Space-time dynamic simulation and prediction method applied to emperor research

Abstract

The invention discloses a spatio-temporal dynamic simulation and prediction method applied to emperor research, which relates to the field of dynamic simulation and prediction, and comprises the following steps: S1, analyzing spatial distribution and landform characteristics of emperor through a geographic information system (GIS), integrating emperor data in different periods, and performing spatio-temporal change analysis; s2, identifying a space-time pattern of emperor distribution through clustering analysis, and discovering association between emperor distribution and natural and humanistic factors; s3, simulating land utilization change around the emperor through a cellular automaton (CA), and constructing a system dynamics model to simulate the long-term trend of emperor environment change; s4, analyzing the future trend of the environment change of the emperor through a time sequence, predicting the spatial and temporal change of the emperor by using a deep learning neural network, and detecting the environment change of the emperor through multi-temporal remote sensing influence; and S5, constructing a three-dimensional model of the emperor, and performing virtual demonstration through VR. And accurate data support is provided for subsequent protection and management of the emperor.

Description

Technical Field

[0001] The present invention relates to the field of dynamic simulation and prediction, and in particular to a spatiotemporal dynamic simulation and prediction method applied to the study of imperial tombs. Background Art

[0002] Earthen sites refer to the remains left over from various activities in human history such as production and life that used earth as the main building material. They are an important cultural relic resource.

[0003] During the Qin and Han dynasties, imperial tombs were often located near the capital, in areas characterized by thick soil, deep water, high terrain, and a strong reservoir of wind and energy. During the Western Han Dynasty, two major mausoleum areas emerged: the Xianyang Plain and the southeastern area of ​​Chang'an City. However, over the past 2,000 years, the natural environment surrounding the Western Han imperial tombs has undergone significant changes. Long-term water erosion, wind erosion, and human damage have reduced the height of many tomb mounds, leaving them loose and even collapsing. This poses a threat to the preservation of underground cultural relics and the surface landscape of the imperial tombs. The impact of environmental evolution on the sites has become a crucial component of imperial tomb conservation. The need to conduct spatiotemporal dynamic simulations of the relationship between the imperial tomb environment and its distribution and natural and human factors, as well as to predict future trends in environmental change and develop appropriate protection and management systems, is a pressing issue. Summary of the Invention

[0004] In order to solve the above-mentioned problems, the present invention provides a spatiotemporal dynamic simulation and prediction method applied to the study of imperial tombs. The spatiotemporal patterns of the distribution of imperial tombs are identified through cluster analysis, and the relationship between the distribution of imperial tombs and natural and human factors is discovered; the land use changes around the imperial tombs are simulated through cellular automata CA, and a system dynamics model is constructed to simulate the long-term trend of the environmental changes of the imperial tombs; the future trend of the environmental changes of the imperial tombs is analyzed through time series, the spatiotemporal changes of the imperial tombs are predicted using deep learning neural networks, and the environmental changes of the imperial tombs are detected through multi-temporal remote sensing, providing accurate data support for the protection and management of the imperial tombs.

[0005] To achieve the above-mentioned purpose, the present invention provides a spatiotemporal dynamic simulation and prediction method for imperial mausoleum research, which specifically comprises the following steps:

[0006] Step S1: Analyze the spatial distribution and topographic features of the imperial tombs through the Geographic Information System (GIS), integrate the data of imperial tombs from different periods, and conduct spatiotemporal change analysis;

[0007] Step S2: Identify the spatiotemporal patterns of the distribution of imperial tombs through cluster analysis, and discover the associations between the distribution of imperial tombs and natural and human factors;

[0008] Step S3: Using cellular automata (CA) to simulate land use changes around the imperial tombs, a system dynamics model is constructed to simulate the long-term trend of environmental changes around the imperial tombs.

[0009] Step S4: Analyze the future trend of environmental changes of the imperial tombs through time series analysis, predict the spatiotemporal changes of the imperial tombs using deep learning neural networks, and detect environmental changes of the imperial tombs through multi-temporal remote sensing.

[0010] Step S5: Construct a three-dimensional model of the imperial mausoleum and conduct a virtual demonstration through VR.

[0011] Preferably, in step S1, the following steps are specifically included:

[0012] Step S11: Collection of spatial data, attribute data, and topographic data; spatial data includes the geographical coordinates, boundaries, and elevations of the imperial tombs; attribute data includes the historical, cultural, and chronological information of the imperial tombs; and topographic data includes the acquisition of digital elevation models (DEMs) and remote sensing images.

[0013] Step S12: Data preprocessing, data cleaning to remove errors and duplicate data, converting the data format to a format compatible with GIS software, Shapefile or Geodatabase, and unifying the coordinate system;

[0014] Step S13: Spatial distribution analysis: import the geographical coordinates of the imperial tombs into GIS, generate a point distribution map to visually display the spatial distribution, and use kernel density estimation (KDE) to analyze the distribution density of the imperial tombs;

[0015] Step S14: topographic analysis, using DEM data to generate topographic information such as contour lines, slope and slope direction, generating a topographic profile along a specific direction, and analyzing topographic changes;

[0016] Step S15: Spatiotemporal data integration: adding timestamps to the imperial tomb data for each period, integrating data from different periods into one database, and organizing the data using a spatiotemporal data model;

[0017] Step S16: Spatiotemporal change analysis, by superimposing data from different summer vacations to detect the addition, disappearance and scale changes of imperial tombs, and analyzing the spatiotemporal patterns of the distribution of imperial tombs. The spatiotemporal patterns include aggregation, diffusion or migration, and the time series analysis method is used to analyze the changing trends of imperial tombs.

[0018] Preferably, in step S2, a clustering algorithm such as K-means, DBSCAN or hierarchical clustering is used to select features suitable for clustering such as geographic coordinates, age, natural or human factors, and identify the spatiotemporal pattern of the distribution of imperial tombs.

[0019] Preferably, in step S3, the construction of the CA model includes defining cells, defining states, and defining rules;

[0020] Define cells: Divide the study area into several cells, where each cell represents a land use type;

[0021] Define state: Define the state of a single cell, including farmland, forestland or construction land;

[0022] Define rules: Specify the cell state transition rules while taking into account the influence of natural and human factors;

[0023] Run the CA model to simulate land use changes, use historical data to verify the accuracy of the CA model, and adjust parameters and rules at any time.

[0024] Preferably, in step S3, a system dynamics model is constructed to simulate the long-term trend of the environmental changes of the imperial mausoleum, specifically comprising the following steps:

[0025] Step S31: Collect environmental data around the imperial mausoleum and data on driving factors affecting environmental change. Environmental data includes air quality, water quality, and vegetation coverage. Driving factor data includes population growth, economic development, and policy changes.

[0026] Step S32: defining variables in the system dynamics model, including environmental quality, population, and economic indicators, constructing relationships between variables, building a causal loop diagram, and formulating equations describing the relationships between variables;

[0027] The population growth model is expressed as:

[0028]

[0029] Where P represents population, B represents birth rate, D represents death rate, I represents emigration rate, and E represents in-migration rate.

[0030] The environmental quality model is expressed as:

[0031]

[0032] In the formula, C represents the pollutant concentration, E represents the pollutant emission rate, and R represents the pollutant degradation rate;

[0033] The economic growth model is expressed as:

[0034] G=r×GDP

[0035] In the formula, r represents the economic growth coefficient, G represents the economic growth rate, and GDP represents the gross domestic product;

[0036] Step S33: Run the constructed system dynamics model to simulate the long-term trend of the environmental changes of the imperial tombs, and use historical data to verify the accuracy of the model;

[0037] Step S34: Analyze the simulation results, identify the long-term trend of environmental changes, and output a trend chart as the simulation result.

[0038] Preferably, in step S4, the following steps are specifically included:

[0039] Step S41: Collect multi-temporal remote sensing images, such as Landsat or Sentinel, covering different time periods to capture environmental changes; collect ground data on the meteorology, soil, and vegetation in the imperial mausoleum area; perform radiometric, geometric, and atmospheric corrections for remote sensing effects to ensure data consistency;

[0040] Step S42: extracting environmental indicators of the imperial mausoleum area based on multi-temporal remote sensing images and constructing a time series. The environmental indicators include NDVI, surface temperature or humidity;

[0041] Step S43: using linear regression statistical method to analyze the changing trend of environmental indicators and identify the changing points;

[0042] Step S44: Select a CNN-LSTM model suitable for time series, extract features from the time series, including seasonality, trend or periodicity as input to the CNN-LSTM model, and divide the time series data into a training set and a test set to train the CNN-LSTM model;

[0043] Step S45: using a change detection algorithm to process the multi-temporal remote sensing imagery, identifying areas of environmental change, and classifying the identified changes;

[0044] Step S46: Use the test set to verify the accuracy of the CNN-LSTM model, use the trained model to predict future changes in the imperial mausoleum environment, and generate prediction results;

[0045] Step S47: Analyze the prediction results and identify the main driving factors of the environmental changes of the imperial tombs;

[0046] Step S48: Apply the prediction results and change detection results to the protection and management of the imperial tombs, formulate protection measures, establish a continuous monitoring mechanism, regularly update data and retrain the model to ensure the accuracy of the prediction.

[0047] Preferably, constructing the three-dimensional imperial mausoleum model in step S5 specifically includes the following steps:

[0048] Step S51: Use a terrestrial laser scanner (LIDAR) to set up multiple scanning stations around the imperial mausoleum, scan each scanning station to obtain point cloud data, and use targets or feature points to perform multi-station data registration; use a drone equipped with a high-resolution camera to capture images of the imperial mausoleum from different angles;

[0049] Step S52: Use point cloud processing software to register and fuse the multi-site point cloud data, remove noise points for simplification and smoothing; import the image data into photogrammetry software, generate a sparse point cloud for aerial triangulation, build a texture model MESH and generate a texture map;

[0050] Step S53: Fusing the point cloud data with the measurement data, and constructing a 3D model using the 3D modeling software SketchUp.

[0051] Preferably, in step S53, the captured high-resolution image is mapped to the surface of the geometric model, the texture coordinates are adjusted to ensure that the texture is aligned with the geometric model, the texture is denoised and color corrected, and the details are enhanced using a normal map or a displacement map.

[0052] Therefore, the present invention adopts the above-mentioned spatiotemporal dynamic simulation and prediction method applied to the study of imperial tombs, which has the following beneficial effects:

[0053] (1) This invention, through spatiotemporal dynamic simulation, can reconstruct the historical evolution of imperial tombs, helping to understand their layout, structure, and environmental changes over time. It also provides a scientific basis for the protection of imperial tombs, predicts the potential impact of natural or human factors on the sites, and formulates effective protection measures.

[0054] (2) The simulation and prediction methods of the present invention help optimize the management strategy of imperial tombs, rationally arrange archaeological excavation, restoration and maintenance work, provide data support for the sustainable use of cultural heritage, and balance the relationship between protection and development.

[0055] (3) This invention provides an intuitive spatiotemporal model, helping researchers to more deeply analyze the historical background and cultural value of imperial mausoleums. Through visual display, it enhances the public's understanding and interest in imperial mausoleum culture, improving educational effectiveness.

[0056] (4) This invention can predict the potential threat of natural disasters to imperial tombs, formulate response plans in advance, and reduce losses. It can also assess the long-term impact of climate change on the site and take adaptive measures.

[0057] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is a flow chart of a spatiotemporal dynamic simulation and prediction method applied to the study of imperial tombs according to the present invention;

[0059] Figure 2 It is a three-dimensional modeling diagram in an embodiment of the present invention. DETAILED DESCRIPTION

[0060] The technical solution of the present invention is further described below with reference to the accompanying drawings and embodiments.

[0061] Unless otherwise defined, technical or scientific terms used in the present invention shall have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs.

[0062] The words “include” or “comprising” and similar words used in the present invention mean that the elements before the word include the elements listed after the word, and do not exclude the possibility of also including other elements. The orientation or position relationship indicated by the terms “inside”, “outside”, “upper”, “lower”, etc. is based on the orientation or position relationship shown in the accompanying drawings. It is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation of the present invention. When the absolute position of the described object changes, the relative position relationship may also change accordingly. In the present invention, unless otherwise clearly stipulated and limited, the terms such as “attachment” should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral whole; it can be directly connected or indirectly connected through an intermediate medium, and it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances.

[0063] Example

[0064] like Figure 1 As shown, a spatiotemporal dynamic simulation and prediction method applied to the study of imperial tombs specifically includes the following steps:

[0065] Step S1: Analyze the spatial distribution and topographic features of the imperial tombs through the Geographic Information System (GIS), integrate the data of imperial tombs from different periods, and conduct spatiotemporal change analysis;

[0066] In step S1, the following steps are specifically included:

[0067] Step S11: Collection of spatial data, attribute data, and topographic data; spatial data includes the geographical coordinates, boundaries, and elevations of the imperial tombs; attribute data includes the historical, cultural, and chronological information of the imperial tombs; and topographic data includes the acquisition of digital elevation models (DEMs) and remote sensing images.

[0068] Step S12: Data preprocessing, data cleaning to remove errors and duplicate data, converting the data format to a format compatible with GIS software, Shapefile or Geodatabase, and unifying the coordinate system;

[0069] Step S13: Spatial distribution analysis: import the geographical coordinates of the imperial tombs into GIS, generate a point distribution map to visually display the spatial distribution, and use kernel density estimation (KDE) to analyze the distribution density of the imperial tombs;

[0070] Step S14: topographic analysis, using DEM data to generate topographic information such as contour lines, slope and slope direction, generating a topographic profile along a specific direction, and analyzing topographic changes;

[0071] Step S15: Spatiotemporal data integration: adding timestamps to the imperial tomb data for each period, integrating data from different periods into one database, and organizing the data using a spatiotemporal data model;

[0072] Step S16: Spatiotemporal change analysis, by superimposing data from different summer vacations to detect the addition, disappearance and scale changes of imperial tombs, and analyzing the spatiotemporal patterns of the distribution of imperial tombs. The spatiotemporal patterns include aggregation, diffusion or migration, and the time series analysis method is used to analyze the changing trends of imperial tombs.

[0073] Step S2: Identify the spatiotemporal patterns of the distribution of imperial tombs through cluster analysis, and discover the associations between the distribution of imperial tombs and natural and human factors;

[0074] In step S2, a clustering algorithm such as K-means, DBSCAN or hierarchical clustering is used to select features suitable for clustering, such as geographic coordinates, age, natural or human factors, to identify the spatiotemporal patterns of the distribution of imperial tombs.

[0075] Step S3: Using cellular automata (CA) to simulate land use changes around the imperial tombs, a system dynamics model is constructed to simulate the long-term trend of environmental changes around the imperial tombs.

[0076] In step S3, the construction of the CA model includes defining cells, defining states, and defining rules;

[0077] Define cells: Divide the study area into several cells, where each cell represents a land use type;

[0078] Define state: Define the state of a single cell, including farmland, forestland or construction land;

[0079] Define rules: Specify the cell state transition rules while taking into account the influence of natural and human factors;

[0080] Run the CA model to simulate land use changes, use historical data to verify the accuracy of the CA model, and adjust parameters and rules at any time.

[0081] In step S3, a system dynamics model is constructed to simulate the long-term trend of the environmental changes of the imperial tombs, which specifically includes the following steps:

[0082] Step S31: Collect environmental data around the imperial mausoleum and data on driving factors affecting environmental change. Environmental data includes air quality, water quality, and vegetation coverage. Driving factor data includes population growth, economic development, and policy changes.

[0083] Step S32: defining variables in the system dynamics model, including environmental quality, population, and economic indicators, constructing relationships between variables, building a causal loop diagram, and formulating equations describing the relationships between variables;

[0084] The population growth model is expressed as:

[0085]

[0086] Where P represents population, B represents birth rate, D represents death rate, I represents emigration rate, and E represents in-migration rate.

[0087] The environmental quality model is expressed as:

[0088]

[0089] In the formula, C represents the pollutant concentration, E represents the pollutant emission rate, and R represents the pollutant degradation rate;

[0090] The economic growth model is expressed as:

[0091] G=r×GDP

[0092] In the formula, r represents the economic growth coefficient, G represents the economic growth rate, and GDP represents the gross domestic product;

[0093] Step S33: Run the constructed system dynamics model to simulate the long-term trend of the environmental changes of the imperial tombs, and use historical data to verify the accuracy of the model;

[0094] Step S34: Analyze the simulation results, identify the long-term trend of environmental changes, and output a trend chart as the simulation result.

[0095] Step S4: Analyze the future trend of environmental changes of the imperial tombs through time series analysis, predict the spatiotemporal changes of the imperial tombs using deep learning neural networks, and detect environmental changes of the imperial tombs through multi-temporal remote sensing.

[0096] In step S4, the following steps are specifically included:

[0097] Step S41: Collect multi-temporal remote sensing images, such as Landsat or Sentinel, covering different time periods to capture environmental changes; collect ground data on the meteorology, soil, and vegetation in the imperial mausoleum area; perform radiometric, geometric, and atmospheric corrections for remote sensing effects to ensure data consistency;

[0098] Step S42: extracting environmental indicators of the imperial mausoleum area based on multi-temporal remote sensing images and constructing a time series. The environmental indicators include NDVI, surface temperature or humidity;

[0099] Step S43: using linear regression statistical method to analyze the changing trend of environmental indicators and identify the changing points;

[0100] Step S44: Select a CNN-LSTM model suitable for time series, extract features from the time series, including seasonality, trend or periodicity as input to the CNN-LSTM model, and divide the time series data into a training set and a test set to train the CNN-LSTM model;

[0101] Step S45: using a change detection algorithm to process the multi-temporal remote sensing imagery, identifying areas of environmental change, and classifying the identified changes;

[0102] Step S46: Use the test set to verify the accuracy of the CNN-LSTM model, use the trained model to predict future changes in the imperial mausoleum environment, and generate prediction results;

[0103] Step S47: Analyze the prediction results and identify the main driving factors of the environmental changes of the imperial tombs;

[0104] Step S48: Apply the prediction results and change detection results to the protection and management of the imperial tombs, formulate protection measures, establish a continuous monitoring mechanism, regularly update data and retrain the model to ensure the accuracy of the prediction.

[0105] Step S5: Construct a 3D model of the imperial mausoleum to provide strong technical support for cultural relic protection and research, and conduct virtual demonstrations through VR. Constructing the 3D imperial mausoleum model in step S5 specifically includes the following steps:

[0106] Step S51: Use a terrestrial laser scanner (LIDAR) to set up multiple scanning stations around the imperial mausoleum, scan each scanning station to obtain point cloud data, and use targets or feature points to perform multi-station data registration; use a drone equipped with a high-resolution camera to capture images of the imperial mausoleum from different angles;

[0107] Step S52: Use point cloud processing software to register and fuse the multi-site point cloud data, remove noise points for simplification and smoothing; import the image data into photogrammetry software, generate a sparse point cloud for aerial triangulation, build a texture model MESH and generate a texture map;

[0108] Step S53: Fusing the point cloud data with the measurement data, and constructing a 3D model using the 3D modeling software SketchUp.

[0109] In step S53, the captured high-resolution image is mapped to the surface of the geometric model, the texture coordinates are adjusted to ensure that the texture is aligned with the geometric model, the texture is denoised and color corrected, and the details are enhanced using a normal map or a displacement map.

[0110] The above method is applied to a certain imperial mausoleum to obtain a panoramic VR image as follows Figure 2 shown.

[0111] Therefore, the present invention adopts the above-mentioned spatiotemporal dynamic simulation and prediction method applied to the study of imperial tombs, identifies the spatiotemporal patterns of the distribution of imperial tombs through cluster analysis, and discovers the relationship between the distribution of imperial tombs and natural and human factors; simulates the land use changes around the imperial tombs through cellular automata CA, and constructs a system dynamics model to simulate the long-term trend of environmental changes in imperial tombs; analyzes the future trend of environmental changes in imperial tombs through time series, uses deep learning neural networks to predict the spatiotemporal changes of imperial tombs, and detects environmental changes in imperial tombs through multi-temporal remote sensing, providing accurate data support for the protection and management of imperial tombs.

[0112] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit the same. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solutions of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A spatiotemporal dynamic simulation and prediction method for imperial mausoleum research, characterized by: The specific steps include: Step S1: Analyze the spatial distribution and topographic features of the imperial tombs through the Geographic Information System (GIS), integrate the data of imperial tombs from different periods, and conduct spatiotemporal change analysis; Step S2: Identify the spatiotemporal patterns of the distribution of imperial tombs through cluster analysis, and discover the associations between the distribution of imperial tombs and natural and human factors; Step S3: Using cellular automata (CA) to simulate land use changes around the imperial tombs, a system dynamics model is constructed to simulate the long-term trend of environmental changes around the imperial tombs. Step S4: Analyze the future trend of environmental changes of the imperial tombs through time series analysis, predict the spatiotemporal changes of the imperial tombs using deep learning neural networks, and detect environmental changes of the imperial tombs through multi-temporal remote sensing. Step S5: Construct a three-dimensional model of the imperial mausoleum and conduct a virtual demonstration through VR.

2. A spatiotemporal dynamic simulation and prediction method for imperial mausoleum research according to claim 1, characterized in that: In step S1, the following steps are specifically included: Step S11: Collection of spatial data, attribute data, and topographic data; spatial data includes the geographical coordinates, boundaries, and elevations of the imperial tombs; attribute data includes the historical, cultural, and chronological information of the imperial tombs; and topographic data includes the acquisition of digital elevation models (DEMs) and remote sensing images. Step S12: Data preprocessing, data cleaning to remove errors and duplicate data, converting the data format to a format compatible with GIS software, Shapefile or Geodatabase, and unifying the coordinate system; Step S13: Spatial distribution analysis: import the geographical coordinates of the imperial tombs into GIS, generate a point distribution map to visually display the spatial distribution, and use kernel density estimation (KDE) to analyze the distribution density of the imperial tombs; Step S14: topographic analysis, using DEM data to generate topographic information such as contour lines, slope and slope direction, generating a topographic profile along a specific direction, and analyzing topographic changes; Step S15: Spatiotemporal data integration: adding timestamps to the imperial tomb data for each period, integrating data from different periods into one database, and organizing the data using a spatiotemporal data model; Step S16: Spatiotemporal change analysis, by superimposing data from different summer vacations to detect the addition, disappearance and scale changes of imperial tombs, and analyzing the spatiotemporal patterns of the distribution of imperial tombs. The spatiotemporal patterns include aggregation, diffusion or migration, and the time series analysis method is used to analyze the changing trends of imperial tombs.

3. The spatiotemporal dynamic simulation and prediction method for imperial mausoleum research according to claim 2 is characterized by: In step S2, a clustering algorithm such as K-means, DBSCAN or hierarchical clustering is used to select features suitable for clustering, such as geographic coordinates, age, natural or human factors, to identify the spatiotemporal patterns of the distribution of imperial tombs.

4. The spatiotemporal dynamic simulation and prediction method for imperial mausoleum research according to claim 3 is characterized by: In step S3, the construction of the CA model includes defining cells, defining states, and defining rules; Define cells: Divide the study area into several cells, where each cell represents a land use type; Define state: Define the state of a single cell, including farmland, forestland or construction land; Define rules: Specify the cell state transition rules while taking into account the influence of natural and human factors; Run the CA model to simulate land use changes, use historical data to verify the accuracy of the CA model, and adjust parameters and rules at any time.

5. The spatiotemporal dynamic simulation and prediction method for imperial mausoleum research according to claim 4 is characterized by: In step S3, a system dynamics model is constructed to simulate the long-term trend of the environmental changes of the imperial tombs, which specifically includes the following steps: Step S31: Collect environmental data around the imperial mausoleum and data on driving factors affecting environmental change. Environmental data includes air quality, water quality, and vegetation coverage. Driving factor data includes population growth, economic development, and policy changes. Step S32: defining variables in the system dynamics model, including environmental quality, population, and economic indicators, constructing relationships between variables, building a causal loop diagram, and formulating equations describing the relationships between variables; The population growth model is expressed as: Where P represents population, B represents birth rate, D represents death rate, I represents emigration rate, and E represents in-migration rate. The environmental quality model is expressed as: In the formula, C represents the pollutant concentration, E represents the pollutant emission rate, and R represents the pollutant degradation rate; The economic growth model is expressed as: G=r×GDP In the formula, r represents the economic growth coefficient, G represents the economic growth rate, and GDP represents the gross domestic product; Step S33: Run the constructed system dynamics model to simulate the long-term trend of the environmental changes of the imperial tombs, and use historical data to verify the accuracy of the model; Step S34: Analyze the simulation results, identify the long-term trend of environmental changes, and output a trend chart as the simulation result.

6. The spatiotemporal dynamic simulation and prediction method for imperial mausoleum research according to claim 5 is characterized by: In step S4, the following steps are specifically included: Step S41: Collect multi-temporal remote sensing images, such as Landsat or Sentinel, covering different time periods to capture environmental changes; collect ground data on the meteorology, soil, and vegetation in the imperial mausoleum area; perform radiometric, geometric, and atmospheric corrections for remote sensing effects to ensure data consistency; Step S42: extracting environmental indicators of the imperial mausoleum area based on multi-temporal remote sensing images and constructing a time series. The environmental indicators include NDVI, surface temperature or humidity; Step S43: using linear regression statistical method to analyze the changing trend of environmental indicators and identify the changing points; Step S44: Select a CNN-LSTM model suitable for time series, extract features from the time series, including seasonality, trend or periodicity as input to the CNN-LSTM model, and divide the time series data into a training set and a test set to train the CNN-LSTM model; Step S45: using a change detection algorithm to process the multi-temporal remote sensing imagery, identifying areas of environmental change, and classifying the identified changes; Step S46: Use the test set to verify the accuracy of the CNN-LSTM model, use the trained model to predict future changes in the imperial mausoleum environment, and generate prediction results; Step S47: Analyze the prediction results and identify the main driving factors of the environmental changes of the imperial tombs; Step S48: Apply the prediction results and change detection results to the protection and management of the imperial tombs, formulate protection measures, establish a continuous monitoring mechanism, regularly update data and retrain the model to ensure the accuracy of the prediction.

7. The spatiotemporal dynamic simulation and prediction method for imperial mausoleum research according to claim 6 is characterized by: Constructing the three-dimensional imperial mausoleum model in step S5 specifically includes the following steps: Step S51: Use a terrestrial laser scanner (LIDAR) to set up multiple scanning stations around the imperial mausoleum, scan each scanning station to obtain point cloud data, and use targets or feature points to perform multi-station data registration; use a drone equipped with a high-resolution camera to capture images of the imperial mausoleum from different angles; Step S52: Use point cloud processing software to register and fuse the multi-site point cloud data, remove noise points for simplification and smoothing; import the image data into photogrammetry software, generate a sparse point cloud for aerial triangulation, build a texture model MESH and generate a texture map; Step S53: Fusing the point cloud data with the measurement data, and constructing a 3D model using the 3D modeling software SketchUp.

8. The spatiotemporal dynamic simulation and prediction method for imperial mausoleum research according to claim 7 is characterized by: In step S53, the captured high-resolution image is mapped to the surface of the geometric model, the texture coordinates are adjusted to ensure that the texture is aligned with the geometric model, the texture is denoised and color corrected, and the details are enhanced using a normal map or a displacement map.

Images