Environmental situation awareness data engineering system and method based on multi-source data fusion

Abstract

The present invention discloses an environmental situation awareness data engineering system based on multi-source data fusion, which relates to the technical field related to environmental situation awareness, including a multi-source data acquisition module, a multi-source data processing module, an environmental evolution analysis module, an ecological restoration assessment module, an ecosystem evolution module and a visualization observation module. The present invention also discloses an environmental situation awareness method based on multi-source data fusion, including collecting environmental data, effectively integrating the data, using model evolution trends and prediction results and the possible impact of environmental changes on human behavior, and presenting them to end users in charts. The UEB model of the present invention is applicable to a variety of climate and terrain conditions, and has high accuracy and reliability in complex environments of high-cold plateaus. The UEB model can help analyze and predict the impact of human activities on environmental elements, as well as the impact of environmental changes on human behavior, deeply explore the interaction between human activities and environmental changes, and provide insights for decision makers.

Description

Technical Field

[0001] The present invention relates to the technical field related to environmental situation awareness, and in particular to an environmental situation awareness data engineering system and method based on multi-source data fusion. Background Art

[0002] Due to their unique climatic conditions and complex topography, high-altitude plateau mountainous areas have extremely high requirements for environmental monitoring and disaster warning. Traditional single data source monitoring methods are difficult to fully capture the complex environmental situation in these areas. Therefore, developing a system that can integrate multi-source data and provide accurate environmental evolution analysis is of great significance for scientific management and disaster prevention and mitigation.

[0003] At present, the existing high-altitude and cold plateau mountain environment situation awareness system still has the following problems: First, it is difficult to adapt to a variety of climate and terrain conditions, and its accuracy and reliability are poor in the complex environment of the high-altitude and cold plateau; Second, it is difficult to simulate climate, hydrology, snowmelt process and other models, and it is impossible to provide a basis for preventing potential threats, resulting in the potential impact of environmental changes on human behavior.

[0004] Therefore, it is necessary to propose an environmental situation awareness data engineering system and method based on multi-source data fusion to solve the above problems. Summary of the invention

[0005] 1. Technical issues to be resolved

[0006] In view of the shortcomings of the prior art, the present invention provides an environmental situation awareness data engineering system and method based on multi-source data fusion, which solves the problems that the existing environmental situation awareness system is difficult to adapt to various climate and terrain conditions, has poor accuracy and reliability in complex environments of high cold plateaus; and is difficult to simulate models such as climate, hydrology, and snowmelt processes, and cannot prevent potential threats.

[0007] (II) Technical solution

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0009] An environmental situation awareness data engineering system based on multi-source data fusion, the data engineering system comprising:

[0010] Multi-source data acquisition module: contains a variety of sensors and remote sensing equipment, used to collect basic meteorological data such as surface temperature, soil moisture, precipitation, wind speed, as well as information on special environmental factors such as glaciers, frozen soil, and snow cover;

[0011] Multi-source data processing module: used to clean, correct and standardize the collected data to ensure data quality. It uses data fusion algorithms to effectively integrate data from different sources and types, and register and align data in spatial and temporal dimensions to ensure data consistency and comparability.

[0012] Environmental evolution analysis module: By acquiring data from the multi-source data processing module, using the UEB model, through the calculation methods of radiation, sensible heat, latent heat and convection heat transfer, comprehensively considering the energy transmission and conversion process in the snow, as well as the simulation of hydrology and snowmelt process, and using the autoregressive model to track the changes of environmental factors over time and space, simulate and predict the dynamic process of environmental factors changing over time and space;

[0013] Ecological restoration assessment module: used to provide restoration measures for topographic damage and to conduct real-time monitoring of slope stability during the management process;

[0014] Ecosystem Evolution Module: Analyze and predict human activities through the UEB model, unify multiple types of data into a high-dimensional space to capture complex behavior patterns, and establish a predictive model to predict the response of human behavior to environmental changes, as well as the possible impact of environmental changes on human behavior;

[0015] Visual observation module: Use the chart library ECharts to convert data into intuitive charts, provide an intuitive graphical user interface, display real-time data and evolution analysis results, make it easier for users to understand data trends and key information, and assist users in environmental management and disaster warning.

[0016] Optionally, the multi-source data acquisition module includes near-ground observation equipment, optical sensors, thermal infrared sensors, microwave sensors, laser radars, night-light remote sensing equipment, and stereo imagers;

[0017] The near-ground observation equipment includes an automatic weather station, a rain gauge and a flux tower. The automatic weather station is used to monitor the temperature, humidity and wind speed meteorological elements in real time to provide basic data for climate change research; the rain gauge is used to obtain precipitation data, and the flux tower is used to measure the carbon dioxide and water vapor exchange between the surface and the atmosphere, which is helpful for studying the carbon cycle and energy balance of the ecosystem; the optical sensor is used to capture the spectral information of the surface and obtain images of multiple spectral bands for observing surface cover changes and vegetation distribution, which is of great value for vegetation status and soil composition research; the thermal infrared sensor obtains temperature distribution information by capturing the thermal radiation of the target object, which is helpful for monitoring surface temperature changes and fire monitoring; The microwave sensor includes a synthetic aperture radar and a microwave radiometer. The synthetic aperture radar has the ability to penetrate clouds and rainfall, and is used to obtain surface information under all-weather conditions. It is suitable for complex and changeable weather conditions in high-altitude and plateau areas. The microwave radiometer is used to observe soil moisture and sea ice concentration, and is of great significance for meteorological and climate change research; the lidar obtains high-precision three-dimensional information of the surface by emitting laser pulses and measuring their echoes, and is widely used in terrain surveying and forest resource investigation; the night light remote sensing equipment monitors the urbanization process and human activities by observing the light intensity on the earth's surface at night; the stereo imager is used to provide a three-dimensional view of the ground objects, which is of great significance for terrain analysis and ecological environment assessment.

[0018] Optionally, the data fusion algorithm in the multi-source data processing module is Kalman filtering. Kalman filtering can process system noise and observation noise to improve data quality. In high-altitude and plateau environments, sensors are greatly affected by the environment and are prone to noise. Kalman filtering reduces the impact of these noises on data accuracy through algorithm optimization, and uses the linear system state equation to optimally estimate the system state using the system's input and output observation data. In high-altitude and plateau environments, sensor measured data is often affected by noise and interference. Kalman filtering can effectively filter these noises and provide more accurate state estimates. While updating the state estimate, the Kalman filtering algorithm also calculates the error covariance matrix, which provides a quantitative indicator for evaluating the uncertainty of the estimated value.

[0019] Optionally, the calculation method for radiation, sensible heat, latent heat and convective heat transfer as well as hydrology and snowmelt processes in the environmental evolution analysis module is as follows: radiation is calculated through solar radiation and surface reflection factors, sensible heat is calculated through the difference between air temperature and surface temperature, latent heat is calculated through the water vapor pressure difference, convective heat transfer is calculated through wind speed and terrain factors, hydrology is simulated by calculating water flow velocity and flow, and snowmelt process is calculated according to the energy balance principle.

[0020] Optionally, the autoregressive model in the environmental evolution analysis module is a statistical model that combines time series autoregression and spatial correlation, and is used to capture the relationship and dynamic changes of variables in time and space dimensions. Its mathematical expression is:

[0021] (I n -ρW)Y t =α+(X t -ρWX t )β+u t ,

[0022] Where: Y t is the value of the dependent variable at time t; X t is the value of the explanatory variable at time t; W is the spatial weight matrix; ρ is the spatial autoregressive coefficient; α and β are the parameters to be estimated; u t is a random error term.

[0023] Optionally, the ecological restoration assessment module includes a topography and geomorphology remodeling unit, a soil reconstruction unit, and a slope stability comprehensive monitoring unit; the topography and geomorphology remodeling unit is used to provide topography remodeling suggestions for topography and geomorphology restoration, and reshape the slag pile around the mining pit through artificial or natural means, so that it is backfilled to the bottom of the mining pit, leveling and restoring the natural terrain; the soil reconstruction unit calculates the thickness of the soil layer, constructs an ecological geological layer profile model using a binary structure of an artificial permafrost layer and a backfill layer, and analyzes the plane distribution, vertical distribution, stratigraphic structure and ground temperature changes of the original permafrost layer; the slope stability comprehensive monitoring unit monitors the slope stability in real time during the treatment process, uses sensors to collect slope displacement, moisture, and temperature data, and performs data analysis and state estimation through Kalman filtering.

[0024] Optionally, the ecosystem evolution module includes a data collection unit, a feature embedding unit, a behavior analysis unit, and a prediction model unit;

[0025] The data collection unit is used for natural and environmental data in the data fusion module, as well as collecting data related to human activities; the feature embedding unit uses embedding technology to map different types of data into a unified high-dimensional space; the behavior analysis unit uses machine learning methods to analyze the interaction and influence between human behavior and environmental elements in the embedding space; the prediction model unit, based on the analysis results, establishes a prediction model to predict the response of human behavior to environmental changes, as well as the possible impact of environmental changes on human behavior; in the ecosystem evolution module, the embedding technology of the feature embedding unit is the core.

[0026] Optionally, the chart library of the visualization observation module supports multiple chart types and realizes dynamic interaction through JavaScript and HTML5; for complex data, WebGL technology is used to realize three-dimensional visualization to provide more comprehensive data display.

[0027] An environmental situation awareness method based on multi-source data fusion includes the following steps:

[0028] A: First, we collect environmental data through multi-source data acquisition modules installed in high-cold plateau mountain locations. The data includes surface temperature, soil moisture, precipitation, and wind speed meteorological data;

[0029] B: Use the multi-source data processing module to pre-process the collected data, including cleaning, correction and standardization, and then effectively integrate data from different sources and types;

[0030] C: The processed data is transmitted to the environmental evolution analysis module, and the UEB model is used to calculate the radiation, sensible heat, latent heat and convective heat transfer as well as the hydrological and snowmelt processes. The autoregressive model is then used to generate the evolution trend and prediction results of environmental factors;

[0031] D: The ecological restoration assessment module provides terrain reshaping suggestions for restoration of topography and landforms based on the data processed by the multi-source data processing module, and conducts real-time monitoring of slope stability during the governance process;

[0032] E: The ecosystem evolution module obtains data processed by the multi-source data processing module and uses the UEB model to analyze and predict human activities and behaviors, and establishes a prediction model to predict the response of human behavior to environmental changes and the possible impact of environmental changes on human behavior;

[0033] F: The above information is converted into intuitive charts through the visual observation module and presented to end users for environmental monitoring and management decisions.

[0034] (III) Beneficial effects

[0035] The present invention provides an environmental situation awareness data engineering system and method based on multi-source data fusion, which has the following beneficial effects:

[0036] 1. The UEB model of the present invention is suitable for a variety of climate and terrain conditions, and performs well in the complex environment of high-altitude plateaus. The UEB model has achieved good results in snowmelt runoff simulation, proving its high precision and reliability in practical applications; the UEB model realizes the accurate simulation of the snowmelt process in the high-altitude plateau mountain environment, which not only improves the scientific nature of the model, but also provides strong support for practical applications.

[0037] 2. The present invention can collect and process environmental data from different data sources in real time. Based on the analysis results, it can guide the formulation of effective environmental and network security response measures. The model comprehensively evaluates the security status of the environment and provides a scientific basis for preventing potential threats. The autoregressive model demonstrates powerful data processing capabilities and in-depth behavioral analysis functions in the environmental situation awareness data system, providing a comprehensive, efficient and accurate solution for environmental management in the special environment of high-altitude plateaus and mountains.

[0038] 3. The ecological restoration assessment module of the present invention enhances the stability and sustainability of the ecosystem by providing terrain remodeling suggestions for restoration of topography and landforms, and real-time monitoring of slope stability during the management process, thereby providing a solid foundation for sustainable development, playing an important role in restoring damaged ecosystems, and contributing to the effective restoration and protection of ecosystems.

[0039] 4. In the environmental situation perception and evolution analysis of high-altitude plateau mountains, the UEB model can help analyze and predict the impact of human activities on environmental factors, as well as the potential impact of environmental changes on human behavior. The UEB model deeply explores the interaction between human activities and environmental changes, provides insights for decision makers, and assists in decision making. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a module schematic diagram of the environmental situation awareness data engineering system of the present invention;

[0041] Figure 2 The figure is a flow chart of the environmental situation awareness method of the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] Example 1

[0044] See also Figure 1 , an environmental situation awareness data engineering system based on multi-source data fusion, the data engineering system includes:

[0045] Multi-source data acquisition module: contains a variety of sensors and remote sensing equipment, including near-ground observation equipment, optical sensors, thermal infrared sensors, microwave sensors, lidar, night light remote sensing equipment, and stereo imagers; near-ground observation equipment includes automatic weather stations, rain gauges, and flux towers. Automatic weather stations are used to monitor temperature, humidity, and wind speed meteorological elements in real time, providing basic data for climate change research; rain gauges are used to obtain precipitation data, and flux towers are used to measure the exchange of carbon dioxide and water vapor between the surface and the atmosphere, which is helpful for studying the carbon cycle and energy balance of ecosystems; optical sensors are used to capture the spectral information of the surface and obtain images of multiple spectral bands for observing changes in surface cover and vegetation distribution, which is of great value for the study of vegetation status and soil composition; thermal infrared sensors obtain temperature distribution information by capturing the thermal radiation of target objects, which is helpful for monitoring surface temperature Microwave sensors include synthetic aperture radar and microwave radiometer. Synthetic aperture radar has the ability to penetrate clouds and rainfall, and is used to obtain surface information under all-weather conditions. It is suitable for complex and changeable weather conditions in high-altitude and plateau areas. Microwave radiometer is used to observe soil moisture and sea ice concentration, which is of great significance for meteorological and climate change research. Lidar obtains high-precision three-dimensional information of the surface by emitting laser pulses and measuring their echoes. It is widely used in topographic mapping and forest resource surveys. Night light remote sensing equipment monitors urbanization and human activities by observing the light intensity on the earth's surface at night. Stereo imagers are used to provide three-dimensional views of objects, which are of great significance for terrain analysis and ecological environment assessment. They are used to collect basic meteorological data on surface temperature, soil moisture, precipitation, wind speed, as well as information on special environmental elements such as glaciers, permafrost, and snow.

[0046] Multi-source data processing module: used to clean, correct and standardize the collected data to ensure data quality. It uses data fusion algorithms to effectively integrate data from different sources and types (such as remote sensing data, ground monitoring data, and meteorological data), and align and register the data in spatial and temporal dimensions to ensure data consistency and comparability.

[0047] Environmental evolution analysis module: By acquiring data from the multi-source data processing module, using the UEB model, through the calculation methods of radiation, sensible heat, latent heat and convection heat transfer, comprehensively considering the energy transmission and conversion process in the snow, as well as the simulation of hydrology and snowmelt process, and using the autoregressive model to track the changes of environmental factors over time and space, simulate and predict the dynamic process of environmental factors changing over time and space. The UEB model can solve the problem of diurnal cycles, with a time resolution of 6 hours or less, capturing the rapid changes in meteorological conditions and snowmelt process. The model is suitable for the basin scale, can record the balance of water and energy, and provide important support for basin management;

[0048] The calculation method of radiation, sensible heat, latent heat and convective heat transfer as well as hydrology and snowmelt in the environmental evolution analysis module is: radiation is calculated through solar radiation and surface reflection factors. The UEB model accurately calculates the net radiation flux by comprehensively considering solar radiation and surface reflection factors. The mathematical formula is as follows:

[0049] Q in =(1-α)·Q s +L↓-L↑,

[0050] Among them, Q in is the net radiation, α is the surface albedo, Q s is the solar short-wave radiation, L↓ is the atmospheric long-wave radiation, and L↑ is the surface long-wave radiation;

[0051] Sensible heat is calculated by the difference between air temperature and surface temperature. The UEB model takes into account the difference between air temperature and surface temperature to further accurately calculate the sensible heat flux. The mathematical formula is as follows:

[0052] H=h c ·(T s -T a ),

[0053] Where H is the sensible heat flux, h c is the surface heat transfer coefficient, T s is the surface temperature, T a is the air temperature;

[0054] The latent heat is calculated by the water vapor pressure difference. The UEB model covers the effect of the water vapor pressure difference on the latent heat flux, ensuring the comprehensiveness and accuracy of the simulation results. The mathematical formula is as follows:

[0055] LE=h v ·(ρ v (T s )-ρ v (T a )),

[0056] Where LE is the latent heat flux, h V is the surface water vapor transfer coefficient, ρ V (T s ) is the value of saturated water vapor density at surface temperature, T s is the surface temperature, ρ V (T a ) is the value of saturated water vapor density at air temperature;

[0057] The convective heat transfer is calculated by wind speed and terrain factors. The mathematical formula is as follows:

[0058] C=h c ·(T s -Ta )+h v ·(ρ v (T s )-ρ v (T a )),

[0059] Where C is the total convective heat transfer, h c is the surface heat transfer coefficient, T s is the surface temperature, T a is the air temperature; h V is the surface water vapor transfer coefficient;

[0060] By calculating the water flow velocity and flow rate and simulating hydrology, the model combined with the Manning formula hydrological calculation formula can accurately predict the water flow velocity and flow rate, which is helpful for flood warning and irrigation system design. The mathematical formula is as follows:

[0061]

[0062] Where Q is the flow rate, A is the wetted cross-sectional area, P is the hydraulic radius, S is the slope, and n is the Manning roughness coefficient;

[0063] By calculating the snowmelt process according to the energy balance principle, when Q in >0, the snow begins to melt, and the snowmelt rate can be calculated by the following formula;

[0064]

[0065] Where M is the snowmelt rate, Q in is the net radiation, H f is the heat of fusion of water; changes in snow cover area are monitored through remote sensing data and estimated by combining snowfall and snowmelt data;

[0066] The autoregressive model in the environmental evolution analysis module is a statistical model that combines time series autoregression and spatial correlation. It is used to capture the relationship and dynamic changes of variables in time and space dimensions. Its mathematical expression is:

[0067] (I n -ρW)Y t =α+(X t -ρWX t )β+u t ,

[0068] Where: Y t is the value of the dependent variable at time t; X t is the value of the explanatory variable at time t; W is the spatial weight matrix; ρ is the spatial autoregressive coefficient; α and β are the parameters to be estimated; u t is the random error term;

[0069] Visual observation module: Use the chart library ECharts to convert data into intuitive charts, provide an intuitive graphical user interface, and display real-time data and evolution analysis results. The chart library of the visual observation module supports a variety of chart types, such as line charts, bar charts, and realizes dynamic interaction through JavaScript and HTML5; for complex data, WebGL technology is used to achieve three-dimensional visualization, providing a more comprehensive data display, making it easier for users to understand data trends and key information, and assisting users in environmental management and disaster warning.

[0070] In this embodiment, by setting up a variety of sensors and remote sensing equipment, it plays a vital role in the special environment of high-altitude plateau mountains. These devices can monitor and analyze multiple factors such as terrain, climate, vegetation, and water bodies, providing strong technical support for scientific research, ecological protection, disaster prevention, and resource management. The multi-source data processing module uses advanced data cleaning and classification technology, and the model ensures data quality, provides standardized data for subsequent analysis, and realizes efficient data preprocessing. It can convert data from different fields into a unified format for easy integration and analysis;

[0071] The UEB model is applicable to a variety of climate and terrain conditions, and performs well in complex environments of high-altitude plateaus. The UEB model has achieved good results in snowmelt runoff simulation, proving its high accuracy and reliability in practical applications. The UEB model has achieved accurate simulation of the snowmelt process in high-altitude plateau mountain environments, which not only improves the scientific nature of the model, but also provides strong support for practical applications. With the intensification of climate change and the impact of human activities, the UEB model is expected to play a greater role in water resources prediction and management, and contribute to environmental protection and sustainable development on a global scale.

[0072] The environmental evolution analysis module can collect and process environmental data from different data sources in real time, such as climate conditions and terrain changes, and enhance spatiotemporal dynamic monitoring. Based on the analysis results, the model can guide the formulation of effective environmental and network security response measures. The model comprehensively evaluates the security status of the environment and provides a scientific basis for preventing potential threats. The model realizes resource optimization management of the entire data analysis process to ensure efficient operation. The autoregressive model demonstrates powerful data processing capabilities and in-depth behavioral analysis functions in the environmental situation awareness data system, providing strong technical support for environmental monitoring, decision support and security defense, and providing a comprehensive, efficient and accurate solution for environmental management in the special environment of high-altitude plateau mountains. Through real-time monitoring and spatiotemporal evolution analysis, the system can effectively predict and respond to environmental changes, providing a scientific basis for disaster prevention and mitigation and resource management.

[0073] Example 2

[0074] This embodiment is further optimized on the basis of Embodiment 1. Specifically, the data fusion algorithm in the multi-source data processing module is Kalman filtering. Kalman filtering can process system noise and observation noise to improve data quality. In the high-altitude and plateau environment, the sensor is greatly affected by the environment and is prone to noise. Kalman filtering reduces the impact of these noises on data accuracy through algorithm optimization, and uses the linear system state equation to optimally estimate the system state using the system's input and output observation data. In the high-altitude and plateau environment, the data measured by the sensor is often affected by noise and interference. Kalman filtering can effectively filter these noises and provide more accurate state estimation. The high-altitude and plateau environment situation awareness system usually includes multiple sensors, such as GPS, barometer and inertial measurement unit. The data measured by each of these sensors has its limitations and uncertainties.

[0075] In this embodiment, the Kalman filter algorithm can fuse the data of these sensors to generate an optimal estimated state. For example, by fusing the altitude data of different sensors, more accurate altitude information can be obtained. In the situation perception of high-altitude plateau environments, this is particularly important for predicting weather changes, temperature trends, etc. Through dynamic system models and historical data, Kalman filtering can predict future environmental situations in real time. Due to the harsh environmental conditions in high-altitude plateaus, real-time data processing is crucial to ensuring personnel safety and equipment operation. Kalman filtering can perform real-time processing while collecting data, and update state estimates in a timely manner to provide a reliable basis for decision-making. While updating the state estimate, the Kalman filter algorithm also calculates the error covariance matrix, which provides a quantitative indicator for evaluating the uncertainty of the estimated value.

[0076] Example 3

[0077] This embodiment is further optimized on the basis of the embodiment 1. Specifically, the system further includes an ecological restoration assessment module, which includes a topography and geomorphology remodeling unit, a soil reconstruction unit, and a slope stability comprehensive monitoring unit, which is used to provide topography and geomorphology damage restoration measures and to monitor the slope stability in real time during the treatment process;

[0078] The landform reshaping unit is used to provide landform reshaping suggestions for landform restoration. Through artificial or natural means, the slag pile around the pit is reshaped and backfilled to the bottom of the pit, leveling and restoring the natural terrain. The volume mathematical formula of landform reshaping is:

[0079]

[0080] Where A and B are the major and minor axes of the ellipsoid, and h is the height;

[0081] The soil reconstruction unit calculates the thickness of the soil layer, uses the binary structure of artificial frozen soil layer and backfill layer to construct the ecological geological layer profile model, and analyzes the plane distribution, vertical distribution, stratum structure and ground temperature changes of the original frozen soil layer. The mathematical formula for calculating the thickness of the soil layer is as follows:

[0082]

[0083] Where m is mass, ρ is soil density, and A is area;

[0084] The comprehensive slope stability monitoring unit monitors the slope stability in real time during the management process, uses sensors to collect slope displacement, moisture, and temperature data, and performs data analysis and state estimation through Kalman filtering.

[0085] In this embodiment, the ecological restoration assessment module enhances the stability and sustainability of the ecosystem by providing landform reshaping suggestions for landform restoration and real-time monitoring of slope stability during the governance process, providing a solid foundation for sustainable development, playing an important role in restoring damaged ecosystems, and contributing to the effective restoration and protection of ecosystems.

[0086] Ecological restoration helps reduce the frequency and impact of natural disasters. By restoring the integrity and function of ecosystems, ecological restoration reduces ecological safety risks and improves the overall quality of the country's ecological environment. By rebuilding ecosystems, ecological restoration provides more habitats for animals and plants, helps protect and increase biodiversity. The enhancement of biodiversity helps maintain the stability and resistance to interference of ecosystems, thereby forming a self-sustaining healthy ecosystem.

[0087] Example 4

[0088] This embodiment is further optimized on the basis of Embodiment 1. Specifically, the system further includes an ecosystem evolution module, which includes a data collection unit, a feature embedding unit, a behavior analysis unit, and a prediction model unit. The UEB model is used to analyze and predict human activity behaviors, and multiple types of data (such as user attributes, environmental factors, and historical behaviors) are unified into a high-dimensional space to capture complex behavior patterns. A prediction model is established to predict the response of human behavior to environmental changes and the possible impact of environmental changes on human behavior.

[0089] The data collection unit is used to collect natural and environmental data in the data fusion module, as well as human activity-related data (such as tourism, agriculture, and mining activity data); the feature embedding unit uses embedding technology to map different types of data (such as geographic location, climate conditions, historical environmental data, and human activity records) into a unified high-dimensional space; the behavior analysis unit uses machine learning methods (such as deep learning) to analyze the interaction and impact between human behavior and environmental elements in the embedded space; the prediction model unit, based on the analysis results, establishes a prediction model to predict the response of human behavior to environmental changes, as well as the possible impact of environmental changes on human behavior;

[0090] In the ecosystem evolution module, the embedding technology of the feature embedding unit is the core, and the mathematical formula is expressed as:

[0091] e i =f(x i ,w),

[0092] Among them, x i is the i-th data point (which can be user attributes or environmental factors), w is the parameter of the embedding model, and e i is the data point x i The embedding vector, the embedding vector e i Used to capture complex features and relationships of data points in high-dimensional space, these embedding vectors can be input into machine learning models for further behavior analysis and prediction.

[0093] In this embodiment, in the environmental situation perception and evolution analysis of high-altitude plateau mountains, the UEB model can help analyze and predict the impact of human activities on environmental elements, as well as the potential impact of environmental changes on human behavior. The UEB model deeply explores the interaction between human activities and environmental changes, and provides insights for decision makers; the prediction model built based on the embedded vector can predict environmental changes and their impact on human behavior, and the prediction model built based on the autoregressive model can predict environmental changes and their impact on human behavior, and assist in decision making.

[0094] like Figure 2 As shown, the present invention also provides an environmental situation awareness method based on multi-source data fusion, comprising the following steps:

[0095] A: First, we collect environmental data through multi-source data acquisition modules installed in high-cold plateau mountain locations. The data includes surface temperature, soil moisture, precipitation, and wind speed meteorological data;

[0096] B: Use the multi-source data processing module to pre-process the collected data, including cleaning, correction and standardization, and then effectively integrate data from different sources and types;

[0097] C: The processed data is transmitted to the environmental evolution analysis module, and the UEB model is used to calculate the radiation, sensible heat, latent heat and convective heat transfer as well as the hydrological and snowmelt processes. The autoregressive model is then used to generate the evolution trend and prediction results of environmental factors;

[0098] D: The ecological restoration assessment module provides terrain reshaping suggestions for restoration of topography and landforms based on the data processed by the multi-source data processing module, and conducts real-time monitoring of slope stability during the governance process;

[0099] E: The ecosystem evolution module obtains data processed by the multi-source data processing module and uses the UEB model to analyze and predict human activities and behaviors, and establishes a prediction model to predict the response of human behavior to environmental changes and the possible impact of environmental changes on human behavior;

[0100] F: The above information is converted into intuitive charts through the visual observation module and presented to end users for environmental monitoring and management decisions.

[0101] In summary: the UEB model of the present invention is applicable to a variety of climate and terrain conditions, and performs well in complex environments of high-altitude and cold plateaus. The UEB model has achieved good results in snowmelt runoff simulation, proving its high accuracy and reliability in practical applications; in the situation perception and evolution analysis of high-altitude and cold plateau mountain environments, the UEB model can help analyze and predict the impact of human activities on environmental factors, as well as the potential impact of environmental changes on human behavior. The UEB model deeply explores the interaction between human activities and environmental changes, provides insights for decision makers, and assists in decision making;

[0102] The multi-source data acquisition module of the present invention can collect and process environmental data from different data sources in real time. Based on the analysis results, it can guide the formulation of effective environmental and network security response measures. The model comprehensively evaluates the security status of the environment and provides a scientific basis for preventing potential threats. The autoregressive model demonstrates powerful data processing capabilities and in-depth behavioral analysis functions in the environmental situation awareness data system, providing a comprehensive, efficient and accurate solution for environmental management in the special environment of high-altitude plateaus and mountains.

[0103] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. An environmental situation awareness data engineering system based on multi-source data fusion, characterized in that: The data engineering system includes: Multi-source data acquisition module: contains a variety of sensors and remote sensing equipment, used to collect basic meteorological data such as surface temperature, soil moisture, precipitation, wind speed, as well as information on special environmental factors such as glaciers, frozen soil, and snow cover; Multi-source data processing module: used to clean, correct and standardize the collected data, use data fusion algorithms to effectively integrate data from different sources and types, and register and align the data in spatial and temporal dimensions; Environmental evolution analysis module: By acquiring data from the multi-source data processing module, using the UEB model, through the calculation methods of radiation, sensible heat, latent heat and convection heat transfer, comprehensively considering the energy transmission and conversion process in the snow, as well as the simulation of hydrology and snowmelt process, and using the autoregressive model to track the changes of environmental factors over time and space, simulate and predict the dynamic process of environmental factors changing over time and space; The calculation methods of radiation, sensible heat, latent heat and convective heat transfer as well as hydrology and snowmelt process in the environmental evolution analysis module are as follows: radiation is calculated by solar radiation and surface reflection factors, sensible heat is calculated by the difference between air temperature and surface temperature, latent heat is calculated by water vapor pressure difference, convective heat transfer is calculated by wind speed and terrain factors, hydrology is simulated by calculating water flow velocity and flow, and snowmelt process is calculated according to the energy balance principle; Ecological restoration assessment module: used to provide restoration measures for topographic damage and to conduct real-time monitoring of slope stability during the management process; Ecosystem Evolution Module: Analyze and predict human activities through the UEB model, unify multiple types of data into a high-dimensional space to capture complex behavior patterns, and establish a predictive model to predict the response of human behavior to environmental changes, as well as the possible impact of environmental changes on human behavior; Visual observation module: Use the chart library ECharts to convert data into intuitive charts, provide an intuitive graphical user interface, display real-time data and evolution analysis results, and assist users in environmental management and disaster warning.

2. The environmental situation awareness data engineering system based on multi-source data fusion according to claim 1 is characterized by: The multi-source data acquisition module includes near-ground observation equipment, optical sensors, thermal infrared sensors, microwave sensors, laser radars, night-light remote sensing equipment, and stereo imagers; The near-surface observation equipment includes an automatic weather station, a rain gauge and a flux tower. The automatic weather station is used to monitor the meteorological elements of temperature, humidity and wind speed in real time. The rain gauge is used to obtain precipitation data, and the flux tower is used to measure the exchange of carbon dioxide and water vapor between the surface and the atmosphere. The optical sensor is used to capture the spectral information of the surface and obtain images of multiple spectral bands for observing changes in surface coverage and vegetation distribution. The thermal infrared sensor obtains temperature distribution information by capturing the thermal radiation of the target object. The microwave sensor includes a synthetic aperture radar and a microwave radiometer. The synthetic aperture radar is used to obtain surface information under all-weather conditions, and the microwave radiometer is used to observe soil moisture and sea ice concentration. The lidar obtains high-precision three-dimensional information of the surface by emitting laser pulses and measuring their echoes. The night light remote sensing equipment monitors urbanization and human activities by observing the light intensity on the earth's surface at night. The stereo imager is used to provide a three-dimensional view of a ground object.

3. The environmental situation awareness data engineering system based on multi-source data fusion according to claim 1 is characterized by: The data fusion algorithm in the multi-source data processing module is Kalman filtering, which can process system noise and observation noise, improve data quality, and make optimal estimates of the system state by using the input and output observation data of the system through the linear system state equation.

4. The environmental situation awareness data engineering system based on multi-source data fusion according to claim 1 is characterized by: The ecological restoration assessment module includes a topography and geomorphology remodeling unit, a soil reconstruction unit, and a slope stability comprehensive monitoring unit; The topography and geomorphology remodeling unit is used to provide topography remodeling suggestions for restoration of topography and geomorphology; the soil reconstruction unit calculates the thickness of the soil layer, uses the binary structure of artificial frozen soil layer and backfill layer to construct an ecological geological layer profile model, and analyzes the plane distribution, vertical distribution, stratigraphic structure and ground temperature changes of the original frozen soil layer; The comprehensive slope stability monitoring unit monitors the slope stability in real time during the management process, uses sensors to collect slope displacement, moisture, and temperature data, and performs data analysis and state estimation through Kalman filtering.

5. The environmental situation awareness data engineering system based on multi-source data fusion according to claim 1 is characterized by: The ecosystem evolution module includes a data collection unit, a feature embedding unit, a behavior analysis unit, and a prediction model unit; The data collection unit is used for collecting natural and environmental data in the data fusion module, as well as collecting data related to human activities; The feature embedding unit maps different types of data into a unified high-dimensional space using embedding technology; The behavior analysis unit uses machine learning methods to analyze the interaction and influence between human behavior and environmental factors in the embedded space; the prediction model unit establishes a prediction model based on the analysis results to predict the response of human behavior to environmental changes and the possible impact of environmental changes on human behavior.

6. The environmental situation awareness data engineering system based on multi-source data fusion according to claim 1 is characterized by: The chart library of the visualization observation module supports multiple chart types and realizes dynamic interaction through JavaScript and HTML5; for complex data, WebGL technology is used to realize three-dimensional visualization to provide more comprehensive data display.

7. The environmental situation awareness data engineering system based on multi-source data fusion according to claim 1 is characterized in that: Including environmental situation awareness methods based on multi-source data fusion, The following steps are involved: A: First, we collect environmental data through multi-source data acquisition modules installed in high-cold plateau mountain locations. The data includes surface temperature, soil moisture, precipitation, and wind speed meteorological data; B: Use the multi-source data processing module to pre-process the collected data, including cleaning, correction and standardization, and then effectively integrate data from different sources and types; C: The processed data is transmitted to the environmental evolution analysis module, and the UEB model is used to calculate the radiation, sensible heat, latent heat and convective heat transfer as well as the hydrological and snowmelt processes. The autoregressive model is then used to generate the evolution trend and prediction results of environmental factors; D: The ecological restoration assessment module provides terrain reshaping suggestions for restoration of topography and landforms based on the data processed by the multi-source data processing module, and conducts real-time monitoring of slope stability during the governance process; E: The ecosystem evolution module obtains data processed by the multi-source data processing module and uses the UEB model to analyze and predict human activities and behaviors, and establishes a prediction model to predict the response of human behavior to environmental changes and the possible impact of environmental changes on human behavior; F: The evolution trends and prediction results are converted into intuitive charts through the visualization observation module and presented to end users for environmental monitoring and management decisions.

Images