Hydrogeological, Engineering Geological and Environmental Geological Exploration System and Method Based on GPS Positioning

Abstract

The present invention relates to the technical field of geological exploration, specifically a hydrogeological, engineering geological and environmental geological exploration system and method based on GPS positioning. The system includes a geographic information integration module, a risk identification and prediction module, an intelligent planning and adjustment module, a geological process simulation module, a project management and collaboration module, a real-time monitoring and adjustment module, and a decision support and optimization module. In the present invention, through a spatial data fusion algorithm, the geographic information integration is optimized to ensure data consistency and integrity. By combining random forest and convolutional neural network, geological risks are identified and the impact of climate change is predicted. Through genetic algorithm and support vector machine algorithm, the exploration plan is intelligently adjusted, the exploration path is planned, and the exploration efficiency is improved. Using computational fluid dynamics technology, geological and hydrological processes are simulated. Combined with the Scrum framework, project management is optimized and the execution efficiency is improved. Using decision tree and graph neural network, the overall efficiency and safety of the project are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of geological exploration, and particularly to a hydrogeological, engineering geological and environmental geological exploration system and method based on GPS positioning. Background Art

[0002] The technical field of geological exploration involves research on groundwater dynamics, geotechnical engineering characteristics, and the impact of geological processes on the environment. Hydrogeology focuses on the distribution, flow, and quality of groundwater, providing a scientific basis for water resource assessment and protection. Engineering geology focuses on analyzing the impact of geological conditions on engineering construction to ensure the safety and stability of buildings and infrastructure. Environmental geology studies the impact of geological processes and activities on human activities and the ecological environment to prevent and mitigate geological disasters.

[0003] Among them, the hydrogeological, engineering geological and environmental geological exploration system based on GPS positioning is a system that uses global positioning system technology for precise positioning and combines geological exploration technology to evaluate the geological conditions of hydraulic projects. Through accurate geographical location information and in-depth geological analysis, it evaluates and monitors the hydrogeological, engineering geological, and environmental geological conditions in the hydraulic environment, supporting the planning, design, construction, and maintenance of water conservancy projects. By providing detailed information on groundwater flow, engineering properties of rocks and soils, and geological environmental risks, it optimizes engineering design, improves construction efficiency, reduces environmental impact, and ensures project safety.

[0004] Traditional hydrogeological, engineering geological and environmental geological exploration systems have deficiencies in data integration, risk identification, exploration plan formulation, project management, and real-time monitoring. Traditional hydrogeological, engineering geological and environmental geological exploration systems manually process geographical information, resulting in fragmented data, insufficient accuracy and integrity, lack of an efficient risk identification and prediction mechanism, inability to timely detect and respond to geological risks, increasing the uncertainty and risks in the exploration process. In the formulation of exploration plans, traditional hydrogeological, engineering geological and environmental geological exploration methods lack sufficient flexibility and self-adaptability, resulting in limited exploration efficiency and accuracy. Traditional linear management methods are not conducive to teamwork and optimal allocation of resources, affecting project execution efficiency. The lack of an effective real-time monitoring and dynamic adjustment mechanism makes it difficult for projects to quickly respond to changes in geological and environmental conditions, causing resource waste and potential safety hazards. Summary of the Invention

[0005] The purpose of the present invention is to solve the drawbacks existing in the prior art, and to propose a hydrogeological, engineering geological and environmental geological exploration system and method based on GPS positioning.

[0006] To achieve the above purpose, the present invention adopts the following technical solutions: The hydrogeological, engineering geological and environmental geological exploration system based on GPS positioning includes a geographic information integration module, a risk identification and prediction module, an intelligent planning and adjustment module, a geological process simulation module, a project management and collaboration module, a real-time monitoring and feedback module, and a decision support and optimization module;

[0007] The described geographic information integration module is based on GPS data, applies Kriging interpolation to evaluate geological attributes, combines with voxel model technology, transforms the data into a three-dimensional geological model, maps and integrates geographical locations and associated geological features, and generates a comprehensive geographic information model;

[0008] The risk identification and prediction module is based on the comprehensive geographic information model, uses random forest and convolutional neural network to identify geological risks, analyzes climate change data, evaluates the impact of climate change on hydrogeological conditions, and generates risk identification and prediction analysis information;

[0009] The intelligent planning and adjustment module is based on the risk identification and prediction analysis information, uses genetic algorithm and support vector machine algorithm to adjust the geological exploration plan, combines historical exploration data, geological features and environmental factors, matches the optimal exploration points and paths, and generates an intelligent exploration planning scheme;

[0010] The geological process simulation module is based on the intelligent exploration planning scheme, uses computational fluid dynamics simulation technology to establish a simulation model of geological structure changes and geological processes, simulates hydrogeological processes, rock layer movement and soil erosion, and generates geological process simulation analysis results;

[0011] The project management and collaboration module is based on the geological process simulation analysis results, uses the Scrum framework, combines task decomposition and progress tracking technology, conducts project task planning, resource allocation, real-time project progress tracking, optimizes the interactive communication tool through natural language processing technology, and generates a project collaboration efficiency improvement scheme;

[0012] The real-time monitoring and adjustment module is based on the project collaboration efficiency improvement scheme, uses surface displacement monitoring and groundwater level monitoring technology to monitor geological exploration activities and environmental conditions in real time, adjusts the exploration plan, conducts risk assessment, and generates a real-time monitoring and adjustment scheme;

[0013] The decision support and optimization module is based on the real-time monitoring and adjustment scheme, uses decision tree and graph neural network to analyze exploration data and monitoring results, provides optimization schemes and decision support, optimizes project efficiency and safety, and generates decision optimization schemes.

[0014] As a further solution of the present invention, the comprehensive geographic information model includes groundwater distribution information, geological structure information, and environmentally sensitive area information. The risk identification and prediction analysis information includes geological disaster risk information, climate change impact information, and geological risk level information. The intelligent exploration planning scheme includes exploration point distribution information, exploration path planning results, and comprehensive environmental and geological analysis results. The geological process simulation analysis results include hydrogeological process simulation, rock layer movement information, and soil erosion process information. The project collaboration efficiency improvement scheme includes project task planning, resource allocation scheme, and progress tracking mechanism. The real-time monitoring and adjustment scheme includes surface displacement monitoring data, groundwater level monitoring data, and exploration plan adjustment information. The decision-making optimization scheme includes exploration data analysis information, monitoring result evaluation information, and project optimization scheme.

[0015] As a further solution of the present invention, the geographic information integration module includes a GPS data integration sub-module, a geographic information data mapping sub-module, and a geological information fusion sub-module;

[0016] Based on GPS data, the GPS data integration sub-module uses a data fusion algorithm to integrate the collected geographical location data, including synchronizing the data from multiple GPS devices in terms of time and coordinate system, removing outliers through data cleaning, optimizing data quality and consistency, and combining data interpolation methods to fill data gaps and generate integrated location data information;

[0017] Based on the integrated location data information, the geographic information data mapping sub-module uses Kriging interpolation and voxel model technology to perform geographic information mapping. By matching the integrated GPS data with existing map resources, using spatial analysis methods to identify geographic features, and matching the features with the geographic coordinate system, it generates geographic feature mapping information;

[0018] Based on the geographic feature mapping information, the geological information fusion sub-module uses a spatial data fusion algorithm to combine geological survey data, hydrographic measurement data, environmental monitoring data, and geographic feature mapping information to construct a geographic model including geological structure, hydrographic features, and environmental conditions, and generates a comprehensive geographic information model.

[0019] As a further solution of the present invention, the risk identification and prediction module includes a climate change analysis sub-module, a geological risk identification sub-module, and a risk prediction analysis sub-module;

[0020] The climate change analysis sub-module is based on a comprehensive geographic information model, uses time series analysis algorithms, combines climate change data, including temperature, rainfall, and wind speed parameters, identifies climate characteristics that affect hydrogeological and environmental geological conditions, uses long short-term memory networks to analyze the changing trends of climate parameters, predicts climate change patterns, and generates climate change characteristic analysis information;

[0021] The geological risk identification sub-module is based on the climate change characteristic analysis information, uses the random forest algorithm to analyze geological, hydrological, and environmental data in the comprehensive geographic information model, identifies geological risks caused by climate change, including landslides, floods, and land subsidence, uses the random forest algorithm to identify risk areas, and generates geological risk identification results;

[0022] The risk prediction and analysis sub-module is based on the geological risk identification results, uses convolutional neural networks and time series prediction techniques to analyze geological risk areas, predict risk trends, combines geological event data and environmental changes, predicts the types, frequencies, and intensities of geological risk events in the target area, and generates risk identification and prediction analysis information.

[0023] As a further aspect of the present invention, the intelligent planning and adjustment module includes a survey point analysis sub-module, a survey path optimization sub-module, and a plan adjustment strategy sub-module;

[0024] The survey point analysis sub-module is based on the risk identification and prediction analysis information, uses the genetic algorithm to analyze historical survey data, geological characteristics, and environmental factors, and uses the genetic algorithm to evaluate multiple survey points in combination with survey costs, accessibility, and geological risks, generating a survey point data set;

[0025] The survey path optimization sub-module is based on the survey point data set, uses the support vector machine algorithm to classify terrain and obstacle factors, combines time factors and cost factors to plan paths for survey points, optimizes the efficiency and economy of survey activities, and generates a survey path planning scheme;

[0026] The plan adjustment strategy sub-module is based on the survey path planning scheme, uses the simulated annealing algorithm to adjust survey points and paths in combination with geological environment and geological risks, matches the survey plan by comparing the costs and benefits of adjustment schemes, and generates an intelligent survey planning scheme.

[0027] As a further aspect of the present invention, the geological process simulation module includes a rock layer movement simulation sub-module, a hydrological process simulation sub-module, and a soil erosion simulation sub-module;

[0028] The rock layer movement simulation sub-module, based on the intelligent exploration and planning scheme, uses the discrete element method and combines the physical properties of the rock layer, including particle size, shape, and density, to simulate the movement, collision, and rearrangement processes of rock layer particles under the action of natural forces, predict the stability and movement path of the rock layer, and generate rock layer movement simulation analysis information;

[0029] The hydrological process simulation sub-module, based on the rock layer movement simulation analysis information, uses the finite difference method to conduct numerical simulation of groundwater flow. By referring to the geometric characteristics, permeability, and water storage capacity of the groundwater aquifer, and combining precipitation, evaporation, and plant absorption factors to analyze the recharge and loss of groundwater, it simulates the groundwater flow and distribution in the hydrogeological process, predicts the changes in groundwater distribution under various hydrological conditions, and generates hydrological process simulation analysis results;

[0030] The soil erosion simulation sub-module, based on the hydrological process simulation analysis results, uses the RUSLE model and the WEPP model, and refers to soil type, slope, vegetation coverage, rainfall, and surface flow velocity to simulate the erosion effect of rainwater and surface water flow on the soil, calculate the rate and spatial distribution of soil erosion and transportation, predict the erosion risk area and soil loss amount, and generate geological process simulation analysis results.

[0031] As a further solution of the present invention, the project management and collaboration module includes a task planning sub-module, a resource allocation sub-module, and a team communication sub-module;

[0032] The task planning sub-module, based on the geological process simulation analysis results, uses the Scrum framework to subdivide project goals. Through the role assignment and task splitting of team members, it configures task personnel and task priorities, optimizes work efficiency, and generates a personnel allocation plan;

[0033] The resource allocation sub-module, based on the personnel allocation plan, uses linear programming and dynamic programming. By evaluating the matching degree between the resource requirements of tasks and the available resources, and using resource levels and optimization techniques, it allocates and optimizes the human, equipment, and financial resources required for the project, and generates a resource allocation plan;

[0034] The team communication sub-module, based on the resource allocation plan, uses natural language processing technology to optimize interactive communication tools, including developing and integrating intelligent communication assistants, and automates project communication tasks, including meeting minutes generation and task update reminders, and generates a project collaboration efficiency improvement plan.

[0035] As a further solution of the present invention, the real-time monitoring and adjustment module includes a geological activity monitoring sub-module, an environmental condition monitoring sub-module, and an exploration plan adjustment sub-module;

[0036] The geological activity monitoring sub-module, based on the project collaboration efficiency improvement plan, uses seismic wave velocity measurement and surface displacement sensing technologies, combines with the Gaussian process regression algorithm, analyzes the collected data, identifies geological activity patterns and anomalies, analyzes the geological activity process, including fault movement and crustal deformation, evaluates the impact of geological activities on the exploration area, and generates geological activity analysis results;

[0037] The environmental condition monitoring sub-module, based on the geological activity analysis results, uses multi-parameter environmental monitoring technologies, real-time tracks and analyzes meteorological conditions, including rainfall, temperature, groundwater level and surface water flow dynamics, uses trend analysis and anomaly detection algorithms, evaluates the potential impact of environmental changes on exploration activities, and generates environmental condition monitoring analysis results;

[0038] The exploration plan adjustment sub-module, based on the environmental condition monitoring analysis results, uses dynamic programming and decision support systems, analyzes the impact of geological activities and environmental changes on the exploration plan, adjusts exploration points, paths and schedules, and generates a real-time monitoring adjustment plan.

[0039] As a further solution of the present invention, the decision support and optimization module includes a data analysis and decision-making sub-module, an optimization strategy generation sub-module, and a security assessment sub-module;

[0040] The data analysis and decision-making sub-module, based on the real-time monitoring adjustment plan, uses decision tree algorithms to classify and analyze exploration data and monitoring results. By extracting key features from batch data, classifying the data, identifying key decision points and risks of exploration activities, and evaluating the impact of multiple decision-making scenarios by analyzing multiple branch results of the data, decision analysis results are generated;

[0041] The optimization strategy generation sub-module, based on the decision analysis results, uses graph neural network algorithms to analyze the relationship network of exploration projects, including the interactions between geological features, environmental factors and exploration activities. Through the iterative update of the network, combined with the feasibility and cost-effectiveness of the project, a management strategy planning plan is generated;

[0042] The security assessment sub-module, based on the management strategy planning plan, uses fault tree analysis and event tree analysis to evaluate the safety risks of exploration activities. By identifying and analyzing the factors and event sequences leading to accidents, evaluating the risk probabilities of multiple scenarios, matching risk mitigation measures and safety guarantee plans, a decision optimization plan is generated.

[0043] The hydrogeological, engineering geological and environmental geological exploration method based on GPS positioning, the hydrogeological, engineering geological and environmental geological exploration based on GPS positioning is executed based on the above-mentioned hydrogeological, engineering geological and environmental geological exploration system based on GPS positioning, and includes the following steps:

[0044] S1: Based on GPS data, adopt data fusion algorithms to synchronize time and coordinate data, and combine data interpolation techniques to improve data quality and integrity, generating geospatial integrated information;

[0045] S2: Based on the geospatial integrated information, adopt random forest algorithms and long short-term memory networks to analyze geological, hydrological, environmental data, and climate change, identify geological risks and their impacts on exploration activities, generating risk identification information;

[0046] S3: Based on the risk identification information, adopt genetic algorithms and support vector machine algorithms, combine historical exploration data, geological features, and environmental factors to match exploration points and paths, generating an exploration path planning scheme;

[0047] S4: Based on the exploration path planning scheme, adopt computational fluid dynamics simulation techniques to simulate hydrogeological processes, and use the Scrum framework to allocate resources and track progress for project tasks, generating geological analysis results and a collaborative efficiency improvement scheme;

[0048] S5: Based on the geological analysis results and the collaborative efficiency improvement scheme, adopt surface displacement and groundwater level monitoring techniques, combine geological monitoring data, adjust the exploration plan, match geological and environmental changes, generating a dynamic adjustment scheme;

[0049] S6: Based on the dynamic adjustment scheme, adopt decision trees and graph neural networks to analyze exploration data and monitoring results, match decision support and optimization schemes, optimize project efficiency and safety, generating a decision support optimization scheme.

[0050] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0051] In the present invention, the integrated processing of geospatial information is optimized through spatial data fusion algorithms to ensure data consistency and integrity. Random forests and convolutional neural networks are adopted to enhance the ability to identify potential geological risks and predict the impacts of climate change. Genetic algorithms and support vector machine algorithms are used to intelligently adjust the exploration plan and improve the selection efficiency of exploration points and paths. Through computational fluid dynamics simulation techniques, geological structure changes and hydrogeological processes are accurately simulated. Combined with the Scrum framework, project management and team collaboration are optimized to improve the execution efficiency and response speed of the project. Decision trees and graph neural networks are used to optimize project efficiency and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 is the system flow chart of the present invention;

[0053] Figure 2 is the schematic diagram of the system framework of the present invention;

[0054] Figure 3 Flow chart of the geographic information integration module of the present invention;

[0055] Figure 4 Flow chart of the risk identification and prediction module of the present invention;

[0056] Figure 5 Flow chart of the intelligent planning and adjustment module of the present invention;

[0057] Figure 6 Flow chart of the geological process simulation module of the present invention;

[0058] Figure 7 Flow chart of the project management and collaboration module of the present invention;

[0059] Figure 8 Flow chart of the real-time monitoring and adjustment module of the present invention;

[0060] Figure 9 Flow chart of the decision support and optimization module of the present invention;

[0061] Figure 10 Schematic diagram of the method steps of the present invention. Detailed implementation manners

[0062] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0063] Embodiment 1

[0064] Please refer to Figures 1 to 2 , the present invention provides a technical solution: a hydrogeological, engineering geological and environmental geological exploration system based on GPS positioning includes a geographic information integration module, a risk identification and prediction module, an intelligent planning and adjustment module, a geological process simulation module, a project management and collaboration module, a real-time monitoring and feedback module, and a decision support and optimization module.

[0065] The geographic information integration module is based on GPS data, applies Kriging interpolation, evaluates geological attributes, combines voxel model technology, converts data into a three-dimensional geological model, maps and integrates geographical locations and associated geological features, and generates a comprehensive geographic information model.

[0066] The risk identification and prediction module is based on the comprehensive geographic information model, uses random forest and convolutional neural network, identifies geological risks, analyzes climate change data, evaluates the impact of climate change on hydrogeological, engineering geological and environmental geological conditions, and generates risk identification and prediction analysis information.

[0067] Based on the risk identification and prediction analysis information, the intelligent planning and adjustment module uses genetic algorithms and support vector machine algorithms to adjust the geological exploration plan. By combining historical exploration data, geological characteristics, and environmental factors, it matches the optimal exploration points and paths, and generates an intelligent exploration planning scheme.

[0068] Based on the intelligent exploration planning scheme, the geological process simulation module uses computational fluid dynamics simulation technology to establish a simulation model of geological structure changes and geological processes, simulates hydrogeological processes, rock layer movement, and soil erosion, and generates geological process simulation analysis results.

[0069] Based on the geological process simulation analysis results, the project management and collaboration module uses the Scrum framework, combines task decomposition and progress tracking technologies, conducts project task planning, resource allocation, and real-time project progress tracking. Through natural language processing technology, it optimizes interactive communication tools and generates a project collaboration efficiency improvement scheme.

[0070] Based on the project collaboration efficiency improvement scheme, the real-time monitoring and adjustment module uses surface displacement monitoring and groundwater level monitoring technologies to monitor geological exploration activities and environmental conditions in real time, adjusts the exploration plan, conducts risk assessment, and generates a real-time monitoring and adjustment scheme.

[0071] Based on the real-time monitoring and adjustment scheme, the decision support and optimization module uses decision trees and graph neural networks to analyze exploration data and monitoring results, provides optimization schemes and decision support, optimizes project efficiency and safety, and generates a decision optimization scheme.

[0072] The geographic information comprehensive model includes groundwater distribution information, geological structure information, and environmentally sensitive area information. The risk identification and prediction analysis information includes geological hazard risk information, climate change impact information, and geological risk level information. The intelligent exploration planning scheme includes exploration point distribution information, exploration path planning results, and comprehensive environmental and geological analysis results. The geological process simulation analysis results include hydrogeological process simulation, rock layer movement information, and soil erosion process information. The project collaboration efficiency improvement scheme includes project task planning, resource allocation scheme, and progress tracking mechanism. The real-time monitoring and adjustment scheme includes surface displacement monitoring data, groundwater level monitoring data, and exploration plan adjustment information. The decision optimization scheme includes exploration data analysis information, monitoring result evaluation information, and project optimization scheme.

[0073] In the geographic information integration module, through GPS data acquisition, using spatial data fusion algorithms, through spatial data synchronization, perform timestamp correction and coordinate transformation to ensure that data from multiple GPS devices are aligned in time and space. By removing outliers and noise, improve data quality. Use spatial interpolation techniques to fill data gaps and ensure continuity and integrity. Adopt geographic information system technology to associate the processed GPS data with geological, hydrological, and environmental data, complete the mapping of geographical locations and geological features, generate a comprehensive geographic information model, and provide an accurate geographic information basis for subsequent risk identification.

[0074] In the risk identification and prediction module, combined with the comprehensive geographic information model, through random forest algorithms and convolutional neural networks, deeply analyze the impacts of geological, hydrological data, and climate change. Combining random forest algorithms, by constructing multiple decision trees, classify geological features to identify geological risk areas. Use convolutional neural networks to process climate change data and identify the associations between climate patterns and geological risks. Combine long-term climate change data with immediate geological information to predict the likelihood and severity of geological risks, generate risk identification and prediction analysis information, and provide a scientific basis for intelligent planning.

[0075] In the intelligent planning and adjustment module, use genetic algorithms and support vector machine algorithms to optimize the exploration plan based on the risk identification and prediction analysis information. Genetic algorithms simulate the natural selection process, combine costs, geological features, and environmental factors, and capture the optimal exploration points through iterative evolution. Support vector machine algorithms are used to optimize the exploration path. Through the classification of terrain and obstacles, match the most economical path, evaluate the geological value, geological risks, and path feasibility of exploration points, generate an intelligent exploration planning scheme, and ensure the efficiency and safety of exploration activities.

[0076] In the geological process simulation module, based on the intelligent exploration planning scheme, adopt computational fluid dynamics simulation technology to simulate geological structure changes and hydrogeological processes. By solving the fluid dynamics equations, simulate rock layer movement, soil erosion, and hydrological processes, and predict the response of geological structures under the action of natural forces. Generate simulation analysis results, reveal the impacts of geological changes on the exploration area, guide actual exploration work, and enhance the scientific nature and practicality of exploration plans.

[0077] In the project management and collaboration module, combined with the results of geological process simulation analysis, the agility of project management is carried out through the Scrum framework. By supporting the dynamic planning of tasks, rapid iteration, and cross-functional team collaboration, it can cope with the uncertain changes in the project. Through natural language processing technology, optimize the interactive communication tool, automatically process meeting minutes and task update reminders, promote information sharing and team interaction, and generate a project collaboration efficiency improvement plan, including detailed task allocation, resource configuration, and progress monitoring plans, to improve project management efficiency and team collaboration quality.

[0078] In the real-time monitoring and adjustment module, using surface displacement and groundwater level monitoring technologies, based on the project collaboration efficiency improvement plan, conduct real-time monitoring of exploration activities. The real-time analysis and processing of monitoring data rely on advanced data processing algorithms to identify changes in the environment and geological activities in real time, and dynamically adjust the exploration plan accordingly. The generated real-time monitoring and adjustment plan includes the adjusted exploration points, paths, and risk assessments to ensure that exploration activities can respond promptly to changes in geological and environmental conditions, and guarantee exploration safety and efficiency.

[0079] In the decision support and optimization module, based on the real-time monitoring and adjustment plan, use decision trees and graph neural networks to deeply analyze exploration data and monitoring results. The decision tree identifies key decision points by constructing decision paths, and uses graph neural networks to analyze the relationships between data, providing multi-dimensional data support for project decisions. The generated decision optimization plan brings together multi-dimensional exploration data analysis, monitoring result evaluation, and project optimization plans to guide the project team to make scientific and reasonable decisions, and optimize the overall efficiency and safety of the project.

[0080] Please refer to Figure 2 and Figure 3 , the geographic information integration module includes a GPS data integration sub-module, a geographic information data mapping sub-module, and a geological information fusion sub-module.

[0081] The GPS data integration sub-module is based on GPS data and uses data fusion algorithms to integrate the collected geographical location data, including synchronizing the time and coordinate systems of data from multiple GPS devices, removing outliers through data cleaning, optimizing data quality and consistency, and combining data interpolation methods to fill data gaps and generate location data integration information.

[0082] The geographic information data mapping sub-module is based on the location data integration information and uses Kriging interpolation and voxel model technologies to map geographic information. By matching the integrated GPS data with existing map resources, using spatial analysis methods to identify geographical features, and matching the features with the geographical coordinate system, it generates geographical feature mapping information.

[0083] Based on the geographical feature mapping information, the geological information fusion sub-module combines geological survey data, hydrographic survey data, environmental monitoring data, and geographical feature mapping information using a spatial data fusion algorithm to construct a geographical model including geological structures, hydrographic features, and environmental conditions, generating a comprehensive geographical information model.

[0084] In the GPS data integration sub-module, through a data fusion algorithm, the received GPS data is comprehensively processed. By unifying the geographical location data collected by multiple GPS receivers, including the synchronization of timestamps and the unification of coordinate systems, data cleaning techniques are used to exclude outliers, including unreasonable location information caused by signal interference or receiver errors, improving the accuracy and reliability of the data. Data interpolation techniques are used to fill in the data blank areas caused by signal loss, ensuring the continuity and integrity of geographical information. The generated integrated location data accurately reflects the actual geographical locations within the monitoring area, guaranteeing the consistency and integrity of the data, providing a solid data foundation for subsequent geographical information mapping and geological information fusion.

[0085] In the geographical information data mapping sub-module, through geographical information system technology, the integrated location data is processed. By matching and docking the integrated GPS data with existing map resources, spatial analysis methods are used to identify and classify geographical features. By analyzing the geographical coordinates of the GPS data, the geographical coordinates are matched with the corresponding locations on the map. Spatial analysis is used to identify topographical and geomorphic features, water system distribution geographical features, and match the features with the geographical coordinate system. The generated geographical feature mapping information details the geographical characteristics of the monitoring area, providing a digital representation of geographical information and laying a foundation for understanding the geological structure, hydrographic characteristics, and environmental conditions of the monitoring area.

[0086] In the geological information fusion sub-module, through a spatial data fusion algorithm, the geographical feature mapping information, geological survey data, hydrographic survey data, and environmental monitoring data are processed. The data from multiple sources are unified in format and standardized. According to the spatial positions of the geographical features, the associated geological, hydrographic, and environmental data are matched and integrated to construct a three-dimensional geographical model reflecting geological structures, hydrographic features, and environmental conditions. The generated comprehensive geographical information model reflects the natural state of the monitoring area, providing multi-dimensional and accurate decision-making support information for hydrogeological, engineering geological, and environmental geological surveys, improving the scientificity and effectiveness of survey planning.

[0087] Please refer to Figure 2 and Figure 4 , the risk identification and prediction module includes a climate change analysis sub-module, a geological risk identification sub-module, and a risk prediction analysis sub-module.

[0088] The climate change analysis sub-module, based on the integrated geographic information model, uses time series analysis algorithms and combines climate change data, including temperature, rainfall, and wind speed parameters, to identify climate characteristics that affect hydrogeological and environmental geological conditions. Using long short-term memory networks, it analyzes the changing trends of climate parameters, predicts climate change patterns, and generates climate change characteristic analysis information.

[0089] The geological risk identification sub-module, based on the climate change characteristic analysis information, uses the random forest algorithm to analyze geological, hydrological, and environmental data in the integrated geographic information model, identifies geological risks caused by climate change, including landslides, floods, and land subsidence, uses the random forest algorithm to identify risk areas, and generates geological risk identification results.

[0090] The risk prediction and analysis sub-module, based on the geological risk identification results, uses convolutional neural networks and time series prediction techniques to analyze geological risk areas, predict risk trends, and combine geological event data and environmental change situations to predict the types, frequencies, and intensities of geological risk events in the target area, generating risk identification and prediction analysis information.

[0091] In the climate change analysis sub-module, through the integrated geographic information model and climate change data, time series analysis and long short-term memory networks are used to identify climate characteristics and predict climate change patterns. Using time series analysis algorithms, trend analysis is performed on climate parameters such as temperature, rainfall, and wind speed to identify climate characteristics with significant changing trends. The long short-term memory network uses target feature learning and prediction of the changing patterns of climate parameters over time, trains the model using historical records of climate data, predicts future climate change trends, generates climate change characteristic analysis information, analyzes the key characteristics and trends of climate change, and provides a key basis for subsequent identification and prediction of geological risks.

[0092] In the geological risk identification sub-module, the random forest algorithm is used to analyze geological, hydrological, and environmental data in the integrated geographic information model. The random forest algorithm trains the data set by constructing multiple decision trees and summarizes the results of each tree to obtain the final prediction result, improving the accuracy and generalization ability of the model, evaluating the impact of climate change on geological conditions, including the increased landslide risk caused by rising temperature, the flood risk caused by rainfall changes, and the impact of wind speed changes on land subsidence. The generated geological risk identification results list the types, distribution areas, and probabilities of various geological risks, providing a scientific basis for risk prediction and the formulation of exploration plans.

[0093] In the risk prediction and analysis sub-module, based on the geological risk identification results, through convolutional neural networks and time series prediction techniques, the analysis and prediction of risk trends are carried out. Convolutional neural networks perform excellently in processing spatial data analysis of geological risk areas. By learning the spatial characteristics of geological event data and environmental changes, the patterns and laws of risk occurrence are identified. The time series prediction technique is used to predict the occurrence time, frequency, and intensity of risk events. Combining the periodic and random characteristics of historical geological events, geological risk events are predicted, generating risk identification and prediction analysis information, providing multi-dimensional risk assessment and early warning for hydrogeological, engineering geological, and environmental geological surveys, assisting decision-makers and survey teams in avoiding risks, and ensuring the safety and effectiveness of survey activities.

[0094] Please refer to Figure 2 and Figure 5 , the intelligent planning and adjustment module includes a survey point analysis sub-module, a survey path optimization sub-module, and a plan adjustment strategy sub-module.

[0095] The survey point analysis sub-module, based on the risk identification and prediction analysis information, uses the genetic algorithm to analyze historical survey data, geological characteristics, and environmental factors. Using the genetic algorithm, combined with survey costs, accessibility, and geological risks, multiple survey points are evaluated, generating a survey point data set.

[0096] The survey path optimization sub-module, based on the survey point data set, uses the support vector machine algorithm to classify terrain and obstacle factors, and combines time factors and cost factors to plan the path for survey points, optimizing the efficiency and economy of survey activities, and generating a survey path planning scheme.

[0097] The plan adjustment strategy sub-module, based on the survey path planning scheme, uses the simulated annealing algorithm to adjust survey points and paths in combination with the geological environment and geological risks. By comparing the costs and benefits of adjustment schemes, the survey plan is matched, generating an intelligent survey planning scheme.

[0098] In the survey point analysis sub-module, through the risk identification and prediction analysis information, the genetic algorithm is used to analyze historical survey data, geological characteristics, and environmental factors. The genetic algorithm mimics the mechanism of natural selection. By initializing a population of candidate survey points, selection, crossover, and mutation operations are performed on the population to capture the optimal survey points. According to survey cost, accessibility, and geological risk factors, fitness scores are assigned to candidate points. Through multiple iterations, the survey points are optimized, generating a survey point data set, providing accurate input for subsequent survey path planning, and ensuring that survey activities can achieve the maximum benefit under the premise of controllable costs and risks.

[0099] In the exploration path optimization sub-module, based on the exploration point dataset, the support vector machine algorithm is used to plan and optimize the exploration path. The support vector machine algorithm classifies the terrain and obstacles by constructing an optimal hyperplane that separates different categories in a multi-dimensional space. In the exploration path planning, according to the terrain features and existing obstacles, feasible paths are identified. Combining time and cost factors, the algorithm evaluates the economy and efficiency of multiple paths and selects the optimal exploration path. An exploration path planning scheme is generated to optimize the exploration cost and ensure the safety of personnel during the exploration activities.

[0100] In the plan adjustment strategy sub-module, based on the exploration path planning scheme, the simulated annealing algorithm is used to adjust the exploration plan. By randomly changing the exploration points and paths, the impact of the adjustment is evaluated to ensure exploration safety and meet the geological environment requirements, and an exploration plan that optimizes costs and benefits is captured. An intelligent exploration planning scheme is generated to adjust the exploration points and paths to ensure that the exploration project can efficiently and flexibly respond to changes in the geological environment and project requirements.

[0101] Please refer to Figure 2 and Figure 6 , the geological process simulation module includes a rock layer movement simulation sub-module, a hydrological process simulation sub-module, and a soil erosion simulation sub-module.

[0102] The rock layer movement simulation sub-module, based on the intelligent exploration planning scheme, uses the discrete element method and combines the physical properties of the rock layer, including particle size, shape, and density, to simulate the movement, collision, and rearrangement processes of rock layer particles under the action of natural forces, predict the stability and movement path of the rock layer, and generate rock layer movement simulation analysis information.

[0103] The hydrological process simulation sub-module, based on the rock layer movement simulation analysis information, uses the finite difference method to conduct numerical simulation of groundwater flow. By referring to the geometric characteristics, permeability, and water storage capacity of the groundwater aquifer and combining precipitation, evaporation, and plant absorption factors to analyze the recharge and loss of groundwater, it simulates the groundwater flow and distribution in the hydrogeological process, predicts the changes in groundwater distribution under various hydrogeological conditions, and generates hydrological process simulation analysis results.

[0104] The soil erosion simulation sub-module, based on the hydrological process simulation analysis results, uses the RUSLE model and the WEPP model, and refers to soil type, slope, vegetation coverage, rainfall, and surface flow velocity to simulate the erosion of soil by rainwater and surface water flow, calculate the rate and spatial distribution of soil erosion and transportation, predict the erosion risk areas and soil loss amount, and generate geological process simulation analysis results.

[0105] In the rock layer movement simulation sub-module, the discrete element method is used to simulate and analyze the dynamic behavior of the rock layer under natural conditions. Through the basic physical properties of the rock layer, including the size, shape, density of particles and the friction between rocks, the processes of particle movement, collision and rearrangement are accurately simulated. Combining with digital description, the physical structure of the rock layer is divided into a discrete system composed of thousands of particles. According to the principles of physics and rock mechanics, the movement trajectories and interactions of particles under the action of gravity and water flow are calculated, including collision detection between particles, force calculation and update of particle positions, predicting the stability and movement paths of the rock layer under the action of various external forces. The generated rock layer movement simulation analysis information is presented in the form of a three-dimensional model, providing a key basis for evaluating the stability of the rock layer and planning protection measures.

[0106] In the hydrological process simulation sub-module, a modular finite difference groundwater flow model is adopted to simulate the groundwater flow and distribution. Combining the physical and geological characteristics of the groundwater aquifer, including geometry, permeability and water storage capacity, and combining precipitation, evaporation and plant absorption on the surface, a multi-dimensional analysis of groundwater recharge and loss is carried out. By dividing the aquifer into a grid system and applying the finite difference method to solve the differential equation controlling groundwater flow, the water head and flow velocity of grid points are calculated. Through iterative solution, the dynamic changes of groundwater flow under various hydrological conditions are simulated. The generated hydrological process simulation analysis results, including the direction of groundwater flow, flow velocity and changes over time, are of crucial significance for predicting water resource distribution, planning water conservancy projects and assessing hydrogeological risks.

[0107] In the soil erosion simulation sub-module, through the RUSLE model and the WEPP model, combining factors such as soil type, slope, vegetation coverage, rainfall and surface flow velocity, the erosion effect of rainwater and surface water flow on the soil is simulated. The RUSLE model is used to evaluate the amount of soil erosion caused by raindrop impact and surface runoff, and the WEPP model is adopted to simulate the soil erosion process and erosion pattern at the whole watershed scale. Combining the soil, terrain and climate data of the target area, the soil erosion rate and sediment transport volume under different scenarios are calculated, and the soil erosion simulation analysis results are generated, revealing the erosion risk areas, erosion degree and time change trends, providing a scientific basis for soil protection, formulation of soil and water conservation measures and land management.

[0108] Please refer to Figure 2 and Figure 7 The project management and collaboration module includes a task planning sub-module, a resource allocation sub-module and a team communication sub-module.

[0109] Based on the results of geological process simulation analysis, the task planning sub-module uses the Scrum framework to break down project goals. Through the role assignment and task splitting of team members, it configures task personnel and task priorities, optimizes work efficiency, and generates a personnel allocation plan.

[0110] Based on the personnel allocation plan, the resource configuration sub-module uses linear programming and dynamic programming. By evaluating the matching degree between the resource requirements of tasks and the available resources, and using resource levels and optimization techniques, it allocates and optimizes the human, equipment, and financial resources required for the project, and generates a resource configuration plan.

[0111] Based on the resource configuration plan, the team communication sub-module uses natural language processing technology to optimize interactive communication tools, including developing and integrating intelligent communication assistants, and automates project communication tasks, such as generating meeting minutes and task update reminders, and generates a project collaboration efficiency improvement plan.

[0112] In the task planning sub-module, by using the Scrum framework for project management and task planning, combined with the results of geological process simulation analysis, it analyzes the goals and requirements of the project. Through the refinement, prioritization, and time estimation of tasks, combined with the role assignment and expertise of team members, it assigns tasks to target personnel. Through regular short-cycle iterations, it ensures the flexibility and response speed of the project, generates a personnel allocation plan, assigns the responsibilities and tasks of team members, ensures the effective progress and efficiency optimization of work, strengthens the controllability and predictability of the project, and improves the synergy of team cooperation and the success rate of project delivery.

[0113] In the resource configuration sub-module, through linear programming and dynamic programming techniques, it scientifically configures and optimizes the management of various types of resources required for the project, collects and analyzes the personnel allocation plan generated by the task planning sub-module, determines the requirements of task units for human, material, equipment, and financial resources, applies linear programming techniques to quantitatively analyze resource requirements, and captures the optimal resource configuration plan by establishing a resource allocation model. Using dynamic programming techniques, it deals with the changes in resource requirements that occur during project execution, ensures the flexibility and adaptability of resource configuration, generates a resource configuration plan, maximizes resource utilization and optimizes cost control, and improves the efficiency and economy of project management.

[0114] In the team communication sub-module, through natural language processing technology, optimize the interactive communication tool, combine with the resource allocation plan, develop and integrate an intelligent communication assistant to automatically process common project communication tasks, including the automatic generation of meeting minutes, automatic reminders for task updates, intelligent classification and forwarding of problem feedback. By analyzing the communication content of project members, combining with preset logic and rules, match the corresponding feedback and execute the corresponding tasks, generate a project collaboration efficiency improvement plan, improve the efficiency of team communication, optimize the accuracy and timeliness of information transmission, reduce the communication burden of project members, strengthen team collaboration, ensure the rapid circulation and effective sharing of information among team members, and provide strong support for the smooth implementation of the project.

[0115] Please refer to Figure 2 and Figure 8 , the real-time monitoring and adjustment module includes a geological activity monitoring sub-module, an environmental condition monitoring sub-module, and an exploration plan adjustment sub-module.

[0116] The geological activity monitoring sub-module, based on the project collaboration efficiency improvement plan, uses seismic wave velocity measurement and surface displacement sensing technologies, combines with the Gaussian process regression algorithm, analyzes the collected data, identifies geological activity patterns and anomalies, analyzes the geological activity process, including fault movement and crustal deformation, evaluates the impact of geological activities on the exploration area, and generates geological activity analysis results.

[0117] The environmental condition monitoring sub-module, based on the geological activity analysis results, uses multi-parameter environmental monitoring technologies to real-time track and analyze meteorological conditions, including rainfall, temperature, groundwater level, and surface water flow dynamics, uses trend analysis and anomaly detection algorithms, evaluates the potential impact of environmental changes on exploration activities, and generates environmental condition monitoring analysis results.

[0118] The exploration plan adjustment sub-module, based on the environmental condition monitoring analysis results, uses dynamic programming and decision support systems to analyze the impact of geological activities and environmental changes on the exploration plan, adjusts exploration points, paths, and schedules, and generates a real-time monitoring and adjustment plan.

[0119] In the geological activity monitoring sub-module, combining seismic wave velocity measurement and surface displacement sensing technologies, using seismic wave velocity measurement technology to capture early signals of underground fault activities and crustal deformation, by analyzing the changes in the propagation velocity of seismic waves in various geological structures, identify geological activity patterns and anomalies. Through surface displacement sensing technology, combined with direct observation data of ground deformation, optimize the monitoring results of fault movement and crustal deformation. Use a real-time data analysis system to comprehensively analyze the data, apply signal processing and pattern recognition technologies to evaluate the impact of geological activities on the exploration area. Generate geological activity analysis results to provide timely geological activity information for the exploration team.

[0120] In the environmental condition monitoring sub-module, by adopting multi-parameter environmental monitoring technology, combining the monitoring of environmental parameters such as rainfall, temperature, groundwater level, and surface water flow dynamics, and using trend analysis and anomaly detection algorithms, the environmental data is analyzed to identify environmental change trends and potential abnormal events. Using the trend analysis algorithm, long-term climate change patterns are identified, and the anomaly detection algorithm is used to capture sudden events and abnormal changes in the short term, in response to changes in environmental conditions that affect exploration activities. The generated environmental condition monitoring analysis results provide real-time and multi-dimensional environmental background information for the exploration plan, enhancing the adaptability and flexibility of the exploration plan.

[0121] In the exploration plan adjustment sub-module, combining dynamic programming and decision support system, the exploration points, paths, and schedules are intelligently adjusted. Using the dynamic programming algorithm, the overall layout of the exploration plan is optimized. By establishing a mathematical model of exploration tasks, an exploration plan that minimizes costs while meeting geological and environmental constraints is captured. The decision support system is used to analyze exploration data, environmental monitoring results, and geological activity information, and linear programming and network flow analysis are used to evaluate the cost-benefit of different adjustment plans, support the exploration team to make scientific decisions, and generate a real-time monitoring adjustment plan to ensure that exploration activities can quickly and accurately respond to changes in geological activities and environmental conditions, improving the efficiency and safety of exploration work.

[0122] Please refer to Figure 2 and Figure 9 , the decision support and optimization module includes a data analysis and decision-making sub-module, an optimization strategy generation sub-module, and a safety assessment sub-module.

[0123] Based on the real-time monitoring adjustment plan, the data analysis and decision-making sub-module uses the decision tree algorithm to classify and analyze exploration data and monitoring results. By extracting key features from batch data, the data is classified to identify key decision points and risks in exploration activities. By analyzing multiple branch results of the data, the impacts of multiple decision-making schemes are evaluated, and decision analysis results are generated.

[0124] Based on the decision analysis results, the optimization strategy generation sub-module uses the graph neural network algorithm to analyze the relationship network of exploration projects, including the interactions between geological features, environmental factors, and exploration activities. Through the iterative update of the network, combined with the feasibility and cost-benefit of the project, a management strategy planning scheme is generated.

[0125] Based on the management strategy planning scheme, the safety assessment sub-module uses fault tree analysis and event tree analysis to evaluate the safety risks of exploration activities. By identifying and analyzing the factors and event sequences leading to accidents, the risk probabilities of multiple situations are evaluated, risk mitigation measures and safety guarantee schemes are matched, and a decision optimization scheme is generated.

[0126] In the data analysis and decision-making sub-module, through the decision tree algorithm, in-depth analysis is carried out on the exploration data and monitoring results. The data formats collected include geographical location information, geological characteristic parameters, environmental monitoring data, and real-time exploration feedback. The data is stored in a structured form for easy algorithm processing. Using the decision tree algorithm, a tree-like structure model is constructed. The nodes represent decision points in terms of attributes, and the branches represent the outputs of the decision points. Feature selection is performed on the data set, and the data set is split according to multiple feature values. The decision tree is recursively constructed, and multiple paths in the tree model are analyzed to identify key decision points and risk areas, and predict the results under multiple decision paths. The generated decision analysis results provide definite guidance for project management, assist decision-makers in evaluating the impacts of multiple solutions, optimize the decision-making process, and improve the efficiency and accuracy of decision-making.

[0127] In the optimization strategy generation sub-module, through the graph neural network algorithm, the relationship network of the exploration project is analyzed. The data format is the relationship data between exploration data and monitoring results, including the connections between geological features and the interactions between environmental factors and exploration activities. The data is represented as nodes and edges in a graph. Using the graph neural network algorithm, feature extraction is performed on each node in the graph. Through the iterative update method, the representation of the node is updated using the neighbor information of the node, learning the structure information of the entire graph and the deep features of the nodes, capturing and learning the complex relationships and patterns between the nodes, generating a management strategy planning scheme, and combining the feasibility, cost-benefit, and potential risks of the project to provide a scientific and reasonable optimization scheme for project execution, improving the implementation efficiency and success rate of the project.

[0128] In the safety assessment sub-module, through the fault tree analysis and event tree analysis methods, multi-dimensional assessment of the safety risks of exploration activities is carried out. Using the fault tree analysis, by constructing a logical model of the fault event, the logical relationships leading to the top-level event are analyzed from multiple initial events to identify multiple ways leading to system failure. Combining the event tree analysis, multiple paths of event development are analyzed, the probabilities and consequences of event development in multiple situations are evaluated, the safety risks and impacts existing in exploration activities are identified and evaluated, a decision optimization scheme is generated, the risk level and risk mitigation measures are determined, providing strong decision support for the safety guarantee of the project, and ensuring that exploration activities are carried out under safe and controllable conditions.

[0129] Please refer to Figure 10 , the hydrogeological, engineering geological and environmental geological exploration method based on GPS positioning, which is executed based on the above-mentioned hydrogeological, engineering geological and environmental geological exploration system based on GPS positioning, includes the following steps:

[0130] S1: Based on GPS data, using the data fusion algorithm, synchronize the time and coordinate data, and combine the data interpolation technology to improve the data quality and integrity, and generate geographical integration information.

[0131] S2: Based on the geospatial integrated information, using the random forest algorithm and long short-term memory network, analyze geological, hydrological, environmental data and climate change, identify geological risks and impacts on exploration activities, and generate risk identification information.

[0132] S3: Based on the risk identification information, using the genetic algorithm and support vector machine algorithm, combined with historical exploration data, geological features and environmental factors, match exploration points and paths, and generate an exploration path planning scheme.

[0133] S4: Based on the exploration path planning scheme, using computational fluid dynamics simulation technology to simulate the hydrogeological process, and using the Scrum framework to allocate resources and track the progress of project tasks, generate geological analysis results and a collaboration efficiency improvement scheme.

[0134] S5: Based on the geological analysis results and the collaboration efficiency improvement scheme, using surface displacement and groundwater level monitoring technology, combined with geological monitoring data, adjust the exploration plan, match geological and environmental changes, and generate a dynamic adjustment scheme.

[0135] S6: Based on the dynamic adjustment scheme, using decision trees and graph neural networks, analyze exploration data and monitoring results, match decision support and optimization schemes, optimize project efficiency and safety, and generate a decision support optimization scheme.

[0136] Using data fusion algorithms to ensure the high consistency and integrity of geographical information, providing an accurate geographical positioning basis for subsequent analysis. The combined use of the random forest algorithm and long short-term memory network enhances the ability to identify potential geological risks, predicts the long-term impact of climate change on geological conditions, provides data-based risk assessment and future prediction, and optimizes risk management. Using the genetic algorithm and support vector machine algorithm to intelligently plan and adjust exploration points and paths, optimize the efficiency and economy of the exploration plan, and improve the efficiency of exploration work. Using computational fluid dynamics simulation technology and the Scrum framework to optimize the efficiency of project management and team collaboration, ensuring the feasibility of the exploration plan and the rapid response ability of project execution. The real-time application of surface displacement and groundwater level monitoring technology, combined with the dynamic adjustment mechanism and decision support system, ensures that exploration activities match geological and environmental conditions, improving the adaptability and flexibility of the project.

Claims

1. A hydrogeological, engineering geological and environmental geological exploration system based on GPS positioning, characterized in that: The system includes a geographic information integration module, a risk identification and prediction module, an intelligent planning and adjustment module, a geological process simulation module, a project management and collaboration module, a real-time monitoring and adjustment module, and a decision support and optimization module; The geographic information integration module is based on GPS data, applies Kriging interpolation to evaluate geological attributes, combines with voxel model technology, converts data into a 3D geological model, maps and integrates geographical locations and associated geological features, and generates a comprehensive geographic information model; The risk identification and prediction module is based on the comprehensive geographic information model, uses random forest and convolutional neural network to identify geological risks, analyzes climate change data, evaluates the impact of climate change on hydrogeological and environmental geological conditions, and generates risk identification and prediction analysis information; The risk identification and prediction module includes a climate change analysis sub-module, a geological risk identification sub-module, and a risk prediction analysis sub-module; The climate change analysis sub-module is based on the comprehensive geographic information model, uses time series analysis algorithms, combines with climate change data including temperature, rainfall, and wind speed parameters, identifies climate characteristics that affect hydrogeological and environmental geological conditions, uses long short-term memory networks to analyze the changing trends of climate parameters, predicts climate change patterns, and generates climate change characteristic analysis information; The geological risk identification sub-module is based on the climate change characteristic analysis information, uses random forest algorithms to analyze geological, hydrological, and environmental data in the comprehensive geographic information model, identifies geological risks caused by climate change including landslides, floods, and land subsidence, uses random forest algorithms to identify risk areas, and generates geological risk identification results; The risk prediction analysis sub-module is based on the geological risk identification results, uses convolutional neural network and time series prediction technologies to analyze geological risk areas, predicts risk trends, combines geological event data and environmental change situations, predicts the types, frequencies, and intensities of geological risk events in the target area, and generates risk identification and prediction analysis information; The intelligent planning and adjustment module is based on the risk identification and prediction analysis information, uses genetic algorithms and support vector machine algorithms to adjust geological exploration plans, combines historical exploration data, geological features, and environmental factors, matches the optimal exploration points and paths, and generates an intelligent exploration planning scheme; The intelligent planning and adjustment module includes an exploration point analysis sub-module, an exploration path optimization sub-module, and a plan adjustment strategy sub-module; The exploration point analysis sub-module is based on the risk identification and prediction analysis information, uses genetic algorithms to analyze historical exploration data, geological features, and environmental factors, and uses genetic algorithms to evaluate multiple exploration points in combination with exploration costs, accessibility, and geological risks, and generates an exploration point data set; The exploration path optimization sub-module is based on the exploration point data set, uses support vector machine algorithms, classifies terrain and obstacle factors, combines time factors and cost factors, plans paths for exploration points, optimizes the efficiency and economy of exploration activities, and generates an exploration path planning scheme; The planned adjustment strategy sub-module adjusts the exploration points and routes based on the exploration path planning scheme, using the simulated annealing algorithm and combining geological environment and geological risks. By comparing the costs and benefits of the adjustment schemes, it matches the exploration plan and generates an intelligent exploration planning scheme; The geological process simulation module, based on the intelligent exploration planning scheme, uses computational fluid dynamics simulation technology to establish a simulation model of geological structure changes and geological processes, simulates hydrogeological processes, rock layer movement, and soil erosion, and generates geological process simulation analysis results; The geological process simulation module includes a rock layer movement simulation sub-module, a hydrogeological process simulation sub-module, and a soil erosion simulation sub-module; The rock layer movement simulation sub-module, based on the intelligent exploration planning scheme, uses the discrete element method and combines the physical properties of the rock layer, including particle size, shape, and density, to simulate the movement, collision, and rearrangement processes of rock layer particles under the action of natural forces, predicts the stability and movement path of the rock layer, and generates rock layer movement simulation analysis information; The hydrogeological process simulation sub-module, based on the rock layer movement simulation analysis information, uses the finite difference method to conduct numerical simulation of groundwater flow. By referring to the geometric characteristics, permeability, and water storage capacity of the groundwater aquifer and combining precipitation, evaporation, and plant absorption factors, it analyzes the recharge and loss of groundwater, simulates the groundwater flow and distribution in the hydrogeological process, predicts the changes in groundwater distribution under various hydrogeological conditions, and generates hydrogeological process simulation analysis results; The soil erosion simulation sub-module, based on the hydrogeological process simulation analysis results, uses the RUSLE model and the WEPP model, and refers to soil type, slope, vegetation coverage, rainfall, and surface flow velocity to simulate the erosion effect of rainwater and surface water flow on the soil, calculates the rate and spatial distribution of soil erosion and transportation, predicts the erosion risk area and soil loss, and generates geological process simulation analysis results; The project management and collaboration module, based on the geological process simulation analysis results, uses the Scrum framework and combines task decomposition and progress tracking technologies to conduct project task planning, resource allocation, and real-time project progress tracking. Through natural language processing technology, it optimizes the interactive communication tool and generates a project collaboration efficiency improvement scheme; The project management and collaboration module includes a task planning sub-module, a resource allocation sub-module, and a team communication sub-module; The task planning sub-module, based on the geological process simulation analysis results, uses the Scrum framework to break down the project objectives. Through the role assignment and task splitting of team members, it configures task personnel and task priorities, optimizes work efficiency, and generates a personnel allocation scheme; The resource allocation sub-module, based on the personnel allocation scheme, uses linear programming and dynamic programming. By evaluating the matching degree between the resource requirements of tasks and the available resources and using resource levels and optimization technologies, it allocates and optimizes the human, equipment, and financial resources required for the project and generates a resource allocation scheme; The team communication sub-module, based on the resource allocation plan, uses natural language processing technology to optimize the interactive communication tool, including developing and integrating intelligent communication assistants, automating project communication tasks such as meeting minutes generation and task update reminders, and generating a project collaboration efficiency improvement plan; The real-time monitoring and adjustment module, based on the project collaboration efficiency improvement plan, uses surface displacement monitoring and groundwater level monitoring technologies to monitor geological exploration activities and environmental conditions in real time, adjust the exploration plan, conduct risk assessment, and generate a real-time monitoring and adjustment plan; The real-time monitoring and adjustment module includes a geological activity monitoring sub-module, an environmental condition monitoring sub-module, and an exploration plan adjustment sub-module; The geological activity monitoring sub-module, based on the project collaboration efficiency improvement plan, uses seismic wave velocity measurement and surface displacement sensing technologies, combined with the Gaussian process regression algorithm, to analyze the collected data, identify geological activity patterns and anomalies, analyze the geological activity process including fault movement and crustal deformation, evaluate the impact of geological activities on the exploration area, and generate geological activity analysis results; The environmental condition monitoring sub-module, based on the geological activity analysis results, uses multi-parameter environmental monitoring technologies to track and analyze meteorological conditions in real time, including rainfall, temperature, groundwater level, and surface water flow dynamics, and uses trend analysis and anomaly detection algorithms to evaluate the potential impact of environmental changes on exploration activities, and generate environmental condition monitoring analysis results; The exploration plan adjustment sub-module, based on the environmental condition monitoring analysis results, uses dynamic programming and decision support systems to analyze the impact of geological activities and environmental changes on the exploration plan, adjust the exploration points, paths, and schedules, and generate a real-time monitoring and adjustment plan; The decision support and optimization module, based on the real-time monitoring and adjustment plan, uses decision trees and graph neural networks to analyze exploration data and monitoring results, provide optimization plans and decision support, optimize project efficiency and safety, and generate a decision optimization plan; The decision support and optimization module includes a data analysis and decision-making sub-module, an optimization strategy generation sub-module, and a safety assessment sub-module; The data analysis and decision-making sub-module, based on the real-time monitoring and adjustment plan, uses the decision tree algorithm to classify and analyze exploration data and monitoring results, extract key features from batch data to classify the data, identify key decision points and risks of exploration activities, and evaluate the impact of multiple decision-making plans by analyzing multiple branch results of the data, and generate decision analysis results; The optimization strategy generation sub-module, based on the decision analysis results, uses the graph neural network algorithm to analyze the relationship network of exploration projects, including the interaction between geological features, environmental factors, and exploration activities, and through the iterative update of the network, combines the feasibility and cost-effectiveness of the project to generate a management strategy planning plan; The safety assessment sub-module, based on the management strategy planning plan, uses fault tree analysis and event tree analysis to evaluate the safety risks of exploration activities, evaluate the risk probabilities of multiple situations by identifying and analyzing the factors and event sequences leading to accidents, match risk mitigation measures and safety guarantee plans, and generate a decision optimization plan.

2. The hydrogeological, engineering geological and environmental geological exploration system based on GPS positioning according to claim 1, characterized in that: The comprehensive geographic information model includes groundwater distribution information, geological structure information, and environmentally sensitive area information. The risk identification and prediction analysis information includes geological disaster risk information, climate change impact information, and geological risk level information. The intelligent exploration planning scheme includes exploration point distribution information, exploration path planning results, and comprehensive environmental and geological analysis results. The geological process simulation analysis results include hydrogeological process simulation, rock layer movement information, and soil erosion process information. The project collaboration efficiency improvement scheme includes project task planning, resource allocation plan, and progress tracking mechanism. The real-time monitoring and adjustment scheme includes surface displacement monitoring data, groundwater level monitoring data, and exploration plan adjustment information. The decision-making optimization scheme includes exploration data analysis information, monitoring result evaluation information, and project optimization scheme.

3. The hydrogeological, engineering geological and environmental geological exploration system based on GPS positioning according to claim 1, wherein: The geographic information integration module includes a GPS data integration sub-module, a geographic information data mapping sub-module, and a geological information fusion sub-module; The GPS data integration sub-module is based on GPS data and uses a data fusion algorithm to integrate the collected geographical location data, including synchronizing the time and coordinate systems of data from multiple GPS devices, removing outliers through data cleaning, optimizing data quality and consistency, and filling data gaps by combining data interpolation methods to generate location data integration information; The geographic information data mapping sub-module is based on the location data integration information and uses Kriging interpolation and voxel model techniques to map geographic information. By matching the integrated GPS data with existing map resources and using spatial analysis methods to identify geographical features and match the features with the geographic coordinate system, geographic feature mapping information is generated; The geological information fusion sub-module is based on the geographic feature mapping information and uses a spatial data fusion algorithm to combine geological survey data, hydrographic survey data, environmental monitoring data, and geographic feature mapping information to construct a geographic model including geological structure, hydrographic features, and environmental conditions, and generate a comprehensive geographic information model.

4. A hydrogeological, engineering geological and environmental geological exploration method based on GPS positioning, characterized in that, The GPS positioning-based hydrogeological and environmental geological exploration system according to any one of claims 1-3 is executed, including the following steps: Based on GPS data, use a data fusion algorithm to synchronize time and coordinate data, and combine data interpolation techniques to improve data quality and integrity, generating geographic integration information; Based on the geographic integration information, use a random forest algorithm and a long short-term memory network to analyze geological, hydrographic, environmental data, and climate change, identify geological risks and their impacts on exploration activities, and generate risk identification information; Based on the risk identification information, use a genetic algorithm and a support vector machine algorithm, combine historical exploration data, geological features, and environmental factors to match exploration points and paths, and generate an exploration path planning scheme; Based on the exploration path planning scheme, use computational fluid dynamics simulation technology to simulate hydrogeological processes, and use the Scrum framework to allocate resources and track the progress of project tasks, generating geological analysis results and a collaboration efficiency improvement scheme; Based on the geological analysis results and the collaborative efficiency improvement plan, adopt surface displacement and groundwater level monitoring technologies, combine geological monitoring data, adjust the exploration plan, match geological and environmental changes, and generate a dynamic adjustment plan; Based on the dynamic adjustment plan, adopt decision trees and graph neural networks, analyze exploration data and monitoring results, match decision support and optimization plans, optimize project efficiency and safety, and generate a decision support optimization plan.

Images