268 results about "Spatiotemporal resolution" patented technology

The invention relates to a method for constructing a high-resolution atmosphere carbon dioxide concentration data set based on XGBoost-BO, and belongs to the technical field of environment monitoring and artificial intelligence modeling. The method comprises the following steps: preprocessing OCO-2 satellite data and multi-source auxiliary data, and fusing the preprocessed OCO-2 satellite data and multi-source auxiliary data to obtain a new data set; a Bayesian optimization method is adopted to search for an optimal hyper-parameter, a target function is optimized through second-order Taylor expansion, a regular term is introduced to control the complexity of the model, and ten-fold cross validation is used to evaluate the performance of the model; quantizing the contribution degree of each feature to model prediction through a tree SHAP method, and analyzing global feature importance ranking and feature contribution distribution of individual samples; and performing model verification by using the test set and the site actual measurement data. According to the method, the problems that an existing model-based reconstruction method is insufficient in interpretation and prone to falling into local optimum are solved, and the temporal-spatial resolution of CO2 concentration monitoring can be improved.

The invention discloses a geological disaster risk intelligent pre-judgment method based on deep learning, and relates to the technical field of geological disaster monitoring and early warning. According to the method, high-precision alignment and feature extraction can be automatically performed on monitoring data with different temporal-spatial resolutions and different physical meanings, such as optical remote sensing, radar measurement, laser point cloud and the like, uniform and information-rich representations are generated, a solid data foundation is laid for subsequent accurate prediction, and the limitation of data splitting application in a traditional method is overcome; a space-time diagram with slope units as nodes is constructed, an attention mechanism diagram convolutional network with hydrological directivity introduced is utilized, and the model can accurately describe the spatial propagation process that slope substances migrate and accumulate along with a confluence path and block a river channel under the rainfall condition; meanwhile, the time sequence module effectively learns the influence of the past hydrological state on the future evolution trend.

The invention provides a high-temporal-spatial-resolution full-profile real-sea accurate corrosion test method and system, and the method comprises the steps: dividing the sea level into three layers of monitoring regions, namely an atmospheric near-sea-level layer, a sea-gas boundary layer and a seawater mixing layer, deploying corresponding sensor arrays in each monitoring region, and synchronously collecting the environmental parameters of each layer in real time; a standard corrosion coupon and a corrosion monitoring sensor for monitoring the local corrosion state of the sample are arranged in each monitoring area; performing space-time alignment on the acquired data to form an environment-corrosion strong association data set; an atmosphere-ocean coupling forecasting system is constructed, simulation and prediction of future environmental parameters are achieved, simulation results serve as input variables of a corrosion prediction model, and a material corrosion life prediction model is established in combination with historical test data. According to the invention, synchronous monitoring of multi-dimensional environmental parameters and material corrosion data within a range of 30 meters above and below the sea level can be realized, and an accurate basis is provided for material selection and corrosion prediction of marine equipment.

The invention relates to the technical field of computers, and discloses a real-time rendering and interaction method and system for an immersive virtual reality scene. The method comprises the following steps: fusing tuner inertial data and eyeball tracking data, and constructing a prospective state prediction model; generating a predictive focus field in combination with scene visual saliency; synthesizing an anisotropic temporal-spatial resolution graph according to the predicted head angular velocity; gPU variable-rate coloring is driven to realize non-uniform rendering; and re-projection or dynamic fuzzy correction is executed in a self-adaptive manner according to the attitude prediction error before display. According to the technical scheme, the perception delay and the rendering load are remarkably reduced, and the frame rate stability and the visual immersion in a high-dynamic scene are improved.

The invention discloses a water vapor chromatography modeling method and device based on GNSS-MET, and belongs to the technical field of atmospheric water vapor information inversion. According to the method, satellite signals and meteorological parameters are obtained through a GNSS-MET receiver, and the oblique path water vapor content (SWV) is calculated to serve as chromatography input; densely and uniformly distributed observation stations are selected to construct a chromatography area, and voxel grids are divided; a horizontal constraint is constructed by using Gaussian distance weighting, a vertical constraint is constructed in combination with a water vapor vertical index distribution characteristic, and ERA5 reanalysis data is introduced as a prior constraint, so that the limitation of a traditional sounding data constraint is solved; and resolving the tomographic equation through a singular value decomposition (SVD) method to obtain three-dimensional water vapor density distribution. According to the method, the high temporal-spatial resolution characteristic of ERA5 data is utilized, the precision and reliability of water vapor chromatography are remarkably improved, and the method is suitable for the fields of extreme weather prediction, meteorological monitoring and the like.

The invention discloses a thunder approaching prediction method and device based on multi-source meteorological data, and particularly relates to the technical field of thunder disaster prediction.The method comprises the steps that standardization processing of temporal-spatial resolution unification is conducted on meteorological satellite data, radar data and lightning positioning data, and standardized temporal-spatial input data is generated; then spatial-temporal features are extracted through a depth separable 3D convolution module, and a compressed spatial-temporal feature graph is generated; then, a channel-space double attention mechanism (CPCA) is applied to the compressed feature map for feature optimization; and finally, processing the optimized feature map through a coding-decoding structure, and outputting a thunder and lightning probability distribution map. According to the method, the problem of spatial-temporal resolution difference and physical feature mismatching in multi-source data fusion is innovatively solved, the calculation efficiency is remarkably improved through a lightweight network architecture, the feature expression ability is enhanced by using an attention mechanism, and high-precision prediction of sudden thunder and lightning events is realized.

The invention provides a high-resolution emission flux inversion system and method. The method comprises the following steps: collecting atmosphere multi-source data; determining a distance weighting function, and calculating the correlation between the grid points in the simulation area and the observation value; generating a set sample meeting physical constraints of the assimilation object; performing singular value decomposition and dimension reduction on the set samples; replacing a tangent line and an adjoint mode of a regional air quality mode with a mixed assimilation method, and obtaining a simulated regional space grid point analysis increment; obtaining corrected concentration and flux distribution data; the data is used for carrying out emission flux inversion, and the unit time emission flux of different positions is estimated. According to the method, a traditional four-dimensional variation mode is replaced with a mixed assimilation method, and the calculation and programming difficulty is reduced; generating a set sample by using a four-dimensional sliding sampling algorithm, reducing dimensions, and calculating resource consumption; a joint assimilation algorithm is introduced to optimize the concentration and flux field, and accurate inversion of the high-temporal-spatial-resolution emission flux is achieved.

The invention discloses a large-scale regional sea wave rapid forecasting method and device based on data driving, and the method comprises the steps: obtaining multi-source marine physical environment data of a target sea area, and generating a standard physical field data flow with unified temporal-spatial resolution; constructing a multi-channel space-time input tensor containing wind field driving information, terrain boundary information and historical wave state information; the difference between the predicted wave height and the real wave height is minimized through a back propagation mechanism, so that a trained wave height prediction model is obtained; receiving latest wind speed field data output by a real-time observation or numerical forecasting mode, and outputting a sea wave significant wave height prediction field at a future target moment; the device is used for implementing the method. According to the technical scheme of the method provided by the invention, through a physical lag alignment mechanism, the time delay of transmitting wind energy to wave energy is accurately captured, and the modeling precision is improved; and meanwhile, rapid deduction of a large-scale sea wave field is realized based on deep learning, and high accuracy and high timeliness are achieved.

The invention relates to a geological disaster early warning algorithm based on hyperspectral and Internet of Things data fusion analysis, and relates to the technical field of geological disaster monitoring and early warning, the geological disaster early warning algorithm comprises the following steps: S1, preprocessing hyperspectral data and Internet of Things data, and respectively extracting spectral-spatial features and dynamic topology time sequence features; s2, fusing the spectrum-space features and the time sequence features to generate cross-modal joint features; s3, performing parameter optimization on the fusion features through a quantum-classical hybrid optimization algorithm, and calculating a disaster risk probability; and S4, based on the optimization result and the risk probability, executing an edge-cloud collaborative early warning decision. According to the method, through non-negative tensor ring decomposition of the hyperspectral data and dynamic topology modeling of the Internet of Things, the limitation of a traditional single data source in temporal-spatial resolution and physical relevance is solved, multi-dimensional joint extraction of spectrum-space-mechanical characteristics can be realized, and the characterization precision of a rock-soil body deformation evolution law is remarkably enhanced.

The invention discloses a point cloud-driven thoracic cavity whole organ dynamic reconstruction and respiration monitoring method and system, and the method comprises the steps: constructing a three-dimensional geometric model corresponding to each target structure in a thoracic cavity based on the thoracic medical image data of a target object, and converting the three-dimensional geometric model into static point cloud data; driving the static point cloud data to perform dynamic deformation simulation in a respiratory cycle based on a respiratory movement rule of the target object to obtain dynamic point cloud data synchronized with a respiratory time phase; performing time-space synchronization association on the dynamic point cloud data and the electrical characteristic parameters, and constructing a digital twin thoracic cavity model; deploying a virtual sensing assembly which dynamically deforms along with the thoracic cavity in the digital twin thoracic cavity model, simulating and monitoring the dynamic breathing process of the target object, and generating a virtual physiological signal; and performing signal processing on the virtual physiological signal to obtain a dynamic reconstruction image reflecting respiratory movement. Continuous simulation of the full-breathing movement process is achieved, and the temporal-spatial resolution and diversity of a virtual database are improved.

The invention relates to a multi-source meteorological data fusion technology, and discloses an air temperature reconstruction method fusing data of a micro-meteorological device, which improves the temporal-spatial resolution and precision of ground temperature under a complex terrain. The method comprises the following steps: densely deploying micrometeorological devices in a complex terrain area to obtain high-frequency observation data, carrying out quality control, and carrying out hierarchical processing in two dimensions of space and time by taking pattern forecast grid point data as an initial background field: in the spatial dimension, dynamically updating a fusion weight for grid points with observation stations by using geographical weighted regression, and carrying out data fusion; a residual machine learning model is combined with multi-topographic feature correction for grid points without observation stations, and a high-precision space fusion background field is generated; in the time dimension, errors after space fusion are decoupled into a trend term and a periodic term, an autoregressive integral moving average model is used for predicting a trend, a Fourier algorithm is used for correcting a periodic phase, and then time dimension machine learning correction is carried out on a grid point of an observation-free station. And finally, complete-process automatic, high-temporal-spatial-resolution and low-error complex terrain area air temperature reconstruction is realized.

A device and system for real-time visualization of the electrophysiologic activity of a brain, particularly at the cortical surface. The neural device can acquire, process, and display high-spatiotemporal-resolution electrophysiologic data in real-time across entire electrode arrays spanning many thousands of electrodes over identified anatomic regions. The system is compatible with thin-film cortical surface electrodes that record from neural tissues without damaging those tissues. The system can be used to guide diagnostic and therapeutic actions with high precision, and also provides the basis for a brain-computer interface.

The invention discloses a land-sea overall land and land space planning method and system, and the method comprises the steps: collecting remote sensing data, marine environment monitoring data and basic geographic and social economic data of a research region, and carrying out the denoising, format conversion and time-space registration preprocessing of the data; fusing the preprocessed data by adopting an enhanced self-adaptive space-time reflectivity fusion model to generate a unified data set with high space-time resolution; constructing a three-level classification system based on the fused data set, carrying out land space suitability dynamic evaluation by adopting an adaptive weighting algorithm, and outputting a classification result and a suitability score; and taking the suitability scoring result as input, performing multi-objective optimization solution by adopting an improved non-dominant genetic algorithm, and generating and outputting a land-sea land space planning scheme. According to the method, the problem of differences of land and sea data in source, format, resolution and updating frequency is effectively solved, a unified space-time reference is established, and the data integration capability and the accuracy of a planning foundation are remarkably improved.

The invention relates to a high-precision land carbon flux reconstruction method based on four-dimensional space-time deep learning. The method comprises the steps of obtaining a multi-source heterogeneous data set and performing preprocessing; constructing a four-dimensional space-time deep learning model architecture which is sequentially connected with a multi-scale space-time feature extraction module, a space-time feature fusion module, a prediction layer and an uncertainty quantization layer from input to output, and taking the preprocessed multi-source heterogeneous data set as input and a carbon flux reconstruction result as output; constructing a loss function, adopting a hierarchical learning rate strategy and introducing a cosine annealing scheduler, and training a four-dimensional space-time deep learning model architecture based on the preprocessed multi-source heterogeneous data set to obtain a four-dimensional space-time deep learning model; and obtaining a carbon flux data reconstruction set, and inputting the four-dimensional space-time deep learning model to generate a carbon flux reconstruction result. By adopting the method, multi-source heterogeneous data can be effectively integrated, the complex spatial-temporal dynamic characteristics of the carbon flux are captured, and accurate reconstruction of the land carbon flux with high spatial-temporal resolution is realized.

The invention relates to a glacier change assessment method based on multi-source data fusion, and the method comprises the steps: collecting radar interference measurement data, optical image data and GPS actual measurement data of a target glacier region, and constructing a multi-source data set; the multi-source data set is preprocessed and then fused, and a fused flow velocity field is obtained; performing spatial gradient analysis on the fused flow velocity field to obtain a local change rate of the flow velocity field, judging a sudden motion event based on the local change rate, and obtaining a motion event distribution diagram; constructing a dynamic flow velocity field for a sudden motion area in the motion event distribution diagram, calculating glacier surface stress distribution, and obtaining glacier motion state distribution; and carrying out time sequence analysis on the glacier motion state distribution, obtaining the change trend of the motion state, evaluating the change condition, and completing the change evaluation of the target glacier area. By integrating the multi-source remote sensing data, the temporal-spatial resolution and precision of glacier change monitoring and evaluation are improved.

The invention belongs to the field of degraded grassland restoration evaluation research, and discloses a degraded grassland restoration evaluation research method based on multivariate remote sensing data, and the method comprises the steps: carrying out the observation through employing a FragMap unmanned aerial vehicle aerial photography analysis system, and carrying out the preprocessing through employing Pixel Base Management Classifier software; collecting grassland above-ground biomass data; acquiring and preprocessing remote sensing data; constructing a grassland coverage and aboveground biomass remote sensing estimation model, and performing precision verification; analyzing grassland coverage and biomass space difference before and after restoration of the degraded grassland; and analyzing space-time dynamic changes of grassland coverage and biomass. According to the method, a high-temporal-spatial-resolution NDVI data set of a research area is constructed by combining a high-temporal-spatial-resolution data fusion algorithm, a grassland coverage and aboveground biomass remote sensing estimation model is constructed by combining ground survey and unmanned aerial vehicle aerial photography, and the grassland coverage and aboveground biomass change conditions before and after a degraded grassland restoration measure is implemented are systematically evaluated. And the restoration effects of different restoration measures on the degraded grassland are evaluated.

The invention discloses a regional ionosphere temporal-spatial resolution refinement method, which comprises the following steps: acquiring real-time GIM data, a solar activity index and a geomagnetic activity index, inputting the data into a trained forecasting model, and outputting a VTEC mean value of a grid center point; calculating an STEC value based on the output VTEC mean value; the training of the forecasting model comprises the following steps: acquiring original GIM data and CORS observation value data, and respectively preprocessing the original GIM data and the CORS observation value data to obtain GIM-VTEC calculated based on the GIM data and puncture point VTEC calculated based on the CORS observation value data; the GIM-VTEC obtained through preprocessing and the puncture point VTEC are matched according to the time and the grid range; acquiring a solar activity index and a geomagnetic activity index, matching the solar activity index and the geomagnetic activity index with the matched VTEC data according to time, and constructing a training sample set; constructing a BP neural network, taking time, longitude, latitude, GIM-VTEC, a solar activity index and a geomagnetic activity index as input, and taking a puncture point VTEC obtained by calculating CORS observation value data as output; and training is carried out on the constructed training sample set, and a trained forecasting model is output.

The invention provides a high-enthalpy shock tunnel free flow electron density two-dimensional diagnosis system and method. The system comprises a laser, a sheet light assembly, a double-camera imaging system, a time sequence synchronizer, a work station and other core components. NO molecules in a flow field are excited by laser to generate fluorescence, two fluorescence images with nanosecond delay are obtained by using a spectroscope and two sets of synchronous acquisition systems, fluorescence lifetime two-dimensional distribution is calculated based on a fluorescence intensity ratio, and then two-dimensional space distribution of electron density is obtained through inversion of a physical model. Non-contact measurement is achieved, interference of a traditional probe on a flow field is avoided, the method has the outstanding advantages of two-dimensional visualization, high temporal-spatial resolution, high measurement precision and the like, and a reliable diagnosis means is provided for high-enthalpy flow field characteristic research and aircraft communication performance evaluation.

The invention relates to the technical field of water ecological environment remote sensing monitoring, in particular to a river total nitrogen concentration remote sensing estimation method based on multi-source data fusion, and the method comprises the following steps: S1, obtaining and processing total nitrogen measured data, and unifying time and a coordinate reference system; s2, processing the Landsat 8 / 9 image, and extracting water body reflectivity and remote sensing indexes; s3, ERA5-Land meteorological data are acquired, and derivation indexes are calculated; s4, DEM elevation data are extracted; s5, fusing the multi-source data to generate a table type data set; s6, screening sensitive indexes based on SHAP and correlation; s7, constructing and evaluating an inversion model; s8, extracting an MNDWI water body mask; s9, generating a feature stack and inverting and outputting a total nitrogen concentration diagram; according to the method, through fusion of multi-source data, construction of a high-precision inversion model and a cloud platform automatic processing flow, high-temporal-spatial-resolution, stable and reproducible remote sensing estimation of the total nitrogen concentration of the river is realized, and the monitoring efficiency and the application value are effectively improved.

The invention provides a shipborne temperature and salt drag data space-time correction method and system based on dynamic positioning, and the method comprises the steps: collecting drag chain attitude data and ship maneuvering data in real time, and obtaining an initial three-dimensional offset estimation value; obtaining corrected drag chain attitude data based on the initial three-dimensional offset estimation value and the marine environment interference information; if the corrected drag chain attitude data shows that the position deviation parameter exceeds a preset deviation threshold value, ship maneuvering data are corrected, and real-time space positioning coordinates of the drag chain are obtained; on the basis of the real-time space positioning coordinates, correcting a ship-borne temperature and salt dragging data acquisition time sequence to obtain matched geographical attribution information; and if the matched geographical affiliation information and the preset initial geographical affiliation data are misplaced, the dynamic deviation parameter is adjusted, and a space-time synchronization correction value is obtained. According to the method, a dynamic positioning technology is utilized, the space-time error of the shipborne thermohaline drag chain data is corrected in real time, the space-time consistency of the data is ensured, and the space-time resolution of the thermohaline data is improved.

The invention discloses a method for inverting a cloud condensation nucleus number concentration profile based on a laser radar and a neural network. The method comprises the following steps: collecting multi-wavelength laser radar data including a backscattering coefficient vertical profile, an extinction coefficient vertical profile, a laser radar ratio and a depolarization ratio; the method comprises the following steps: acquiring an atmospheric temperature profile and a water vapor mixing ratio profile which are in time-space synchronization with multi-wavelength laser radar data, performing grid alignment on a vertical height, and constructing a multi-channel input feature set for each preset target supersaturation ratio; and constructing a convolutional neural network profile inversion model, taking the multi-channel input feature set as input and the cloud condensation nucleus number concentration profile data as output, training the model, and obtaining the trained convolutional neural network profile inversion model. According to the method, the limitation of continuous, high-precision and high-temporal-spatial-resolution detection of CCN number concentration vertical distribution is overcome, and key data support is provided for the fields of weather forecast, climate models, artificial influence weather and the like.

The invention provides a hydraulic engineering space-time heterogeneous deformation signal decoupling and analysis method, and belongs to the technical field of deformation monitoring, and the method comprises the following steps: collecting Beidou observation data, InSAR images and environment monitoring data; performing data processing on the Beidou observation data and the InSAR image to obtain a three-dimensional deformation result; carrying out data cleaning on the processed Beidou observation data, the processed InSAR image and the processed environment monitoring data; and performing data analysis on the cleaned data, performing space-time decomposition and classification on the high space-time resolution displacement sequence, extracting deformation components with different scales and characteristics, and performing correlation analysis on each deformation component and environment monitoring data to identify and explain a physical driving mechanism of deformation. According to the invention, based on multi-source data such as Beidou observation data, InSAR images and environment monitoring data, superposition features of high temporal-spatial resolution deformation monitoring results are extracted and separated by using an ICA method, and the requirements of hydraulic engineering on accurate identification and classification of deformation features in different modes and corresponding mechanism explanation are met.

The invention discloses a space-time fusion method for lake chlorophyll a concentration remote sensing inversion, and relates to the technical field of environment monitoring. Wherein a plurality of chlorophyll a concentration inversion graphs are generated through multi-source satellite data, space, time and attribute three-dimensional features are extracted based on the plurality of chlorophyll a concentration inversion graphs, and finally collaborative fusion of multi-dimensional features is realized through a tensor fusion mechanism. Thus, through integration of multi-source remote sensing images, high temporal-spatial resolution extraction of the lake surface chlorophyll a is realized, cooperative utilization of multi-dimensional features is completed in a decision-making layer, fundamental bottlenecks of a traditional fusion method in the aspects of physical significance transparency and data universality are overcome, the temporal-spatial change trend of lake water quality parameters can be further mastered, and the method is suitable for being applied to lake water quality monitoring. And the development of lake water environment research is further promoted.

The invention discloses a conditional diffusion method for reconstructing multi-source meteorological data for tropical cyclones. The conditional diffusion method comprises the following steps: acquiring an infrared radiation brightness set, a polarization correction temperature set and a sea surface wind speed of different tropical cyclones in a specified historical period; constructing a polarization correction temperature reconstruction model based on the conditional diffusion model; the input of the polarization correction temperature reconstruction model is an infrared radiation brightness temperature set, and the output target is a polarization correction temperature set; carrying out transfer learning on the trained polarization correction temperature reconstruction model to form a sea surface wind speed reconstruction model; the input of the sea surface wind speed reconstruction model is an infrared radiation brightness temperature set, and the output target is the sea surface wind speed. Therefore, the mapping relation from the infrared radiation brightness temperature to the multi-source meteorological data is established through generative deep learning of conditional diffusion, so that the multi-source meteorological data with the temporal-spatial resolution the same as that of geostationary orbit observation is reconstructed, and good performance is shown on various meteorological indexes and computer vision indexes.

The invention discloses a near-infrared two-region dual-channel fluorescent nanoprobe as well as a preparation method and application thereof, and relates to the technical field of biomedical imaging. A nano probe A and a nano probe B included in the near-infrared two-region dual-channel fluorescent nano probe are both of a core-shell structure, two NIR-IIb fluorescent nano probes adaptive to different excitation wavelengths (808 nm and 980 nm) are constructed by precisely regulating and controlling the types and proportions of lanthanide elements, dual-channel imaging is achieved, limitation of a single excitation wavelength is broken through, spectral crosstalk is eliminated, and the near-infrared two-region dual-channel fluorescent nano probe has the advantages of high sensitivity, high sensitivity, high sensitivity and the like. The method has the characteristics of material uniformity and biological safety. The near-infrared IIb region dual-channel imaging system has the characteristics of high temporal-spatial resolution and signal separation, and has significant application value in the field of living body multi-target synchronous observation. Compared with a traditional two-photon microscope technology, the imaging method has a wider observation view field, a local craniotomy operation does not need to be carried out on an experimental mouse, and physiological trauma is remarkably reduced.

The invention provides a brain-computer interface motor imagery real-time control method and system fusing multi-modal feature extraction and dynamic decision, electronic equipment and a storage medium, and the method comprises the steps: obtaining a high-temporal-spatial-resolution electroencephalogram signal through a multi-channel electroencephalogram signal collection device, and covering a target brain region to support a motor imagery task; the system preprocesses the electroencephalogram signals and generates high-quality input data through filtering and standardization; a multi-modal feature extraction method is adopted, and spatial domain and time frequency features are fused to generate a comprehensive feature vector; generating classification probability distribution according to the comprehensive feature vector through a dynamic decision-making mechanism; based on confidence threshold judgment, outputting a control instruction or triggering a re-calibration process; and through real-time feedback and personalized adjustment, the motor imagery control performance is optimized. According to the method, the control precision and the response speed of the brain-computer interface system are remarkably improved by fusing the multi-dimensional features and a dynamic decision-making mechanism.

The invention provides a meteorological prediction method and device, and the method comprises the steps: obtaining state variable data at a prediction starting moment in a target region, and enabling the state variable data to serve as initial state variable data, and the state variable data comprises meteorological data and environment variable data; inputting the initial state variable data into a pre-constructed target meteorological prediction model to obtain meteorological prediction data of a predicted target moment; wherein the target meteorological prediction model is obtained by training layer by layer by using a pre-constructed sample data set based on a machine learning algorithm and an atmospheric motion multi-scale theoretical framework; the sample data set comprises multi-level meteorological data samples. According to the invention, based on an atmospheric motion multi-scale theoretical framework, a machine learning algorithm is combined, a physical mechanism and data driving deep fusion ultrahigh temporal-spatial resolution meteorological prediction model is constructed, and meteorological prediction with high accuracy and few occupied computing resources is realized.

The invention discloses an ionized layer three-dimensional electron density chromatography method based on a space-time coding neural network. The method comprises the following steps: acquiring electron density profile data and driving parameters; aligning the electron density profile data and the driving parameters according to a space-time grid to obtain an electron density data set; the electron density data set is input into an implicit neural network for training, an ionosphere three-dimensional electron density model is obtained, and the implicit neural network is obtained through construction based on space-time coding and a multi-layer perceptron algorithm; and simulating or predicting the three-dimensional electron density value of the ionized layer by using the three-dimensional electron density model of the ionized layer. By fusing the multi-source occultation electron density data and the solar geomagnetic driving factor, high-precision and high-temporal-spatial-resolution ionosphere tomography, namely ionosphere three-dimensional electron density reconstruction, can be realized, and quasi-real-time high-precision ionosphere monitoring can be realized.

The invention discloses a multi-scale heterogenous remote sensing data collaborative water quality inversion method, computer equipment and a medium, and belongs to the technical field of water quality remote sensing monitoring. S3, an inversion model is constructed, and the step S3 comprises the steps of S31, wave band combination optimization and correlation analysis; s32, constructing a multi-scale heterogeneous remote sensing data collaborative fusion inversion model; and S33, multi-source data collaborative wave band selection and model determination. According to the method, high-frequency and high-spatial-resolution water quality inversion is realized, the spatial-temporal resolution and precision are improved, a more comprehensive and accurate water quality inversion model is constructed, the robustness of the model in a turbid water body and an eutrophicated water body is remarkably improved, the adaptability to a complex water body is enhanced, and the method is suitable for large-scale popularization and application. An efficient and economical technical means is provided for water quality inversion in a complex water body environment, and the method has remarkable low cost and universality.

Disclosed is a server for expanding the spatio-temporal resolution of weather data and providing the same to a terminal, the server comprising: a reception unit for receiving weather data having a preset spatial resolution and temporal resolution from a weather model; a conversion unit for converting the received weather data into matrix data including forecast values for each longitude and latitude; an expansion unit for dividing the longitudes and latitudes of the matrix data more finely than the preset spatial resolution and interpolating the forecast values at positions of the divided longitudes and latitudes to expand the spatial resolution; and a transmission unit for transmitting the weather data with the expanded spatial resolution to the terminal.