211 results about "Cloud cover" patented technology

The present invention relates to a solar azimuth estimation method and system based on multi-channel feature enhancement and region-aware attention, belonging to the technical field of intelligent navigation for low-altitude economy unmanned systems. Aiming at the problem of decreased accuracy in solar azimuth estimation based on polarization images under complex cloud cover conditions, the present invention proposes a deep learning framework integrating multi-channel features and direction-aware attention. First, based on polarization light field information acquired by a division-of-focal-plane polarization camera, a three-channel composite input feature composed of a polarization intensity map, an adaptive threshold gradient map, and high-frequency residual edge information is constructed. Second, a ResNet backbone network embedded with a squeeze-and-excitation mechanism is adopted, and a direction-aware polarization attention module is introduced to achieve adaptive fusion of multi-scale features through luminance guidance, deep feature enhancement, and a gradient edge branch.

The invention discloses a multi-mode short-term photovoltaic power prediction method and device based on a satellite cloud atlas, and the method comprises the steps: obtaining real-time meteorological data, historical photovoltaic power data and cloud cluster image data, and carrying out the preprocessing of the data; a GPAformer model is established, and the meteorological data after noise reduction are predicted; the method comprises the following steps: establishing an SA-Convlstm model, capturing a cloud cluster movement track, extracting time change characteristics, predicting cloud cluster image data, introducing a cloud shielding model, and correcting the prediction deviation of SA-ConvLSTM under the condition that a cloud layer is dense or changes rapidly; establishing a photovoltaic power KAN-COGCN prediction model, and performing photovoltaic power prediction by taking the meteorological factors, the cloud cluster motion time sequence characteristics and historical photovoltaic power data obtained by prediction of the GPAformer and the SA-ConvLSTM model as input; using an improved alpha evolutionary algorithm IAE to optimize hyper-parameters of the three models; and performing error correction on a prediction result by establishing an adaptive wavelet RBF neural network to obtain a final prediction result. According to the invention, the precision and effectiveness of photovoltaic power prediction can be improved.

The invention relates to the technical field of satellite remote sensing monitoring, in particular to a method for monitoring a resident-free island by adopting satellite remote sensing, which comprises the following steps of: acquiring optical images and cloud layer data of a target island through optical and meteorological satellites, predicting a cloud shielding probability, and scheduling a radar satellite when the cloud shielding probability exceeds a threshold value; comparing the effective area of the optical image with a reference demand, triggering radar imaging when a difference value reaches a preset proportion, extracting a coastline feature point set from a historical image, calculating a spatial distribution entropy screening subset, constructing an optimized affine transformation matrix to compensate a radar image, and obtaining a new optical image when the cloud cover is low. Coastline feature point errors of the calibration radar image and the new optical image are calculated, secondary compensation is carried out, global time sequence monitoring data are generated, monitoring continuity and data consistency in a cloud shielding scene are improved, and the method is suitable for resident-free island dynamic monitoring.

The invention discloses a hybrid photovoltaic prediction method based on SARIMA-LSTM, and the method comprises the steps: carrying out the calculation according to historical photovoltaic power generation data in an SCADA system, wherein the historical photovoltaic power generation data comprise the power generation power and the accumulated power generation amount, and the meteorological data comprise the irradiance, the temperature, the humidity, the wind speed, the cloud cover and the like, and are obtained from a meteorological station or an open-source data platform; statistics is carried out by combining an SARIMA model with a seasonal prediction function and an LSTM model for processing a time sequence, and a more accurate photovoltaic power generation prediction value is obtained after combined prediction and evaluation. Compared with the prior art, short-term prediction and long-term prediction can be considered, and seasonal change data prediction is more accurate.

The invention discloses a large-range high-frequency all-sky earth surface solar irradiance machine learning estimation method and system suitable for a cloudy area, and relates to the technical field of irradiance estimation, and the method comprises the steps: obtaining earth surface radiation observation data, generating a station position table, and constructing a training data set; constructing a ground solar radiation degree model, and dividing the training data set into a training set and a test set according to a proportion of 80% to 20%; determining hyper-parameters of the Xgboost algorithm through parameter search, training the model on the training set, and checking the model by using the test set; new satellite reflectivity is used for observing data and meteorological elements, data cleaning is carried out, and the model is input to estimate the space-time distribution of the total solar radiation irradiance of the earth surface. According to the method, the space and time precision of radiation inversion is improved, the complex nonlinear characteristics and data interaction relation are accurately captured, efficient inversion of the earth surface solar radiation degree is achieved, and the prediction performance and generalization ability of the model are remarkably improved.

The invention discloses a time sequence remote sensing composite under-cloud reconstruction method and system based on observation modeling and a radiation reconstruction network, and belongs to the technical field of remote sensing, and the method comprises the steps: carrying out the mask processing of a composite cloud time sequence remote sensing image based on observation, and obtaining a real degraded sequence after mask; inputting the real degraded sequence into the trained radiation reconstruction network to obtain a cloudless surface reflectance sequence, and completing composite under-cloud reconstruction; wherein the training of the radiation reconstruction network comprises the following steps: constructing a simulated degradation-cloudless pairing data set; building a radiation reconstruction network; and training the constructed radiation reconstruction network by using the constructed simulated degradation-cloudless pairing data set to obtain a trained radiation reconstruction network. According to the method, joint processing of the space-time spectrum data is realized, the method can be effectively applied to joint processing of thin cloud radiation deviation correction and thick cloud information loss reconstruction, and finally reconstruction of the surface reflectance sequence under the composite cloud is realized.

The invention discloses an urban and rural land dynamic evaluation system based on satellite remote sensing monitoring, relates to the technical field of land monitoring, solves the problem of low accuracy recognition when a change area is recognized during dynamic evaluation of an original remote sensing image, and provides a dynamic evaluation method for the urban and rural land based on satellite remote sensing monitoring through feature vector comparison (standard vector and abnormal vector distinguishing). The contour partition corresponding to the abnormal vector is marked as a'change partition ', the partition disappearance interference caused by natural factors (such as cloud layer coverage) can be eliminated in combination with the limitation of an image acquisition period within three days, and a real land use change area is accurately positioned. A standard partition is introduced as a reference, and quantitative analysis of spatial position and morphological difference of a change area is realized through vector set translation coincidence verification of front and back images.

The invention relates to a sun meridian detection and course angle real-time calculation method based on polarized light field vector characteristics, and aims to solve the problems that a traditional sun meridian detection method is easily interfered in low signal-to-noise ratio scenes such as haze and cloud layer shielding, lens distortion causes polarization angle errors, the false detection rate is high, and the calculation accuracy is high. In order to solve the problems that the real-time performance and robustness of course calculation are affected due to the fact that single polarization angle information is difficult to fully reflect the sun direction, polarization parameter calculation is carried out by utilizing a multi-channel polarization image, and the sun meridian is detected by adopting Hough transform through fisheye lens correction, bilateral filtering and candidate region screening, so that the real-time performance and robustness of course calculation are improved. And a multi-point inversion method is combined to accurately obtain a sun vector and a zenith angle and an azimuth angle thereof, and finally a course angle is calculated in real time. The problems of imaging distortion and insufficient real-time processing in the traditional sun positioning technology can be effectively solved, and a powerful navigation positioning technical guarantee is provided for the fields of unmanned aerial vehicles, autonomous navigation, polarized light navigation and the like.

The present invention relates to a real-time heading angle calculation method based on the vector characteristics of the polarized light field. Aiming at the problems of traditional solar meridian detection methods, such as being easily disturbed in low signal-to-noise ratio scenarios like haze and cloud cover, the occurrence of polarization angle errors and high false detection rates caused by lens distortion, and the difficulty of using single polarization angle information to fully reflect the solar direction, which affects the real-time performance and robustness of heading calculation. This method calculates polarization parameters by using multi-channel polarization images.

The invention belongs to the field of computer vision, and particularly relates to a cloud cover density calculation method combining image features and superpixel partition merging and a corresponding device thereof. The method comprises the following steps: 1, preprocessing an original image P0 containing the sky and the cloud layer to obtain a gray level image H1, an HSV image P1, a Lab image P2, a color enhancement image E1 and a gray level enhancement image E2 which correspond to different color spaces; 2, P0 is divided into a plurality of superpixel areas, and background elimination is carried out by combining characteristic information of H1, P1, P2, E1 and E2; gradually combining the superpixel regions belonging to the cloud layer or the sky; and 3, extracting values of an S channel and a Lab color space three channel of the superpixel region, generating a four-dimensional feature vector, and inputting the four-dimensional feature vector into a K-means algorithm for clustering. And 4, calculating the cloud cover density according to the clustering result of the K-means algorithm. The problem that the sky and cloud layer image segmentation task is difficult to process by the existing traditional image segmentation technology is solved.

The invention discloses a lightning approaching trend forecasting method and system. The method comprises the steps of obtaining cloud cover space distribution and a time sequence, extracting a first cloud cover texture feature vector, and generating a cloud cover hierarchical feature matrix; performing dimensionality reduction on the first cloud cover texture feature vector to generate a second cloud cover texture feature vector, and generating a regionalized cloud cover distribution feature set through clustering in combination with the cloud cover hierarchical feature matrix; extracting humidity, temperature and wind field data to generate a lightning trigger factor data set, and analyzing a regionalized cloud cover distribution feature set by adopting a time sequence analysis method and an optical flow method to form a cloud cover dynamic feature set; and according to the cloud cover dynamic feature set and the cloud cover hierarchical feature matrix, in combination with a pre-established lightning association cloud type label, generating a lightning intensity grade classification feature set and the like. According to the invention, through deep fusion and dynamic optimization of spatial-temporal characteristics, the precision and timeliness of lightning prediction are significantly improved, and efficient technical support is provided for meteorological disaster early warning.

The invention discloses an intelligent smoke furnace catalysis operation condition suitability grading method. The method comprises the steps that basic parameters of an operation point are obtained; calling a Passive-Toner algorithm to calculate the atmospheric stability grade of the operation point; the continuous cigarette lighting source intensity is calculated according to the used flame bar combustion data; calculating the vertical airflow distribution of the operation point by adopting a Matviyerv vertical velocity theoretical model based on the altitude and vertical airflow observation data of the operation point; based on the continuous cigarette lighting source intensity, calculating the ice nucleus number concentration distribution in the cloud in combination with the vertical airflow distribution and the horizontal wind field; calculating an operation suitability index by adopting a comprehensive index algorithm in combination with the lifting condensation height, the cloud amount and the cloud classification data; and performing grading processing on the job suitability index according to a set threshold value combination so as to output a plurality of job suitability grading results. According to the method, comprehensive analysis is carried out by considering the meteorological condition and the catalytic condition of the operation point, so that the accuracy and the credibility of an operation condition suitability judgment result are improved to a certain extent.

The invention relates to an intelligent photovoltaic sunshade method and system based on cloud cover recognition, and aims to improve the power generation efficiency of a photovoltaic system and achieve typhoon resistance. According to the method, cloud amount data are collected in real time through a multispectral camera and a meteorological station sensor, and feature values of cloud are extracted after preprocessing. A deep belief network (DBN) model of a double-layer RBM structure is used for power supply prediction, and model parameters are optimized through particle swarm optimization (PSO). And intelligently adjusting the angle of the sun shield or starting an anti-typhoon mode according to a comparison result of the predicted power supply quantity and a dynamically adjusted threshold value. The system further comprises an environment parameter prediction module and a user interaction interface, and the comfortable and energy-saving indoor environment of the near-zero-carbon building is achieved. The method and the system provided by the invention can effectively deal with extreme weather, optimize energy utilization and have a wide application prospect.

The invention provides an air conditioner indoor environment parameter control method and system, and relates to the technical field of air conditioner control. External environment information and internal heat source information such as sunlight intensity data and cloud cover prediction data outside a building and the operation state and real-time power consumption data of large electronic equipment inside the building are obtained; the preset building physical attribute parameters are combined, the predicted total heat load increment of all the areas in the future preset time can be calculated in advance, an adjusting instruction is generated in advance before the indoor environment parameters actually change, the operation state of an air conditioner system executing mechanism is adjusted, accurate and active control can be achieved, and the control efficiency is improved. According to the method, local supercooling or superheating possibly caused by a traditional method is avoided, the comfort consistency of the indoor environment is remarkably improved, meanwhile, the energy utilization efficiency is optimized, and energy waste is effectively reduced.

The invention discloses an unmanned ship maritime millimeter wave cloud radar and background field data maneuvering fusion method and device and a medium, and relates to the technical field of meteorological detection. The method comprises the following steps: acquiring a navigation route and radar detection parameters of the unmanned ship; based on the navigation route of the unmanned ship and the radar detection parameters, the unmanned ship is controlled to navigate autonomously according to the set route; wherein a millimeter wave cloud radar system is carried on the unmanned ship; obtaining millimeter wave cloud radar data of the unmanned ship in the sailing process; wherein the millimeter wave cloud radar data are acquired by a millimeter wave cloud radar system based on radar detection parameters; performing cloud cover inversion on the millimeter wave cloud radar data based on a reflectivity and cloud cover formula to obtain cloud cover data in a navigation route process; and interpolating the cloud cover data into the three-dimensional cloud cover data of the background field data to obtain fusion data. According to the invention, accurate fusion of the radar data and the background field data can be realized, so that more comprehensive and more accurate cloud layer information can be obtained.

The invention relates to the technical field of image recognition, in particular to a horticultural product fungal disease image recognition system and method, and the system comprises an image collection module, an image segmentation module, an anomaly detection module, a feature extraction module, a disease recognition module and a decision output module. In the prior art, the intensity of a light supplementing lamp is manually adjusted, and instantly changing illumination conditions (such as cloud layer shielding and tree shadow shaking) are difficult to deal with in an open-air plantation, so that leaf scab details are often submerged by strong light or dim light is blurred; according to the scheme, a closed-loop linkage system of ambient light perception and an annular LED is innovatively deployed, and the light supplementing intensity is reversely adjusted in a millisecond level by tracking ambient brightness in real time, so that purple gray hyphae of downy mildew in mist in the morning and anthracnose black spots under the noon burning sun present completely consistent color saturation and texture definition in imaging; and the problem of misdiagnosis caused by illumination fluctuation in the traditional method is thoroughly solved.

The invention relates to the technical field of power system grid connection, in particular to an AI-based distributed photovoltaic power station grid connection access capacity evaluation optimization method, system and device and a storage medium. The method comprises the following steps: acquiring topological structure parameters of a power grid, line parameters and historical operation data of a photovoltaic power station, identifying voltage out-of-limit nodes and line overload nodes by simulating the operation state of the power grid under multi-stage access capacity, and determining the bearing capacity boundary of the power grid; time sequence fluctuation characteristics of photovoltaic output are extracted, meteorological data of irradiation intensity, temperature and cloud cover are combined, a photovoltaic output fluctuation range is predicted through an AI algorithm, and an access capacity constraint condition is obtained; analyzing the matching relationship between the power grid regulation resource capacity and the photovoltaic output fluctuation amplitude, calculating the up-regulation margin and the down-regulation margin of the power grid, and determining a capacity safety margin threshold by combining the occupation degree of the photovoltaic access capacity on the regulation resource; and generating an optimal access capacity scheme by integrating a power grid operation state, photovoltaic output prediction and economic benefits through an AI intelligent algorithm.

The invention relates to the technical field of design and layout of a building photovoltaic system and renewable energy source evaluation, in particular to a mountainous area building surface solar energy potential evaluation method and device and a storage medium. The building surface solar energy potential evaluation method does not depend on traditional meteorological monitoring data and is suitable for coupling influence of cloud layer dynamic change and complex terrain shielding. By combining MODIS data, a digital elevation model and a machine learning algorithm, solar energy potential evaluation of the outer surface of a mountainous area town building without meteorological data can be realized, so that the problem that a traditional method depends on basic meteorological data is solved. Through the combination of three-dimensional modeling and multi-scale analysis, the limitation of an existing method under the influence of clouds, complex terrains and building shielding is overcome, particularly, the dynamic influence of cloud change and the shielding influence of the complex terrains can be effectively considered, the calculation efficiency and precision are improved, and the method is suitable for popularization and application. And a new technical path is provided for solar energy resource evaluation in mountainous cities and towns.

The invention relates to a weather modification work target cloud layer identification method, system and device and a medium, and belongs to the technical field of weather cloud layer identification, and the identification method comprises the steps: obtaining original cloud layer image data of a target cloud layer region, carrying out the preprocessing, and generating a standardized feature image; performing multi-level feature extraction on the standardized feature image based on a feature extraction network to generate a feature map; traversing the feature map based on a region suggestion network, and generating an initial detection result; performing feature alignment processing on the bounding box of the candidate region based on a region-of-interest pooling algorithm, and outputting feature vectors of the candidate region to a classification regression network to obtain a detection result set; performing full convolution segmentation operation on each candidate region in the detection result set to generate a pixel-level segmentation mask; the cloud cover proportion, the cloud layer category, the texture morphological characteristics and the vertical height parameters of the target cloud layer area are calculated respectively, and a cloud layer characteristic parameter set is constructed and obtained; the cloud feature recognition accuracy can be improved.

The invention provides a three-dimensional cloud type classification method, device and equipment based on multi-source meteorological data fusion, and a medium. The method comprises the following steps: acquiring satellite data, radar data, numerical mode data and ground observation data, and performing preprocessing; a three-dimensional cloud cover analysis method is adopted, the three-dimensional cloud cover of numerical mode data is used as a background field, and a multi-source data fused three-dimensional cloud cover lattice point field is formed; establishing and training a plurality of cloud type classification models by using an XGBOOST multi-classification method, and matching the corresponding cloud type classification models based on the diagnosis results of the solar elevation angle of each grid point of the multi-source data fused three-dimensional cloud cover grid point field at the monitoring moment and the cloud layer distribution in the vertical direction to obtain the cloud type classification of each cloud layer in the vertical direction. And generating a three-dimensional cloud type classification result to solve the problem that the three-dimensional cloud type classification monitoring is limited due to the lack of effective training samples due to the fact that only satellite data is used and cannot penetrate through the uppermost cloud layer to obtain a vertical structure.

The present application relates to the technical field of aviation meteorological support, and provides a meteorological display and alarm method, system, device and medium for aircraft navigation, which comprises receiving an aircraft route plan and collecting numerical weather forecasts of each place at the takeoff time of the aircraft; extracting wind speed, temperature, relative humidity, liquid water content and cloud droplet particle number density, and calculating the horizontal visibility, aircraft icing index, total cloud cover and aircraft turbulence index at the forecast time through adaptive attenuation interpolation based on feature perception; constructing an information box and a floating box of the route points on the aircraft route map; and performing meteorological display and alarm for aircraft navigation through the information box and the floating box according to the aircraft route plan. The present application uses regional meteorological forecast results to form meteorological forecast results for flight routes, can intuitively display the comprehensive meteorology on the route and form an alarm prompt, reduces the risk of information omission, increases the safety margin, and reduces the meteorological information processing workload of flight support personnel.

The invention relates to the technical field of irradiance estimation, in particular to an irradiance estimation method and device, electronic equipment and a storage medium, and the method comprises the following steps: obtaining ground site historical data of a research region, reanalysis data of the research region and an aerosol public data set; dividing weather types into clear sky samples and cloudy sky samples according to the obtained historical ground station data of the research area; inputting the clear sky sample, the reanalysis data and the aerosol public data set into a solar irradiance model to calculate clear sky expected irradiance GHIcs; obtaining observation data of a geostationary orbit meteorological satellite, and estimating a cloud cover coefficient CI by using satellite reflectivity; inputting the multi-cloud sky sample and the cloud cover coefficient CI into a cloud index-based semi-empirical model, and calculating a clear sky coefficient Kc; and multiplying the clear sky expected irradiance GHIcs by the clear sky coefficient Kc to obtain an irradiance estimation value under the all-sky condition. Through the improvement of the method, the regional adaptability and the estimation accuracy of irradiance estimation are improved.

The invention relates to the technical field of photovoltaic power generation power prediction, and discloses a photovoltaic power generation system output prediction system and method. According to the method, historical power generation data of a target photovoltaic power station and environment monitoring data including illumination intensity, environment temperature, assembly temperature, cloud coverage and the like are collected; time alignment processing is carried out on the data to form a synchronous data sequence, and then meteorological features and power generation features in the synchronous data sequence are extracted; the method comprises the following steps: constructing a dynamic correlation model of meteorological characteristics and power generation characteristics, calculating an instantaneous influence weight of meteorological fluctuation on power generation power, dividing sensitive time periods and non-sensitive time periods of the power generation power according to the instantaneous influence weight, extracting high-fluctuation meteorological characteristics in the sensitive time periods, and extracting steady-state meteorological characteristics in the non-sensitive time periods; and inputting the high-fluctuation meteorological characteristics into a first prediction network to generate a short-term power prediction value, inputting the steady-state meteorological characteristics into a second prediction network to generate a long-term power prediction value, and fusing the short-term power prediction value and the long-term power prediction value to generate a complete output power prediction curve.

Some embodiments of the present disclosure provide inventive concepts for estimating a value for an environmental heat stress index at a target microscale location. Meteorological data indicative of parameters such as relative humidity, air temperature, wind characteristics, or atmospheric cloud cover for a geographic area representative of a larger geographic area that includes the target microscale location can be obtained. Localized terrain data specific to the target microscale location can be obtained. A bias correction can be performed on the meteorological data based on the localized terrain data, generating microscale meteorological data that reflects conditions at the target microscale location. The heat stress index value, representing heat-related risk specific to the target microscale location, can be determined using the microscale meteorological data and can be a real-time or forecast value used for providing actionable insights or alerts for health and safety purposes.

An LSTM-Attention-OOA photovoltaic power prediction method based on similar daily clustering comprises the following steps: firstly, integrating historical photovoltaic power data and meteorological monitoring data (including irradiance, temperature, cloud cover and the like), and analyzing and screening key meteorological characteristics by using grey relational degree; similar daily clustering analysis is carried out through K-means, and an optimal clustering number is determined by adopting an elbow rule. And for different weather clusters, similar days are selected by using cosine similarity. And an LSTM-Attention-OAA prediction model is constructed: an LSTM layer captures a time sequence dependency relationship, an Attention mechanism dynamically allocates each time step weight to highlight an important meteorological period, an OOA is introduced to automatically adjust and optimize hyper-parameters, and autonomous optimization of model performance is realized. According to the method, through a progressive architecture of'feature screening-data clustering-intelligent prediction ', the prediction precision under different weather conditions is remarkably improved, and the method is of great significance in improving stable operation of a power system.

The invention discloses a mountainous area fog forecasting method, which comprises the following steps that: through the cooperative work of a satellite sub-module, a ground sub-module and a forecasting sub-module, the accurate forecasting of a foggy weather condition is realized, and the satellite sub-module records the complete cycle change of a cloud layer and an air temperature, extracts parameters and carries out space-time analysis; the ground submodule records fog visibility, aerosol concentration and air temperature data in real time; the prediction sub-module receives and processes the data, establishes a foggy day prediction model by using cloud computing and machine learning technologies, sets thresholds of different foggy day types, and predicts and judges the foggy day types by comparing the real-time monitoring data with the thresholds; by combining a satellite remote sensing image processing technology and ground real-time monitoring data, the system can obtain more comprehensive and accurate meteorological information, thereby improving the accuracy and reliability of foggy day prediction. A machine learning algorithm is utilized to train a large amount of historical data, so that the prediction model can learn rules and features generated by foggy days, and the prediction precision is improved.

The invention develops a surface temperature intelligent downscaling seasonal characterization and analysis method based on GeoAI machine learning. According to the method, interpolation and downscaling can be carried out on a surface temperature missing area influenced by cloud layer factors through urban landscape characteristic index products and incomplete satellite surface temperature inversion data. Through a specific stratified sampling mechanism, the problems of training deviation and over-fitting caused by insufficient representativeness of a data training set are solved, and a surface temperature product which takes seasons as units and has a 10m resolution ratio and a complete space-time sequence is generated. Verification shows that the method can accurately compensate for surface temperature data loss caused by factors such as cloud cover, ensures space integrity and time continuity of the surface temperature data, truly reflects the surface temperature of a research area when a satellite passes, and effectively represents seasonal space-time evolution of an urban thermal environment. Besides, the invention further develops a GeoAI-based feature importance intelligent evaluation framework, landscape features strongly related to the surface temperature can be analyzed and screened, scientific support and reference are provided for accurate characterization, modeling and optimization of the urban thermal environment, and the method has important application value.

The invention relates to the technical field of clean energy, and discloses a photovoltaic ultra-short-term power prediction method, which comprises the steps of obtaining radar cloud picture data of a target photovoltaic field station; taking the real-time radar cloud picture data as report starting data, and performing meteorological extrapolation based on the fused cloud cluster change characteristics of the radar cloud picture data to obtain extrapolated radar cloud picture data; inputting the extrapolated radar cloud picture data and the historical radar cloud picture data into a pre-trained extrapolated cloud picture correction model to obtain corrected radar cloud picture data; determining meteorological characteristics of the target photovoltaic station based on the corrected radar cloud picture data; performing photovoltaic power prediction on the target photovoltaic station based on the meteorological characteristics to obtain a photovoltaic power prediction result; the radar cloud picture data is used for meteorological feature extraction and photovoltaic power prediction, so that the influence of low precision of distributed photovoltaic ultra-short-term power prediction caused by complex weather phenomena with low precision or lack of cloud measurement can be reduced.

The invention relates to the technical field of data analysis, and provides a meteorological state prediction method and system based on a spatio-temporal interpolation coupling model.According to the embodiment of the invention, after credibility authentication of a meteorological forecast field database is passed, a historical meteorological forecast data set is called, and a dynamic influence area is divided by combining geographic position coordinate information of a target observation point; determining a cloud cover ratio time sequence change trend under the condition of no rainfall in the region, and building a meteorological state prediction model of space-time interpolation coupling by combining the visibility state parameters; and then inputting the current meteorological observation data set into the meteorological state prediction model, carrying out spatial-temporal feature coupling calculation to obtain a current state feature vector, and generating a meteorological state prediction result that the target observation point contains a nepheline state within a preset time period based on the current state feature vector, thereby effectively improving the accuracy and reliability of meteorological prediction.

The invention provides a photovoltaic power generation prediction method and device, and the method comprises the steps: collecting an atmospheric motion vector diagram (including a lower-layer wind field, a middle-layer wind field and an upper-layer wind field), and determining a target region and an adjacent search region. The method comprises the following steps: extracting cloud factors from a search area, and converting the cloud factors into cloud influence factors of each wind field on the cloud amount change of a target area; carrying out support vector machine (SVM) regression training by taking the cloud influence factor and the cloud factor as inputs and taking the cloud cover and the irradiance prediction value of the target area as outputs; and evaluating the prediction performance of the trained SVM and then deploying the SVM to predict photovoltaic power generation. Through extraction and analysis of an atmospheric motion vector diagram (AMV) and combination of SVM regression training, accurate prediction of the cloud cover and irradiance of a target area is realized, and then prediction of photovoltaic power generation is realized.