378 results about "Precipitationshed" patented technology

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 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 provides an atmospheric precipitable water quantity inversion method and system based on multi-source satellite remote sensing data, and relates to the technical field of remote sensing data. After clear sky pixels are screened, radiation brightness temperature data, digital elevation model data and spatio-temporal feature coding data are processed through three feature extraction branches, obtained feature representations are spliced and input into a feature fusion network, a spatial attention module is introduced in the feature fusion stage, finally, a composite loss function is adopted for training, and the feature fusion network is constructed. And high-precision atmospheric precipitable water quantity inversion is realized. According to the method, the multi-source data characteristics are fully utilized, and the inversion precision and the space continuity are improved.

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 provides a watershed artificial precipitation enhancement operation effect evaluation method based on hydrological simulation, and belongs to the technical field of artificial influence weather, and the method comprises the steps: obtaining first data and second data; based on the first data, settling a rainfall-runoff process, selecting a preset hydrological model to carry out a drainage basin hydrological batch simulation test, calibrating hydrological parameters, and constructing a drainage basin hydrological simulation forecast model; based on the second data, calculating the natural precipitation of the non-operation area and the operation precipitation of the operation area, and constructing a natural precipitation-operation precipitation data sequence; based on the natural precipitation-operation precipitation data sequence, inputting the natural precipitation into the watershed hydrological simulation forecasting model to obtain runoff before precipitation enhancement operation, and inputting the operation precipitation into the watershed hydrological simulation forecasting model to obtain runoff after precipitation enhancement operation; and based on the runoff before the rainfall enhancement operation and the runoff after the rainfall enhancement operation, carrying out quantitative evaluation on the artificial rainfall enhancement operation effect of the drainage basin. Scientific quantitative evaluation of the artificial precipitation enhancement operation effect of the watershed is realized.

The invention discloses a short temporary rainfall intensity prediction and identification method based on space-time composite attention, and the method comprises the following steps: obtaining an IMERG satellite rainfall data set, and carrying out the data construction and marking of a target region; establishing a space-time composite attention network, accessing an MFGA module and a TSMA module layer by layer, and performing non-negative activation on output to ensure physical interpretability; proposing a C-DWABP loss function, performing direction asymmetrical penalty aiming at a pixel-level prediction error, and introducing a grading weight mapped according to a real rainfall intensity grade at the same time; based on the output, intensity classification is carried out through a microthresholding ordered layer, and learnable threshold stability training is set; generating a forecast product, and obtaining an hour-by-hour precipitation grid in future 1-6 hours and a corresponding intensity identification result; according to the method, the precision of short temporary rainfall intensity prediction is improved, the false alarm rate is reduced, and a heavy rainfall event is effectively identified.

The invention belongs to the technical field of ecological information, and particularly relates to a Qinghai-Tibet Plateau land-gas coupling strength prediction method and system based on a CMIP6 model and emergence constraints. The method comprises the following steps: collecting monthly total precipitation and soil humidity data of a historical period and a future period in nine earth system models in a CMIP6 model, and constructing a data set; performing data preprocessing on the data set through spatial resolution unification and multi-source data fusion; constructing an emergence constraint model based on the preprocessed data; and calculating a land-gas coupling strength index according to a coupling measurement method based on the emergence constraint model. According to the method, by means of emerging constraint, the uncertainty of the model is reduced, the standard deviation of the land-gas coupling strength after constraint is reduced by 65.12%, the prediction precision of the space-time trend is improved, and the problems that a CMIP6 model is underestimated to the northeast and southwest of the Qinghai-Tibet Plateau and is overestimated to the west and northwest of the Qinghai-Tibet Plateau are solved.

The invention discloses an irrigation index prediction method based on meteorological data and field moisture capacity, and relates to the technical field of intelligent agriculture, and the method comprises the steps: collecting real-time meteorological data, real-time soil volumetric water content data, soil matrix potential data and future precipitation forecast data, and carrying out quality control and time alignment processing to obtain a multi-source data set; the method comprises the following steps: calculating evapotranspiration of a reference crop according to real-time meteorological data, obtaining actual water demand of the crop in combination with a crop coefficient, calculating a moisture stress coefficient according to real-time soil volumetric water content data and a field moisture capacity static parameter value, and obtaining a basic irrigation demand index in combination with future precipitation forecast data. According to the method, the evapotranspiration amount is separated by adopting the Shuttleworth-Wallace model, the irrigation index integrating the crop evapotranspiration amount, the water deficit amount and the effective precipitation amount is generated on the basis of multi-period rolling water balance calculation and risk decision rules, and online calibration of soil parameters and optimization of irrigation decision are achieved.

The invention relates to the technical field of civil engineering, and discloses a road subgrade settlement prediction method and system based on multi-source data. The method comprises the following steps: acquiring and correcting a precipitation sequence and roadbed soil moisture distribution data; analyzing rainfall accumulation characteristics and carrying out penetration risk classification, thereby extracting a penetration depth estimation value, and utilizing finite element analysis to simulate a soil body saturation state change trend; quantifying a soil body supporting capacity reduction range, constructing and calibrating a settlement initiation probability calculation model, and obtaining settlement probability distribution; identifying a high-risk evolution area, integrating path weights and accumulated influence factors, and generating a settlement prediction interval subjected to multi-dimensional verification; and fusing the prediction interval and actual roadbed structure data through a geographic information system to generate a comprehensive evaluation report. According to the method, the whole-process accurate evaluation of the roadbed settlement risk from multi-source perception, mechanism simulation to space prediction is realized, and the accuracy and timeliness of the roadbed settlement risk prediction and the pertinence of engineering maintenance are improved.

The invention is suitable for the technical field of rainfall forecast correction, and provides a regional short-term rainfall quantitative forecast machine learning correction method integrated with weather system information, and the method comprises the steps: determining an initial forecast factor based on meteorological elements in an ECMWF mode, the meteorological elements comprise a precipitation field, ground transformation, convection effective potential energy, UV wind fields of 500hPa, 850hPa and 925hPa, relative humidity, temperature and vertical speed; taking the dichotomy labels corresponding to the 500hPa slot line and the tangent line between 850hPa and 925hPa as newly added forecast factors, and constructing a four-dimensional training set according to the initial forecast factors and the newly added forecast factors; converting the four-dimensional training set into a three-dimensional training set; training a random forest regression model through the three-dimensional training set, and outputting a rainfall forecast field within a preset time; according to the CMASH3 mode rainfall forecast data and a preset judgment logic, dynamically correcting the rainfall forecast field within a preset time, and generating a target rainfall forecast product; and the accuracy of heavy rainfall forecasting is effectively improved.

The invention relates to the technical field of meteorology and hydrology, in particular to a rainfall space reconstruction method, system and device based on terrain and meteorological multi-factor fusion driving and a medium, and the method comprises the steps: obtaining space terrain factors and meteorological observation data of a target area, and employing a BP neural network to progressively interpolate missing measurement values of meteorological driving variables in a layered manner; setting a missing detection elimination rule based on a wet season and a dry season to process precipitation data; constructing a 14-dimensional high-dimensional input feature system fusing a space terrain factor, a time sequence factor and a meteorological driving factor; nonlinear models such as an XGBoost model, a BP neural network model or an LSTM model are used for training, and finally the monthly scale precipitation space reconstruction of the grid is achieved. According to the method, the problems that a traditional interpolation method is poor in adaptability in a complex terrain area and insufficient in multi-factor driving relation description are effectively solved, and the precision and the physical consistency of precipitation space distribution are remarkably improved.

The invention discloses a rainstorm ground waterlogging prediction method, device, equipment and product, and relates to the technical field of urban waterlogging prediction.The rainstorm ground waterlogging prediction method comprises the steps that ephemeris and ground observation station data are obtained, the atmospheric moisture delay amount and the high-altitude water vapor conversion factor are calculated respectively, the historical water vapor content is calculated, and the future atmospheric precipitable water amount is predicted; rainfall time distribution data are obtained through rainstorm intensity decomposition; calculating the rainwater overflow amount of the catchment area in combination with the water discharge amount time distribution data of the urban drainage pipe network; and iterative calculation is carried out by using a digital elevation model grid to obtain the waterlogging depth, and waterlogging early warning information is sent out. By constraining the total rainfall amount, the rainfall amount can be effectively constrained by predicting the precipitable water amount based on the satellite ephemeris; the underground pipe network drainage is restrained, and a water flow condition in a pipe channel is simulated by adopting an SWMM model; and finally, the waterlogging accumulated water volume is calculated, constraint verification is carried out on each link of urban waterlogging, and relatively high precision and relatively long timeliness are ensured.

The invention discloses an electric power facility disaster early warning method and system for tower level identification, and particularly relates to the field of risk assessment of electric power facility disaster early warning, and the method comprises the steps: respectively collecting the data of wind speed, temperature, humidity, precipitation and icing thickness in the range of a target tower and an adjacent tower; and synchronously collecting vibration data and current fluctuation data of the corresponding tower. Point-by-point difference and cross comparison is carried out on various monitoring data, residual changes are extracted, a difference value chain between towers is established, a disaster risk value is calculated step by step in combination with the phase coupling condition between monitoring parameters, and a risk assessment map and a disaster critical state are generated when the risk value reaches a critical level. Therefore, the real risk under the simultaneous action of multiple disaster factors is reflected, the problem that the dangerous synchronous effect is covered as a medium risk by the existing method is avoided, and relatively timely and reliable risk assessment and early warning are realized.

The invention provides a hydrological big data real-time monitoring method and device based on quantum computing and a medium, and belongs to the technical field of hydrological data processing. Hydrological data and change data of a surface water body are collected; determining river course roughness and infiltration coefficient parameters as a hydrological change actual data set by using a quantum annealing process; predicting hydrological change data in the drainage basin based on a random forest regression model; performing comparative analysis on the hydrological change data and a prediction result based on the real-time rainfall data to generate a parameter adjustment instruction; setting a water level change threshold value and a precipitation threshold value; and receiving the precipitation in real time, triggering a historical similar flood event case library retrieval function on the basis of a threshold exceeding condition, and outputting an early warning response record corresponding to a historical event. A quantum walking algorithm is used for simulating flood diffusion, a submerging depth thermodynamic diagram is generated in combination with a digital elevation model, the flood submerging range and depth distribution are rapidly and accurately displayed, and visual and visual support is provided.

The invention relates to a rainfall observation method and device, a computer system and a medium, and solves the problem of high-reliability observation of regional rainfall. The method comprises the following steps: firstly, adopting reanalysis data and earth system mode output data to construct a first deep learning model of satellite inversion rainfall so as to reconstruct a lattice long-series rainfall data set; then, taking the rainfall attenuation information of the historical period as input, obtaining a rainfall simulation series of the corresponding historical period through different rainfall attenuation and rainfall intensity models, determining regional rainfall under the different rainfall attenuation and rainfall intensity models through a weighted link method, and preferably selecting an optimal rainfall attenuation and rainfall intensity model through long-series lattice rainfall data of the historical period; furthermore, a second deep learning model is constructed by adopting satellite inversion data and rainfall data inverted by a rainfall attenuation and rainfall intensity model, real-time correction of regional precipitation is realized, finally, real-time rainfall information of the region is deduced by adopting the optimal rainfall attenuation and rainfall intensity model and taking a real-time mobile signal as input, and the regional average precipitation corrected in real time is obtained.

The invention discloses a foundation space ionosphere and troposphere integrated joint detection method and device, and belongs to the technical field of satellite navigation, and the method comprises the steps: detecting the vertical total electron content of an ionosphere: extracting the inclined total electron content of the ionosphere at an ionosphere puncture point, and converting the inclined total electron content into the vertical total electron content of the ionosphere; detecting a foundation Beidou ionosphere disturbance index; and detecting an ionosphere phase scintillation index, a troposphere zenith total delay, a troposphere precipitable amount and an ionosphere amplitude scintillation index, and outputting ground-based Beidou space ionosphere and troposphere integrated joint detection parameters. The method effectively improves the reliability, robustness and meteorological perception capability of a navigation positioning system in a complex atmospheric environment, and is especially suitable for special environmental conditions such as severe convection weather, typhoon landing, violent disturbance of an ionized layer and the like.

The invention provides a flood disaster multi-source information monitoring method and system and electronic equipment, and relates to the technical field of data processing. The method comprises the following steps: determining a precipitation area and accumulated precipitation according to ground observation precipitation data; according to the satellite remote sensing data and the digital elevation model, identifying cities and towns in the rainfall area, and determining a confluence area in the cities and towns and the real-time area and the initial ponding depth of the confluence area; according to the digital elevation model, the rainfall area is divided according to the terrain, and a plurality of monitoring areas and terrain confluence factors of the monitoring areas are obtained; when a preset condition is met, updating the real-time data, and inputting the real-time data and the topographic confluence factor into a water depth prediction model to obtain a predicted ponding depth; and according to the predicted ponding depth and the preset depth, monitoring and early warning are carried out on the ponding condition of the monitoring area. And the predicted ponding depth can be continuously obtained without depending on satellite remote sensing data, so that the monitoring can be continuously carried out in time.

The invention provides an urban meteorological collaborative analysis method based on multi-source data fusion, and the method employs a multi-source data fusion mechanism to combine with rainfall data from GNSS inversion, meteorological data of a ground meteorological station and static geographic information, such as altitude, terrain gradient and the like, and achieves the collaborative analysis of urban meteorological data through the fusion of multi-source data. According to the method, the relation between different meteorological variables can be comprehensively and accurately reflected, namely, the capacity of capturing the complex cooperative relation between the meteorological variables is improved, the precision and response speed of urban meteorological prediction are improved, then extreme weather events such as short and temporary heavy rainfall can be accurately predicted, an early warning signal is sent out in time, and the early warning effect is improved. And important support is provided for urban management and disaster prevention and control.

The invention belongs to the technical field of remote sensing hydrology, and particularly discloses a multi-source rainfall depth space-time fusion method and device, electronic equipment and a storage medium. The method comprises the steps of performing data preprocessing on multi-source rainfall data of a to-be-measured area, and determining multi-source rainfall data of a target temporal-spatial resolution; inputting the multi-source rainfall data with the target temporal-spatial resolution into a rainfall classification regression model to obtain a rainfall prediction result of the to-be-detected area output by the rainfall classification regression model; the rainfall classification regression model is constructed based on a deep learning model and a machine learning model, is obtained through training according to a multi-source rainfall data sample and a rainfall data label corresponding to the multi-source rainfall data sample, and is used for identifying each rainfall position in a to-be-detected region based on a fusion feature obtained through feature extraction and fusion of the multi-source rainfall data. And the precipitation amount of each precipitation position is predicted. According to the invention, the method can effectively improve the deep space-time fusion effect of the multi-source rainfall data, and achieves the high-precision and high-temporal-spatial-resolution rainfall prediction.

The invention provides a method, device and equipment for predicting the water level of an urban inland inundation point and a medium. The method comprises the steps of obtaining position information of the urban inland inundation point and water level measurement data of a past time period; based on the position information, grid meteorological data of the waterlogging associated spatial vector in a target time period are determined, the target time period comprises a past time period before the current moment and a prediction time period after the current moment, and the waterlogging associated spatial vector comprises at least one waterlogging associated grid; the precipitation amount in the grid meteorological data is extracted, and a space-time precipitation vector of the waterlogging associated space vector is generated; and obtaining water level prediction information of the urban inland inundation point in the prediction time period by using the inland inundation prediction model based on the space-time rainfall vector and the water level measurement data. In this way, the future condition of the water level of the urban inland inundation point can be accurately predicted.

The invention discloses a quantitative rainfall estimation method based on a Hurdle-IMDL framework. The method comprises the following steps: acquiring historical rainfall measurement data and meteorological satellite observation data; constructing a biased quantitative rainfall estimation probability model based on a Hurdle model, correcting a biased rainfall estimation probability sub-model according to an IMDL method, substituting into empirical distribution to construct an empirical quantitative rainfall estimation probability model, and deriving a negative logarithm likelihood function of the empirical quantitative rainfall estimation probability model; constructing an AI model, and optimizing the AI model by taking a negative log-likelihood function as a loss function; and inputting meteorological satellite observation data of a to-be-inverted region into the trained AI model to obtain an estimated value of a parameter of the empirical quantitative precipitation estimation probability model, and estimating the precipitation according to conditional expectation. According to the invention, the Hurdle model is used to solve the zero expansion problem, the IMDL learning method is used to cope with the long tail problem, and the inversion accuracy of extreme rainfall is improved.

The invention discloses a refined remote sensing atmospheric water vapor inversion method based on a GNSS and a Transform. The method comprises the following steps: acquiring OLCI remote sensing data, ERA5 meteorological data and GNSS-PWV data of a target area; performing quality control on the OLCI remote sensing data, and screening effective observation data; performing space-time registration on the OLCI remote sensing data, the ERA5 meteorological data and the GNSS-PWV data, and constructing a multi-dimensional feature vector; inputting the multi-dimensional feature vector into a Transform model for training, and learning a coupling relationship between features through a self-attention mechanism; and outputting an atmospheric precipitable water quantity inversion result based on the trained Transform model. According to the invention, the precision and spatial resolution of atmospheric water vapor detection are improved.

The invention discloses a rainfall short-term and imminent forecasting method and device based on GNSS-PWV and numerical weather forecast fusion, and the method comprises the steps: calculating the real-time atmospheric precipitable water amount measured through GNSS signal delay, and obtaining the meteorological observation data and numerical weather forecast data of a base station; respectively constructing a physical forecasting model and a machine learning forecasting model through the atmospheric precipitable water amount, the variable quantity of the atmospheric precipitable water amount, the base station meteorological observation data and the numerical weather forecasting data, and respectively forecasting the precipitation probability and the precipitation amount by utilizing the physical forecasting model and the machine learning forecasting model; and a hybrid forecasting model is constructed, the model fuses the precipitation probability and precipitation forecast by the physical forecasting model and the machine learning forecasting model, and the final precipitation probability and final precipitation are obtained. According to the method, on the basis of traditional numerical weather forecast, time-varying information of GNSS-PWV is intelligently fused, and adaptive optimization is realized by dynamically adjusting the weights of a physical model and a data driving model, so that the precision and reliability of short and temporary rainfall forecast are remarkably improved.

The invention discloses a short-time approaching rainfall prediction method based on multi-source fusion data and an MIM network, and the method comprises the steps: carrying out the space-time matching of radar observation data, Chinese land surface data assimilation system data and site observation data, carrying out the preprocessing of the matched data, including feature factor extraction, missing value processing and the like, building a deep learning model, and carrying out the prediction of the short-time approaching rainfall. The model is trained, and a multi-source fusion rainfall inversion result is output based on real-time radar data; furthermore, errors of a falling area and rainfall intensity of intelligent grid rainfall forecast are identified, a phase correction technology is utilized to correct a position error of an intelligent grid forecast rainfall zone, meanwhile, precision evaluation is performed on a prediction effect of the deep learning model according to the rainfall amount of short-time nowcasting, and intelligent prediction of short-time nowcasting is realized.

The invention provides a high-speed rail operation environment safety intelligent sensing early warning method and system, and the method comprises the steps: carrying out the time-space alignment of the wind speed, wind direction and rainfall data issued by a meteorological part and the data collected by a device at a preset position of a railway perimeter based on reverse distance weight interpolation; based on the pre-trained strong wind prediction model and precipitation prediction model, outputting kilometer-level and hour-level refined wind and rain prediction results; the millimeter-wave radar, the laser radar and the high-definition video are jointly calibrated in a unified world coordinate system, personnel and foreign matters are detected by a target detection model, and a second-level intrusion behavior recognition result is realized. By means of remote sensing and aircraft inspection, hidden danger objects, external environment abnormity and infrastructure abnormity are efficiently recognized. And in combination with the multi-factor detection result related to the risk, efficient, automatic and accurate analysis and early warning are performed according to the preset grading early warning rule, so that the operation risk of the high-speed rail is remarkably reduced.

The invention relates to the technical field of vegetation recovery, and discloses a multi-condition adaptation method for vegetation recovery of power grid engineering in hilly and mountainous areas, which realizes accurate adaptation of a vegetation recovery scheme and different environmental conditions by carefully analyzing and partitioning various conditions such as gradient, soil layer thickness, precipitation, illumination intensity and the like. The success rate and efficiency of vegetation recovery are obviously improved; suitable plants are selected and combined with a scientific soil improvement and planting process, diversified vegetation communities are constructed, water and soil loss is effectively reduced, biological diversity is increased, and balance and stability of an ecological system are promoted; an intelligent irrigation system and a dynamic monitoring system are adopted, reasonable utilization of water resources and scientific management of the vegetation recovery process are achieved, labor cost and resource waste are reduced, and long-term sustainability of vegetation recovery is guaranteed; the method is suitable for vegetation restoration of different types of power grid projects in hilly and mountainous areas, has high universality and popularization value, and can provide effective reference for ecological restoration of similar regions.

The invention discloses a multi-source rainfall data fusion method for a regional landslide early warning threshold. The method comprises the following steps: improving the spatial resolution of long-sequence raster data by adopting a statistical downscaling technology; according to the landslide position, selecting an optimal neighborhood method or a Thiessen polygon method to generate a site and grid representative precipitation sequence pair; establishing a dry day / wet day discrimination model based on the characteristics of the rainfall event triggering the landslide; correcting daily precipitation based on a quantile mapping method; and constructing a regional rainfall landslide threshold curve and performing precision test. According to the method, the defects of low precision of long-sequence grid data, short site data time sequence and space-time difference between a site rainfall observation position and a landslide occurrence position can be improved, and an effective means for establishing a rainfall type landslide early warning system is provided for a data lacking area. Meanwhile, the method can be migrated to rainfall type landslide risk assessment in a global future climate situation mode, and scientific support is provided for constructing a climate adaptation type disaster reduction system.

The invention relates to a rainfall prediction map convolution method based on graph reconstruction and spatial self-attention, and belongs to the technical field of crossing of artificial intelligence and urban meteorological early warning technologies. The method and the device are used for solving the problems of excessive smoothness and insufficient spatial dependency capture caused by dependence on a geographic adjacency relation in precipitation prediction of a traditional graph convolutional network. A sparse graph structure reflecting real meteorological association is constructed by calculating a Pearson's correlation coefficient of Beidou multi-base-station meteorological time series data, and a traditional geographic adjacency matrix is replaced; designing a dynamic space self-attention mechanism, fusing the static association graph and a dynamic attention weight, and realizing adaptive aggregation of long-range dependence between nodes; and in combination with multilevel feature propagation of graph convolution and an attention matrix, the modeling capability of a heterogeneous meteorological spatial mode is improved. According to the method, the accuracy of short temporary rainfall prediction is remarkably improved, the method is particularly suitable for association mining of base stations which are far in geographic distance but similar in meteorological feature, and a high-robustness spatial feature extraction scheme is provided for a meteorological early warning system.

The invention relates to the technical field of meteorological remote sensing, in particular to a three-dimensional wind speed and wind direction detection method and system based on GNSS tomography inversion, and the method comprises the steps: building a three-dimensional water vapor density tomography inversion model through obtaining observation data and meteorological observation data of a plurality of GNSS observation stations, obtaining water vapor density distribution of different height layers, and obtaining a three-dimensional wind speed and wind direction detection model; further obtaining the PWV (atmospheric precipitable water) of each height layer; a three-dimensional wind field inversion algorithm is established by utilizing a coupling relation between water vapor transportation and a wind field and combining a spatial position of a GNSS observation station and spatial and temporal variation characteristics of PWV of different height layers, so that quantitative estimation of wind speeds and wind directions of the different height layers is realized, and three-dimensional wind speed and wind direction quantitative detection based on GNSS tomography inversion can be realized. And important observation data support is provided for meteorological monitoring and numerical weather forecast.

The invention discloses a forest fire danger early warning system and method based on meteorological and vegetation data analysis, and relates to the technical field of fire risk prediction and control. According to the forest fire danger early warning system and method based on meteorological and vegetation data analysis, fine grid division is carried out on a target forest area through a high-resolution DEM and a multispectral or hyperspectral image, and vegetation type identification is carried out on each monitoring subunit; calculating a wet-dry cycle index WDI, a monsoon effect index MFI and a dry thunderstorm risk factor DRF by combining hourly wind speed, wind direction, relative humidity, precipitation and vapor pressure difference meteorological data; through extracting canopy height, canopy density, under-forest shrub and grass layer thickness and high VOC tree species coverage rate, fuel continuity coefficient FCI and volatile matter flammability index VEI are calculated, and accurate quantification of continuity and flammability of vertical ladder fuel and horizontal canopy is realized. And a comprehensive fire danger index FFI is constructed and subjected to hierarchical management after judgment, so that the dynamism, the hierarchical property and the pertinence of fire danger early warning are realized, and the forest fire danger prevention and control precision and the patrol resource utilization efficiency are improved.