1232 results about "Precipitation" patented technology

The invention provides a mesoscale convection parameter optimization method and system based on a genetic algorithm, and relates to the technical field of weather forecast, and the method comprises the steps: modeling a rainfall evolution state through a Sheng differential equation, inferring and recognizing power system parameters in combination with variation, and extracting features through a space-time heterogeneous graph neural network and a diffusion probability model; the parameter threshold is corrected by adopting the physically guided neural network, and the optimization objective function is constructed through the deep neural network to realize parameter optimization, so that the accuracy of rainfall forecasting can be improved, the forecasting error can be reduced, and the method has relatively strong adaptability and generalization ability.

The invention discloses a traceable road surface runoff pollutant monitoring method and system, and relates to the technical field of water pollution monitoring. The method comprises the following steps: capturing environmental factors of precipitation, air temperature and traffic flow according to road surface basic monitoring data, extracting pollutant concentration data of sampling points, analyzing relevance of the environmental factors, identifying and classifying pollutant concentrations, and obtaining pollutant concentration change trend characteristics. According to the method, the relationship between the environmental factors and the pollutants is accurately analyzed by capturing the environmental factors and the pollutant concentration data, the understanding of the change trend of the pollutant concentration is improved, the pre-judgment precision of future changes is effectively improved, in real-time data comparison, error analysis helps to identify deviations and adjust model weights, the prediction accuracy is improved, and the prediction accuracy is improved. Through monitoring resource demand prediction, optimization of monitoring point layout and resource configuration and dynamic adjustment of a monitoring strategy, pollutant concentration monitoring is more flexible and accurate, and monitoring efficiency and response speed are improved.

The invention provides a power equipment meteorological monitoring and early warning system based on artificial intelligence. The power equipment meteorological monitoring and early warning system based on artificial intelligence comprises a data acquisition module, a data preprocessing module, a spatio-temporal feature fusion module and a meteorological disaster prediction model, the meteorological disaster prediction model adopts a deep reinforcement learning framework, inputs a multi-dimensional spatio-temporal feature matrix, and carries out meteorological disaster prediction on the multi-dimensional spatio-temporal feature matrix. And outputting meteorological disaster risk levels and key parameter predicted values in a future preset time period, including a wind speed, precipitation, temperature anomaly and tropical cyclone path probability, a dynamic early warning threshold generation module, an early warning decision module and a model optimization module. The power equipment meteorological monitoring and early warning system based on artificial intelligence provided by the invention has the advantages that the data interpolation precision of a complex terrain region can be improved, high-precision prediction of a typhoon path, short-time strong wind and an icing risk can be realized, and the early warning accuracy and defense response efficiency of a power system to meteorological disasters can be comprehensively improved.

The invention discloses a water level monitoring and management method based on multi-source information fusion, and relates to the technical field of water level monitoring and management. Comprising the following steps: acquiring a water level and water level related data by adopting a sensor, and acquiring surface feature information and meteorological data through GIS data; performing data cleaning and standardization on the collected data; a convolutional neural network is adopted to analyze infrared cloud picture data obtained by satellites to predict precipitation, a weighted average method is adopted to carry out multi-source information fusion, and water level prediction is carried out through a hydrological model; and performing real-time water level monitoring and water level management decision according to accurate water level data obtained by data fusion. Through the above steps, the system can provide a more comprehensive view angle for water level management by fusing multi-source information, and can more accurately predict the water level change trend, thereby optimizing the water resource management strategy and flood control measures.

The invention relates to an electric power meteorological disaster risk early warning method and system based on artificial intelligence. The method comprises the following steps: cleaning and preprocessing basic meteorological data including temperature, humidity, wind speed and precipitation to obtain a cleaned basic meteorological data set; on the basis of satellite cloud picture or radar image data, meteorological changes are modeled through a neural network model, assimilation features are obtained, and the basic meteorological data and the assimilation features are spliced to form a joint feature vector; and constructing a comprehensive disaster risk assessment model based on the meteorological factors, the power grid factors and the geographic information, carrying out training and multi-objective optimization on the comprehensive disaster risk assessment model, and carrying out real-time electric power meteorological disaster risk early warning by using the optimized comprehensive disaster risk assessment model. According to the invention, meteorological data, power grid equipment states and geographic information can be monitored in real time, meteorological disasters possibly suffered by power equipment can be accurately warned, and the safety and stability of a power system are improved.

The invention discloses an AI-NWP three-dimensional closed-loop bidirectional dynamic feedback coupling method for extreme rainfall event area simulation and a program product, and belongs to the technical field of meteorological numerical simulation and artificial intelligence fusion. According to the method, a mid-term forecast field is generated based on an AI global weather prediction model, an analysis field is constructed by assimilating multi-source observation data, and a high-resolution NWP region mode is driven to perform rolling simulation. Furthermore, a space-time residual field is constructed by using the difference between an NWP region simulation result and live data, a residual learning model is trained, an AI model prediction structure is fed back and corrected, and dynamic weight adjustment updating of the AI prediction model is realized. A closed-loop two-way feedback system among AI output, NWP simulation and residual evaluation is integrally formed, the space structure reduction capability and the area positioning precision of a medium-term heavy rainfall event are effectively improved, the continuous predictability and the simulation credibility of an extreme weather process are remarkably enhanced, and the method has good stability, universality and engineering expansion value.

The invention discloses a regional water supply emergency scheduling method and system. The method comprises the following steps: fusing GIS and IoT data to construct a dynamic three-dimensional topology model; historical water consumption and meteorological data are decomposed through wavelet multi-scale decomposition, and a prediction model is input to obtain a water consumption prediction value of a scheduling day period; on the basis of reservoir water storage, flow, water quality, rainfall and pollution source data collected in real time, a flow-water quality coupling model is used for predicting the reservoir inflow and water quality of a dispatching day; the method comprises the following steps: establishing a multi-objective function by combining water consumption prediction, storage prediction and current water storage, embedding a water quality constrained multi-objective optimization model, and solving by adopting an NSGA-II algorithm to obtain a Pareto optimal scheduling scheme set; and finally, a scheme is selected to be issued and executed. According to the method, data-physical collaborative intelligent scheduling decision is realized, the water supply demand is met under the condition that the water supply quality is stable, the condition of water shortage of the user terminal is avoided, and the water quality of the user terminal can continuously reach the standard.

The invention relates to the technical field of internet-of-things control, in particular to a wheat-corn annual water nitrogen content adjusting system, which comprises a data sensing module for acquiring soil humidity and nitrogen content data in a wheat-corn growth cycle, filtering the soil humidity and nitrogen content data and generating processed soil data; based on the processed soil data, a set standard threshold value is compared, and a soil state result is obtained. According to the method, the adjustment strategy is dynamically generated by further combining water and nitrogen demand standards of different growth stages, instant weather forecast data is synchronously analyzed when the strategy is generated, multi-dimensional environmental factors such as precipitation, wind speed, temperature and air humidity are considered, and an optimization adjustment scheme which better conforms to real-time demands of crops and environmental changes is generated. In the execution process, an instruction received by the irrigation and fertilization machinery is not a static single execution instruction any more, but is iteratively executed based on real-time feedback and environmental dynamics.

The invention belongs to the technical field of rainfall prediction, and discloses a short and temporary rainfall prediction method based on multi-model random scheduling integration, which develops a robust training and pushing framework based on a continuous rolling prediction strategy, and decomposes long-sequence prediction into manageable stages. According to the method, training is carried out through teacher forcing and planned sampling, error propagation is relieved, and the training process is stabilized. The invention further designs asymmetric encoder-decoders (DSE and AFD) that achieve lower FLOPs than competitive baselines under standardized assessment, where DSE selectively compresses significant features and AFD stepwise reconstructs details to mitigate excessive smoothing problems. Finally, an intensity weighted Gaussian KL divergence loss function is designed, and the key problem of data balance is solved by modeling and predicting on a distribution level and endowing a large weight to a meteorological important heavy rainfall event.

The invention discloses a non-point source pollution and waterlogging collaborative four-pre management and control system based on short temporary rainfall forecast, which relates to the technical field of urban water environment management and comprises a short temporary rainfall forecast module, a non-point source pollution control module, a waterlogging management module, a four-pre management and control platform, an intelligent decision support system, a real-time monitoring and feedback system and a water ecological management module. By integrating meteorological monitoring, hydrological monitoring and environment monitoring data, high-precision short and temporary rainfall forecast is realized by using a machine learning algorithm, the operation strategies of the intelligent catch basin and the initial rain storage pond are dynamically adjusted to control non-point source pollution, and meanwhile, the waterlogging risk is predicted and preventive measures are taken in combination with real-time hydrological data. According to the technology, integrated management of forecasting, early warning, rehearsal and plans is achieved through a four-pre-management and control platform, an intelligent decision support system, a real-time monitoring and feedback system and a water ecological management module under the sponge city design concept are used in an auxiliary mode, and the efficiency and effect of urban water environment management are comprehensively improved.

The invention relates to the technical field of intelligent irrigation, in particular to an agricultural water-saving irrigation intelligent regulation and control system which comprises a growth stage recognition module, a moisture monitoring module, a meteorological data synchronization module, an irrigation strategy scheduling module and a feedback correction module. According to the method, high-precision identification of crop stage states, improvement of stage judgment accuracy, screening of key growth period blocks, focusing of regulation and control targets, improvement of resource utilization efficiency, layered acquisition and trend comparison of humidity data and construction of a deep and shallow layer dynamic response structure are realized through time sequence analysis of rice key growth parameter amplification; the method comprises the following steps of: enhancing moisture change resolution, synchronously fitting a humidity rhythm and weather prediction, improving regulation and control perspectiveness, eliminating a rainfall interference window, combining with a water demand gear, realizing block precise irrigation, feeding back a regulation and control result through double indexes of humidity and leaf chromatic aberration, constructing set mapping, forming a closed-loop regulation and control mechanism, and enhancing adaptability and execution precision.

The invention relates to the technical field of building construction, in particular to a foundation pit dewatering prediction method based on a digital twinborn technology, which comprises the following steps of: 1, establishing a multi-source data fusion layer; 2, establishing a digital twin modeling layer; 3, establishing an intelligent prediction algorithm layer; 4, establishing a dynamic optimization decision layer, and generating a precipitation well optimization scheme based on a prediction result; according to the method, engineering geological data of a geological survey report before excavation of the building foundation pit, historical meteorology of a building location and hydrogeological data are utilized, digital twinning is carried out on precipitation during the whole construction period of the proposed building foundation pit on the basis of a digital twinning technology, the precipitation period, daily precipitation and influence of precipitation on foundation pit supporting are predicted, and the foundation pit supporting effect is improved. According to the method, the influence of settlement deformation of surrounding buildings is reduced, digital simulation is provided for smooth construction of a whole project, and measurement and prediction are provided for the project and the surrounding environment, so that the construction cost is greatly reduced.

The invention relates to a high-dimensional statistics and hydrodynamic force coupled flood risk assessment method and system. The method comprises the following steps: acquiring historical observation data covering river flow, tide level and rainfall events; constructing a univariate marginal distribution function; connecting the univariate marginal distribution functions of the river flow, the tide level and the rainfall event, and simulating a joint probability distribution function; coupling the joint probability distribution function with the mechanism model to obtain a probability-mechanism coupling model; inputting the determined joint probability boundary condition into a probability-mechanism coupling model, simulating to obtain composite flood scenes in different return periods, and comparing the composite flood scenes with single variable flood scenes in different return periods; and quantizing the contribution of each variable to the change of the submerging area by using the obtained submerging area and the corresponding rainfall event, river flow and coastal tide level data. According to the method, the defect that traditional single-factor evaluation cannot capture multi-factor interaction is overcome, and the accuracy of flood disaster evaluation is greatly improved.

The invention relates to the technical field of power transmission lines, in particular to a power transmission line toughness evaluation method and system considering important loads under an ice disaster. The method comprises the following steps: firstly, constructing an icing thickness real-time growth model considering multiple parameters such as water-ice density, an ice precipitation rate, a wind speed and air water content, carrying out regionalization analysis on a power transmission line according to weather parameters such as the wind speed and the precipitation rate, respectively calculating a unit length fault rate of each section, and comprehensively obtaining an overall fault probability of the whole line; then establishing a toughness evaluation system comprising a disturbance performance index, a recovery speed index and an important load maximum loss index, and dividing the affected process into five stages of system normal operation, performance reduction, performance maintenance, preliminary recovery and complete recovery; and finally, carrying out normalization processing on the evaluation indexes, determining the weight by adopting an optimization algorithm, and calculating the toughness value of the system. The fault prediction accuracy and the system recovery efficiency are remarkably improved through regional analysis and multi-dimensional evaluation, and the power supply reliability of important loads is effectively guaranteed.

The invention relates to a multi-source data fusion rainfall revision model construction method based on dynamic physical constraints, and belongs to the technical field of artificial intelligence and meteorology and hydrology crossing. The method comprises the steps that multi-source heterogeneous data such as satellites, reanalysis, sites and terrains are acquired and fused, and a standardized space-time sample set is constructed; constructing a special deep learning network comprising a double-flow encoder, a cross-scale physical attention fusion module and a decoder; constructing a composite loss function fusing data fidelity, terrain uplift constraint and wind field advection constraint; designing a dynamic constraint gating mechanism, and adaptively adjusting a physical constraint weight according to a real-time atmospheric state; and a high-precision precipitation revision model is obtained by optimizing the composite loss function training network. According to the method, the key physical process is embedded into the model in a dynamic adjustable mode, the problems that a traditional method is poor in physical consistency and generalization ability are solved, and a revised precipitation field which is physically reasonable and higher in precision can be generated under complex terrains and changeable weather.

The invention relates to a rainfall nowcasting method based on U-KAN grading loss weighting and frequency self-adaption, which comprises the following steps: (1) carrying out quality control and screening on a radar puzzle, and establishing a data set; (2) dividing a training set, a verification set and a test set, and standardizing; (3) constructing a U-KAN model, selecting training parameters and inputting data: combining a traditional Unet structure with a KAN network to construct the U-KAN model; then performing model training to obtain a prediction result; the prediction result is restored to the original magnitude through destandardization; (4) introducing a loss function based on a root-mean-square error and grade weighting in a model training stage, and performing post-processing on model output by adopting a frequency deviation correction method; (5) integrating and averaging the forecast products processed by the two complementary strategies, and recording the forecast products as U-KANE; and (6) predicting a rainfall result in the next three hours by using radar echo data in the past one hour, and outputting a rainfall short-term and imminent forecast result by the U-KANE.

The invention discloses a plateau airport refined weather forecast system based on deep learning. The system comprises a data acquisition module, a data processing module, a model training module, a prediction output module and an evaluation and optimization module. According to the system, an improved Transform deep learning model is adopted, a high-resolution numerical forecasting product of the European mid-term weather forecasting center and airport high-frequency automatic observation data are fused, and single-point and hour-level accurate meteorological element forecasting is achieved. On the basis of a 0.4-degree global numerical forecasting product of the ECMWF, the system obtains key meteorological factors such as temperature, rainfall and wind field. For the complex terrain and extreme weather conditions of the plateau airport, the model structure is optimized, and the multi-source data fusion and transfer learning technology is introduced, so that the forecasting precision and timeliness are remarkably improved. The method effectively solves the problems that a traditional numerical forecasting mode is large in forecasting error and poor in timeliness in a plateau area, and provides intelligent guarantee for aviation safety and operation efficiency of a plateau airport.

The invention relates to the technical field of agricultural intelligent irrigation, in particular to an intelligent irrigation control system and method based on meteorological environment acquisition, and the system comprises a sensing layer, a transmission layer, a control layer, a cloud layer and an execution layer. Then meteorological environment data collected by the sensing layer is transmitted to the control layer through a wireless transmitting module and a wireless receiving module, and a controller of the control layer is integrated with an edge computing unit, a communication unit and a decision-making unit; the problems that an existing agricultural meteorological monitoring and irrigation control system is high in network transmission load coefficient, and the edge computing capability of sensor nodes cannot be effectively utilized; the problem that an irrigation control algorithm based on a static threshold mechanism or a single statistical model lacks adaptive processing of rainfall time sequence prediction and dynamic response ability of specific requirements of crop growth stages is solved.

The invention discloses a slope physical similarity model device and a slope internal crack evolution identification method, and relates to the technical field of open pit coal mine slope ecological protection, and the slope physical similarity model device comprises a similar material simulation system, a monitoring system and an artificial rainfall system. Through cooperation of the similar material simulation system, the monitoring system and the artificial rainfall system, surface water seepage field change and instability process simulation caused by slope rock-soil mass fracture evolution under different main control factors can be artificially controlled, and temperature, rainfall, stress, fracture development and other characteristic changes in the whole process can be monitored in real time; the method can deeply explore the internal relationship with slope instability, obtain the slope instability failure path, failure source and key block, determine the main control factor threshold of each stage, reveal the seepage and instability mechanism of the open pit coal mine slope under the freeze-thaw cycle, and improve the stability of the open pit coal mine slope. And a theoretical basis is provided for establishment of multi-source criteria of seasonal freeze-thaw landslide of the high and cold opencast coal mine and early-and-middle-stage early warning.

The present invention provides a device and method for the resource utilization of urban waste incineration slag, which relates to the technical field of slag waste recycling. The device for the resource utilization of urban waste incineration slag includes an equipment frame and a crusher installed on the equipment frame. It further includes a flow and precipitation component, a water addition component, and a resource recovery component installed on the equipment frame. The crusher transfers the crushed slag to the water addition component. The water addition component is used to add water to the ash slag and make it flow into the flow and precipitation component. After operation and precipitation, it is then discharged onto the resource recovery component. It also includes multiple groups of stirring components for stirring the slurry in the flow and precipitation component. The device and method for the resource utilization of urban waste incineration slag, by setting the flow and precipitation component, can obtain precipitation within the operation time compared with a fixed sedimentation tank, and can be flipped and dumped, and flushed with high-pressure water, making it easier to clean the internal slurry and preventing blockage.

The invention provides a rainfall enhancement operation effect evaluation method and device for intelligently predicting natural rainfall, and the method comprises the steps: determining an operation influence region and a comparison region based on the range of artificial rainfall enhancement operation; the contrast area is not influenced by a catalyst for artificial precipitation increasing operation; respectively carrying out rainfall extrapolation prediction on the contrast area and the work influence area through a rainfall prediction model to obtain rainfall prediction data of the contrast area and rainfall prediction data of the work influence area; respectively obtaining real rainfall data of the comparison area and real rainfall data of the operation influence area; based on the rainfall prediction data of the comparison area and the real rainfall data of the comparison area, obtaining a rainfall prediction error of the rainfall prediction model; and on the basis of the rainfall prediction data of the operation influence area, the real rainfall data of the operation influence area and the rainfall prediction error of the rainfall prediction model, obtaining the absolute rainfall increment of the artificial rainfall enhancement operation. And the accuracy of effect evaluation is improved.

The invention discloses a figure operation effect quantitative evaluation method based on analogue simulation and live rainfall, and the method comprises the steps: collecting related data, and carrying out the preprocessing of the related data; the related data comprises reanalysis field or analysis field data, lattice live rainfall field information and artificial influence weather operation information; numerical simulation is started, the precipitation increasing rate and the operation influence area range are calculated, and accuracy evaluation is carried out on precipitation in the influence area of mode simulation; calculating the average precipitation increasing rate on the precipitation simulation hit grid point, and complementarily calculating the average precipitation increasing rate on the precipitation simulation missing report grid point; and calculating the rainfall increment based on the actual rainfall, optimizing the rainfall increment according to offset to obtain a corrected rainfall increment, and outputting the corrected rainfall increment as an evaluation result. The method not only can improve the precision of quantitative evaluation of the weather modification operation effect, but also has good interpretability, and can be directly applied to a quantitative evaluation system of the weather modification operation effect.

The invention provides a regional ecological environment quality evaluation method and system based on remote sensing data, and relates to the technical field of environment remote sensing and ecological monitoring, and the method comprises the steps: extracting red light and near-infrared reflectivity at the peak of a growing season by using Landsat8 satellite data, and calculating a mixed vegetation index; synchronously measuring vegetation indexes of pure vegetation and bare soil on site to obtain a vegetation coverage rate, and obtaining water transparency, suspended solid concentration and chlorophyll a concentration through on-site measurement on the basis of green light, red light, blue light and near-infrared reflectivity in a heavy rainfall period and a dry season; the method comprises the following steps: constructing a linear regression model of reflectivity and water quality parameters through a least square method, calculating a water quality index, constructing an extreme weather influence factor based on ten-year extreme weather data, and finally fusing a vegetation coverage rate, water quality, the extreme weather influence factor, annual precipitation, annual average temperature, optimal regional vegetation temperature and historical rainfall extremum. And constructing an ecological quality index, and dividing ecological environment quality grades.

The invention provides an intelligent path planning method and system based on dynamic road condition prediction. The method comprises the steps of firstly obtaining multi-source dynamic data of a target area; then, constructing a weather influence prediction model to predict weather influence parameters in a future time period; secondly, constructing a weather-traffic coupling model, and respectively establishing correlation models of corresponding precipitation, traffic flow density and average vehicle speed according to road types through historical data analysis, so as to estimate the traffic efficiency of each road section under a dynamic weather condition; and finally, generating a plurality of candidate paths according to the passing efficiency, screening out an alternative path set meeting a multi-target optimization condition from the candidate paths, performing simulation evaluation on the alternative path set, and determining an optimal path according to a simulation result. Compared with a traditional static path planning method, the method has the advantages that the responsiveness of a traffic system to meteorological disasters is remarkably improved, and predictable navigation service is provided for intelligent network connection vehicles.

The invention discloses a minute-level mountain approaching rainfall forecasting method and system based on improved Vision Transform topographic physical constraints, and the method comprises the steps: building a model training data set based on the multi-source meteorological observation station data and topographic feature data of a complex mountain region; a Vision Transform network is improved on the basis of a position adaptive dynamic convolutional network and a rain-free mask feature extraction strategy; a combined loss function capable of providing terrain forced precipitation physical constraints is constructed; the improved Vision Transform network is trained on the basis of the training data set, and an optimal approaching rainfall forecasting model is obtained; and inputting the real-time multi-source meteorological observation grid point data and the topographic feature grid point data into the optimal close rainfall forecast model to obtain close rainfall forecast. According to the method, the heavy rainfall position forecasting performance can be obviously improved, and the minute-level approaching heavy rainfall forecasting skill in the complex mountain environment is improved.

The invention discloses a deep learning and numerical mode seamless fusion-based short temporary rainfall forecasting method. The method comprises the steps of constructing a short temporary rainfall initial forecasting model based on a Vison Transform network, and constructing a deep learning and numerical mode seamless fusion-based short temporary rainfall correction forecasting model based on an improved U-Net network; and collecting various meteorological data in real time, preprocessing the data, inputting the preprocessed data into the trained short-temporary rainfall forecast optimal model to obtain 0-6h short-temporary rainfall forecast, fusing the short-temporary rainfall forecast with 2-6h short-temporary rainfall forecast in a real-time regional numerical mode, inputting the trained short-temporary rainfall optimal correction forecast model, and obtaining 0-6h seamless fused short-temporary rainfall forecast. The method solves the problems that in the prior art, deep learning extrapolation and numerical mode short and temporary rainfall fusion forecasting is discontinuous in time, inconsistent in spatial position and low in forecasting accuracy.

The invention discloses an aeronautical ice accretion identification method based on multi-source data, which solves the coverage blind area of a single data source (mode / satellite) through multi-source data fusion processing, improves the integrity of a three-dimensional space, and further establishes a scene classification foundation through cloud layer structure identification and accurate division of a cloud area / a precipitation area. Through membership function construction processing, a nonlinear relation between meteorological elements and icing is quantified, and a traditional threshold value method is replaced; furthermore, through physical scene classification processing, single-layer cloud / multi-layer cloud / freezing water freezing mechanisms are distinguished, and misjudgment is avoided; through initial index calculation, CTTmap is dynamically adjusted according to different scenes, and satellite detection deviation is corrected; finally, through dynamic index correction processing, vertical motion, supercooled water and a real-time report are introduced, and result self-adaptive optimization is achieved.

According to the typhoon disaster dynamic risk estimation method and system based on intelligent grid forecasting, meteorological data of an intelligent grid forecasting system with high refinement degree and good accuracy are adopted, intelligent grid forecasting data are corrected by fusing observation data, and data deviation is effectively reduced. The typhoon wind and rain comprehensive index can objectively reflect the typhoon composite disaster-inducing effect, and the typhoon wind and rain comprehensive index is based on the nature of a disaster-inducing mechanism, and the limitation of single-element evaluation is solved by dynamically fusing wind speed and rainfall data. The disaster-pregnant environment influence coefficient considering the dynamic influence of the terrain factors is constructed, the limitation of traditional fixed geographic parameters is broken through, and the risk assessment error caused by neglecting the dynamic nature of the disaster-pregnant environment in a traditional model is solved. A typhoon disaster risk assessment model based on index weight is designed, the risk assessment model focuses on disaster-causing risk, exposure degree and vulnerability key factors, the model structure is simplified, and the calculation efficiency is improved.

The invention discloses a spatio-temporal feature fused medium and long term rainfall prediction method, an adopted prediction model is a fusion prediction model combining an expansion causal convolutional neural network (DC-CNN) and a bidirectional long and short term memory (BiLSTM) network, and the fusion prediction model is used for rainfall prediction; the DC-CNN captures spatial information in an original time sequence and applies the spatial information to a subsequent prediction task; the BiLSTM effectively processes the time dependence of the sequence data, and models and predicts the time sequence. According to the DC-CNN-BiLSTM model, the precision and stability of rainfall prediction can be effectively improved through the mutual cooperation between the DCNN network and the BiLSTM network.

The invention belongs to the field of electric power, and discloses a downscaling method, device and equipment for a rainfall forecast field, and a storage medium, and the method comprises the steps: obtaining meteorological data, inputting the meteorological data into a fortune meteorological model, and enabling the fortune meteorological model to generate an initial forecast field based on the meteorological data; cutting the initial forecasting field to obtain an initial rainfall forecasting field of the target area, and inputting the initial rainfall forecasting field into a pre-trained downscaling model which comprises a shallow feature extraction module, a deep feature extraction module and a reconstruction module, a shallow feature extraction module extracts initial features from the initial rainfall forecast field based on a convolutional layer; the deep feature extraction module captures the spatial dependency relationship of the precipitation field from the shallow feature map through the residual block; the reconstruction module converts the deep feature map into a high-resolution downscaling precipitation field based on a pixel rearrangement operation. The spatial resolution and accuracy of rainfall forecast are improved through a downscaling model based on SwinIR.