614 results about "Weather forecasting" patented technology

The invention relates to the technical field of dynamic scheduling, in particular to a dynamic optimization scheduling algorithm for a photovoltaic energy storage system, which is characterized in that based on a working environment of the photovoltaic energy storage system, environment illumination intensity data is acquired in real time, average power generation under the same illumination intensity is extracted, and weather conditions in a future time period of a current region are received through weather forecast data; and predicting the generating capacity in a future period to obtain generating capacity evaluation information. According to the invention, by capturing the environment illumination condition in real time and combining the historical power generation data, the future power generation condition of the photovoltaic system is effectively predicted, the load change of the power grid is monitored in real time, and the influence brought by specific activities is considered, so that timely response can be made when the demand of the power grid fluctuates, and the supply and scheduling of electric energy are optimized; according to the invention, continuous monitoring and abnormity processing are carried out on the power generation equipment, and the abnormal condition of the equipment is handled by correcting the discharge capacity in real time, so that the risk in operation of the energy storage system is reduced, and solid technical support is provided for stable operation of a power grid.

The invention provides a weather forecast learning system based on an artificial intelligence algorithm, and the system comprises a data access collection module which collects a multi-source data set; the data fusion and processing module is used for carrying out data fusion and processing to obtain a multi-source fusion data set; the AI model design module is used for constructing a multi-model collaborative architecture and carrying out multi-model parallel training and optimization; the model fusion module is used for carrying out multi-model weighted fusion to obtain an AI model; the real-time prediction module is used for updating a prediction result according to the real-time data; the visualization and interpretability module is used for designing a visualization interface and carrying out interpretability verification; and the evaluation and iteration module is used for carrying out comprehensive evaluation and continuous improvement on a prediction result in combination with evaluation indexes. According to the method, accurate and reliable observation data can be obtained, massive meteorological data are efficiently processed by combining an artificial intelligence algorithm, trend analysis and prediction are automatically carried out, and a reliable prediction result is generated.

The invention relates to the technical field of intelligent control and optimization of a photovoltaic power generation system, and discloses a self-adaptive photovoltaic module inclination angle adjusting method and system based on environmental conditions, and the method comprises the steps: obtaining short-term weather forecast data through a meteorological data interface, analyzing the weather forecast data, and predicting the environmental change in several hours in the future; monitoring pollution data of the surface of the photovoltaic module in real time through a sensor, and judging whether the pollution degree affects the power generation efficiency or not; according to the prediction result and the pollution degree, the inclination angle of the photovoltaic module is dynamically adjusted, the power generation efficiency under the upcoming illumination condition is optimized, the inclination angle of the photovoltaic module is dynamically adjusted in combination with short-term weather forecast data obtained by the meteorological data interface, and the power generation efficiency of the photovoltaic system under the complex environment is remarkably improved. The system can quickly respond to environmental changes, and efficiency loss caused by adjustment lag is avoided. And multi-factor collaborative optimization is realized, and the maximum power generation efficiency of the photovoltaic system under various conditions is ensured.

The invention belongs to the technical field of weather forecast, and discloses an information fusion dual-polarization radar urban heavy rainfall short-term and imminent forecast deep learning method and system. The invention provides a novel urban heavy rainfall short-term and imminent forecasting method based on meteorological radar data through a research thought of'space-time-space-time fusion 'on the basis of a deep learning technology in combination with a physical mechanism of heavy rainfall. According to the method, heavy rainfall is accurately forecasted by analyzing spatial and temporal distribution characteristics of heavy rainfall, extracting high-dimensional spatial characteristics, developing a super-resolution heavy rainfall spatial characteristic extraction model, combining time evolution characteristics of heavy rainfall and adopting an LSTM and spatial and temporal characteristic fusion model, and the accuracy and timeliness of urban heavy rainfall forecasting are improved.

The invention provides a new energy electric power meteorological prediction method and device based on a multi-modal large model, and belongs to the field of meteorological prediction. The method provided by the invention comprises the steps of obtaining multi-source meteorological observation data and new energy station operation data, and generating a multi-modal fusion feature; a large meteorological prediction model is constructed, the large meteorological prediction model adopts a dynamic graph neural network structure, nodes represent geographic space positions, edges represent spatial adjacent relations, and node features comprise numerical values of meteorological elements; using the multi-modal fusion features to train the meteorological prediction large model, and minimizing a meteorological element prediction error; and inputting real-time multi-source data of a to-be-predicted area into the trained meteorological prediction large model, and outputting meteorological types and meteorological element values of the to-be-predicted area within a preset duration. According to the method and the device provided by the invention, the problems of insufficient accuracy of new energy electric power weather prediction, weak combination of geographical and physical rules and difficulty in adaptation to different weather types can be solved.

The invention discloses a radar echo extrapolation method and system based on frequency domain enhancement, and the method mainly comprises the following steps: obtaining and preprocessing a historical radar echo grayscale image sequence, generating a sequence sample through a sliding window, and dividing the sequence sample into a training set, a verification set and a test set; the method comprises the following steps: constructing a frequency domain enhanced U-Net network comprising an encoder-decoder structure, introducing a multi-scale deep convolution structure into an encoder and a decoder, and enhancing frequency domain features by using a frequency domain dynamic attention mechanism in jump connection; inputting the training set into the model for training by adopting a composite loss function comprising intensity weighted loss, frequency domain consistency loss and structural similarity loss; and inputting the test set into the trained model, and outputting a radar echo prediction result at a future moment. The method can be effectively applied to the fields of short-term and temporary weather forecast, severe convection monitoring and the like, and provides more accurate and reliable radar echo prediction support for meteorological disaster early warning.

The invention relates to the technical field of weather forecasting, in particular to a weather clock forecasting system based on multi-source data fusion, which comprises an equipment terminal and a cloud end, the cloud end comprises a data acquisition module, a data processing module and a data transmission module, the data acquisition module is used for acquiring position information of the equipment terminal and multi-source data at the position, and the data processing module is used for processing the position information; the data processing module performs grid division on the target area range based on the position information of the equipment terminal to obtain grid units, and the data processing module is further used for mapping the position information of the equipment terminal into the grid units to obtain a target unit grid of the position where the equipment terminal is located. According to the method, the local feature data is introduced into the fine meteorological data of the target grid unit for correction, so that the finally obtained meteorological correction data has a finer space description capability, and the defect that prediction is inaccurate due to the fact that a traditional meteorological model ignores the local feature data under complex terrains or urban microclimate is overcome.

The invention discloses an intelligent distributed photovoltaic power station optimal scheduling and operation and maintenance management method and system, and relates to the technical field of optimal scheduling. Historical power generation data, real-time meteorological data and future weather forecast of a photovoltaic power station are acquired; according to the historical power generation data, the real-time meteorological data and the future weather forecast, inputting the historical power generation data, the real-time meteorological data and the future weather forecast into a pre-trained power generation prediction model to obtain a photovoltaic power generation prediction value in a future time period; and obtaining the power grid demand power of the photovoltaic power station, and planning the charging and discharging strategy of the energy storage system according to the absolute value of the difference between the power grid demand power and the photovoltaic power generation prediction value. The difference between the power grid demand power and the photovoltaic generating capacity prediction value is analyzed, the output power of the photovoltaic power station and the charging and discharging mode of the energy storage system are adjusted according to the difference, the completion degree of the charging and discharging strategy is judged through the charging and discharging time of the energy storage system, the adjusting function of the energy storage system is fully played, and the energy storage efficiency is improved. And the reliability and continuity of power supply are improved.

The invention relates to a runoff hydropower station generating capacity prediction method based on depth data fusion, and the method comprises the following steps: S1, carrying out data layer fusion, integrating multi-source hydro meteorological data, obtaining multi-source data from a meteorological station, a hydrological station, a satellite remote sensing platform and a numerical weather forecasting system, carrying out the cleaning, interpolation and normalization processing of the data, and carrying out the prediction of the generating capacity of a runoff hydropower station; performing data space-time alignment; s2, carrying out feature layer fusion, firstly inputting a multi-source data set of a unified space-time reference, carrying out feature extraction, carrying out feature fusion based on a self-attention mechanism, embedding a water balance equation in a deep learning model, and obtaining a comprehensive feature vector; and S3, performing prediction, inputting the comprehensive feature vector in the step S2, and performing power generation prediction by using a deep neural network.

The invention relates to the field of weather forecasting, and discloses a marine meteorological coupling refined forecasting method and system, which are used for improving the precision and reliability of marine meteorological coupling forecasting. Comprising the following steps: based on a non-exchangeable geometric vortex equation and an external differential form, constructing a conservation manifold dynamic field in combination with submarine topography data, and realizing strict conservation of mass flux under a complex terrain; an additional pressure item caused by vacuum fluctuation is quantified, and an interface energy field of quantum correction is generated; the recognition precision of the mesoscale vortex and the frontal surface structure is improved; a spectral element method and lattice Boltzmann method mixed solver is combined, and high-precision coupling of ocean vertical layering and the atmospheric process is achieved. According to the method, the defects of conservation, interface energy transmission, initial field non-physics and grid adaptive capacity of a traditional method are overcome, refined forecasting of 72-hour typhoon paths, ocean frontal surfaces and energy flux is supported, and key technical support is provided for extreme weather early warning and climate change research.

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 discloses an artificial intelligence meteorological data processing system and method, and aims to improve the accuracy and real-time performance of meteorological prediction. The system comprises a data acquisition module, a data preprocessing module, a data storage module, an artificial intelligence analysis module, a prediction output module, a feedback learning module and an anomaly detection module. Through real-time acquisition and fusion of multi-source data, the system performs cleaning, noise reduction, interpolation and format conversion on meteorological data, and performs modeling and prediction by using a long-short-term memory network. The system adopts a Bayesian optimization and adaptive learning rate adjustment mechanism to ensure the precision and stability of the model. And the anomaly detection module is used for identifying extreme weather events and continuously optimizing model parameters through a feedback learning mechanism. The prediction result is visualized in a graphical manner, and an alarm is generated when an abnormality is detected. The method is suitable for the fields of weather forecast, agriculture, traffic and the like, and has wide application value.

The invention provides a new energy green electricity transaction quantity reporting strategy algorithm based on deep learning. The new energy green electricity transaction quantity reporting strategy algorithm based on deep learning comprises the following steps: a, data collection: acquiring multi-source data from an electricity market, a weather forecast system, historical power generation data and a load prediction system, the data including historical electricity price, weather conditions, power generation power and power grid load data, and recording as X = {x1, x2,..., xn}, wherein xi is a time sequence data feature vector. According to the new energy green power transaction quantity reporting strategy algorithm based on deep learning, the problem of prediction errors caused by randomness and intermittency in new energy power generation is innovatively solved through a deep learning technology, and the prediction accuracy of the new energy green power transaction quantity reporting strategy algorithm based on deep learning is improved. Power generation fluctuation and weather change features are extracted through a multilayer convolutional neural network, and extreme weather events are automatically identified in combination with an attention mechanism, so that the algorithm can more accurately capture market fluctuation.

The invention discloses a wind speed forecasting system based on deep learning, and belongs to the technical field of weather forecasting. The system comprises a coupled mode framework which integrates a triple nested architecture of an atmospheric mode WRF, an ocean mode ROMS and a sea wave mode SWAN, and transmits variables through a model coupling tool MCT; the deep learning roughness parameterization module is integrated in an MYNN boundary layer scheme of the atmospheric mode WRF and calculates the sea surface roughness in real time; the full-wave spectrum integration module is embedded into the ocean mode ROMS, receives wave spectrum data provided by the ocean mode SWAN and calculates a Stokes drift profile; and the intelligent correction module is used for carrying out spatial interpolation on the wind speed data output by the mode, correcting errors by combining a LightGBM model, and outputting a final forecast product. According to the method, the deep neural network is embedded into the WRF boundary layer model kernel, the sea surface roughness parameter is updated in real time, the wave evolution process is dynamically responded, and the space-time adaptive capacity of wind field forecasting under the complex sea condition is remarkably improved.

The invention provides an HY-2A ocean water vapor inversion method based on machine learning, and the method comprises the steps: constructing a high-quality HY-2A scanning microwave radiometer data set through the data preprocessing, matching, feature extraction and normalization processing of HY-2A satellite scanning microwave radiometer data and ERA5 reanalysis data. A plurality of machine learning models are used for training and testing, Bayesian optimization is used for realizing hyper-parameter automatic adjustment, an optimal solution in finite time is obtained, an SHAP method is used for explaining the models, contribution of each characteristic variable is clear, interpretability of the used machine learning models is improved, and finally high-precision inversion of the water vapor over the sea is realized. The method has efficient calculation performance, can realize rapid processing of large-scale marine meteorological data, and improves the interpretability of a machine learning model. The method has important application value in numerical weather forecast, ocean extreme weather forecast, climate monitoring and other geophysical and meteorological fields.

The invention relates to a wind resource prediction method based on quality control assimilation of multi-source observation data, and the method comprises the steps: integrating the multi-source observation data, including a multi-band radar reflectivity factor, a radial speed, a ground observation station, and wind profile radar data; quality control processing such as mottle removal, data filling, speed folding removal and discontinuous data removal is carried out, so that the accuracy and continuity of the data are improved; then, through lattice point interpolation and three-dimensional variation assimilation technologies, the processed observation data are fused into an initial background field, and an analysis field closer to the actual atmospheric state is generated, so that the reliability of severe convective weather risk assessment is remarkably improved, and the accuracy of wind energy prediction is also enhanced; and more comprehensive, detailed and stable information support is provided for weather forecast and energy management.

Data integration and distribution systems. A system includes a graphical user interface (GUI). Weather and market data are collected. A weather symbology including symbol elements linked to segments of the collected weather data and rules for generating weather symbology instructions are stored. The GUI is generated for display on a user device. A weather symbology instruction is determined based on at least one requested symbol element indicated in a weather data request and the rules. A weather forecast dataset is created from among the collected weather data based on the weather symbology instruction. A presentation package including the weather forecast dataset and the collected market data is generated such that the weather forecast dataset is integrated with the collected market data. The presentation package is presented on the GUI and updated concurrent with changes to at least one of the weather data, the market data and user input.

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 discloses a wind power prediction method based on a pre-training model and low-rank self-adaption, and relates to the technical field of wind power generation, and the method comprises the steps: obtaining historical meteorological data and numerical values of a wind power plant, obtaining weather forecast data, and obtaining historical operation data and numerical weather forecast data of a wind motor; cleaning and normalizing the acquired data, dividing historical meteorological data and historical operation data into a training set and a test set, selecting a pre-training model according to a wind power prediction demand, and training the pre-training model by using the training set. According to the method, the pre-training model is combined with low-rank self-adaption, so that the model can accurately capture the change rule of wind power, prediction errors are reduced, prediction precision is improved, low-rank decomposition is carried out on a model parameter matrix, the parameter quantity of model training is reduced, calculation complexity is reduced, rapid training and real-time prediction of the model are facilitated, and the method is suitable for large-scale popularization and application. The stability of the power system of the wind power plant is improved.

The invention discloses a photovoltaic cleaning robot operation scheduling method and system based on environment prediction, and belongs to the technical field of photovoltaic power station intelligent operation and maintenance and robots, and the method comprises the steps: obtaining weather forecast data, photovoltaic panel real-time dust accumulation data and historical power generation efficiency attenuation data, and generating environment prediction parameters; generating a dynamic weight value based on the environment prediction parameters and a preset power generation loss threshold value, and judging the sweeping emergency degree of each photovoltaic panel area; distributing an operation priority according to the cleaning emergency degree, and generating an initial cleaning task sequence; and a multi-robot cooperative path planning result is generated by combining the photovoltaic power station topological structure and the real-time position data of the robots. According to the method, the environment prediction technology and the dynamic scheduling strategy are combined, the cleaning task can be adaptively adjusted according to weather changes and dust accumulation conditions, the robot operation path is optimized, and the power generation efficiency of a photovoltaic power station and the utilization rate of robot resources are remarkably improved.

The invention discloses a multi-source data and physical information fused tornado space-time intelligent prediction method, which comprises the steps of collecting observation data of a Doppler weather radar and reanalysis data of a mid-term weather forecast center, performing projection conversion, space alignment, time interpolation and the like of space-time dimensions, and fusing key physical characteristics of the tornado; establishing a space-time convolution model network suitable for tornado multi-scale feature extraction, inputting fusion features and corresponding coordinate information, and outputting a prediction control quantity of tornado space-time evolution; a physical control equation of the atmospheric motion and thermodynamic process is converted into a penalty term, a space-time convolution model loss function is embedded, and physical information constraint is carried out on network parameters; and obtaining tornado prediction control quantities of different time windows in the future, and generating a probability graph of the potential development area of the tornado. Through fusion of multi-source data and a physical mechanism, future tornado event probability is quantified, and reliable data support and scientific basis are provided for meteorological prediction and emergency response.

The invention relates to the technical field of weather forecast, discloses a method for classifying severe convection weather forecast, and aims to solve the problem that complexity of severe convection weather requires multi-dimensional data support, so that a three-dimensional data acquisition network covering'ground-air-sky 'needs to be constructed. Ground observation data need to include minute-level rainfall, hourly air temperature and humidity (emphatically paying attention to humidity difference between 850hPa and 500hPa and reflecting unstable stratification) and 10-minute average wind speed of a meteorological station, and high-altitude detection data need to extract temperature vertical profiles (calculating convective condensation height LCL) and wind speed vertical shear (shear values of 0-3km and 0-6km) at 08 o'clock and 20 o'clock every day. According to the method for classifying severe convection weather forecast, new signals (such as sudden cloud top brightness temperature drop) observed in real time are rapidly absorbed, and meanwhile, the method is adaptive to severe convection characteristic differences of different areas (such as mountainous areas and plains) and different seasons, so that the forecast precision is improved, and the requirements of refined disaster prevention for high-accuracy and high-timeliness forecast are met.

The invention relates to the technical field of sea surface temperature prediction, and discloses a sea surface temperature prediction method based on a spatio-temporal enhanced ConvGRU, which comprises the following steps: preprocessing a sea surface temperature data set obtained by ERA5 reanalysis data of an European mid-term weather forecast center, and dividing the sea surface temperature data set into a training set, a verification set and a test set; inputting the data of the training set into a deep learning algorithm model of spatio-temporal position attention enhancement for training, using the data of the verification set to evaluate the model precision and adjust parameters, and using the test set to evaluate the generalization ability and prediction precision of the model; the model comprises a multi-scale feature extraction module, a position attention enhancement module and a convolution gating cycle unit module. And preprocessing sea surface temperature data of a sea area to be predicted, and inputting the sea surface temperature data into the qualified model for sea surface temperature prediction. According to the method disclosed by the invention, the processing capability of spatial information can be improved, and the prediction accuracy is improved.

The invention discloses a garden partition intelligent water-saving irrigation regulation and control system based on the Internet of Things, and belongs to the field of irrigation regulation and control systems. According to the system, a basic water demand model containing static characteristics of plants, soil and the like is established for each subarea through a central processing controller, real-time environment data and weather forecast are fused, and future irrigation water demand and optimal time are calculated in a prospective mode. The core innovation of the method lies in that after irrigation, the system performs feedback iterative optimization on a basic water demand model by comparing the efficiency deviation of the actual change and the predicted change of the soil humidity to form a self-learning closed loop. According to the method, conversion from passive response to active prediction is achieved, the method has the advantages of being accurate, prospective and self-adaptive, the method can continuously adapt to environmental changes, and the intelligent level and the water saving effect of irrigation are remarkably improved.

The invention belongs to the technical field of wind power weather forecasting, and provides an all-region three-dimensional wind speed correction method and system, and the method comprises the steps: constructing a weather numerical forecasting model, and obtaining wind field forecasting data; fusing the preprocessed multi-source data by adopting an optimal interpolation method to obtain three-dimensional space-time continuous wind field analysis data; based on the wind field forecast data and the wind field analysis data, features are extracted and fused, then a historical forecast error sample set is constructed, a wind speed correction model is constructed, and the historical forecast error sample set is utilized to train the wind speed correction model; introducing an initial value, a physical parameter and boundary condition disturbance, calculating a mean value and a standard deviation of each set result, extracting a probability distribution feature of a wind speed, constructing a confidence interval, estimating a probability density function, and quantifying an occurrence probability of an extreme wind speed event; and the prediction result of the wind speed correction model and the multi-source wind field observation data are fused to generate final three-dimensional wind field data, so that the actual requirements of wind power prediction and power grid dispatching can be met.

The invention relates to the field of business forecasting, and discloses an intelligent weather forecasting system for numerical mode simulation, which is used for timely adjusting decisions according to business execution states and comprehensively improving weather forecasting accuracy and business decision scientificity, adaptability and real-time performance. The intelligent weather forecasting system based on numerical mode simulation comprises the steps that a cross-scale continuous correction vortex field is generated through spatial fractional order Laplace operation in combination with a bit vortex conservation law, meteorological phase change events such as cyclones and frontal surfaces are recognized through continuous coherence analysis topology, and invalid data are filtered; a Riemannian metric field of meteorological-commercial curvature conservation mapping is constructed based on conformal differential transformation, a decision manifold is constructed in combination with symplectic structure tensor and Gaussian curvature constraint, decision parameters such as a minimum entropy generation path output logistics curvature coefficient and an inventory elastic factor are solved, and real-time commercial data feedback is introduced to realize dynamic closed-loop calibration of the decision manifold. And the decision-making precision and response timeliness of commercial systems such as supply chains and energy sources in extreme weather are remarkably improved.

The embodiment of the invention discloses a photovoltaic power prediction method and device, electronic equipment and a storage medium. The method comprises the steps that original photovoltaic power data and original weather forecast data are acquired; performing data preprocessing on the original photovoltaic power data and the weather forecast data to obtain photovoltaic power data and numerical weather forecast data; screening a meteorological element set with high correlation with the photovoltaic power from the numerical weather forecast data; and inputting the photovoltaic power data, the numerical weather forecast data and the meteorological element set into a pre-constructed SCBAM-TCN-UNet combined model, and outputting to obtain a photovoltaic power prediction result. According to the method, the precision and robustness of photovoltaic short-term power prediction can be improved, and efficient and reliable prediction support is provided for power grid dispatching and operation plans.

The invention discloses a multi-drive process multi-factor agricultural non-point source pollution prediction method based on coupling meteorological numerical forecasting. The method comprises the following steps: firstly, introducing numerical weather forecast data, and constructing a high-precision weather driving field with kilometer-level space and hour-level time resolution by combining WRF dynamic downscaling, DEM terrain correction and conservation resampling; secondly, establishing a multi-drive process coupling model system which comprises a meteorological drive layer, a hydrological response layer, a pollutant migration layer and a crop feedback layer and is used for simulating runoff production, sediment erosion, nitrogen and phosphorus migration and transformation and crop transpiration and root nutrient absorption processes; thirdly, performing precision verification on a simulation result by using observation data, and identifying key meteorological and hydrological factors through an error transfer matrix and a sensitivity analysis method; and finally, realizing parameter adaptive correction by adopting a long short-term memory network, finishing parameter optimization in combination with a multi-target genetic algorithm, packaging the model chain through a containerization technology, and realizing cross-platform deployment and visual output of a pollution load result. The method can be used for agricultural non-point source pollution prediction and management.

The invention discloses a radar echo extrapolation method based on a space-time attention mechanism, and the method comprises the steps: firstly obtaining the radar echo data of a target region, carrying out the preprocessing of the obtained radar echo data, carrying out the sliding grouping of the preprocessed radar echo data, carrying out the data augmentation, and obtaining a radar echo sequence data set, dividing the data into a training set and a test set; a radar echo prediction network model based on a SimVP architecture is constructed, training and testing are carried out, and a multi-target loss function is adopted to supervise model training; and a future radar echo image is obtained through real-time prediction. Through the method, the dynamic evolution of complex weather phenomena such as storm can be more accurately captured, the precision and interpretability of short-time approaching weather forecast can be remarkably improved, more reliable technical support is provided for timely and accurate early warning of meteorological disasters, and the method has important practical application value.

The invention provides a weather forecasting method and device based on time coding autoregression and electronic equipment, which are applied to the field of weather forecasting, and the method comprises the steps: carrying out weather forecasting based on a deep learning self-attention model of the current day number, taking meteorological element data as input, and taking time information corresponding to a plurality of times as constraint conditions, obtaining weather forecast results corresponding to a plurality of times in the current day number; for the weather forecast of the target number of days, iteratively executing the following steps until a weather forecast result of each target time of each number of days in the target number of days is obtained; taking the weather forecast results corresponding to a plurality of times in the current day number as input, and taking the time information corresponding to the plurality of times as constraint conditions to carry out weather forecast to obtain weather forecast results corresponding to the plurality of times in the next day number; according to the invention, the accuracy can be kept in the continuous weather forecast process, and error accumulation is reduced.