Patents
Literature
86 results about "Flash flood" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
A flash flood is a rapid flooding of low-lying areas: washes, rivers, dry lakes and depressions. It may be caused by heavy rain associated with a severe thunderstorm, hurricane, tropical storm, or meltwater from ice or snow flowing over ice sheets or snowfields. Flash floods may occur after the collapse of a natural ice or debris dam, or a human structure such as a man-made dam, as occurred before the Johnstown Flood of 1889. Flash floods are distinguished from regular floods by having a timescale of fewer than six hours between rainfall and the onset of flooding. The water that is temporarily available is often used by plants with rapid germination and short growth cycles and by specially adapted animal life.
Mountain torrent debris flow early warning system based on multi-source data comprehensive analysis
The invention discloses a mountain torrent debris flow early warning method and system based on multi-source data comprehensive analysis. And the monitoring system carries out multi-source monitoring on rainfall, material source and mud level change characteristics of the ditch domain. The method is based on double-threshold rainfall intensity parameters, a quantitative analysis model of channel mud level and flow, and a blocking and collapsing mechanism of object source deformation. The threshold value of each element is determined according to the disaster history, a disaster outbreak probability formula is established, and key factor weights are screened through a random forest algorithm. And data preprocessing is carried out through cross validation and dynamic adjustment. And substituting monitoring data into the analysis model, and comprehensively judging the early warning level of the mountain torrent debris flow. And issuing an early warning signal of a corresponding level to the object in the threatened area through the early warning system. After operation, an incremental random forest method is adopted to update the model through online learning, data redisk is carried out, and model threshold correction and parameter inversion analysis are carried out. According to the pre-warning system, a multi-index combined action comprehensive monitoring and pre-warning evaluation system for quantitative analysis is established.
Owner:陈建君
Modal decomposition and deep learning-based rainstorm torrential flood disaster-causing element prediction method and system
The invention discloses a rainstorm torrential flood disaster-causing element prediction method and system based on modal decomposition and deep learning, and solves the problems that a traditional model is insufficient in non-linear time sequence feature capture, and a physical model depends on complex data and is weak in generalization ability. Comprising the steps of collecting flow, flow velocity and water level data of an upstream site as input, and taking downstream disaster point data as output; preprocessing the data; a frost ice optimization algorithm is adopted to optimize variational mode decomposition parameters; a Fourier transform high and low frequency feature enhanced attention network is constructed, low-frequency and high-frequency components are divided, trend features are extracted through a fluctuation enhancement module, dynamic changes are captured through a multi-path difference calculation unit, self-perception attention is introduced to achieve feature weighted fusion and long-term memory, and a downstream hydrological state prediction result is output. By optimizing a modal decomposition and deep learning cooperation mechanism, the precision, robustness and generalization ability of sudden mountain torrent prediction are significantly improved, and the method is suitable for disaster emergency management in complex scenes of small and medium watersheds.
Owner:NAT INST OF NATURAL HAZARDS MINISTRY OF EMERGENCY MANAGEMENT OF CHINA
Meteorological water conservancy disaster intelligent grading early warning linkage call routing method and system
ActiveCN120510683ATelephonic communicationMessaging/mailboxes/announcementsResponse strategyRisk rating
The invention discloses a meteorological water conservancy disaster intelligent grading early warning linkage call routing method and a meteorological water conservancy disaster intelligent grading early warning linkage call routing system. A meteorological water conservancy two-factor early warning matrix is constructed, a cross-department data fusion channel is established, an early warning coupling model is developed, and multi-dimensional early warning fusion is achieved. And formulating a water conservancy special response strategy library, wherein the water conservancy special response strategy library comprises river water level grading routing and mountain torrent risk area customization strategies. And developing an intelligent water conservancy enhancement module, such as a flood control project topology analysis engine and a water and rain work condition semantic analyzer. The method is characterized in that a three-element risk rating model is constructed by an initiative dynamic coupling algorithm, and a water conservancy emergency response topology network based on double dimensions and a water conservancy project BIM data and meteorological early warning space superposition analysis module are adopted. The accuracy and comprehensiveness of disaster early warning can be improved, the timeliness and effectiveness of emergency response are ensured, and the intelligent level and disaster response capacity of the system are improved.
Owner:SHENZHEN DONGSHEN ELECTRONICS
Deep learning-based less-data small-watershed water level forecasting method
The invention discloses a deep learning-based less-data small-watershed water level forecasting method. The method comprises the following steps of: acquiring historical hourly rainfall data of a plurality of upstream rainfall stations of a small watershed and historical hourly water level data of a downstream water level station; preprocessing the acquired data, and screening rainfall sessions with the rainfall capacity of over 15mm per hour within 24 hours and corresponding water level data; the method comprises the following steps: performing data enhancement through a double-generation GAN model, generating simulated rainfall data by a first GAN model by taking white noise as input, generating simulated water level data by a second GAN model by taking rainfall data as input, combining historical data and simulated data, performing normalization, and dividing the data into a training set, a verification set and a test set according to a proportion; constructing a CNN-LSTM hybrid prediction model, training the model by taking a Nash coefficient as an optimization target, and verifying the prediction model by adopting a progressive verification strategy; and deploying the model for real-time water level prediction to obtain a water level prediction result. The method can break through the bottleneck of few data, and achieves the high-precision mountain torrent early warning of the small watershed water level.
Owner:HANGZHOU DINGCHUAN INFORMATION TECH CO LTD +1
Mountain torrent forecasting method suitable for different formation mechanisms
Owner:INST OF GEOGRAPHICAL SCI & NATURAL RESOURCE RES CAS +1
Flash flood simulation method applicable to red-bed soft rock regions
InactiveUS20260023194A1Climate change adaptationDesign optimisation/simulationWater storageVegetation
A flash flood simulation method includes: obtaining a water storage in a vegetation root zone and obtaining an actual evaporation at any point in the vegetation root zone within a target watershed; obtaining a total infiltration rate in an unsaturated zone based on an infiltration model; obtaining a saturation overland flow and an interflow based on a vertical distance from a wetting front to a slope surface; updating an average saturated groundwater table depth based on the interflow and the total infiltration rate of the unsaturated zone; constructing a flash flood model for the target watershed based on the water storage of the vegetation root zone, the actual evaporation, the total infiltration rate of the unsaturated zone, the saturation overland flow, the interflow, and the average saturated groundwater table depth; and simulating an event-based flood hydrograph of the target watershed based on the flash flood model for the target watershed.
Owner:SUN YAT SEN UNIV
Mountain torrent disaster dynamic plan generation method, product and equipment based on causal inference
The invention discloses a method, a product and equipment for generating a mountain torrent disaster dynamic plan based on causal inference, and belongs to the technical field of mountain torrent disaster monitoring. The method comprises the following steps: S1, acquiring multi-source data, and extracting causal features of the multi-source data; during extraction, dual robust data deviation elimination is realized based on a tendency scoring model and a result regression model; s2, performing dynamic causal graph modeling based on the extracted causal features and a historical disaster data set, and updating the weight to obtain a causal graph with a time sequence weight; s3, determining a current disaster situation state according to the causal diagram information, and performing anti-fact plan generation in combination with a preset intervention measure set to obtain an optimal plan set; and S4, performing multi-department collaborative execution based on the optimal plan set. According to the method, the pain point problems of passive response, lack of causal support and cross-department collaboration low efficiency of a traditional mountain torrent plan can be solved.
Owner:CHINA INST OF WATER RESOURCES & HYDROPOWER RES
Mountain torrent early warning rainfall threshold dynamic adjustment method and system
InactiveCN121527971ARainfall/precipitation gaugesWeather condition predictionHydrometryAtmospheric sciences
The invention discloses a mountain torrent early warning rainfall threshold dynamic adjustment method and system, and relates to the technical field of hydrological early warning, and the method comprises the steps: obtaining basic rainfall data and a basic early warning threshold of a target region; according to the basic rainfall data, performing calculation to obtain a multi-factor correction factor; the multi-factor correction factors comprise an early-stage wettability correction factor, a rainfall intensity correction factor and a rain pattern mode correction factor; calculating to obtain a comprehensive correction factor according to the multi-factor correction factor; according to the comprehensive correction factor and the basic early warning threshold value, calculating to obtain a dynamic early warning threshold value; the dynamic early warning threshold value comprises a ready transfer dynamic early warning threshold value and an immediate transfer dynamic early warning threshold value; and determining a rainfall early warning level according to the dynamic early warning threshold and the real-time rainfall. According to the invention, the early warning threshold can be dynamically adjusted according to the real-time working condition, and the accuracy and timeliness of mountain torrent early warning are improved.
Owner:ZHEJIANG UNIV OF WATER RESOURCES & ELECTRIC POWER
A flash flood and debris flow monitoring device based on phased array radar technology
This invention discloses a flash flood and debris flow monitoring device based on phased array radar technology, comprising a base, a support plate, and a mounting plate. A column is rotatably connected to the top of the base, and a fixing groove is provided on the top of the base, within which a fixing mechanism corresponding to the column is fixedly connected. A support rod is slidably inserted into the top of the column, and the top of the support rod is fixedly connected to the bottom of the support plate. A support block is fixedly connected to one side of the column, and the support block is connected to the support plate via turnbuckles. A fixing rod is rotatably connected to the top of the support plate via a rotating rod, and the top of the fixing rod is fixedly connected to the bottom of the mounting plate. A sliding groove is provided on the top of the support plate, within which a screw is rotatably connected. A slider is threaded onto the screw, and the slider is connected to the mounting plate via a transmission rod. This invention, through the setting of multiple adjustment mechanisms, allows the monitoring device to be freely adjusted according to actual installation needs, thereby effectively improving the installation and usage effect of the monitoring device.
Owner:TIANJIN FEIYUE BROTHER MONITORING & CONTROL CO LTD
Simulation Methods for Flash Floods and Debris Flows Based on Rheological Evolution Characteristics
ActiveCN120124518BClimate change adaptationDesign optimisation/simulationSoil scienceNumerical models
This invention belongs to the field of flash flood and debris flow disaster prevention and mitigation, and provides a method for simulating flash flood and debris flow processes based on rheological evolution characteristics. The method includes the following steps: establishing a generalized numerical model of the target channel; using a CFD-DEM coupled model to simulate the transport process of sediment particles in the generalized numerical model under the action of water flow or debris flow slurry; and, based on the semi-empirical relationship between the drag coefficient and Reynolds number of sediment particles carried by flash floods and debris flows, derived in this invention, realizing real-time adjustment of rheological parameters during the simulated flash flood and debris flow transport process through the bidirectional coupling mechanism of the CFD-DEM coupled model. This invention's method can more realistically simulate the spatial distribution of sediment particles during flash flood and debris flow transport, increasing the accuracy of flash flood and debris flow process simulation, and solving the problem that existing technologies struggle to simulate the rheological evolution phenomenon of flash floods and debris flows caused by changes in volumetric sediment content.
Owner:SICHUAN UNIV
Mountain torrent debris flow monitoring and early warning method based on image sample intelligent generation
The invention relates to a mountain torrent debris flow monitoring and early warning method based on image sample intelligent generation, and belongs to the technical field of geological disaster monitoring and early warning, and the method comprises the following steps: video collection and transmission: collecting video data of a mountain torrent debris flow channel in real time; data preprocessing and amplification: preprocessing the collected video data, intelligently generating a preprocessed original photo by using an AIGC technology, and amplifying a sample data set; training and testing an early warning model: training and testing a sample by using a deep learning model based on the amplified sample data set, and establishing an early warning model to realize monitoring and early warning of the mountain torrent debris flow; model evaluation and adjustment: evaluating the model obtained by training, and adjusting model parameters according to an evaluation result to optimize performance; the mountain torrent debris flow early warning method based on AIGC and deep learning has the beneficial effects that diversified mountain torrent debris flow scene samples are generated, and the problem of insufficient sample data sets is effectively solved.
Owner:INST OF MOUNTAIN HAZARDS & ENVIRONMENT CHINESE ACADEMY OF SCI
Mountain torrent disaster early warning method, device, equipment and medium
The invention discloses a mountain torrent disaster early warning method, device and equipment and a medium, and relates to the technical field of hydrological monitoring and disaster early warning. The method comprises the steps of determining theoretical confluence time according to static attributes of a target drainage basin, determining an observation window of a rainfall event according to the theoretical confluence time, and performing sliding window analysis on a rainfall process of the rainfall event by using the observation window to obtain accumulated rainfall in the observation window, according to runoff reduction analysis, the accumulated rainfall is converted into effective peak flow, the effective peak flow is compared with disaster-causing flow, and early warning is given out according to a comparison result. According to the early warning method, the observation window is associated with the flow concentration time of the drainage basin, and the peak rainfall related to the flow concentration time of the drainage basin is captured based on the accumulated rainfall counted by the observation window, so that the rainfall process is prevented from being split by statistics in a fixed time period, and the early warning effectiveness is improved.
Owner:四川省达州水文水资源勘测中心
A flash flood induced landslide disaster risk early warning method and device and a storage medium
The application discloses a mountain torrent induced landslide disaster risk early warning method and device and a storage medium, and relates to the technical field of geological disaster meteorological risk early warning.
Owner:GUANGZHOU INST OF GEOGRAPHY GUANGDONG ACAD OF SCI
Mountain torrent disaster early warning system based on deep learning and air-space-ground integrated perception
PendingCN121963412ADiversity guaranteedGuaranteed accuracyMeasurement devicesAlarmsTerrainSynthetic aperture radar
The invention relates to the technical field of disaster early warning processing, in particular to a mountain torrent disaster early warning system based on deep learning and air-space-ground integrated perception. The system comprises the following modules: a space-air-ground sensing module, an edge calculation preprocessing module, a deep learning prediction module and an intelligent decision and early warning module. Wherein the air-space-ground sensing module is used for collecting multi-source data; wherein the multi-source data comprises earth surface deformation data obtained through a spaceborne synthetic aperture radar, high-precision topographic data obtained through an unmanned aerial vehicle laser radar, hydrological sensing data obtained through a ground internet-of-things distributed sensor, and meteorological numerical forecasting data obtained through a meteorological data interface. Through air-space-ground integrated perception, physical constraint deep learning and edge intelligence technologies, mountain torrent multi-source data collaborative acquisition and accurate mountain torrent disaster prediction are realized, so that the comprehensiveness, reliability and timeliness of mountain torrent disaster early warning are improved.
Owner:YANGTZE RIVER WATER CONSERVANCY COMMISSION HYDROLOGY MIDDLE YANGTZE RIVER HYDROLOGY & WATER RESOURCES SURVEY BUREAU (YANGTZE RIVER WATER CONSERVANCY COMMISSION HYDROLOGY MIDDLE YANGTZE RIVER WATER ENVIRONMENT MONITORING CENT) +1
Mountain torrent disaster risk avoiding guidance and emergency command system and method based on edge calculation
The invention discloses a mountain torrent disaster risk avoiding guidance and emergency command system and method based on edge computing, and relates to the technical field of mountain torrent disaster dispatch, in the method, an edge disaster sensing and gathering module gathers disaster dynamic data and positioning information on a target monitoring mountainous area map, and a comprehensive disaster situation map is constructed; an intelligent risk-avoiding path planning module automatically plans a risk-avoiding path by using a dynamic cost grid algorithm and an A path-finding algorithm according to the comprehensive disaster situation map, and generates a path instruction; a self-adaptive emergency command decision module automatically matches a preset emergency plan to generate a command instruction according to the real-time submerging range, the early warning level and the affected population density of each disaster area; and the multi-mode guide instruction issuing module sends a path instruction and a command instruction. According to the invention, the efficiency and rationality of mountain torrent disaster risk avoiding guidance and emergency command can be improved.
Owner:CHINA INST OF WATER RESOURCES & HYDROPOWER RES
A method, apparatus and equipment for classifying flash flood disasters
This application discloses a method, apparatus, and equipment for classifying flash flood disasters, relating to the field of disaster monitoring technology. The method includes: acquiring a geographic feature dataset of multiple watershed nodes in a target area, and constructing a feature matrix based on the geographic feature dataset; inputting the feature matrix into a flash flood disaster classification model, and outputting the classification probability of each watershed node belonging to each flash flood disaster category; the flash flood disaster classification model is used to: calculate the edge weight matrix of the graph structure formed by the feature matrix and the watershed nodes in the target area using a multi-head attention mechanism; perform sparsification processing on the edge weight matrix, and perform graph convolution operation based on the feature matrix and the sparsified edge weight matrix to obtain aggregated features; perform global feature enhancement on the aggregated features to obtain enhanced features; and output the classification probability of each watershed node belonging to each flash flood disaster category based on the enhanced features. This application can improve the accuracy of flash flood disaster classification.
Owner:CHINA INST OF WATER RESOURCES & HYDROPOWER RES
A large-scale watershed hydrological modeling method based on variable grids
ActiveCN120317033BClimate change adaptationDesign optimisation/simulationHydrometryAtmospheric sciences
The present invention provides a large-scale watershed hydrological modeling method based on a variable grid, which belongs to the field of large-scale distributed hydrological modeling. The large-scale watershed hydrological modeling method is as follows: first, the size of the basin basic grid is determined based on the spatial resolution of the available basic data and weighing the calculation time of the distributed hydrological model at different resolutions; second, the grid level is determined according to the rainfall level of a flood event and the flash flood prevention level; finally, according to the grid level of different partitions, the basic grid is aggregated into coarse grids of different levels to complete the variable grid hydrological modeling of the watershed. The present invention is applicable to large-scale watershed flood forecasting systems, and can meet the timeliness requirements of flood control decisions while ensuring the refined modeling of key areas.
Owner:DALIAN UNIV OF TECH
Mountain torrent debris flow dynamic decision method and system based on multi-agent and LLM
This application discloses a dynamic decision-making method and system for flash floods and debris flows based on multi-agent and LLM (Limited Language Model), belonging to the field of emergency management and intelligent decision-making technology. This method constructs an intelligent decision-making architecture based on a large model and multi-agent collaboration. It solves the execution challenges of complex disaster tasks through the division of labor and cooperation among multiple agents, and overcomes the decision-making limitations of traditional systems by leveraging the deep reasoning capabilities of a large language model. Specifically, the multi-agent collaborative framework decomposes disaster prevention and control decisions into sub-tasks such as intent parsing, contingency plan retrieval, spatial analysis, data acquisition, and analysis and prediction. Each functional agent focuses on its area of expertise, improving the efficiency and accuracy of task execution. The agent communication protocol ensures efficient information interaction and collaborative scheduling between modules, realizing fully automated processing from task input to data output.
Owner:SICHUAN UNIV
A partition classification parallel training method of a flash flood risk prediction large model
The application discloses a kind of mountain torrent risk prediction big model's partition classification parallel training method, the method includes the following steps: step 1, mountain torrent disaster sample big data construction;Step 2, mountain torrent disaster is classified and input-output strategy is formulated;Step 3, partition classification carries out big model parallel training;Step 4, big model input strategy adjustment;Step 5, interactive automatic optimization big model parameter.The method disclosed in the application improves the generalization ability and prediction accuracy of mountain torrent risk prediction big model by partition classification of sample big data;Proposed mountain torrent risk prediction big model parallel training method improves training efficiency;Using the characteristics of big model back propagation, calculate the relative contribution of input elements to mountain torrent disaster, guide to simplify input elements, on the basis of ensuring prediction accuracy, light weight mountain torrent risk prediction big model.
Owner:CHINA INST OF WATER RESOURCES & HYDROPOWER RES
A simulation experiment system and method for blockage-opening of mid-flow in hillside rainstorm soil
The present invention relates to a simulation experimental system and method for the blockage and opening of a mid-flow in a hillside rainstorm soil, which integrates an artificial rainfall device, a layered soil simulation device, a drainage and water collection device, and a video monitoring device. The layered soil simulation device is sequentially buried with clay, loam, and sandy soil layers from bottom to top. The preferential flow path is simulated by artificial or natural means such as inserting a steel needle into the soil and then pulling it out, cultivating earthworms to form caves, etc.; by laying loose materials such as pollen, catkins, and artificial particles on the soil surface, the materials scattered on the soil surface in nature that can block the preferential flow path are simulated; by simulating the process of "opening-blocking-opening" of the preferential flow path, the state transition conditions of the blockage or opening of the preferential flow path in the soil are explored. The present invention collects and analyzes the layered runoff on the hillside by simulating hydrological processes such as rainfall, infiltration, and runoff generation, explores the excitation conditions of the mid-flow in a rainstorm soil, and supports further exploration of the key mechanism and constitutive relationship of flash flood formation.
Owner:WUHAN UNIV ASSET INVESTMENT & MANAGEMENT CO LTD +1
A method for vegetation creation on alluvial rockfall riverbanks
This invention relates to the field of cultivation technology for specific crops or plants not mentioned above, and discloses a method for creating vegetation on alluvial and rockfall riverbanks. The method involves identifying weak erosion zones less affected by unstable landslides and alluvial deposits left by flash floods through exploration. Perennial vines are then planted at these locations to cover the remaining riverbank area, preventing damage to the vegetation from alluvial deposits and fallen rocks. Microenvironmental wells are dug within the weak erosion zones, and the perennial vines are planted inside to block flash floods from damaging the vegetation and surrounding soil. The soil within the wells is rotated, with topsoil containing a large amount of sand and gravel, being infertile and unable to retain water, being turned to the bottom of the well, thus no longer hindering vegetation growth and facilitating groundwater infiltration. The deeper soil, free of sand and gravel, relatively fertile, and with better water retention, is turned to the top layer, allowing the vegetation within the well to grow better. The combination of these methods overcomes the damage and stress to vegetation, enabling the creation of vegetation on riverbanks where normal growth is impossible.
Owner:BEIJING FORESTRY UNIVERSITY
Intelligent early warning and automatic triggering type emergency linkage system for small watershed mountain torrents
An intelligent early warning and automatic triggering type emergency linkage system for small watershed mountain torrents of the present invention belongs to the technical field of mountain torrent disaster monitoring and early warning, and comprises a data acquisition and processing module, a risk assessment module, an early warning judgment module and an emergency response triggering module. According to the method, early warning can be given out earlier, precious time is won for disaster prevention and reduction, it is ensured that emergency resources are put to the most needed place with the optimal path in the shortest time, the response efficiency is remarkably improved, the system can continuously learn from practice, the early warning and response performance of the system is continuously improved, and the continuous self-evolution ability is achieved.
Owner:HANGZHOU YONGJI WATER SCI & TECH
Real-time mountain torrent disaster monitoring method and system integrating radar and video
The invention relates to the technical field of mountain torrent monitoring, in particular to a mountain torrent disaster real-time monitoring method and system integrating radar and video. Comprising the following steps: respectively acquiring a water velocity signal and a mountain torrent region image sequence through radar equipment and video equipment, and aligning the frequency difference of acquired data through a timestamp calibration mechanism to form a multi-source data set with preliminarily aligned time and space; motion feature vectors and boundary contour features are extracted from the data set, filtering smoothing processing is carried out on the motion features, and noise is removed; correcting timestamp offset, ensuring data time unification, and associating motion features with boundary contour features through space mapping to generate a fusion feature map; calculating the corresponding relation between the water velocity and the boundary contour through the fusion feature map, generating a dynamic hydrological parameter distribution map, marking a high-risk disaster range, generating a comprehensive monitoring report, and determining the mountain torrent disaster state in real time. According to the invention, the real-time monitoring precision and early warning capability of mountain torrent disasters are effectively improved.
Owner:XIANDAI WATER SAVING ENG TECH HENAN PROV
Mountain torrent disaster comprehensive risk prediction method and system based on multi-source data
The invention discloses a mountain torrent disaster comprehensive risk prediction method and system based on multi-source data, and relates to the technical field of mountain torrent disaster risk prediction.The method comprises the steps of multi-source data acquisition, multi-source data analysis and mountain torrent disaster prediction feedback, the multi-source data is accurately acquired, then the state corresponding to a region is evaluated, and the risk prediction accuracy is improved. And predicting whether the mountain torrent disaster occurs in the region and the disaster level, analyzing to obtain early warning maintenance of the mountain torrent disaster corresponding to the region, executing negative hidden danger cost pre-simulation of the adopted maintenance set under the mountain torrent disaster risk level, and evaluating to obtain the cost of the adopted early warning maintenance of the mountain torrent disaster corresponding to the region. And adaptive early warning maintenance under the corresponding mountain torrent disaster of the region is obtained through screening, so that accurate prediction of the corresponding mountain torrent disaster risk of the region is realized, effective measures are taken for prevention of a prediction result in time, and dangerous influence and risk loss caused by the mountain torrent disaster are reduced.
Owner:XINING METEOROLOGICAL BUREAU
Method for predicting positions of lost persons under mountain torrent and debris flow disasters
ActiveCN120689770ACharacter and pattern recognitionGeological measurementsFeature extractionAlgorithm
The invention provides a method for predicting positions of lost persons under mountain torrent and debris flow disasters, and belongs to the field of disaster rescue. The method comprises the following steps: acquiring multi-source data fusing a thermal infrared image, a radar image and a terrain; feature extraction is carried out on the acquired multi-source data, so that the positions of the lost persons under the mountain torrent and debris flow disasters can be identified in a multi-source mode from person tracks, human body heat radiation and human body skeleton detection; constructing a comprehensive analysis function based on the extracted features; and based on the comprehensive analysis function, obtaining predicted values of different positions at the time t, and completing prediction of the position of the lost person. The invention aims to solve the problems of low accuracy and low efficiency of the existing lost person position prediction method.
Owner:SICHUAN HUIZHI ANTAI TECH +1
Early warning method for important village of mountain flood prevention based on small reservoir water and rainfall condition monitoring
This invention discloses a method for early warning of flash floods in important villages based on small reservoir hydrological and rainfall monitoring. The method first collects data from the study area, constructing a multi-source heterogeneous data fusion system and a hydrological-topographic-socioeconomic correlation network for the study area. Then, it constructs spatial location and water flow path correlations between small reservoirs and important villages, generating inundation range maps and delineating risk zones based on the topography, building layout, and set water level thresholds of the important villages. A reservoir-river-village hydrodynamic coupling model is constructed to calculate the correlation between small reservoir monitoring indicators and village disaster events, and this is input into a disaster-causing water level inversion model to obtain the probability distribution of disaster-causing water levels. Finally, a flash flood disaster early warning model is constructed, extracting the probability distribution of disaster-causing water levels as model input to perform multi-timescale risk forecasting and classify early warning levels, developing differentiated early warning schemes for different levels. This improves the scientific rigor and effectiveness of flash flood disaster prevention.
Owner:ZHEJIANG INST OF HYDRAULICS & ESTUARY
Hydrological model parameter calibration method for watershed lacking hydrological data
The invention relates to the technical field of watershed hydrological model parameter calibration, in particular to a hydrological model parameter calibration method for a watershed lacking hydrological data, which comprises the following steps: determining a watershed A lacking data and a watershed B controlled by an adjacent hydrological station (reference station) with data, and collecting hydrometeorological and underlying surface feature data of the two watersheds; calculating the design flood of the drainage basin A and the drainage basin B by using a rainstorm runoff survey algorithm; comparing the design flood calculated by the rainstorm runoff of the watershed B close to the data with the design flood calculated by the actually measured flow data, and determining a flood correction coefficient kappa for correcting the design flood calculated by the watershed A lacking the data by using the rainstorm runoff calculation algorithm; inputting the model parameters of the data-lacking watershed A and the design surface rainstorm into a hydrological model; simulating an outlet section flood; and comparing a simulation result with a corrected rainstorm runoff checking result, analyzing parameter sensitivity, and adjusting and optimizing model parameters. The method is suitable for parameter calibration of the data-lacking small-watershed mountain torrent forecasting model, and a new means is provided for flood control and disaster reduction.
Owner:POWER CHINA KUNMING ENG CORP LTD +1
Traffic engineering premises mountain torrent risk early warning analysis method based on multi-source perception
PendingCN121352526AHuman health protectionMathematical modelsEnvironmental resource managementDecision model
The invention discloses a traffic engineering premises mountain torrent risk early warning analysis method based on multi-source perception, and relates to the technical field of mountain torrent disaster monitoring and emergency management, and the method comprises the steps: carrying out the mountain torrent audio feature recognition of sound pressure signals based on a pre-trained AI model, and carrying out the water body form mutation recognition of video streams; in the far-end server, multi-source sensor data and weather forecast data are fused, weights are distributed to the sensors according to the topographic and geological risk levels of the river reach where the sensors are located, and the comprehensive risk score of the upstream river reach is calculated; predicting a flood routing path, a flood routing speed and a flood range based on the upstream comprehensive risk score and a hydraulic model; dynamically planning an optimal escape path according to the prediction result and the real-time acquired position information of the stationed personnel; according to the method, the upstream fusion decision model based on distance attenuation and river reach weight is adopted, so that the downstream station can sense the threat from the upstream early and accurately.
Owner:SICHUAN HIGHWAY PLANNING SURVEY DESIGN AND RESEARCH INSTITUTE LTD
Mountain torrent disaster early warning information broadcasting terminal
The invention discloses a mountain torrent disaster early warning information broadcasting terminal, and relates to the technical field of mountain torrent disaster early warning, and the terminal comprises an information receiving unit which analyzes, collects and verifies multi-source data; the AI operation processing unit classifies and sorts the data, predicts a trend, judges an early warning level and optimizes pushing; the display output unit converts the data into three-dimensional content and displays the three-dimensional content in multiple forms; the sound-light alarm unit adjusts sound and light and broadcasts according to grades; the user interaction unit records behavior data and supports personalized setting, and all the units cooperate to achieve intelligent early warning; according to the invention, multi-source data is processed through the information receiving unit, and the energy quantification and coupling prediction model of the AI unit is combined, so that the dependence of a traditional single data source is broken through, a full-chain intelligent decision is formed, and the prediction accuracy and the grade division scientificity are improved; meanwhile, the early warning form is adjusted through an energy threshold adaptation algorithm, three-dimensional rendering and grading acousto-optic technologies are integrated, the understanding threshold is reduced through multi-modal interaction, the risk avoiding decision time is shortened, and the disaster prevention efficiency is improved.
Owner:SICHUAN UNIV
A flash flood disaster zoning method integrating attributes and structures
The present invention provides a method for flood disaster zoning that integrates attributes and structures, which relates to the technical field of flood disaster zoning. The method includes the following steps: (1) Preprocess rainfall and terrain factors and spatially aggregate them to the scale of each small watershed as the rainfall and terrain attributes of the small watershed; (2) According to the small watershed boundary data, use the center of the small watershed to represent the small watershed and serve as the nodes of the graph, and construct the edges between the nodes for adjacent small watersheds, so as to construct a graph structure to represent the spatial structure relationship of the small watershed; (3) Use the attributes and spatial structure relationship of the small watershed as inputs, and utilize three graph convolutional neural network modules to construct a graph autoencoder to simultaneously perform feature expression learning on the attributes and spatial structure of the small watershed; (4) Establish a graph decoder according to the output of each graph convolutional neural network module to simultaneously realize the reconstruction of the small watershed spatial structure and the clustering of small watersheds; (5) Merge small watersheds of the same category according to the best clustering result of the small watersheds to obtain the final flood disaster zoning scheme.
Owner:HOHAI UNIV +1