Flood prevention and debris flow prevention geological disaster control method and system

Abstract

The invention relates to the technical field of flood prevention and debris flow prevention, and particularly discloses a geological disaster prevention and control method and system for flood prevention and debris flow prevention, and the method comprises the steps: 1, carrying out the real-time monitoring and data collection of the disaster conditions of flood and debris flow, and deploying a multi-parameter sensor network in a target region, collecting rainfall, soil moisture content, surface displacement, underground water level, debris flow velocity and flow data in real time; through cooperative monitoring of the sensor network and the unmanned aerial vehicle, comprehensive perception of disaster characteristics is realized; based on a machine learning model, a risk level is dynamically generated, and the early warning accuracy is improved; facilities such as an intelligent drainage system and a self-adaptive flood gate realize active intervention of disasters; based on the block chain and machine learning technology, the credibility of disaster situation data is ensured, and a scientific basis is provided for post-disaster reconstruction; through VR simulation and the user terminal, public disaster prevention consciousness and emergency capability are improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of flood control and debris flow prevention, and particularly relates to a flood control and debris flow prevention method and system. BACKGROUND

[0002] Geological disasters (such as floods and debris flows) are one of the major natural disasters that threaten human life and property safety, destroy ecological environment and restrict social and economic development worldwide. In recent years, due to global climate change, frequent extreme weather events and human engineering activities (such as unreasonable development and deforestation), the frequency and intensity of geological disasters have shown a significant upward trend. The traditional geological disaster prevention method has the following technical bottlenecks and deficiencies:

[0003] Existing geological disaster monitoring relies on a single sensor (such as a rain gauge or a displacement sensor), which is difficult to fully reflect the multi-dimensional characteristics of disaster occurrence (such as rainfall, soil moisture content, ground displacement, groundwater level, etc. Coupling); sensor data and spatial data such as unmanned aerial vehicles and satellite remote sensing lack effective fusion, resulting in low disaster risk assessment accuracy and inability to achieve dynamic early warning; some areas still rely on manual inspection, with long data collection cycle, which is difficult to meet the rapid response needs of sudden disasters. Therefore, a flood control and debris flow prevention method and system are proposed. SUMMARY

[0004] The purpose of the present application is to provide a flood control and debris flow prevention method and system to solve the problems raised in the background.

[0005] To achieve the above purpose, the present application provides the following technical solutions:

[0006] A flood control and debris flow prevention method, comprising:

[0007] Step 1: Real-time monitoring and data collection of flood and debris flow disaster conditions, deploying a multi-parameter sensor network in the target area, collecting rainfall, soil moisture content, ground displacement, groundwater level, debris flow velocity and flow data in real time; At the same time, through regular inspection by unmanned aerial vehicles, high-resolution image data of the target area is obtained, and potential landslides, debris flow channels and vegetation cover changes are identified;

[0008] Step 2: Risk assessment and early warning model construction of flood and debris flow disaster conditions, fusion of sensor data and unmanned aerial vehicle image data, input into a machine learning-based geological disaster risk assessment model, and generation of real-time risk level; When the risk level reaches "medium" or "high", trigger an early warning signal, and push early warning information to the user terminal through the communication module;

[0009] Step three: proactive measures for flood and debris flow disaster conditions;

[0010] Step four: emergency response and post-disaster assessment for flood and debris flow disaster conditions. After the disaster, the UAV automatically performs post-disaster image collection to generate a disaster impact range map. Based on historical data and post-disaster images, the disaster assessment module generates a recovery recommendation report to guide post-disaster reconstruction.

[0011] Preferably, the multi-parameter sensor network comprises:

[0012] Rain gauge for real-time monitoring of rainfall intensity;

[0013] Soil moisture sensor for monitoring soil water content changes;

[0014] Displacement sensor for monitoring surface or rock mass displacement;

[0015] Groundwater level sensor for monitoring groundwater dynamics;

[0016] Debris flow velocity sensor and flow sensor for monitoring debris flow motion parameters.

[0017] Preferably, the construction steps of the geological disaster risk assessment model include:

[0018] Step one: training support vector machine (SVM) or random forest (RF) classification model based on historical disaster data and geographic information data (GIS);

[0019] Step two: input real-time collected sensor data and UAV image features, output risk level;

[0020] Step three: the model is regularly updated by new data to adapt to changes in regional geological conditions.

[0021] A geological disaster prevention and control system for flood and debris flow prevention, comprising:

[0022] Data acquisition layer, the data acquisition layer includes multi-parameter sensor network and unmanned aerial vehicle; the multi-parameter sensor network is used for real-time acquisition of geological and environmental parameters; the unmanned aerial vehicle is used for inspection and image collection;

[0023] Data processing layer, the data processing layer includes central control platform and communication module; the central control platform integrates data fusion module and risk assessment model; the communication module is used for data transmission and early warning information pushing;

[0024] Execution control layer, the execution control layer includes intelligent drainage system, flood control gate, debris flow diversion trench and flexible blocking net mechanical device;

[0025] A user interaction layer comprising a user terminal, the user terminal comprising a mobile phone APP and a PC terminal management platform, is used for receiving early warning information and checking system status.

[0026] Preferably, the user interaction layer further comprises a virtual reality (VR) disaster simulation module and a blockchain disaster data storage module; the virtual reality (VR) disaster simulation module is used for enabling users to simulate disaster occurrence scenarios through VR devices to learn escape skills and emergency measures; and the system generates a personalized training report according to user operation records to improve public disaster prevention awareness.

[0027] The blockchain disaster data storage module is used for enabling post-disaster image data and evaluation reports to be encrypted and stored through blockchain technology, ensuring that the data cannot be tampered with, and providing a reliable basis for insurance claims and liability identification.

[0028] Preferably, the execution control layer further comprises an intelligent drainage and water storage integrated system and an adaptive flood control gate.

[0029] The intelligent drainage and water storage integrated system comprises an underground water storage tank, a water level sensor and a drainage pump, the underground water storage tank is arranged in a low-lying area of a city, and dynamic balance of water storage and drainage is realized through linkage of the water level sensor and the drainage pump; the adaptive flood control gate automatically adjusts the opening degree through real-time water level data and weather forecasts.

[0030] Preferably, a bionic super-hydrophobic coating is arranged on the adaptive flood control gate, and a honeycomb-shaped aluminum alloy support structure is embedded in the adaptive flood control gate.

[0031] Preferably, a permeation valve and a water quality monitoring module are arranged on the underground water storage tank.

[0032] Compared with the prior art, the present application has the following advantages:

[0033] The present application realizes all-around monitoring of disaster precursors before disaster occurrence by deploying a multi-parameter sensor network and unmanned aerial vehicle inspection, collecting key parameters such as rainfall, soil moisture content, ground displacement and debris flow velocity in real time, and combining high-resolution image data, thereby avoiding the limitations of a single data source; the unmanned aerial vehicle regular inspection can identify potential landslide bodies, debris flow channels and vegetation coverage changes, and timely discover changes in geological conditions to provide the latest data support for risk assessment.

[0034] The present application is based on a machine learning model, fuses sensor data and unmanned aerial vehicle image features, dynamically generates real-time risk level, overcomes the subjectivity of traditional experience judgment, improves the accuracy of early warning; when the risk level reaches "medium" or "high", the system automatically triggers the early warning signal, and pushes the early warning information to the user terminal through the communication module, ensures that the relevant personnel take risk avoidance measures in time, reduces the personnel casualties and property losses; by regularly updating the model parameters, adapt to the changes of regional geological conditions, continuously improve the reliability of risk assessment;

[0035] The present application realizes the dynamic balance of water storage and drainage in urban low-lying areas through the linkage control of underground water storage tank, water level sensor and drainage pump, relieves the waterlogging pressure and reduces the flood risk; combined with real-time water level data and weather forecast, automatically adjusts the opening degree of the gate, accurately controls the river water level, and prevents flood overflow; the bionic super-hydrophobic coating and the honeycomb-shaped aluminum alloy support structure improve the impact resistance and service life of the gate; after the disaster occurs, the unmanned aerial vehicle automatically performs the post-disaster image acquisition task, generates a disaster influence range map, and provides intuitive data support for emergency rescue and post-disaster assessment; based on historical data and post-disaster images, the disaster assessment module generates a recovery suggestion report, which clearly defines the reconstruction priority, resource allocation scheme and ecological restoration measures, and guides the scientific reconstruction after the disaster; the blockchain technology ensures that the post-disaster image data and the assessment report are tamper-proof, provides a reliable basis for insurance claims, liability identification and subsequent research, reduces disputes, and improves social credibility;

[0036] The present application realizes the comprehensive perception of disaster characteristics through the cooperation of sensor network and unmanned aerial vehicle; based on a machine learning model, dynamically generates a risk level, improves the accuracy of early warning; intelligent drainage system, self-adaptive flood control gate and other facilities realize the active intervention of disasters; based on blockchain and machine learning technology, ensure the credibility of disaster data, and provide scientific basis for post-disaster reconstruction; through VR simulation and user terminal, improve the public disaster prevention consciousness and emergency ability. BRIEF DESCRIPTION OF DRAWINGS

[0037] Figure 1 The step flow chart of the present application. DETAILED DESCRIPTION

[0038] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0039] As Figure 1 shown, a geological disaster prevention method for flood control and debris flow prevention, comprising:

[0040] Step one: Real-time monitoring and data collection of flood and debris flow disasters, deploying multi-parameter sensor networks in target areas, real-time collection of rainfall, soil moisture content, ground displacement, groundwater level, debris flow velocity and flow data; at the same time, through regular inspection by unmanned aerial vehicle, high-resolution image data of the target area is obtained, and potential landslide body, debris flow channel and vegetation coverage change are identified;

[0041] Step two: Risk assessment and early warning model construction of flood and debris flow disasters, fusion of sensor data and unmanned aerial vehicle image data, input into the geological disaster risk assessment model based on machine learning, generation of real-time risk level; when the risk level reaches "medium" or "high", trigger the early warning signal, and push the early warning information to the user terminal through the communication module;

[0042] Step three: Active defense measures for flood and debris flow disasters;

[0043] Step four: Emergency response and post-disaster assessment of flood and debris flow disasters, after the disaster occurs, the post-disaster image collection is automatically executed by the unmanned aerial vehicle, and the disaster influence range map is generated; and based on the historical data and post-disaster image, the recovery suggestion report is generated through the disaster assessment module, guiding the post-disaster reconstruction.

[0044] The application further specifically details that the multi-parameter sensor network comprises:

[0045] Rain gauge for real-time monitoring of rainfall intensity;

[0046] Soil moisture sensor for monitoring soil moisture content change;

[0047] Displacement sensor for monitoring ground or rock mass displacement;

[0048] Groundwater level sensor for monitoring groundwater dynamics;

[0049] Debris flow velocity sensor and flow sensor for monitoring debris flow motion parameters.

[0050] The application further specifically details that the construction steps of the geological disaster risk assessment model comprise:

[0051] Step one: Based on historical disaster data and geographic information data (GIS), support vector machine (SVM) or random forest (RF) classification model is trained;

[0052] Step two: Input real-time collected sensor data and unmanned aerial vehicle image features, and output risk level;

[0053] Step three: The model is regularly updated by new data to adapt to the change of regional geological conditions.

[0054] A geological disaster prevention system for flood and debris flow prevention comprises:

[0055] A data acquisition layer comprises a multi-parameter sensor network and a UAV; the multi-parameter sensor network is used for real-time acquisition of geological and environmental parameters; the UAV is used for inspection and image acquisition;

[0056] A data processing layer comprises a central control platform and a communication module; the central control platform integrates a data fusion module and a risk assessment model; the communication module is used for data transmission and early warning information pushing;

[0057] An execution control layer comprises intelligent drainage systems, flood prevention gates, debris flow diversion channels and flexible blocking nets;

[0058] A user interaction layer comprises a user terminal, which comprises a mobile phone APP and a PC terminal management platform, and is used for receiving early warning information and checking system status;

[0059] Further details of the application, the user interaction layer further comprises a virtual reality (VR) disaster simulation module and a blockchain disaster data storage module; the virtual reality (VR) disaster simulation module is used for enabling users to simulate disaster occurrence scenes through VR devices, learn escape skills and emergency measures; and the system generates a personalized training report according to user operation records, thereby improving public disaster prevention awareness; the blockchain disaster data storage module is used for enabling post-disaster image data and evaluation reports to be encrypted and stored through blockchain technology, thereby ensuring that the data cannot be tampered with, and providing a reliable basis for insurance claims and liability identification; the execution control layer further comprises an intelligent drainage and water storage integrated system and a self-adaptive flood prevention gate; the intelligent drainage and water storage integrated system comprises an underground water storage tank, a water level sensor and a drainage pump, the underground water storage tank is arranged in a low-lying area of a city, and through linkage of the water level sensor and the drainage pump, dynamic balance of water storage and drainage is realized; the self-adaptive flood prevention gate automatically adjusts the opening degree through real-time water level data and weather forecasts, a bionic super-hydrophobic coating is arranged on the self-adaptive flood prevention gate, a honeycomb-shaped aluminum alloy support structure is embedded in the self-adaptive flood prevention gate, a permeation valve and a water quality monitoring module are arranged on the underground water storage tank;

[0060] As can be seen from the above, the geological disaster prevention method and system for flood and debris flow prevention of the application realizes dynamic and intelligent prevention and control of flood and debris flow disasters by integrating multi-source data acquisition, intelligent risk assessment, active defense engineering and emergency response mechanism, and constructing a “monitoring-early warning-defense-evaluation” whole-chain technical system, and the working principle is as follows:

[0061] Rain gauges, soil moisture sensors, displacement sensors, groundwater level sensors, and debris flow velocity and flow sensors are deployed in the target area to collect real-time data on rainfall intensity, soil moisture content, surface displacement, groundwater level, and debris flow movement parameters. High-resolution image data of the target area is obtained periodically by drones, and image recognition technology is used to identify potential landslide bodies, debris flow channels, and changes in vegetation coverage, addressing the spatial coverage limitations of ground sensors.

[0062] Sensor data and drone image data are spatially and temporally aligned and feature-extracted by the data fusion module of the central control platform, forming multi-dimensional disaster feature vectors to support subsequent risk assessment. Data is transmitted in real-time to the central control platform through communication modules (such as 4G / 5G, LoRa, etc.), ensuring data timeliness and integrity.

[0063] Based on historical disaster data and geographic information data (GIS), a classification model is trained using support vector machine (SVM) or random forest (RF) algorithm to learn the non-linear relationship between disaster occurrence and multi-source parameters. Real-time sensor data and drone image features are input into the model to output the current regional risk level (low, medium, high). The model is iteratively optimized periodically with new data to adapt to dynamic changes in regional geological conditions (such as rock and soil properties, vegetation coverage), improving assessment accuracy. When the risk level reaches "medium" or "high", the system automatically triggers a warning signal and pushes warning information to user terminals (mobile APP, PC management platform) through communication modules, including disaster type, risk level, impact range, and emergency suggestions.

[0064] Underground water storage tanks are deployed in urban low-lying areas to monitor water level changes in real-time through water level sensors. When the water level exceeds the threshold, the drainage pump automatically starts to drain excess water into the municipal pipe network or natural water bodies. When rainfall is insufficient, the water storage tank supplies water to the surrounding soil through a permeation valve, achieving dynamic balance between water storage and drainage.

[0065] The gate automatically adjusts the opening degree by integrating water level sensors and weather forecast data to control the water level of the river or channel, preventing flood overflow. The gate surface is coated with biomimetic super-hydrophobic material to reduce water flow resistance, reduce sediment adhesion, and extend the service life of the gate. The gate is embedded with a honeycomb-shaped aluminum alloy structure inside to improve impact resistance and withstand debris flow impact.

[0066] After a disaster occurs, drones automatically collect post-disaster imagery, generating a disaster impact map that labels the affected areas, damaged roads, and collapsed buildings. Based on historical data and post-disaster imagery, machine learning algorithms assess disaster losses (e.g., economic losses, casualties, and ecological damage) and generate recovery recommendations. These include reconstruction priorities, resource allocation plans, and ecological restoration measures, providing a scientific basis for post-disaster reconstruction. Post-disaster imagery and assessment reports are encrypted and stored using blockchain technology to ensure data immutability, providing a trusted data source for insurance claims, liability determination, and subsequent scientific research.

[0067] Users use VR devices to simulate disaster scenarios and learn escape routes, emergency avoidance skills, and rescue procedures. The system generates personalized training reports based on user operation records, assesses users' disaster prevention capabilities, and enhances public awareness of disaster prevention. Users can view system status (such as sensor data, risk level, and warning information) in real time through a mobile app or PC management platform, receive disaster warnings, and query post-disaster assessment reports, achieving transparency and participation in disaster prevention.

[0068] Through the above technical solution, a multi-parameter sensor network and drone inspections are deployed to collect key parameters such as rainfall, soil moisture, surface displacement, and debris flow velocity in real time. Combined with high-resolution image data, this enables comprehensive monitoring of disaster precursors, avoiding the limitations of a single data source. Regular drone inspections can identify potential landslides, debris flow channels, and changes in vegetation cover, promptly detecting changes in geological conditions and providing the latest data support for risk assessment.

[0069] Based on machine learning models, sensor data and drone image features are integrated to dynamically generate real-time risk levels, overcoming the subjectivity of traditional empirical judgments and improving the accuracy of early warnings. When the risk level reaches "medium" or "high", the system automatically triggers a warning signal and pushes warning information to the user terminal through the communication module, ensuring that relevant personnel take timely risk avoidance measures to reduce casualties and property losses. By regularly updating model parameters to adapt to changes in regional geological conditions, the reliability of risk assessments is continuously improved.

[0070] Through the linkage control of underground reservoir, water level sensor and drainage pump, the dynamic balance of water storage and drainage in urban low-lying areas is realized, the waterlogging pressure is relieved, and the flood risk is reduced; combined with real-time water level data and weather forecast, the opening degree of the gate is automatically adjusted, the river water level is accurately controlled, and flood overflow is prevented; the bionic super-hydrophobic coating and the honeycomb-shaped aluminum alloy support structure improve the impact resistance and service life of the gate; after the disaster occurs, the unmanned aerial vehicle automatically performs the post-disaster image acquisition task, generates a disaster influence range map, and provides intuitive data support for emergency rescue and post-disaster assessment; based on historical data and post-disaster images, the disaster assessment module generates a recovery suggestion report, clearly defines the reconstruction priority, resource allocation scheme and ecological restoration measures, and guides the scientific reconstruction after the disaster; the blockchain technology ensures that the post-disaster image data and the assessment report are not tamperable, provides credible evidence for insurance claims, responsibility identification and subsequent scientific research, reduces disputes, and improves social credibility;

[0071] The present application realizes comprehensive perception of disaster characteristics through sensor network and unmanned aerial vehicle cooperative monitoring; based on machine learning model, dynamically generates risk level, improves early warning accuracy; intelligent drainage system, adaptive flood control gate and other facilities realize active intervention of disaster; based on blockchain and machine learning technology, ensure the credibility of disaster data, provide scientific basis for post-disaster reconstruction; through VR simulation and user terminal, improve the public disaster prevention consciousness and emergency ability.

[0072] Although the embodiments of the present application have been shown and described, it can be understood by those skilled in the art that various changes, modifications, replacements and variations can be made to the embodiments without departing from the principles and spirits of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A method for preventing floods and debris flows, characterized in that: include: Step 1: Real-time monitoring and data collection of flood and debris flow disasters. Deploy a multi-parameter sensor network in the target area to collect real-time data on rainfall, soil moisture, surface displacement, groundwater level, debris flow velocity, and flow rate. At the same time, regular drone inspections will be used to obtain high-resolution image data of the target area to identify potential landslides, debris flow channels, and changes in vegetation cover. Step 2: Conduct risk assessment and build an early warning model for flood and debris flow disasters. Sensor data is integrated with drone imagery data and fed into a machine learning-based geological hazard risk assessment model to generate a real-time risk level. When the risk level reaches "medium" or "high," an early warning signal is triggered and the warning information is pushed to the user terminal via the communication module. Step 3: Take proactive measures to prevent floods and debris flows; Step 4: Conduct emergency response and post-disaster assessments of flood and mudslide disasters. After a disaster occurs, drones are used to automatically collect post-disaster images and generate a disaster impact map. Based on historical data and post-disaster images, a disaster assessment module generates a recovery recommendation report to guide post-disaster reconstruction.

2. A method for preventing floods and debris flows according to claim 1, characterized in that: The multi-parameter sensor network comprises: Rain gauge, used to monitor rainfall intensity in real time; Soil moisture sensor, used to monitor changes in soil moisture content; Displacement sensors, used to monitor surface or rock displacement; Groundwater level sensor, used to monitor groundwater dynamics; Debris flow velocity sensor and flow sensor are used to monitor debris flow movement parameters.

3. The method for preventing floods and debris flows according to claim 1, wherein: The steps of constructing the geological disaster risk assessment model include: Step 1: Based on historical disaster data and geographic information data (GIS), train a support vector machine (SVM) or random forest (RF) classification model; Step 2: Input real-time collected sensor data and drone image features, and output the risk level; Step 3: The model is regularly updated with new data to adapt to changes in regional geological conditions.

4. A geological disaster prevention system for flood control and debris flow prevention, characterized in that: include: A data acquisition layer, comprising a multi-parameter sensor network and a drone; The multi-parameter sensor network is used to collect geological and environmental parameters in real time; the drone is used for inspection and image acquisition; Data processing layer, which includes a central control platform and a communication module; the central control platform integrates a data fusion module and a risk assessment model; the communication module is used for data transmission and early warning information push; An execution control layer, which includes mechanical devices for an intelligent drainage system, flood control gates, debris flow diversion channels, and flexible retaining nets; The user interaction layer includes a user terminal, which includes a mobile phone APP and a PC management platform for receiving early warning information and viewing system status.

5. A geological disaster prevention system for flood and debris flow control according to claim 4, characterized in that: The user interaction layer also includes a virtual reality (VR) disaster simulation module and a blockchain disaster data storage module; the virtual reality (VR) disaster simulation module is used to enable users to simulate disaster scenarios through VR devices and learn escape skills and emergency measures; The system also generates personalized training reports based on user operation records to enhance public awareness of disaster prevention; The blockchain disaster data notarization module is used to encrypt and store post-disaster image data and assessment reports through blockchain technology, ensuring that the data cannot be tampered with, and providing a credible basis for insurance claims and liability determination.

6. A geological disaster prevention system for flood and debris flow control according to claim 4, characterized in that: The executive control layer also includes an intelligent drainage and water storage integrated system and an adaptive flood control gate; The intelligent integrated drainage and water storage system includes an underground water reservoir, a water level sensor and a drainage pump. The underground water reservoir is deployed in low-lying areas of the city. The water level sensor and the drainage pump are linked to achieve a dynamic balance between water storage and drainage. The adaptive flood control gate automatically adjusts its opening and closing degree based on real-time water level data and weather forecasts.

7. A geological disaster prevention system for flood and debris flow control according to claim 6, characterized in that: The adaptive flood control gate is provided with a bionic super-hydrophobic coating, and a honeycomb aluminum alloy supporting structure is embedded in the interior of the adaptive flood control gate.

8. The geological disaster prevention system for flood and debris flow control according to claim 6, characterized in that: The underground water reservoir is provided with a permeation valve and a water quality monitoring module.

Images