328results about "Weather condition prediction" patented technology

To provide a flood state estimation device, a flood state estimation method, a system, and a program that can estimate in real time, from a posted image, a flood state of an area including a photographed place.SOLUTION: A flood state is estimated by using a flood state estimation device 1 having: an image collection unit 11 that collects posted flood images through the Internet; a flood level specification unit 12 that specifies a flood level in the posted flood images by using a learning model that is built with a plurality of data sets as training data which are formed of flood images including a water surface and reference objects to be a reference of flood depth estimation and flood level data of the flood images; a photographed place specification unit 13 that specifies a photographed place of the posted flood images; a related data acquisition unit 14 that acquires photographed places of the posted flood images, and topographic data and precipitation data of the periphery of the place; and a flood state estimation unit 15 that estimates a flood state of an arbitrary area including the photographed places of the posted flood images from the flood level of the posted flood images and the topographic data and precipitation data.SELECTED DRAWING: Figure 1

The application discloses a self-adaptive flood forecasting method, a terminal and a storage medium. The method comprises the following steps: generating a high signal-to-noise ratio local hydrological real-time data stream through adaptive sampling and a double-channel differential quantization technology; receiving an upstream input data stream, performing flood evolution calculation based on a viscoelastic dynamics model and fusing a dynamically identified input delay to obtain an original prediction value; for model parameters, a confidence ellipse is constructed based on ridge regression, the residual of real-time data and the prediction value is compared through statistical projection, the measurement noise and the river physical drift are intelligently distinguished, and the parameters are updated smoothly; finally, the original prediction value is corrected by solving a convex optimization problem subject to safety constraints, and a physically credible final prediction value is output. The corresponding terminal comprises corresponding modules for realizing the above steps. The application realizes high-precision, self-adaptive and intrinsically safe flood forecasting.

The application discloses a rice tillering prediction method and device and a machine readable storage medium, and relates to the technical field of crop planting. The method comprises the following steps: acquiring forecast weather information after rice transplanting, determining first micro-environment weather information based on the forecast weather information and a preset green return period forecast weather-micro-environment weather corresponding relationship, and determining a prediction time when the rice enters a tillering period based on the first micro-environment weather information and a tillering starting weather threshold. Second micro-environment weather information is determined based on the forecast weather information, the tillering period forecast weather-micro-environment weather corresponding relationship and the prediction time when the rice enters the tillering period, effective tillering prediction time range and ineffective tillering prediction starting time of the rice are determined based on the second micro-environment weather information and preset effective weather data. Through the prediction of effective tillering and ineffective tillering of the rice, reference bases can be provided for agricultural operations such as application of tillering fertilizer, field exposure and inhibition of ineffective tillering, so that the yield of the rice is improved.

By changing the operating modes of weather observation sensors, including weather radar, according to the weather phenomenon being predicted, weather phenomena can be predicted with higher accuracy than before. [Solution] The weather forecasting device 3 is a variable-mode weather observation sensor that observes precipitation data and wind direction and wind speed data in an observation range, which is a spatial range to be observed. It includes a weather forecasting unit 5 that receives weather observation data, including precipitation data and wind direction and wind speed data, observed by a weather observation sensor including a weather radar 1 that is positioned so that the observation range encompasses a predetermined weather forecast area, and predicts the weather in the weather forecast area for a predetermined future forecast time range and outputs weather forecast data including precipitation; a sensor data storage unit 4 that stores the installation position, observation range and observation accuracy of each weather observation sensor; and a sensor control unit 6 that receives weather forecast data and controls the weather observation sensor, including changing the operating mode of the variable-mode weather observation sensor.

The application belongs to the technical field of deep learning and meteorological prediction, and particularly relates to a daily precipitation grade classification method based on GA-XGBoost. The method realizes autonomous learning of time sequence characteristics of precipitation, reduces the non-stability of precipitation data, and accurately classifies and predicts daily precipitation. The method comprises the following steps: preprocessing original precipitation data, including data screening, data cleaning, data classification and smote method balanced dataset; establishing an XGBoost model and initializing hyperparameters; using a genetic algorithm to optimize network parameters; inputting each subsequence into the model for training and prediction and comparing and analyzing the results.

The present application belongs to the technical field of hydrological forecasting, and specifically relates to a multi-source adaptive transfer learning data-scarce watershed daily runoff prediction method, which comprises the following steps: selecting multiple source watersheds with long sequence observation data, independently training a basic prediction model based on a Transformer architecture by using historical hydrological and meteorological data of the source watersheds, and constructing a source watershed prior knowledge base containing diversified production and confluence mechanisms; adopting a parameter freezing and differential fine-tuning strategy, transferring the source watershed basic model to a data-scarce target watershed, fine-tuning the output layer by using limited measured daily runoff samples of the target watershed on the basis of keeping the parameters of the Transformer feature extraction layer fixed, and constructing multiple transfer branch models; establishing a dynamic attention module to realize real-time sensing of the evolution of meteorological environmental elements of the target watershed and self-adaptive calculation of the dynamic confidence weight of each transfer branch model at the current time; and based on the weight, weighting and integrating the preliminary prediction values of each branch model to obtain the final daily runoff prediction result of the target watershed.

This invention relates to the field of resource scheduling technology, specifically a multi-agent-based collaborative scheduling method for emergency communication resources. This invention dynamically calculates the link capacity limit based on the current rainfall intensity by querying a rain attenuation zone carrying capacity table; driven by the water diffusion rate, and combined with base station geographical distribution parameters and population density distribution parameters, it predicts the service supply and demand gap and performs pre-allocation of links to be migrated; it calculates the expected signal-to-noise ratio (SNR) of candidate frequency bands based on the rain attenuation coefficient of the operating frequency band, and performs rain attenuation availability screening and interference conflict detection; simultaneously, it establishes an error record based on the deviation between the measured SNR and the theoretical value, enabling adaptive correction in subsequent scheduling processes. This method can improve the accuracy of emergency communication resource scheduling, link stability, and critical service assurance capabilities in disaster environments.

The application discloses a strong wind disaster monitoring and early warning method based on Beidou GNSS-R, comprising the following steps: 1, a UAV carrying a GNSS-R receiving device is located at the periphery of a heavy rainfall area to carry out wind speed detection operation on the water surface inside the heavy rainfall area, and data solving is performed on the obtained satellite observation; 2, an LSTM wind speed inversion model fusing double-factor decoupling is constructed, the received satellite observation and the solving result are inputted and error correction is performed, the water surface wind speed of the reflection point area is inversely predicted, and the future time step wind speed prediction is obtained based on the past time step wind speed inversion result; 3, a boundary adaptive grid and a dynamically updated Kriging interpolation model are established, the wind speed data of a missing area of a specific signal reflection point is obtained, and the wind speed data of the missing area of the reflection point is supplemented; and 4, a double-effect strong wind early warning strategy of wind speed time sequence extrapolation and inversion stability cooperation is constructed, and it is judged whether strong wind will occur and early warning is performed.

This application discloses a multi-scale forecasting method and system for polar sea ice, relating to the field of climate forecasting technology. The method includes: acquiring raw sea ice concentration observation data; preprocessing the raw sea ice concentration observation data to obtain preprocessed data; extracting multi-scale spatial features from the preprocessed data to obtain feature tokens at multiple scales; aligning the feature tokens at multiple scales by feature dimensions to obtain aligned features; performing cross-scale attention fusion on the aligned features to obtain cross-scale fused features; performing intra-scale modeling optimization on the cross-scale fused features to obtain intra-scale optimized features; and performing linear mapping restoration and spatial decoding on the intra-scale optimized features to obtain sea ice concentration forecast results. The sea ice concentration forecast results include future daily, weekly, and monthly sea ice concentration forecasts. This application can solve the problems of single-scale modeling and information silos in existing technologies.

This invention discloses a drought early warning method based on energy flux, causal relationship analysis, and machine learning. The method includes the following steps: S1, acquiring energy flux and drought indicators, determining the optimal lag time through causal reasoning, and constructing a multi-order lag feature set; S2, establishing a tree model, using regression / kernel methods and a time series model candidate set, optimizing hyperparameters through particle swarm optimization, integrating two layers in a stacked manner, adaptively optimizing the performance of comprehensive regression and event recognition, and outputting a predicted sequence; S3, setting multi-level early warning rules according to drought thresholds, mapping drought levels, and evaluating effectiveness through statistical precision and recall; S4, calculating contribution using an additive feature attribution algorithm, identifying nonlinear thresholds to form sensitivity analysis, and improving interpretability. This invention achieves a 7-11 month early warning prediction of drought based on energy flux, with a drought early warning recall rate of 66.67%-75.86%, significantly improving the accuracy and interpretability of drought early warning.

The application belongs to the field of sub-seasonal climate prediction, and provides a sub-seasonal climate prediction method and system based on the combination of dynamic model downscaling and machine learning downscaling, which comprises the following steps: S1, generating initial field and model boundary field information required for dynamic downscaling based on global climate model output data; S2, driving regional climate model to perform dynamic downscaling by using the initial field and model boundary field information; S3, generating input field required for machine learning downscaling based on the output circulation field information of the regional climate model; S4, performing machine learning downscaling correction optimization on the output circulation field of dynamic downscaling based on a convolution model; S5, performing machine learning super-resolution based on the output data of machine learning downscaling correction; and S6, generating sub-seasonal prediction information of double downscaling of dynamic model and machine learning. The application utilizes the complementary advantages of dynamic downscaling and deep learning downscaling, improves the sub-seasonal prediction skill, and copes with new challenges brought by climate change.

The application discloses a northwest Pacific tropical cyclone sub-season prediction method and system, and relates to the technical field of atmospheric science. The method comprises the following steps: extracting the ACE distance average of each type of TC in each time window from climatological data and taking the ACE distance average as a prediction label of each time window; taking a plurality of large-scale environmental fields used for climatological reanalysis as potential prediction factors, and obtaining a plurality of components of each potential prediction factor; constructing a single-variable prediction model for each component of each type of TC, pre-training and evaluating each single-variable prediction model through the components and the prediction label, and selecting the optimal component combination; constructing a multi-variable prediction model for each type of TC, training the multi-variable prediction model through the component combination and the prediction label, and deploying the prediction after the training; and generating an ACE high-resolution spatial probability map of a target prediction period of the northwest Pacific according to a prediction result. The application can realize accurate tropical cyclone sub-season prediction.

The application discloses an airborne radar downburst optimized detection method and belongs to the technical field of radar signal processing. An airborne Doppler radar is used to emit a radar waveform to a possible wind shear dangerous area in front of a route, and wind speed estimation in a transmission direction is obtained by analyzing radar echo IQ data. The application sets a pitch angle of radar scanning according to a take-off or landing stage of an airplane. After receiving the IQ signal, frequency domain correction is performed, data is preprocessed according to spectrum width information, and a wild value area is eliminated. After the preprocessing is completed, a frequency domain clutter suppression algorithm is used to suppress a ground clutter area near zero frequency, and then wind shear wind speed estimation is performed. The application proposes a novel vertical wind speed estimation model, establishes a connection between a downburst core area range and a vertical wind speed gradient, forms a detection and sensing capability for a three-dimensional area of the downburst, and proposes an airplane scanning strategy for optimizing the model.

A device tracking method, a device, and a vehicle are provided, relating to the field of tracking technologies, including: determining location data of a first device, wherein the location data includes satellite location data and / or network location data; and sharing the location data with a second device. The distance between the first device and the second device is less than a preset distance.

The present application relates to the technical field of irradiance prediction, and discloses a short-term irradiance AI prediction system and method combined with meteorological satellite data. The method collects a historical meteorological satellite remote sensing data sequence and a ground irradiance monitoring data sequence of a target area to form a training sample set. Multi-scale spatio-temporal feature extraction is performed on the historical meteorological satellite remote sensing data sequence to generate a three-dimensional meteorological feature tensor. The ground irradiance monitoring data sequence and the three-dimensional meteorological feature tensor are spatio-temporally aligned and matched to establish a meteorological-irradiance correlation feature matrix. A deep spatio-temporal fusion network model is then constructed, and the meteorological-irradiance correlation feature matrix is input into the model for end-to-end training to obtain a trained irradiance prediction model. Real-time meteorological satellite remote sensing data flow is acquired, real-time three-dimensional meteorological feature tensors are extracted and input into the trained model, and an irradiance prediction value sequence within a preset time window in the future is output.

This invention discloses a method for constructing a local short-term precipitation forecast model based on a neural network, relating to the field of precipitation prediction technology. By utilizing radar echo sequences, multi-source environmental field data, and surface precipitation observation data of the target area, a spatiotemporally consistent training sample pair is constructed. A two-branch neural network model is established, including an encoder-evolution branch, a modulation branch, and a gated fusion decoder. With the goal of minimizing the composite loss function, the neural network model is trained using the training samples to obtain a deterministic forecast model. Using the output of the deterministic forecast model and the current environmental field as conditions, a conditional generation network is established to generate several probabilistic precipitation forecast fields, forming a probabilistic forecast set for quantifying forecast uncertainty. The trained deterministic forecast model and the conditional generation network are integrated and deployed, inputting real-time meteorological data to output deterministic and probabilistic local short-term precipitation forecasts.

This invention discloses a radar echo extrapolation method based on test-time training, proposing the REE-TTT model. This model introduces a spatiotemporal test-time training module, dynamically adjusting parameters based on the context of the input radar sequence during inference, achieving robust adaptation to non-stationary meteorological distributions. By designing a task-specific attention projection scheme, it replaces the linear projection in standard test-time training with a differentiated projection composed of temporal and motion attention, significantly enhancing the ability to represent the dynamic spatiotemporal evolution characteristics of precipitation systems. Simultaneously, the model combines weighted loss for strong echo regions and focal frequency loss constraining high-frequency structures to improve forecast accuracy and detail fidelity. This invention significantly outperforms existing mainstream models in both prediction accuracy and cross-regional zero-sample generalization ability, and is particularly suitable for short-term forecasts of out-of-data distributions or extreme precipitation scenarios.

The present application relates to the technical field of precipitation forecast, solves the problem that the prior art is prone to underestimate the peak value of precipitation or produce false alarm under strong convective weather, and particularly relates to a short-impending precipitation forecast method fusing GNSS and water conservancy rain measurement radar, GNSS observation data and water conservancy rain measurement radar base data in a monitoring area are acquired, pretreated, corresponding atmospheric precipitable water distribution field and radar reflectivity factor distribution field are generated, based on a preset time sliding window, time sequence characteristics of the atmospheric precipitable water distribution field and the radar reflectivity factor distribution field are extracted, and the two are superimposed in channel dimension to construct a multi-channel spatio-temporal fusion input tensor. The present application overcomes the defect that the traditional extrapolation method rapidly decays with the prolongation of the forecast time, significantly improves the prediction accuracy of the rainstorm center intensity and the falling area, reduces the missed report and underestimation of the precipitation event, and solves the problem of low prediction accuracy of the traditional linear extrapolation algorithm under strong convective weather.

This application provides a method and system for intelligent scheduling of cascade hydropower stations based on basin-level early warning, belonging to the field of optimization scheduling technology. The method includes: building a multi-process coupled model of the basin and outputting real-time forecast results; constructing a point-line-area level early warning map; constructing marginal flood control risk functions and marginal power generation benefit functions for each reservoir based on the point-line-area level early warning map and the current operating data of each reservoir; constructing an objective function based on the marginal flood control risk function and marginal power generation benefit function with the goal of maximizing the expected comprehensive efficiency of the cascade; solving for the spatial distribution scheme of cascade risk and benefit; dynamically replacing flood control risks among different reservoirs within a preset risk threshold range according to the spatial distribution scheme of cascade risk and benefit, generating a differentiated joint scheduling scheme that includes the discharge time history and water level control trajectory of each reservoir. This solves the technical problems of low efficiency and insufficient accuracy in the scheduling decisions of cascade hydropower stations in existing technologies.

This invention provides a PM2.5 prediction method based on spatial zoning of meteorological factors. Using the ST-DBSCAN clustering algorithm, monitoring stations are scientifically zoned based on the spatial distribution characteristics of meteorological factors, grouping stations with similar meteorological conditions into the same zone. This fully considers the spatial heterogeneity of meteorological factors and avoids noise interference caused by mixing all stations in the model. Furthermore, spatial constraint values ​​are calculated within each zone to quantify the spatial impact of surrounding stations on the target station, enhancing the prediction model's ability to perceive spatial correlations and improving prediction accuracy. Simultaneously, an LSTM neural network model is used to fuse historical PM2.5 concentrations and spatial constraint values ​​for prediction, effectively capturing the temporal dynamics and spatial correlation characteristics of PM2.5 concentration changes, thus exhibiting stronger spatiotemporal modeling capabilities.

This invention provides a method, apparatus, electronic device, and storage medium for calculating cloud judgment parameters. The method includes: determining the satellite position vector, solar vector, and satellite attitude matrix in the cloud judgment time inertial frame based on the time interval between the current time and the cloud judgment time; calculating the position information of the ground imaging point corresponding to each pixel after the time interval based on the satellite payload installation information, pixel line-of-sight information, and the satellite position vector and satellite attitude matrix in the cloud judgment time inertial frame; and calculating the cloud judgment parameters for each ground imaging point based on the position information of the ground imaging point corresponding to each pixel after the time interval and the solar vector in the cloud judgment time inertial frame. The cloud judgment parameters include at least one of the following: satellite zenith angle, solar zenith angle, geographic latitude and longitude, and relative azimuth angle. This solution can provide cloud judgment parameters for the cloud judgment process of satellite payloads.

A wireless communication system according to one embodiment includes: a weather radar antenna that is provided in the wireless station and receives a weather radar signal transmitted from the wireless station toward the node station and reflected; rainfall amount prediction circuitry configured to predict a rainfall amount between the wireless station and the node station on the basis of the weather radar signal received; quality prediction circuitry configured to predict quality of wireless communication between the wireless station and the node station on the basis of the rainfall amount predicted; and switching control circuitry configured to perform control to switch a line connecting the node station and the wireless station to another line connecting the node station and another communication station before interruption of the line in a case where the quality of the wireless communication predicted is less than a predetermined threshold.

The application discloses a meteorological prediction method based on hierarchical graph neural network and hidden variable injection, and belongs to the technical field of meteorological science and high-performance computing, which comprises the following steps: obtaining real-time global high-resolution meteorological reanalysis data, preprocessing to obtain a global meteorological state tensor, constructing a global meteorological probability prediction model, extracting and integrating the global meteorological state tensor step by step to obtain the coarsest level node features, performing feature extraction, distribution prediction and reparameterization sampling on the coarsest level node to obtain hidden variables, injecting the hidden variables into the coarsest level node features in a non-intrusive residual superposition mode to obtain fused large-scale circulation features, and then performing step-by-step optimization transmission on the fused large-scale circulation features to obtain meteorological prediction of the next moment. The application can more efficiently explore multi-modal distribution, optimize the probability distribution, greatly reduce the calculation cost, and improve the clarity, uncertainty quantification capability and reasoning efficiency of global meteorological prediction.

The application provides an influenza risk forecast method, device and equipment based on high-impact weather classification, and relates to the technical field of influenza risk forecast. The method comprises the following steps: acquiring weather forecast data of a future period, and determining future high-impact weather process information based on the weather forecast data of the future period; acquiring current high-impact weather process information and previous high-impact weather process information; determining a high-impact weather complexity intensity index according to the previous high-impact weather process information, the current high-impact weather process information and the future high-impact weather process information; and determining an influenza risk forecast level according to the high-impact weather complexity intensity index and a process type of the future high-impact weather process. The application constructs a forecast model based on the evolution law of the high-impact weather process, breaks through the limitation of meteorological element data, accurately associates the internal relationship between the weather change trend and the occurrence and spread of influenza, and forecasts more accurately.

The application discloses an extreme weather prediction and identification method based on multi-model integration and machine learning coupling, and belongs to the field of climate-adaptive building design and building environment engineering. The technical scheme comprises the following steps: taking the GCM data set of CMIP6 and the RCM data set of CORDEX as original data, combining ERA5 reanalysis data to perform deviation correction and time downscaling processing; constructing a prediction model integrating random forest algorithm and SSP-RCP multi-scenario framework, dividing training set and test set according to time sequence, and realizing multi-scale prediction after standardization and super parameter optimization; constructing an extreme weather identification system based on quantile threshold method, dividing heat wave and cold wave threshold, and quantifying the duration, intensity and severity thereof; and finally generating a high-granularity regional future extreme weather data set for 2024-2034. The application can provide high-precision and high-temporal and spatial resolution meteorological data, provide support for building simulation and climate-adaptive building design, and has good regional adaptability and promotion potential.

The application discloses a multi-scale historical similar rainfall pattern retrieval method based on a self-supervised Transformer. The application divides historical rainfall data and a to-be-retrieved rainfall sample into hour, day and event scales; then, a self-supervised feature extraction model is used to encode the features of the scale-divided historical rainfall data to obtain a historical feature vector, and the historical feature vector is stored in a master library and a sub-library mode to obtain a historical feature library; the self-supervised feature extraction model is used to encode the to-be-retrieved rainfall sample to extract a to-be-retrieved vector; based on the to-be-retrieved feature vector, Top-K initial similar candidate sets are screened from the historical feature library through similarity calculation; the initial similar candidate sets are comprehensively evaluated from three dimensions of spatial distribution, intensity feature and time evolution, and finally, a similar rainfall pattern is output. The application realizes accurate and rapid retrieval of the hour, day and event scale historical similar rainfall pattern.

An electronic device and method for adaptively storing data in bundle form. An aspect of the present disclosure provides an electronic device comprising: a processor; a memory storing instructions; a first storage storing data; and a second storage having a radiation tolerance higher than that of the first storage, wherein, when executed by the processor, the instructions cause the electronic device to transfer data stored in the first storage to the second storage when a deterioration of a space weather environment of a region of space in which the electronic device is located occurs, and to transfer data stored in the second storage to the first storage when the deterioration of the space weather environment is resolved, and wherein the data stored in the first storage or the data stored in the second storage is data that is transmitted to another electronic device via space communications in bundle form.

Systems and methods for triggering a stowing of one or more solar trackers comprise receiving weather data, the weather data including one or more hail parameters, determining the one or more hail parameters exceed a first corresponding one or more hail parameter thresholds, and triggering a stowing of one or more solar trackers. The one or more hail parameters include one or more of a probability of hail, a predicted size of hail, or a predicted location of hail. The systems and methods include one or more of determining the probability of hail exceeds the first hail probability threshold, determining the predicted size of hail exceeds the first hail size threshold, or determining the predicted location of hail exceeds the first threshold distance for trigging the stowing of the one or more solar trackers.