Land use demand prediction method based on system dynamics model
Through the land use demand forecasting method based on the system dynamics model, the problem of inaccurate land use demand forecasting in the existing technology is solved, and the impact of land use structure is evaluated and policy simulation is realized, providing accurate prediction results and strategic support. .
Patent Information
- Application Number
- CN202411716436.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-27
- Publication Date
- 2025-02-18
AI Technical Summary
The existing technology is difficult to accurately predict land use demand and cannot effectively simulate the complex mutual influence and circular feedback between multiple drivers, resulting in unoptimized land use and difficulty in adapting to climate change.
The land use demand prediction method based on the system dynamics model is adopted to predict land use demand by determining modeling boundaries, compiling data lists, building a land use demand system framework, analyzing causal relationships, building mathematical models, verifying and calibrating model parameters.
It has achieved an assessment of the impact of socio-economic and climate change on the land use structure, simulated the long-term impact of different policies on the system, provided accurate land use demand forecast results, and supported the formulation of land use strategies and resource allocation optimization.
Smart Images
Figure CN119476635A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of land use demand models, and in particular to a land use demand prediction method based on a system dynamics model. Background Art
[0002] Lack of accurate land demand forecasts or insufficient forecast accuracy can lead to a series of problems, such as disorderly urban expansion, housing shortages, traffic congestion, increased natural disaster risks, and insufficient adaptation to climate change. Socioeconomic and climate change are the main factors affecting land use types. Therefore, analytical tools that comprehensively consider multiple factors such as population growth, economic development, policy changes, and climate conditions are needed to simulate the impact of these factors on land use demand. System dynamics models can study the impact of human activities and climate change on future land use structure at the national scale, which is of great significance for optimizing resource allocation and adapting to climate change. In the past, traditional models only used mathematical and statistical methods to explore the external connection between land use change and its driving factors, and could not simulate the complex mutual influence and circular feedback relationship between land use change and multiple driving forces. Therefore, it is necessary to propose a land use demand forecasting method based on system dynamics model to simulate and analyze feedback loops and nonlinear dynamics within the system. It can simulate the long-term impact of different policies on the system and help policymakers make in-depth decisions based on time series analysis. Summary of the invention
[0003] The purpose of the present invention is to overcome the deficiencies of the prior art and provide a land use demand prediction method based on a system dynamics model.
[0004] To achieve the above purpose, the technical solution provided by the present invention is:
[0005] A land use demand forecasting method based on system dynamics model, comprising:
[0006] Determine the modeling boundaries and define the model time and space boundaries;
[0007] Compile an inventory of land type, socio-economic and climate data based on model temporal and spatial boundaries;
[0008] A framework for constructing a land use demand system based on an inventory of land type, socio-economic and climate data;
[0009] Analyze the framework structure of the land use demand system and draw a stock-flow diagram to represent the cause-effect relationship between the variables in the land use demand system;
[0010] According to the causal relationship between various variables in the land use demand system, the mathematical relationship between various variables in the land use demand system is expressed by mathematical function equations, so as to construct a land use demand prediction model;
[0011] Validate the land use demand forecasting model and calibrate the model parameters using real land use data;
[0012] Land use demand forecasting is carried out by validating and calibrating the land use demand forecasting model.
[0013] Furthermore, the temporal boundary of the model is the historical period, and the spatial boundaries of the model are the eastern region, the central region, the western region, and the northeastern region.
[0014] Furthermore, the inventory of land type, socio-economic and climate data compiled included
[0015] Land types include cultivated land, forest land, construction land, water area, grassland, wetland and unused land;
[0016] Social and economic data include GDP, fixed asset investment, investment in the primary, secondary and tertiary industries, population at the end of each year, grain crop output, livestock meat output and aquaculture product output;
[0017] Climate factors include average annual precipitation and average annual temperature.
[0018] Furthermore, the constructed land use demand system includes socio-economic subsystem, climate subsystem, and land subsystem;
[0019] In the social and economic subsystem, GDP is used as the state variable, and the primary industry investment, secondary and tertiary industry investment, and urbanization rate are used as auxiliary variables to feed back to various types of land in the land subsystem. Combined with the changes in afforestation area and wetland protection rate, the changes in the demand for various types of land use can be examined. GDP is determined by the GDP growth rate; population size is used as the state variable, and the population growth rate is used as the auxiliary variable. The population size is determined by the population growth rate.
[0020] In the climate subsystem, annual average temperature and annual precipitation are auxiliary variables, which feed back to the cultivated land, grassland and water areas in the land subsystem by affecting grain yield and production, livestock meat production and aquatic product production.
[0021] Furthermore, based on the causal relationship between various variables, historical data analysis was carried out. After many experiments, the changes in various variables and the quantitative relationship between variables were determined by directly obtaining relevant survey data, table function method, linear regression method and curve fitting method, so as to construct a land use demand prediction model.
[0022] Furthermore, the method of comparing historical data with real data is used to evaluate the simulation error. If the absolute value of the error is within the set range, the structure of the land use demand prediction model is considered to be reasonable and can provide reliable prediction results. Otherwise, the land use demand prediction model is trained and optimized until the error requirements are met.
[0023] Compared with the existing technology, the principle and advantages of this solution are as follows:
[0024] 1. It can effectively evaluate the impact of socio-economic and climate change on future land use structure, and solve the problem of land use type demand prediction under the influence of multiple factors.
[0025] 2. The present invention is simple, convenient and easy to operate. It combines historical data to predict land use types under human activities and climate change, and calculates error values to ensure the accuracy and scientificity of the prediction. The prediction results can provide a basis for adjusting land use type requirements.
[0026] 3. Establishing a land use demand forecasting method based on the system dynamics model provides important technical and methodological support for formulating land use strategies to adapt to climate change. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the services required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0028] Figure 1 It is a principle flow chart of a land use demand prediction method based on a system dynamics model of the present invention;
[0029] Figure 2 It is a framework structure diagram of the land subsystem, the socio-economic subsystem and the climate subsystem in a land use demand prediction method based on a system dynamics model of the present invention;
[0030] Figure 3 It is a stock-flow diagram between various variables in a land subsystem, a socio-economic subsystem and a climate subsystem in a land use demand prediction method based on a system dynamics model of the present invention;
[0031] Figure 4 The present invention is a list of relational equations involved in a land use demand prediction model constructed in a land use demand prediction method based on a system dynamics model. DETAILED DESCRIPTION
[0032] The present invention will be further described below in conjunction with specific embodiments:
[0033] like Figure 1 As shown, the land use demand prediction method based on the system dynamics model described in this embodiment includes the following steps:
[0034] S1. Determine the modeling boundary and define the model time and space boundaries; the model time boundary is the historical period, and the model space boundaries are the eastern region, central region, western region and northeastern region.
[0035] Among them, the eastern region includes Beijing, Tianjin, Hebei, Shanghai, Jiangsu, Zhejiang, Fujian, Shandong, Guangdong and Hainan; the central region includes Shanxi, Anhui, Jiangxi, Henan, Hubei and Hunan; the western region includes Inner Mongolia, Guangxi, Chongqing, Sichuan, Guizhou, Yunnan, Tibet, Shaanxi, Gansu, Qinghai, Ningxia and Xinjiang; the northeastern region includes Liaoning, Jilin and Heilongjiang.
[0036] S2. Compile an inventory of land type, socio-economic and climate data based on the model's temporal and spatial boundaries.
[0037] Land types include cultivated land, forest land, construction land, water area, grassland, wetland and unused land;
[0038] Social and economic data include GDP, fixed asset investment, investment in the primary, secondary and tertiary industries, population at the end of each year, grain crop output, livestock meat output and aquaculture product output;
[0039] Climate factors include average annual precipitation and average annual temperature.
[0040] S3. Construct a framework for land use demand system based on land type, socio-economic and climate data inventories;
[0041] like Figure 2 As shown, the constructed land use demand system includes socio-economic subsystem, climate subsystem and land subsystem;
[0042] In the social and economic subsystem, GDP is used as the state variable, and the primary industry investment, secondary and tertiary industry investment, and urbanization rate are used as auxiliary variables to feed back to various types of land in the land subsystem. Combined with the changes in afforestation area and wetland protection rate, the changes in the demand for various types of land use can be examined. GDP is determined by the GDP growth rate; population size is used as the state variable, and the population growth rate is used as the auxiliary variable. The population size is determined by the population growth rate.
[0043] In the climate subsystem, annual average temperature and annual precipitation are auxiliary variables, which feed back to the cultivated land, grassland and water areas in the land subsystem by affecting grain yield and production, livestock meat production and aquatic product production.
[0044] S4. Analyze the framework structure of the land use demand system and draw a stock-flow diagram to represent the cause-effect relationship between the variables in the land use demand system, such as Figure 3 shown.
[0045] S5. Based on the causal relationship between various variables, historical data analysis was conducted. After many experiments, the changes in various variables and the quantitative relationship between variables were determined by directly obtaining relevant survey data, table function method, linear regression method and curve fitting method, so as to construct a land use demand prediction model.
[0046] The relationship equations involved in the land use demand prediction model are as follows: Figure 4 shown.
[0047] S6. Validate the land use demand prediction model and calibrate the model parameters using real land use data.
[0048] In this step, the simulation error is evaluated by comparing historical data with real data. If the absolute value of the error is within 10%, it is considered that the structure of the land use demand prediction model is reasonable and can provide reliable prediction results. Otherwise, the land use demand prediction model is trained and optimized until the error requirements are met.
[0049] S7. Carry out land use demand forecasting by verifying and calibrating the land use demand forecasting model.
[0050] The present invention can predict land use demand under human activities and future climate change. It can conduct multi-scenario simulations based on different development scenarios and policy changes, such as different assumptions about urbanization speed, fluctuations in agricultural land demand, and adjustments to environmental protection policies, to evaluate the impact of different future trends on land use.
[0051] The embodiments described above are only preferred embodiments of the present invention and are not intended to limit the scope of implementation of the present invention. Therefore, all changes made according to the shape and principle of the present invention should be included in the protection scope of the present invention.
Claims
1. A land use demand forecasting method based on system dynamics model, characterized in that: include: Determine the modeling boundaries and define the model time and space boundaries; Compile an inventory of land type, socio-economic and climate data based on model temporal and spatial boundaries; A framework for constructing a land use demand system based on an inventory of land type, socio-economic and climate data; Analyze the framework structure of the land use demand system and draw a stock-flow diagram to represent the cause-effect relationship between the variables in the land use demand system; According to the causal relationship between various variables in the land use demand system, the mathematical relationship between various variables in the land use demand system is expressed by mathematical function equations, so as to construct a land use demand prediction model; Validate the land use demand forecasting model and calibrate the model parameters using real land use data; Land use demand forecasting is carried out by validating and calibrating the land use demand forecasting model.
2. The land use demand prediction method based on system dynamics model according to claim 1, characterized in that: The temporal boundary of the model is the historical period, and the spatial boundaries of the model are the eastern region, the central region, the western region, and the northeastern region.
3. The land use demand prediction method based on system dynamics model according to claim 1, characterized in that: In the inventory of land type, socio-economic and climate data compiled, Land types include cultivated land, forest land, construction land, water area, grassland, wetland and unused land; Social and economic data include GDP, fixed asset investment, investment in the primary, secondary and tertiary industries, population at the end of each year, grain crop output, livestock meat output and aquaculture product output; Climate factors include average annual precipitation and average annual temperature.
4. The land use demand prediction method based on system dynamics model according to claim 1, characterized in that: The constructed land use demand system includes socio-economic subsystem, climate subsystem, and land subsystem; In the social and economic subsystem, GDP is used as the state variable, and the primary industry investment, secondary and tertiary industry investment, and urbanization rate are used as auxiliary variables to feed back to various types of land in the land subsystem. Combined with the changes in afforestation area and wetland protection rate, the changes in the demand for various types of land use can be examined. GDP is determined by the GDP growth rate; population size is used as the state variable, and the population growth rate is used as the auxiliary variable. The population size is determined by the population growth rate. In the climate subsystem, annual average temperature and annual precipitation are auxiliary variables, which feed back to the cultivated land, grassland and water areas in the land subsystem by affecting grain yield and production, livestock meat production and aquatic product production.
5. The land use demand prediction method based on system dynamics model according to claim 1, characterized in that: Based on the causal relationship between various variables, historical data analysis was carried out. After many experiments, the changes in various variables and the quantitative relationship between variables were determined by directly obtaining relevant survey data, table function method, linear regression method and curve fitting method, so as to construct a land use demand prediction model.
6. The land use demand prediction method based on system dynamics model according to claim 1, characterized in that: The simulation error is evaluated by comparing historical data with real data. If the absolute value of the error is within the set range, the structure of the land use demand prediction model is considered to be reasonable and can provide reliable prediction results. Otherwise, the land use demand prediction model is trained and optimized until the error requirements are met.