29 results about "Climate forecast" patented technology

The invention relates to the technical field of meteorological monitoring and climate prediction, in particular to a Qinghai-Tibet Plateau composite extreme climate event attribution evaluation method. The method comprises the steps that ground observation, remote sensing and reanalysis data are integrated through a multi-source data dynamic space-time weight fusion technology, and abnormal value correction and non-uniform interpolation are achieved; identifying a composite event by adopting a multivariable combined extreme index and a space-time coupling graph model and generating a structured label, wherein the structured label comprises strength, range, duration and evolution path; constructing a multi-scale causal network to analyze the contribution of the driving factor, and implementing physical constraint disturbance based on causal weight; recovering high-resolution response by using a Bayesian agent model and combining topographic constraint random downsampling, and deducing spatio-temporal evolution through an event propagation network; and a kernel polynomial hybrid uncertainty propagation framework is adopted to generate a probabilistic scene set, and multi-level risk early warning and dynamic knowledge base optimization are realized. According to the invention, the attribution precision and early warning efficiency of plateau composite extreme events are comprehensively improved.

The invention provides a glacier dynamic early warning method and system, and the method comprises the steps: enabling a core agent to adjust a base sliding coefficient of a target model according to the melt water amount of a target glacier body in a past observation time period through employing the capability of an agent AI for learning a complex mode from data and the preciseness of an ice flow model in dynamics deduction, and achieving the dynamic early warning of the glacier. And the target model carries out deduction prediction based on climate forecast data on the basis of the adjusted base sliding coefficient so as to generate a prediction change result of the target glacier body in a prediction time period, and the accuracy and robustness of the prediction change result are guaranteed by accurately setting the base sliding coefficient under the condition that the two modes are combined. The risk assessment model obtains an instability index of the target glacier body in the prediction time period according to the prediction change result; and the risk assessment model triggers early warning when the instability index exceeds a corresponding dynamic threshold value, so that accurate implementation of early warning is ensured.

The invention provides a plateau rainfall prediction method, system and device based on intelligent similarity correction, and relates to the technical field of short-term climate prediction.The method comprises the steps that mode rainfall data of a month to be predicted, multivariable historical factor data corresponding to the mode rainfall data and global historical annual rainfall error data are obtained, determining standard grid point data of the wind field, the height field and the air temperature and effective historical annual rainfall error data; inputting the standard grid point data and the effective historical annual rainfall error data into a pre-trained error prediction model to obtain a prediction error field output by the error prediction model; and based on the prediction error field, correcting the mode precipitation data to obtain the final predicted precipitation. According to the method, multivariable information is integrated, the nonlinear synergistic effect relationship is mined more deeply, the description capability of the rainfall anomaly driving mechanism of the to-be-predicted region is enhanced, and compared with a traditional single-variable or linear scheme, the accuracy of similar selection and rainfall season prediction is effectively improved.

The invention belongs to the technical field of hydrology and water resource and climate prediction crossing, and discloses a medium-and-long-term runoff prediction method fusing a data enhancement technology and a machine learning model, which comprises the following steps: collecting runoff data and climate system index data of a target area, performing factor screening by adopting a replacement accuracy method, the method comprises the following steps: dividing data into a training set and a test set, constructing a time lag factor, carrying out SMOTE data enhancement on the training set, carrying out runoff prediction model construction by using a support vector machine regression model, carrying out parameter optimization by using grid search, calculating an evaluation index to carry out model performance evaluation, and finally predicting and outputting a medium and long-term runoff time sequence according to the model. The method effectively solves the problem of low prediction precision caused by data scarcity and insufficient factor selection in a traditional method. The method overcomes the problems of data scarcity, imbalance and insufficient model generalization ability in medium and long term runoff prediction, and has wide application prospects in the fields of medium and long term runoff prediction and water resource management.

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

The invention discloses a conditional multi-mode gathering method and device for improving ENSO cycle simulation, and relates to the technical field of climate prediction and numerical simulation. The method comprises the following steps: acquiring ENSO simulation results of a plurality of climate modes; calculating a correlation coefficient between the ENSO simulation result and the ENSO observation result of each climate mode; determining a threshold value based on the performance index of each climate mode; dividing climate modes into a positive correlation class, a negative correlation class and a weak correlation class according to the relation between the correlation coefficient and a threshold value; multiplying the simulation result of the negative correlation climate mode by-1 to obtain a correction result of the negative correlation climate mode; and carrying out set average on the correction result of the negative correlation climate mode and the simulation result of the positive correlation climate mode to obtain a final improved ENSO simulation result. According to the method, the consistency of each feature of the ENSO is simulated, the simulation of climate change influencing the ENSO is improved, and the accuracy of ENSO cycle simulation and the reliability of future estimation are improved.

The invention discloses a climate prediction method and device based on hot start and background constraint and a medium. The method comprises the following steps: training an auto-encoder by using actual climate data in a first historical annual interval, and taking the auto-encoder as an initial climate prediction model decoder; obtaining first climate data of a current year and a second historical year interval predicted by a specified climate prediction model; for each month in the second historical annual interval, generating a sample pair of the month by taking the first climate data of the month and a preset number of months as an input feature and taking the actual climate data of the month as a label; the training sample library is used for training a climate prediction model trained in the last year with the minimum joint loss as the target, and the joint loss comprises a precision constraint representing model prediction performance, a climate background constraint and a prediction score constraint; the trained model is used for predicting the climate of the current year. The continuous evolution and stable prediction of the prediction model are realized, and the convergence speed of the prediction model is improved.

The invention relates to the field of climate prediction, in particular to a regional coupling climate extension period prediction method and system. The method comprises the following steps: acquiring ocean water depth basic data, and optimizing the ocean water depth basic data to obtain ocean water depth optimized data; constructing a regional ocean model based on the ocean water depth optimization data; constructing a weather research and forecast model, and constructing a coupler interpolation parameter file based on the weather research and forecast model and the regional ocean model; constructing a coupling mode prediction system of the target region by utilizing the weather research and forecast model and the regional ocean model based on a coupler interpolation parameter file; and obtaining climate extension period prediction data by using the coupling mode prediction system based on a global atmospheric seasonal prediction product and a global ocean prediction product which are obtained in advance. The problem that in the prior art, climate extension period prediction is not accurate enough is solved, and the accuracy of climate extension period prediction is improved by optimizing ocean water depth data and a coupling mode prediction system.

The invention relates to the technical field of hydro meteorology, in particular to a method and a system for predicting and tracing extreme hydrological events in a reservoir area. The method comprises the following steps of S1, collecting meteorological and hydrological data, a global climate mode data set, geographic space data and stable isotope data of a reservoir area, and unifying a multi-source data scale through a time sequence fusion algorithm; according to the method, isotope data is adopted as an independent evidence constraint model, and compared with a traditional single model method, the method can more comprehensively capture a complex mechanism of occurrence of an extreme event, so that a simulation result is closer to an actual situation, and countermeasures can be taken in the face of an extreme climate event; the climate prediction and the isotope traceability technology are coupled for the first time, how causes of the extreme events change under different future climate scenes can be pre-judged in advance, and the research method and the model framework are not only suitable for specific areas, but also can be widely applied to research of the extreme events of large reservoirs and drainage basins.

The invention relates to the technical field of climate prediction, in particular to a high-resolution refined underlying surface sub-seasonal climate prediction method and a related device, and the method comprises the steps: respectively carrying out the correlation analysis according to monthly average analysis data, first monthly average reanalysis data, a weather reanalysis data set and a weather forecast center reanalysis data set, obtaining a plurality of key regions and a plurality of buffer regions, screening to obtain a target simulation region, a target time step size and a target spatial resolution, and obtaining a first region climate mode; processing according to an output result of the third-generation climate prediction system and the first region climate mode to obtain a target initial boundary field; obtaining a target initial field, an initial configuration file and a target region climate mode according to the first region ground data and an output result of a preset third-generation climate prediction system; and performing simulation analysis processing according to the target instruction data to obtain target prediction data. According to the method, the problem of regional high-precision and high-accuracy sub-seasonal climate prediction is solved.

This invention discloses an intelligent generation method for reservoir flood control scheduling maps based on adaptive control, belonging to the field of reservoir flood control technology. It includes: capturing the interannual fluctuations and trends of future runoff through long-term predicted runoff sequences corrected by VMD-LSTM, providing high-quality input data for multi-objective optimization models; and daily forecasts of 1-7 days provided by short-term flood rolling forecast models, which facilitates real-time integration into the optimization process through dynamic weighting mechanisms, achieving seamless coupling between forecast information and scheduling decisions. The collaborative architecture of long-term and short-term forecasts ensures both the climate adaptability of long-term operating rules and enhances the emergency response capability of real-time scheduling to extreme hydrological events. This invention realizes full-chain adaptive control from climate prediction to scheduling decisions, significantly improving the flood control and comprehensive water use benefits in complex watersheds.

This invention discloses a climate prediction method and apparatus based on observation constraints and a multi-time-dependent sliding window. The method includes: acquiring the first climate data for the current and historical years predicted by a specified climate system model; for each month in the historical year: using the first climate data of that month and a predetermined number of previous months as input features, and the actual climate data of that month as labels, generating sample pairs for that month and adding them to a training sample library; training a pre-constructed climate prediction model using the training sample library with the objective of minimizing the joint loss, the joint loss including the root mean square error, spatial anomaly correlation coefficient, and prediction score characterizing the model's prediction performance; for any month to be predicted in the current year: inputting the first climate data of that month and a predetermined number of previous months into the trained climate prediction model, and outputting the climate prediction result for that month. This invention improves the reliability and fine spatiotemporal resolution of climate prediction.

According to the monthly-scale rainstorm disaster risk dynamic estimation method and system based on the climate prediction mode provided by the invention, rainstorm rainfall threshold value calibration, rainstorm disaster risk assessment, risk grade division and threshold value determination in the climate prediction mode are realized, and the standardization and objectification level of rainstorm disaster risk estimation is improved. According to the monthly-scale rainstorm disaster risk dynamic estimation method and system based on the climate prediction mode, a certain deviation exists between day-by-day rainfall data calculated based on the history of the climate prediction mode and day-by-day rainfall observation data of a national meteorological station (nationality station for short); the observation value and the mode data are adopted to calibrate the rainstorm rainfall threshold value of the climate prediction mode, the rainstorm process is identified and extracted according to the calibrated rainstorm rainfall threshold value, and the rainstorm process identification accuracy is improved.

This disclosure provides a three-dimensional dynamic diagnostic method and apparatus for extreme drought events. The method includes acquiring drought index data and historical three-dimensional circulation fields of a target region, constructing a standardized anomaly field matrix, determining extreme drought grid points based on drought index data and performing regional connections to obtain drought event domains and regional extreme drought events; selecting key physical quantity fields in the historical three-dimensional circulation field, constructing a joint anomaly field matrix by combining it with the standardized anomaly field matrix, identifying the first mode and the dominant circulation pattern through singular value decomposition, reconstructing the three-dimensional physical quantity anomaly field of the dominant circulation pattern based on the first mode, and calculating the dynamic and thermal contribution values; tracing the source of the dominant circulation pattern and constructing the physical mechanism chain of the dominant circulation pattern. This achieves a comprehensive understanding of the mechanism from source forcing to local impacts, providing a directly applicable diagnostic framework and physical basis for the physical attribution of drought, the verification of prediction models, and extended-range climate prediction.

The invention provides a machine learning-based sub-season day-by-day rainfall prediction result correction method and system, and relates to the technical field of climate prediction. According to the method, in consideration of the deficiency of the prediction capability of the numerical mode on the circulation element of the predicted region at the time scale of the second season, the circulation element of the predicted region is not selected as the prediction feature, but the high-influence key region reflected by the numerical mode is objectively screened as the prediction feature; compared with some similar machine learning prediction methods, the method is more suitable for sub-seasonal climate prediction in feature selection, and mode data mining is more sufficient. Besides, in consideration of climate state differences in a year, data of adjacent report starting days and forecast days are used as samples, so that information inconsistency caused by importing atmospheric circulation information with great climate state differences into a model is avoided, generalization ability of the model is improved, and higher prediction precision and higher prediction speed are achieved.

The invention relates to the field of climate prediction, and provides a western pacific ocean subtropical high pressure intensity sub-season prediction method and system based on a similar sea temperature evolution background, and the method comprises the steps: S1, collecting day-by-day data and week-by-week data of a western pacific ocean subtropical high pressure intensity index; s2, classifying evolution trend backgrounds of the sea temperature indexes every year by utilizing clustering analysis; s3-S4, for each sea temperature evolution trend background category, obtaining a corresponding cumulative probability distribution curve of the West Pacific Ocean subtropical high pressure intensity index of observation and mode return; s5, determining the background category of the real-time forecast sea temperature evolution trend; and S6, according to the determined real-time forecast sea temperature evolution trend background category, performing probability matching correction on the predicted western pacific ocean subtropical high pressure intensity index by using a corresponding observation and mode return cumulative probability distribution curve. The method can provide scientific and technological support for correctly mastering the high evolution trend of the XiTaisui and improving the accuracy rate of sub-seasonal climate prediction.

The invention provides a power grid load prediction method and system based on temperature sensitivity evaluation, and relates to the technical field of power grid load prediction, and the method comprises the steps: obtaining a plurality of historical total load sequences and synchronous temperature sequences of a plurality of industries in a target region, and carrying out the calculation to obtain a correlation index; screening out a plurality of temperature-sensitive industries in combination with a preset sensitivity threshold; for any temperature-sensitive industry, decomposing the historical total load sequence into a historical temperature-sensitive load sequence and a historical basic load sequence through a load temperature decoupling model; predicting a basic load component of a future time period based on the historical basic load sequence; based on the historical temperature-sensitive load sequence, the weather forecast data of the future time period and the ENSO climate prediction state information, a temperature-sensitive load component of the future time period is obtained through prediction; and adding the basic load component and the temperature-sensitive load component to obtain a power grid total load prediction result of any temperature-sensitive industry in a future time period. The technical problem of inaccurate power grid load prediction in the prior art is solved.

The invention relates to the technical field of climate prediction, in particular to a basin climate prediction combination intelligent recommendation method and device, and the method comprises the following steps: constructing a multi-dimensional climate prediction combination, and obtaining a candidate climate prediction combination pool according to the multi-dimensional climate prediction combination; establishing a score calculation mechanism, and performing scale-division score calculation on the candidate climate prediction combination pool to obtain climate prediction score indexes; performing comprehensive analysis on the basis of the climate prediction scoring indexes to obtain a recommendation list ranking of the multi-dimensional climate prediction combination; acquiring climate prediction demand information, and performing time matching according to the climate prediction demand information to obtain the optimal report starting time of the multi-dimensional climate prediction combination; and combining the recommendation list ranking and the optimal report starting time to obtain an optimal climate prediction combination, and realizing intelligent recommendation of the climate prediction combination. According to the invention, by obtaining the optimal climate prediction combination, the accurate requirements for climate prediction in diversified scenes can be met.

The invention provides a novel prediction set buffer structure and method, and relates to the technical field of engineering and manufacturing, and the structure comprises a climate prediction unit and a regulation and control unit: the climate prediction unit generates a high-precision daily rainfall simulation curved surface through curved surface simulation, threshold optimization and data fusion; the regulation and control unit comprises an electric control center and a cloud processor and can output regulation and control instructions. The device comprises a supporting plate, a top plate and a buffer part made of a graphene composite material and a memory alloy. The device has the beneficial effects that the integrated application of a high-precision regional climate prediction technology is realized; innovative fusion of a self-adaptive buffer structure and an intelligent material is realized; the prediction module transmits the meteorological data to the electric control center, automatically calculates the required power-on time, and regulates and controls the rigidity coefficient and angle of the buffer structure; and meanwhile, remote monitoring and manual intervention are realized through a mobile phone APP.

Spatio-temporal climate forecasts are analyzed and one or more resiliency policies for a supply chain are dynamically generated. The resiliency policy is embedded in a resiliency reasoning graph and a temporal feedback loop is performed based on user feedback regarding the generated resiliency policy and user interaction with the resiliency reasoning graph. One or more machine learning models are updated based on the user feedback and a joint optimization of the machine learning models is re-solved based on the user feedback. The resiliency policy is updated based on the updated machine learning models based on the user feedback and an operation of a supply chain is adjusted based on the updated resiliency policy.

A prediction device 1 comprises: a climate prediction unit 11 that calculates a predicted value of the climate on the basis of a scenario; a top-down economy prediction unit 12 that calculates, by calculating a predicted value of the economy on the basis of the scenario and correcting the predicted value of the economy using the predicted value of the climate through a top-down approach, a predicted value of the economy including the influence of a top-down climate change; and a bottom-up economy prediction unit 13 that corrects a sector value using the predicted value of the climate, inputs the corrected sector value to a general equilibrium model that deals with economic equilibrium between sectors, and obtains a predicted value of the economy including the influence of a bottom-up climate change from the general equilibrium model, with the predicted value of the economy including the influence of the top-down climate change as a constraint condition of the general equilibrium model.

The application discloses a microclimate prediction method, system, device and medium based on an attention mechanism, and comprises the following steps: acquiring meteorological data of a region to be predicted, wherein the meteorological data comprises historical local meteorological data of the region to be predicted and surrounding meteorological station prediction information; inputting the meteorological data into a climate prediction model for prediction classification to obtain climate prediction data, wherein the climate prediction model comprises a feature extraction module, a residual connection module, a normalization module and a prediction module connected in sequence, and the feature extraction module comprises a long short-term memory network module and an attention module arranged in parallel. The technical scheme disclosed by the application can be extended to the prediction of other meteorological elements and can improve the prediction accuracy.

This invention relates to the field of climate prediction and meteorological data downscaling technology, providing a rapid method for predicting future climate scenarios in small watersheds by integrating deep learning and dynamic downscaling. The method includes: Step 1: Target area delineation and input data preprocessing; Step 2: Dynamic downscaling simulation and annotation, and benchmark data generation; Step 3: Training sample construction and TA-UNet downscaling surrogate model training; Step 4: Future climate downscaling and prediction dataset generation. This invention addresses the core contradiction in existing technologies that cannot simultaneously achieve prediction accuracy, physical consistency, and computational efficiency. It provides a future climate prediction scheme for high-altitude small watersheds, constructs a standardized, end-to-end technical system adapted to high-altitude cold mountain scenarios, and enables the rapid and stable generation of high-resolution future climate prediction data for high-altitude glacial small watersheds. This provides reliable and refined meteorological data support for geological and hydrological disaster risk assessment and major engineering construction in high-altitude cold mountain areas.

This invention relates to the field of numerical weather and climate prediction technology, and in particular to a method and system for dynamic downscaling subseasonal prediction based on land surface reconstruction. The method includes the following steps: obtaining subseasonal atmospheric prediction results to obtain atmospheric side boundary conditions; acquiring reanalysis data and processing the data to construct a land surface model forcing field; constructing an offline land surface process model to update land surface variables to obtain land surface state; performing consistency processing on the land surface state to generate an initial land surface state; and obtaining subseasonal regional climate prediction results based on the atmospheric side boundary conditions and the initial land surface state. This invention, through continuous reconstruction of land surface processes, fully preserves the memory and cumulative effect of land surface variables, improves the physical rationality and spatial continuity of the initial land surface state, and effectively suppresses instability problems in the initialization stage of regional dynamic models, thereby enhancing the stability and operational applicability of subseasonal regional dynamic downscaling prediction.

The application provides a highland precipitation prediction method, system and equipment based on intelligent similarity revision, and relates to the technical field of short-term climate prediction. The method comprises the following steps: obtaining mode precipitation data of a to-be-predicted month, corresponding multivariate historical factor data and global historical annual precipitation error data, and determining standard grid data of wind field, height field and air temperature and effective historical annual precipitation error data; inputting the standard grid data and the effective historical annual precipitation error data into a pre-trained error prediction model to obtain a prediction error field output by the error prediction model; and revising the mode precipitation data based on the prediction error field to obtain a final predicted precipitation. The application integrates multivariate information, deeply excavates the nonlinear synergistic relationship thereof, enhances the ability to depict the precipitation anomaly driving mechanism of the to-be-predicted region, and effectively improves the accuracy of similar selection and precipitation seasonal prediction compared with a traditional single variable or linear scheme.

The invention discloses a climate prediction method and equipment based on observation constraint and a multi-aging sliding window. The method comprises the following steps: acquiring first climate data of current and historical years predicted by a specified climate system model; for each month in a historical year, taking the first climate data of the month and a preset number of months as an input feature, taking the actual climate data of the month as a label, generating a sample pair of the month, and putting the sample pair into a training sample library; using the training sample library to train a pre-constructed climate prediction model with minimum joint loss as a target, the joint loss including a root-mean-square error representing model prediction performance, a spatial anomaly correlation coefficient and a prediction score; and for any to-be-predicted month in the current year, inputting the first climate data of the to-be-predicted month and a set number of previous months into the trained climate prediction model, and outputting a climate prediction result of the to-be-predicted month. According to the invention, the reliability and fine temporal-spatial resolution of climate prediction are improved.

The application discloses a climate prediction method and device based on a hot start and background constraint, and a medium. The method comprises the following steps: training a self-encoder by using actual climate data of a first historical annual interval, and then decoding the self-encoder as an initial climate prediction model decoder; obtaining first climate data of a current annual interval and a second historical annual interval predicted by a specified climate prediction model; for each month in the second historical annual interval: taking the first climate data of the month and a set number of months before the month as input features, and taking actual climate data of the month as a label, to generate a sample pair of the month; training the climate prediction model trained in the last year by using a training sample library, with the joint loss being minimized as the target, wherein the joint loss comprises an accuracy constraint representing the prediction performance of the model, a climate background constraint and a prediction score constraint; and the trained model is used for predicting the climate of the current year. The application realizes continuous evolution and stable prediction of the prediction model, and improves the convergence speed of the prediction model.

An object of a system according to an embodiment is to predict a consumption trend on the basis of weather data and optimize purchase.SOLUTION: A system includes a data acquisition part, a prediction model generation part, a weather prediction part, a consumption trend prediction part, and a purchase optimization part. The data acquisition unit acquires past data of the Meteorological Agency. The prediction model generation unit generates a prediction model based on the data acquired by the data acquisition unit. The weather prediction unit predicts weather based on the satellite data. The consumption trend prediction unit predicts a consumption trend based on the weather data predicted by the weather prediction unit. The purchase optimization part optimizes purchase based on the consumption trend predicted by the consumption trend prediction part.SELECTED DRAWING: Figure 1

The application relates to the field of climate prediction, in particular to a regional coupling climate extended-range prediction method and system. The method comprises the following steps: acquiring marine water depth basic data, and optimizing the marine water depth basic data to obtain marine water depth optimized data; constructing a regional marine model based on the marine water depth optimized data; constructing a weather research and forecast model, and constructing a coupler interpolation parameter file based on the weather research and forecast model and the regional marine model; constructing a coupling mode prediction system of a target region by using the weather research and forecast model and the regional marine model based on the coupler interpolation parameter file; and obtaining climate extended-range prediction data by using the coupling mode prediction system based on pre-acquired global atmospheric seasonal prediction products and global marine prediction products. The application solves the problem that the climate extended-range prediction is not accurate enough in the prior art, and improves the accuracy of the climate extended-range prediction by optimizing the marine water depth data and the coupling mode prediction system.