150results about How to "Guaranteed prediction accuracy" patented technology

The invention discloses an efficient skin disease segmentation method based on multiple scales and a mixed attention mechanism, and the method comprises the steps: firstly carrying out the preprocessing of a skin mirror image through data enhancement, and then inputting the skin mirror image into a convolutional neural network for feature extraction, thereby obtaining a skin lesion segmentation region prediction map. According to the method, the convolutional neural network is applied, multi-scale features of local information and global information can be extracted from a skin mirror image, and the feature representation capability is enhanced through feature fusion. The objective of the invention is to solve the problems of changeable lesion areas, irregular shapes and the like of skin disease images, and improve the accuracy and robustness of skin disease image segmentation.

The invention belongs to the technical field of power prediction, and discloses a new energy power prediction method and system based on multi-source meteorological data fusion, and the method comprises the steps: obtaining meteorological data from different meteorological data sources in real time or at regular time through a data obtaining module; carrying out preliminary screening and preprocessing on the obtained data by utilizing a data processing module; the data fusion module is used for integrating meteorological data from different sources by adopting an advanced data fusion algorithm to eliminate data redundancy; a mathematical model or a machine learning model suitable for new energy power prediction is constructed by using the prediction model module based on meteorological data of multi-source fusion; and the result output and evaluation module is used for outputting the prediction result to a user in a visual form, and carrying out real-time or regular evaluation on the prediction result. The method has the characteristics of diversified data sources, advanced data fusion technology, flexible prediction model construction, high real-time performance and accuracy, wide application scenarios and the like.

The invention provides a converter steelmaking endpoint carbon temperature prediction method and device based on adaptive data enhancement, and relates to the technical field of converter steelmaking. The method comprises the following steps: preprocessing data in a historical production data set in a converter steelmaking process; the preprocessed data set is processed through an adaptive SMOTE data enhancement technology; building a steelmaking endpoint carbon temperature prediction model based on the random forest; and training a steelmaking end point carbon temperature prediction model according to the processed data set, and obtaining a converter steelmaking end point carbon temperature prediction result according to the trained adaptive data enhanced steelmaking end point carbon temperature prediction model. The invention aims to improve the sample size and diversity of a data set in the converter steelmaking process by using a data preprocessing method and a self-adaptive SMOTE data enhancement algorithm, remove redundant information, reduce the labor cost of manual arrangement and data processing, and introduce a self-adaptive mechanism according to the data distribution density and different working conditions. And the generalization ability and the prediction precision of the model are improved.

The invention discloses a semi-supervised learning flow field prediction method based on a Gaussian mixture model. The method comprises the steps of obtaining a flow field calculation data set through a CFD calculation method; dividing the data set into a marked flow field data set, an unmarked flow field data set and a verification set; according to the marked flow field data set, constructing a flow field prediction model based on deep learning; training the flow field prediction model to obtain pseudo-labeled flow field data; respectively training the mixed data set by using the flow field prediction model and a pre-constructed decoder model; obtaining a simple sample in the pseudo-labeled flow field data through a bipartite Gaussian mixture model based on a design loss function; adding the simple samples into the flow field prediction model in an equal proportion until the training is completed; and verifying the flow field prediction effect by using the verification set to obtain a modeling flow field. By effectively utilizing the unmarked data, the prediction capability of the model under the condition of processing an unknown flow field is greatly enhanced while the prediction precision is maintained.

The invention relates to the technical field of photovoltaic power generation, and discloses a photovoltaic power generation capacity time sequence prediction method based on an improved Transform model, and the method comprises the following steps: S1, carrying out the cleaning and standardization processing of environment data and power generation capacity data; s2, extracting local features from the input multivariate time sequence data by using a convolutional layer; s3, introducing a new dynamic weight adjustment module, and dynamically adjusting the attention weight according to the correlation between the environmental factors and the power generation amount; s4, proposing a staged decoding mechanism, reducing the calculation amount through preliminary prediction and refined decoding, and paying attention to important information; s5, performing end-to-end training on the model in combination with the optimized attention mechanism and the generative decoder; and S6, using the trained model to carry out generating capacity prediction on new data, and using an evaluation index to evaluate a prediction result.

The invention relates to a machine tool thermal error modeling method based on a time convolution network and transfer learning, which comprises the following steps: data acquisition: providing a network based on an encoder-decoder architecture based on the time convolution network, inputting the acquired data of source (sufficient) and target (few) machine tools into an encoder, and carrying out data processing on the encoder; the method comprises the following steps of: coding and decoding to output a reconstruction sequence, and adding a reconstruction loss function which is calculated by the reconstruction sequence output by a decoder on a loss function with only one predicted value, so that deep features in thermal error data can be extracted through the architecture, and the prediction precision is improved; in order to achieve enough prediction precision on another target machine tool, transfer learning is used to obtain a loss function adapted to a field, the loss functions are summarized, iterative updating is repeated until deep learning regression algorithm training is completed, and accurate prediction of the thermal error value on the target machine tool is realized.

The embodiment of the invention provides a die forging equipment hydraulic system energy consumption prediction method with a self-learning function, and belongs to the technical field of data processing, and the method specifically comprises the steps: analyzing the energy consumption characteristics of an energy conversion unit of a die forging equipment hydraulic system, and obtaining the key energy consumption characteristics of the die forging equipment hydraulic system; an energy consumption data set is extracted and preprocessed, and an energy consumption feature set corresponding to the data information is extracted in combination with the key energy consumption features; based on the key energy consumption characteristics and the energy consumption characteristic set, using different energy consumption prediction fusion algorithms to construct an energy consumption prediction sub-model of each energy conversion unit; optimizing each energy consumption prediction sub-model through an incremental learning and transfer learning algorithm; evaluating each optimized energy consumption prediction sub-model through cross validation and a preset evaluation index; and performing energy consumption prediction on the energy conversion unit of the hydraulic system of the die forging equipment by utilizing each optimized energy consumption prediction sub-model. Through the scheme disclosed by the invention, the prediction efficiency, accuracy and adaptability are improved.

The invention discloses a method and device for predicting the geological storage amount of carbon dioxide and a medium, and relates to the technical field of carbon dioxide capture, utilization and burying. The method comprises the steps that whether a to-be-predicted oil and gas reservoir and a control oil and gas reservoir are in the same block or not is judged; if yes, inputting the geological data, the production dynamic data and the injection parameter combination scheme of the to-be-predicted oil and gas reservoir into the optimal control oil and gas reservoir carbon dioxide geological sequestration quantity prediction model to determine the whole-area accumulated carbon dioxide geological sequestration quantity of the to-be-predicted oil and gas reservoir; if not, geological data, production data and an injection parameter value range of the to-be-predicted oil and gas reservoir are obtained, migration training is conducted on the optimal control oil and gas reservoir carbon dioxide geological sequestration quantity prediction model, and a to-be-predicted oil and gas reservoir carbon dioxide geological sequestration quantity prediction model is obtained; and determining the whole-area accumulated carbon dioxide geological sequestration amount of the to-be-predicted oil and gas reservoir. According to the invention, the precision and efficiency of carbon dioxide geological sequestration quantity prediction are improved.

The invention discloses a TBM card machine risk comprehensive identification method. The method comprises the following steps: S1, defining a TBM card machine risk level; s2, constructing a TBM card machine risk prediction system; s3, advanced judgment and identification of TBM card machine risks are carried out; s4, TBM card machine risk approaching identification is carried out; s5, drilling and coring; and S6, thrust and torque analysis. According to the method, a surrounding rock detection method for a long distance and a short distance is established, TBM jamming risk comprehensive judgment combining multiple modes of advanced geological forecast, tunneling parameter judgment, slag state judgment, drilling and coring judgment and escape critical state judgment is achieved, the number of times of drilling and coring development is reduced while the prediction precision is guaranteed, and the prediction efficiency is improved. The probability of misjudgment and missed judgment is reduced to the maximum extent, and the method has wide popularization value and remarkable economic and social benefits.

The invention discloses a turbulent boundary layer wall surface pressure pulsation prediction method based on deep learning, and belongs to the field of noise prediction, and the method comprises the steps: training a neural network based on unsteady and steady flow simulation data of wall surface grid points to obtain a turbulent boundary layer wall surface pressure pulsation prediction model; a large batch of samples are obtained through one-time simulation calculation, the cost of sample obtaining can be obviously reduced, a large amount of time is saved, and therefore the prediction precision and timeliness of the deep learning model are guaranteed; the nonlinear relation between the turbulent boundary layer parameters and the wall surface pressure pulsation frequency spectrum is established through a deep learning method, a clear mathematical formula is not needed, and meanwhile the difficulty of mathematical requirements is reduced; compared with a traditional prediction method, the method provided by the invention is higher in applicability, wider in application field and higher in generalization ability; in addition, through simulation verification, the method has the advantages of being accurate in result, small in error, efficient in calculation and the like.

The invention provides a cumulative time error prediction method based on a time window LSTM model. The method comprises the steps of obtaining historical data of a sensor; performing time feature processing on the historical data, and selecting the historical data in a time window with a certain length as a time sequence; an LSTM model is used for modeling and training the time sequence, the input of the LSTM model is the sensor time error change condition in the time window, and the output of the LSTM model is the difference value between the sensor time at the current moment and the standard time; and correcting the sensor time according to a prediction result of the LSTM model. The actual time is independent from the time on the sensor, so that the time synchronization process is simplified; through selection of a time window, consumption of computing resources is remarkably reduced on the premise that prediction precision is guaranteed; through a correction mechanism, high-precision synchronization is achieved, computing resources are optimized, and it is ensured that sensor time and standard time are kept consistent.

The invention discloses an identity recognition method and system based on 3D tooth point cloud multi-feature fusion. The method comprises the following steps: collecting a 3D tooth point cloud of a to-be-recognized identity; inputting the 3D tooth point cloud of which the identity is to be recognized and each 3D tooth point cloud of which the identity is registered in the identity database into the trained tooth multi-feature fusion identity recognition backbone network, and outputting a registration result between the 3D tooth point cloud of which the identity is to be recognized and each 3D tooth point cloud of which the identity is registered; the backbone network comprises a color feature extraction module, a structural feature extraction module, a feature fusion module, a local sampling feature extraction module, a feature aggregation module, a coarse correspondence prediction module, a point cloud decoding module, a fine correspondence prediction module and a prediction registration module. And taking the identity information of the 3D tooth point cloud with the registered identity, which is optimally registered with the 3D tooth point cloud with the identity to be identified, as the identity label of the 3D tooth point cloud with the identity to be identified. According to the invention, identity recognition can be carried out based on the 3D tooth point cloud.

The invention relates to the technical field of medical information, and discloses a pancreatic cancer risk prediction method based on machine learning and multi-modal data, and the method comprises the steps: obtaining the multi-modal data of a target user; performing time sequence deduction on the molecular biological detection data to generate a virtual molecular time sequence; time sequence signals are extracted from the virtual molecule time sequence and the time sequence behavior monitoring data; calculating the dynamic coupling strength between the two time sequence signals to obtain a space-time coupling coefficient; weighted fusion is carried out on the features, and unified multi-modal feature representation is constructed; carrying out multi-modal feature representation training to obtain a special risk prediction model for the target user; and obtaining a risk quantitative score, and identifying a key risk driving factor which contributes to the score most. According to the invention, through multi-modal time sequence fusion and personalized modeling, early-stage, dynamic and explainable and evaluable pancreatic cancer risks are realized.

The invention provides a whole sea area sound scattering layer resource abundance prediction method and electronic equipment. The method comprises the following steps: constructing a standard sound scattering layer NASC data set; constructing a sound scattering layer resource abundance prediction model based on machine learning; predicting the resource abundance of the sound scattering layer based on the trained resource abundance prediction model of the sound scattering layer; and optimizing the predicted NASC value by adopting a Kriging interpolation method to obtain a resource distribution diagram of the sound scattering layer of the whole sea area. Aiming at the problem that the survey area cannot cover the whole sea area in the fishery resource acoustic survey process, the resource abundance of the acoustic scattering layer of the sea area without hydroacoustic survey can be predicted.

The invention discloses a bridge support displacement online probability prediction method, which comprises the following steps: acquiring historical monitoring data of main beam temperature and support displacement, and introducing a group of false points to construct a probability prediction model based on a flow sparse Gaussian process, according to the approximate posterior distribution and the real posterior distribution, constructing a variational free energy boundary as a lower bound of a logarithmic marginal likelihood function, deriving an optimal variational free energy boundary and optimal approximate posterior distribution, and obtaining a specific expression of a probability prediction model; when new monitoring data is obtained, new monitoring data and old historical monitoring data are summarized in combination with new false points and old posterior distribution, new approximate posterior distribution is derived, new real posterior distribution is derived by using the Bayesian theorem, then model parameters and posterior distribution are updated online, and a new specific expression of the probability prediction model is obtained. According to the method, massive health monitoring flow data of the bridge is processed based on the flow sparse Gaussian process model, online probability prediction of bridge support displacement is achieved, and the method has high engineering application value.

The invention discloses an ecological environment dynamic monitoring system based on machine learning, and relates to the technical field of artificial intelligence. The system comprises a sensor monitoring part, a feature extraction and mapping part, a support vector analysis and decision part and a prediction risk assessment part. The sensor monitoring part comprises a sample ecological region sensor group and a target ecological region sensor group; the sample ecological region sensor group comprises a plurality of same sample sensor groups; the target ecological region sensor group only comprises one target sensor group which is the same as the sample sensor group; the feature extraction and mapping part is used for obtaining mapping features; constructing a dynamic system state reconstruction equation; the support vector analysis and decision part is used for constructing an optimal support vector prediction controller; and the prediction risk assessment part is used for judging whether ecological environment early warning needs to be carried out or not according to the prediction judgment value. According to the invention, comprehensive monitoring, precise modeling and intelligent early warning of the ecological environment are realized.

A regional carbon emission prediction method and system based on carbon emission flow and big data analysis, in S1 regional division, the target area is divided into multiple sub-areas, each sub-area is labeled, and the main information set and secondary information set of each sub-area are formed according to different labels; S2 performs MIC correlation analysis to rank the correlation of the features affecting carbon emissions in the sub-area secondary information set; S3 constructs a sub-area carbon emission prediction model; S4 performs simulation calculation based on the constructed carbon emission prediction models of each sub-area, and outputs the regional carbon emission prediction results. This design can not only obtain different prediction models according to different data types, so as to make differentiated predictions for different regions, but also effectively reduce the difficulty of solving through labeling processing, and shorten the regional carbon emission prediction time.

The invention provides a water environment index change trend prediction and model establishment method and device, and a medium, and the model establishment method comprises the following steps: obtaining historical index data of a target water environment and driving influence factor data of the historical index data, and enabling the historical index data and the driving influence factor data to be used for establishing a training data set; hyper-parameters of the water environment index change trend prediction model are determined by adopting an automatic optimization algorithm, and the key hyper-parameters comprise a learning rate, the size of a convolution kernel and the number of neurons; the training data set is used for training a water environment index change trend prediction model, and a basic network model of the water environment index change trend prediction model is a combination of a convolutional neural network, a long and short term memory neural network and a self-attention mechanism. The method is based on the CNN-LSTM-Attention neural network model and adopts the automatic optimization algorithm to adjust the hyper-parameters, so that the parameter setting optimality in the model training process is ensured, higher adaptability and stability are obtained, and a more reliable water environment index change trend prediction result can be provided.

The invention discloses a modeling method of a point-by-point weighted mixed proxy model based on mixed measurement. The modeling method comprises the following steps: extracting a training sample; four sub-agent models are constructed, and hyper-parameter optimization is carried out; determining a local reference model and a global reference model of each sample point according to the LOO cross validation error and the GMSE error, and determining a global weight coefficient; determining the sample density; estimating local precision; determining a local weight coefficient; obtaining a local error measure-based preliminary mixed agent model; and obtaining a point-by-point weighted mixed proxy model based on the mixed measure. According to the method provided by the invention, each prediction point should be predicted by the corresponding local sub-agent model with the optimal prediction capability as far as possible, the local fitting precision is further improved, and meanwhile, through remixing with the global reference model with the optimal global fitting precision, the local fitting precision is further improved. And the global fitting precision of the pointwise weighted mixed agent model is further improved.

The invention discloses a tensor-kernel neural network for efficient prediction modeling and a modeling method thereof, and the tensor-kernel neural network comprises a kernel function mapping module which is used for carrying out the nonlinear kernel mapping of input data to obtain high-dimensional data; the tensor decomposition module is used for performing low-rank reconstruction on high-dimensional data and extracting low-dimensional features; and the deep neural network is used for training and predicting the extracted data low-dimensional features and outputting a prediction result. The loss function can effectively balance the reconstruction error and the prediction error in the model training process, and the generalization ability of the model is improved. In combination with Gaussian radial basis kernel function nonlinear kernel mapping, nonlinear input data is mapped to a high-dimensional feature space, and low-rank reconstruction is performed on high-dimensional data through a CP decomposition method; and finally, training and predicting the extracted low-dimensional features through a deep neural network. According to the method, the calculation efficiency and the prediction precision can be remarkably improved in high-dimensional data modeling; and the calculation complexity is reduced, and meanwhile, accurate extraction of data features and efficient training of the model are ensured.

The invention provides a deep learning-based method and system for establishing a nozzle profile ablation regression prediction model. According to the method, a nozzle profile ablation regression prediction model is constructed based on two-dimensional profile ablation data of an existing test nozzle and wall surface data obtained by numerical simulation of the corresponding test nozzle for ignition conditions, and the prediction time cost and the calculation cost are effectively reduced on the premise that the prediction precision is guaranteed; the invention further provides a method for extracting data points for a single two-dimensional ablated profile curve to form a data set. According to the method, points are taken according to the horizontal coordinate of the spray pipe, and a data set is formed by wall surface data obtained by extracting numerical simulation of points on a two-dimensional molded line of the corresponding horizontal coordinate and the wall surface retreat amount of an ignition experiment. According to the method, on the basis of limited experimental data and limited computing resources, the prediction time cost and the computing cost are reduced on the premise that the precision is guaranteed.

The invention relates to the technical field of laser amplification, and discloses a high-efficiency dye laser amplification technology, which comprises the following steps of using high repetition frequency ultrafast laser as a pumping source, and carrying out beam expansion and collimation on pumping light through a telescope system; the dye concentration is adjusted in real time through the microfluidic system, and the dye concentration is monitored in real time through the fluorescence detection system; a photonic crystal frequency doubling crystal is used for frequency doubling conversion; pumping light intensity, dye concentration and output power data are collected and subjected to standardization processing; performing data analysis and system parameter optimization through a deep learning model; and the temperature distribution of the laser amplifier is monitored and adjusted in real time by using an intelligent thermal management system. By integrating the high-repetition-frequency ultrafast laser pumping source and the telescope system, uniform beam expansion and collimation of light beams are realized, and the laser amplification efficiency and stability are remarkably improved. Compared with the prior art, the influence of uneven light spots on the amplification effect is effectively reduced, and the quality and consistency of output light beams are ensured.

The invention discloses a ship track prediction method based on Attention-BiLSTM, and relates to the technical field of ship track prediction. The method comprises the following steps: acquiring ship AIS data, weather data and date attribute data; carrying out abnormal data detection and elimination on the ship track data, and filling missing data after elimination; establishing a ship track feature input candidate set, selecting a feature input variable influencing the ship track, determining a delay order between the ship track and the feature input variable, and constructing a feature vector; dividing the feature vector into a limited number of sub-model action ranges, and performing boundary division and boundary estimation; and establishing a ship track prediction model for each sub-model action range, and realizing rolling prediction of the ship track through the ship track prediction model. Accurate high-quality data and reasonable action range division are provided for ship track prediction, the ship track prediction precision is guaranteed, and the purposes of ship reasonable path planning, resource optimization scheduling and marine navigation safety improvement are achieved.

The invention provides a method for predicting a radiation field after deformation of a flexible antenna based on infinitesimal dipoles. The method comprises the following implementation steps: initializing parameters; calculating the initial spatial position and attitude of each infinitesimal dipole; the dipole moment of each infinitesimal dipole is calculated; calculating the pose variation of the infinitesimal dipole after the flexible antenna is deformed; and obtaining a radiation field prediction result after deformation of the flexible antenna. An infinitesimal dipole is arranged in the center of each finite element unit, the flexible antenna is equivalent to a plurality of infinitesimal dipoles, the dipole moment of each infinitesimal dipole and a union vector Green function matrix and an attitude matrix after the flexible antenna is deformed are calculated, a radiation field after the flexible antenna is deformed is calculated, and the infinitesimal dipole array is obtained. The method can adapt to the situation that the flexible antenna deforms in different dimensions, avoids the defect that the radiation field is calculated through the surface current of a one-dimensional bending deformation model in the prior art, and preferentially widens the application range of prediction on the premise of guaranteeing the prediction precision and efficiency.

The invention discloses a novel power system output regulation and control strategy generation method and device and a control system, and belongs to the technical field of power system regulation and control. The output regulation and control strategy generation method comprises the following steps: representing net load historical data corresponding to net load climbing demand uncertainty characteristics by adopting a Gaussian mixture model; the uncertainty of the net load climbing requirement is reduced; inputting the net load day-ahead prediction data corresponding to the net load historical data and the net load uncertainty scene set into a two-stage risk avoidance model based on the lowest operation cost and the worst condition risk probability assessment theory; the two-stage risk avoidance model divides the whole strategy generation process into day-ahead optimization scheduling plan generation and intra-day real-time scheduling plan generation; the day-ahead optimal scheduling plan is optimized by using the obtained intra-day real-time scheduling plan to obtain a safe and economic output scheduling strategy; and furthermore, the novel power system is controlled in different scenes to realize efficient, stable and economical operation.

The present invention discloses a full-process model of an oscillating water column device based on CFD simulation and an efficiency prediction method thereof, wherein the device comprises a numerical wave water tank and an air chamber arranged at one end of the numerical wave water tank, the side of the air chamber is connected to an air duct, a momentum source term region is arranged in the air duct, and the width of the momentum source term region is consistent with the blade width of the turbine in the device to be evaluated. The full-process model disclosed by the present invention can accurately introduce the damping effect of the air turbine into the air chamber, fully consider the dynamic coupling effect between the air turbine and the air chamber, can truly reflect the working state of the oscillating water column, and make a reasonable prediction of the full-process efficiency.

The invention discloses an ore separation injection control method and system and a medium, and the method comprises the steps: updating the estimated movement time of ore on a belt according to the # imgabs0 # moment, if the ore position # imgabs2 # at the # imgabs1 # moment is greater than or equal to the distance # imgabs3 # from a detector to an injection point, adding 1 to the number of iterations # imgabs4 #, updating the ore position # imgabs6 # at the # imgabs5 # moment, and if the number of iterations # imgabs2 # is greater than or equal to the distance # imgabs3 # from the detector to the injection point, adding 1 to the number of iterations # imgabs4 #; a Kalman filter is adopted to update the predicted value # imgabs9 # of the belt speed of the belt at the # imgabs7 # moment to the # imgabs8 # moment until the condition is met, and finally the estimated movement time # imgabs10 # of the ore on the belt is updated, and the delay time of ore separation blowing control is determined. The uncertainty caused by belt speed fluctuation and sensor feedback delay is effectively reduced on the premise of ensuring the prediction precision of the ore motion trail.

The invention relates to the technical field of solar radiation prediction, in particular to a satellite-ground combined ultra-short-term solar radiation prediction method and system. Comprising the following steps: S1, collecting current state data and historical big data based on solar radiation; s2, preprocessing the ground-based cloud picture and the air-based cloud picture; and S3, identifying cloud layer state data based on the constructed cloud layer identification model. And S4, the solar radiation attenuation prediction model is adopted to identify the total solar radiation attenuation rate, and a radiation attenuation table is constructed. And S5, predicting cloud layer state change data and satellite observation total radiation change data by adopting an extrapolation method, and further calculating to obtain future short-term ground observation total radiation prediction data. According to the method, by combining observation of a stationary satellite and an all-sky imager, satellite-ground combined observation of cloud conditions of different height layers is realized, the influence of cloud in a whole atmospheric column on solar short-wave radiation is fully considered, the prediction precision is maintained, the operation process is optimized, and the precision and efficiency of solar radiation attenuation prediction are improved.

The invention provides a water return area water bloom prediction method and device, and relates to the technical field of environmental science. The method comprises the following steps: acquiring geographic hydrological data and environment monitoring data of a target hydrological environment, and constructing a three-dimensional hydrodynamic water temperature model of a backwater area according to the geographic hydrological data and the environment monitoring data; constructing a three-dimensional eutrophication model of the backwater area based on the water temperature, the water depth, the horizontal flow velocity and the wind speed obtained by the three-dimensional hydrodynamic water temperature model of the backwater area; constructing a BP neural network model based on the backwater area three-dimensional eutrophication model, and training the BP neural network model; and obtaining a water bloom risk prediction result of the water return area of the target hydrological environment by using the neural network model. According to the method, the backwater area three-dimensional hydrodynamic water temperature model is constructed, data support is provided for chlorophyll a calculation of the backwater area eutrophication model, a large number of high-frequency detection devices do not need to be added, the model operation time is greatly shortened, and the model prediction efficiency is improved.

The invention provides a rainfall data observation quality control method fusing multiple machine learning models, and relates to the technical field of meteorological observation. The method comprises the steps of obtaining rainfall data of a pre-observation area, and performing observation quality evaluation to obtain an abnormal part; adopting a generative adversarial network to repair an abnormal part in the obtained rainfall data to obtain repaired rainfall data; based on the restored rainfall data, meteorological factors used for complexity analysis are extracted; complexity analysis is carried out based on the extracted meteorological factors, and complexity scores of the meteorological factors are generated; and determining a discrimination path of the current rainfall data based on the complexity score. According to the method, through a series of steps of meteorological factor extraction, generative adversarial network restoration, complexity analysis and path dynamic switching judgment, high-precision observation and real-time adjustment of rainfall data are realized under different meteorological conditions, and reliable data support is provided for meteorological prediction.