
(43) Determining the weight of each driving factor by using an analytic hierarchy process, and manufacturing a land use transfer suitability atlas by using an MCE (multi-criterion evaluation) model;
(44) And selecting a land utilization initial year, a land utilization change transfer matrix, a land utilization transfer suitability image set and a prediction period, carrying out land utilization change simulation, comparing with actual land utilization data, and carrying out simulation result precision evaluation by using Kappa coefficients.
Further, the step (43) includes the steps of:
(431) Establishing a hierarchical structure model according to the interrelationships among decision targets, criteria and schemes;
(432) Comparing the importance of the factors, and adopting relative scale to measure to construct a judgment matrix A;
(433) Calculating a single-layer weight vector and performing consistency check;
(435) And calculating index weights when all the judgment matrixes pass the consistency test.
Further, in step (432), element m in A ij The method meets the following conditions:
wherein: m is m ij Represents the relative importance degree between the ith index and the jth index in the same layer of indexes, m ji The relative importance degree between the jth index and the ith index in the index of the same layer is represented;
in step (433), a consistency index CI is calculated to check the inconsistency of the matrix, the CI having a functional expression of
AW=λ max W (4)
Wherein: lambda (lambda) max To judge the maximum eigenvalue of matrix A, W is the corresponding lambda max Is subjected to normalization processing;
calculating a random consistency index RI:
calculate the consistency ratio CR:
when CR <0.1, the judgment matrix passes the consistency check.
Further, in step (44), the Kappa coefficient is calculated as follows:
wherein: n is the total number of grids; n is n 1 To simulate a consistent grid number; n is the number of land types, n=6; p (P) 0 Representing a simulated uniform grid scale; p (P) e Representing the inverse of the number of land types.
Further, the step (5) includes the following steps:
(51) Performing error analysis on the simulation result, adjusting land utilization transfer rules according to the analysis result, re-developing model simulation and evaluating the simulation result until obtaining the simulation result meeting the precision requirement;
(52) Selecting an initial year and a prediction period, formulating a corresponding land use transfer matrix and a transfer suitability image set, and performing simulation prediction to obtain land use images of the coming year;
(53) The prediction results are further analyzed, including the quantity change and the space transfer change of each type of land utilization.
The land utilization change prediction system based on data analysis and machine learning comprises a data acquisition module, a data preprocessing module, a machine learning model training module, a model verification and evaluation module, a prediction module, a result analysis and interpretation module;
the data acquisition module is used for collecting and arranging historical land utilization data and related environmental factor data;
the data preprocessing module is used for preprocessing the acquired data, such as cleaning, feature extraction, standardization and the like;
the machine learning model training module is used for training and modeling a machine learning model on the preprocessed data;
the model verification and evaluation module is used for verifying and evaluating the trained model so as to ensure the prediction accuracy and reliability;
the prediction module is used for predicting land utilization change by using the trained model and generating a prediction result;
and the result analysis and interpretation module is used for analyzing and interpreting the predicted result, extracting the variation trend and pattern and providing support and guidance for decision and planning.
The beneficial effects are that: compared with the prior art, the invention has the remarkable advantages that: on the treatment of land use change influencing driving factors, the weight of the land use influencing factors is quantized by combining an MCE model with a analytic hierarchy process system, and a scientific and simple method is provided for the weighting of decision indexes; the land utilization change prediction model is built based on the CA-Markov model and machine learning training is carried out, so that the precision of land utilization change simulation prediction is improved, the change trend and mode of land utilization can be accurately predicted, and a scientific basis is provided for land resource management and decision making. In addition, the invention provides a complete land utilization change prediction system, which has high degree of mechanization and complete and easy operation of the module.
Drawings
FIG. 1 is a schematic flow chart of the present invention;
FIG. 2 is a view of a current image of land use according to the present invention;
FIG. 3 is a plot of land use transfer suitability of the present invention;
FIG. 4 is a simulated comparison of land use according to the present invention;
FIG. 5 is a diagram showing future land use change predictions in accordance with the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
As shown in fig. 1, the land utilization change prediction method based on data analysis and machine learning according to the present invention comprises the steps of:
step 1: collecting the image data, geographic elevation data, road data and the like of the land utilization of the predicted area, and constructing a data set;
collecting predicted basin land utilization image data, basin DEM data, gradient data, road data (expressway, highway, railway) and the like;
step 2: determining a classification standard of land utilization types, and preprocessing data;
determining classification standards of land utilization types according to the attributes of the data sources and the land classification standards and combining the actual conditions of the prediction areas and the requirements of the prediction targets; converting the unified data coordinate system of the raster data into the same projection coordinate system, and overlapping the trimming data range with the research area to ensure that the raster numbers of all raster data are equal; determining the resolution of raster data according to the size of the predicted area, the model operation time and the calculation accuracy;
step 3: calculating a land use transfer matrix;
performing grid reclassification, grid surface turning, vector fusion, intersection and other treatments, calculating land use transfer change through a grid calculator, and finishing to obtain a land use transfer matrix;
land use transfer matrix:
wherein: s is S ij (i, j=1, 2, …, n) represents an area (or probability) that the i-th land type is converted to the j-th land type, and i=j represents an area (or probability) that the land type is not converted; n is the number of land types.
Step 4: and constructing a land use change prediction model based on the CA-Markov model according to land use transfer change and land use change driving factors by using a machine learning algorithm.
Selecting driving factors which influence land use changes, such as: DEM, gradient, distance from road, etc., to perform rasterization processing of data; carrying out superposition statistical analysis on the driving factor image and land utilization data, and determining the relation between the distribution of each land utilization type and the driving factor; determining the weight of each driving factor by using an analytic hierarchy process, and manufacturing a land use transfer suitability atlas; and selecting a land utilization initial year, a land utilization change transfer matrix, a land utilization transfer suitability image set and a prediction period, carrying out land utilization change simulation, comparing with actual land utilization data, and carrying out simulation result precision evaluation by using Kappa coefficients.
Analytical hierarchy process: the method is a decision analysis method combining qualitative and quantitative analysis for solving the complex problem of multiple targets. The method is simple and practical, requires less quantitative information, and can be well applied to the weighting of land utilization driving factors. The method comprises the following steps:
a. establishing a hierarchical structure model according to the interrelationships among decision targets, criteria and schemes;
b. comparing the factors with each other, and comparing the importance degree by adopting relative scale, thus constructing the element m in the judgment matrix A ij The method meets the following conditions:
wherein: m is m ij The relative importance degree between the ith index and the jth index in the index of the same layer is expressed.
c. Calculating single-layer weight vector and performing consistency check
Defining a consistency index:
AW=λ max W (4)
wherein: lambda (lambda) max To judge the maximum eigenvalue of matrix A, W is the corresponding lambda max Is used for the feature vector after normalization processing.
Defining a random consistency index:
defining a consistency ratio:
it is considered that the judgment matrix passes the consistency check when CR < 0.1.
d. When all the judgment matrixes pass the consistency test, the index weight can be calculated.
The Kappa coefficient is calculated as follows:
wherein: n is the total number of grids; n1 is the number of grids which are consistent in simulation; n is the number of land types, n=6; p (P) 0 Representing a simulated uniform grid scale; p (P) e Representing the inverse of the number of land types.
Step 5: model training is carried out, and the trained model is utilized to predict land utilization changes in a certain period in the future.
Performing error analysis on the simulation result, adjusting land utilization transfer rules according to the analysis result, re-developing model simulation and evaluating the simulation result until obtaining the simulation result meeting the precision requirement; selecting an initial year and a prediction period, formulating a corresponding land use transfer matrix and a transfer suitability image set, and performing simulation prediction to obtain land use images of the coming year; the prediction results are further analyzed, including the quantity change and the space transfer change of each type of land utilization.
The invention also relates to a land use change prediction system based on data analysis and machine learning, which comprises the following components: and a data acquisition module: for collecting and collating historical land use data and related environmental factor data. And a data preprocessing module: the method is used for carrying out preprocessing operations such as cleaning, feature extraction, standardization and the like on the acquired data. Machine learning model training module: for training and modeling machine learning models on the preprocessed data. Model verification and evaluation module: for verifying and evaluating the trained models to ensure prediction accuracy and reliability. And a prediction module: and predicting land utilization change by using the trained model, and generating a prediction result. Result analysis and interpretation module: analyzing and explaining the predicted result, extracting the variation trend and mode, and providing support and guidance for decision and planning.
The method takes the simulation prediction of the land utilization change of the river basin as the practical application.
(1) Drainage basin profile
The climate transition area of the east Asia monsoon wetting area and the semi-wetting area at the river basin is an overlapped area of three transition zones of south-north climate, high-low latitude and sea-land phase, the weather system is complex and changeable, the large-scale circulation and water vapor conveying background has very obvious influence on the climate characteristics of the river basin, and the climate transition area is a sensitive area of climate change in China, so that the typical area drought and waterlogging characteristics of no-drop drought and water waterlogging and strong rainfall flood of the river basin are formed. The river basin has rich natural resources and large cultivated area, and is an important grain-producing base in China. Meanwhile, the population density of the drainage basins is high, the land utilization modes are complex and changeable, and the contradiction between natural ecology and economic and social development is increasingly prominent.
Collecting land utilization image data (data resolution is 1 km) of 3 stages of river basin 1995, 2005 and 2015, and performing data preprocessing (data cutting, correction and the like) by a space analysis tool; determining land utilization classification standards, and calculating a land utilization transfer matrix; determining an influence factor of land use transfer change, wherein the model construction considers factors such as a basin DEM, a gradient, a distance from a road (highway, railway, high speed) and the like to be selected as the land use transfer influence factor; performing image superposition analysis on land use transfer influence factors and Huaihe land use data, determining the relation between the distribution of each land use type and the driving factors, and manufacturing a land use transfer suitability atlas through an MCE model; and (3) model input is carried out based on the CA-Markov model, a land utilization change prediction model is constructed, and land utilization simulation prediction is carried out.
According to the implementation, the land utilization types of the river basin are classified into 6 major categories according to the first-level type classification standard of the table 1, and the simulation prediction of land utilization change is carried out based on the classification standard. The land utilization transfer area matrices of the river basin in 1995-2005 and 2005-2015 are calculated as shown in tables 2 and 3 respectively. The land use transfer suitability image produced by combining the MCE multi-criterion evaluation model is shown in fig. 3 (the graph is the suitability of cultivated land transfer), the Kappa coefficient based on the 2015 land use change (fig. 4) simulated by the land use transfer change in 1995-2005 and the actual measurement is 0.9302, which is higher than the precision of the traditional model (the Kappa coefficient is generally considered to be 0.75, namely the simulation effect is better). Therefore, the land use change prediction model constructed based on the method has higher precision, and meanwhile, the land use change pattern of the river basin 2025 year is predicted based on the land use pattern of 2015 as shown in fig. 5.
TABLE 1 land type Classification criteria
Table 2 land use transfer area matrix unit: km 2
Table 3 land use transfer area matrix unit: km 2
Claims (10)
1. The land utilization change prediction method based on data analysis and machine learning is characterized by comprising the following steps of:
(1) Collecting data and constructing a data set;
(2) Determining a classification standard of land utilization types, and preprocessing data;
(3) Calculating a land use transfer matrix;
(4) Constructing a land use change prediction model based on a CA-Markov model according to land use transfer change and land use change driving factors through a machine learning algorithm;
(5) Model training is carried out, and future land utilization changes are predicted through the trained model.
2. The land use change prediction method based on data analysis and machine learning of claim 1, wherein in step (1), the collected data includes image data, geographical elevation data and road data of predicted land use.
3. The land use change prediction method based on data analysis and machine learning as claimed in claim 1, wherein the step (2) comprises the steps of:
(21) Determining a classification standard of land utilization types according to the attribute of the data source, the land classification standard, the actual condition of a prediction area and the prediction target requirement;
(22) Converting the unified data coordinate system of the raster data into the same projection coordinate system, and overlapping the trimming data range with the research area to ensure that the raster numbers of all raster data are equal;
(23) And determining the resolution of the raster data according to the size of the predicted area, the model operation time and the calculation precision.
4. The land use change prediction method based on data analysis and machine learning as claimed in claim 1, wherein the step (3) comprises the steps of:
(31) After grid reclassification, grid surface turning, vector fusion and intersection treatment are carried out, land use transfer change is calculated by a grid calculator, and a land use transfer matrix S is obtained ij :
Wherein: s is S ij Indicating the area or probability of the i-th land type being converted to the j-th land type, indicating that the land type does not occur when i=jArea or probability of transition; i=1, 2, …, n; j=1, 2, …, n; n is the number of land types.
5. The land use change prediction method based on data analysis and machine learning as claimed in claim 1, wherein the step (4) comprises the steps of:
(41) Selecting a driving factor influencing land utilization change, and performing data rasterization;
(42) Carrying out superposition statistical analysis on the driving factor image and land utilization data, and determining the relation between the distribution of each land utilization type and the driving factor;
(43) Determining the weight of each driving factor by using an analytic hierarchy process, and manufacturing a land use transfer suitability atlas by using an MCE (multi-criterion evaluation) model;
(44) And selecting a land utilization initial year, a land utilization change transfer matrix, a land utilization transfer suitability image set and a prediction period, carrying out land utilization change simulation, comparing with actual land utilization data, and carrying out simulation result precision evaluation by using Kappa coefficients.
6. The method of river basin land use change prediction based on data analysis and machine learning of claim 5, wherein step (43) comprises the steps of:
(431) Establishing a hierarchical structure model according to the interrelationships among decision targets, criteria and schemes;
(432) Comparing the importance of the factors, and adopting relative scale to measure to construct a judgment matrix A;
(433) Calculating a single-layer weight vector and performing consistency check;
(434) And calculating index weights when all the judgment matrixes pass the consistency test.
7. The method for predicting land use as in claim 6, wherein in step (432), element m in a ij The method meets the following conditions:
wherein: m is m ij Represents the relative importance degree between the ith index and the jth index in the same layer of indexes, m ji The relative importance degree between the jth index and the ith index in the index of the same layer is represented;
in step (433), a consistency index CI is calculated to check the inconsistency of the matrix, the CI having a functional expression of
AW=λ max W (4)
Wherein: lambda (lambda) max To judge the maximum eigenvalue of matrix A, W is the corresponding lambda max Is subjected to normalization processing;
calculating a random consistency index RI:
calculate the consistency ratio CR:
when CR <0.1, the judgment matrix passes the consistency check.
8. The land use change prediction method based on data analysis and machine learning as claimed in claim 7, wherein in step (44), the calculation formula of Kappa coefficient is as follows:
wherein: n is the total number of grids; n is n 1 To simulate a consistent grid number; n is the number of land types, n=6; p (P) 0 Representing a simulated uniform grid scale; p (P) e Representing the inverse of the number of land types.
9. The land use change prediction method based on data analysis and machine learning as claimed in claim 1, wherein the step (5) comprises the steps of:
(51) Performing error analysis on the simulation result, adjusting land utilization transfer rules according to the analysis result, re-developing model simulation and evaluating the simulation result until obtaining the simulation result meeting the precision requirement;
(52) Selecting an initial year and a prediction period, formulating a corresponding land use transfer matrix and a transfer suitability image set, and performing simulation prediction to obtain land use images of the coming year;
(53) The prediction results are further analyzed, including the quantity change and the space transfer change of each type of land utilization.
10. The land utilization change prediction system based on data analysis and machine learning is characterized by comprising a data acquisition module, a data preprocessing module, a machine learning model training module, a model verification and evaluation module, a prediction module, a result analysis and interpretation module;
the data acquisition module is used for collecting and arranging historical land utilization data and related environmental factor data;
the data preprocessing module is used for preprocessing the acquired data, such as cleaning, feature extraction, standardization and the like;
the machine learning model training module is used for training and modeling a machine learning model on the preprocessed data;
the model verification and evaluation module is used for verifying and evaluating the trained model so as to ensure the prediction accuracy and reliability;
the prediction module is used for predicting land utilization change by using the trained model and generating a prediction result;
and the result analysis and interpretation module is used for analyzing and interpreting the predicted result, extracting the variation trend and pattern and providing support and guidance for decision and planning.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311023749.3A CN117114176A (en) | 2023-08-15 | 2023-08-15 | Land utilization change prediction method and system based on data analysis and machine learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311023749.3A CN117114176A (en) | 2023-08-15 | 2023-08-15 | Land utilization change prediction method and system based on data analysis and machine learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117114176A true CN117114176A (en) | 2023-11-24 |
Family
ID=88808409
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311023749.3A Pending CN117114176A (en) | 2023-08-15 | 2023-08-15 | Land utilization change prediction method and system based on data analysis and machine learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117114176A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117408495A (en) * | 2023-12-12 | 2024-01-16 | 菏泽市自然资源和规划局 | Data analysis method and system based on comprehensive management of land resources |
-
2023
- 2023-08-15 CN CN202311023749.3A patent/CN117114176A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117408495A (en) * | 2023-12-12 | 2024-01-16 | 菏泽市自然资源和规划局 | Data analysis method and system based on comprehensive management of land resources |
CN117408495B (en) * | 2023-12-12 | 2024-03-29 | 菏泽市自然资源和规划局 | Data analysis method and system based on comprehensive management of land resources |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111665575B (en) | Medium-and-long-term rainfall grading coupling forecasting method and system based on statistical power | |
CN102222313B (en) | Urban evolution simulation structure cell model processing method based on kernel principal component analysis (KPCA) | |
CN107463730A (en) | A kind of streamflow change attribution recognition methods for considering Spatio-temporal Evolution of Land Use | |
CN105243435A (en) | Deep learning cellular automaton model-based soil moisture content prediction method | |
CN101853290A (en) | Meteorological service performance evaluation method based on geographical information system (GIS) | |
CN106980750B (en) | A kind of Soil Nitrogen estimation method of reserve based on typical correspondence analysis | |
CN102184423B (en) | Full-automatic method for precisely extracting regional impervious surface remote sensing information | |
CN102567648B (en) | Granularity adaptive grid sampling method for green land ecological evaluation unit | |
CN113505521B (en) | Urban waterlogging rapid forecasting method based on neural network-numerical simulation | |
CN108764527B (en) | Screening method for soil organic carbon library time-space dynamic prediction optimal environment variables | |
CN102646164A (en) | Land use change modeling method and system implemented in combination with spatial filtering | |
CN117114176A (en) | Land utilization change prediction method and system based on data analysis and machine learning | |
CN107798383A (en) | Improved core extreme learning machine localization method | |
CN108733952B (en) | Three-dimensional characterization method for spatial variability of soil water content based on sequential simulation | |
CN103839113B (en) | Microscopic simulation method based on house selecting models of house-renting selectors and house selecting models of house-purchasing selectors | |
CN114398951A (en) | Land use change driving factor mining method based on random forest and crowd-sourced geographic information | |
CN114861277A (en) | Long-time-sequence national soil space function and structure simulation method | |
CN116796799A (en) | Method for creating small-river basin flood rainfall threshold model in area without hydrologic data | |
CN109933901B (en) | MCR city expansion simulation method for optimizing service value of ecosystem | |
CN106483490A (en) | Wireless location method based on support vector cassification | |
CN104424373A (en) | Elaborate expression method for space variable correlation | |
CN116663779B (en) | Multi-depth fertility point-surface conversion method and device for cultivated land soil | |
CN102880753B (en) | Based on the land utilization space characteristic dimension conversion method of fractal dimension | |
KR102526361B1 (en) | System and method for analyzing effect of ground surface regarding heat wave and cold wave at local level | |
Lu et al. | Uncertainty quantification of machine learning models to improve streamflow prediction under changing climate and environmental conditions |
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 |