9 results about "Climate index" patented technology

The invention belongs to the technical field of electric power meteorology, and provides a medium and long term wind and light resource prediction method and system considering climate remote correlation factors, and the method comprises the steps: obtaining global climate index historical data, and carrying out the standardization processing of the data, and obtaining a standardized climate index; for the historical resource sequence of the target station, calculating the mutual information value of the standardized climate index, and constructing a forecasting factor set by taking the lag time corresponding to the maximum value of the mutual information as the optimal early warning window period; extracting wind and light resource measured data of the same period in historical years to construct a reference probability density function; and taking the reference probability density function as prior distribution, combining a preset dynamic mode prediction result as a likelihood function, and outputting a prediction result containing a deterministic value and a confidence interval. By means of the characteristic that ocean signals change slowly, the method breaks through the 15-day prediction limit of an atmospheric mode, effective trend prediction from the quarterly level to the annual level is successfully achieved, and the requirement for medium and long term resource evaluation is met.

The invention discloses a space-time pattern prediction method based on forest carbon sink climate change. The method comprises the following steps: collecting vegetation data, soil data, meteorological data, topographic data and special interference factor data of a target forest area; preprocessing the collected multi-source data, and performing space-time matching on the preprocessed data; quantifying a climate index of the target forest region; taking a Biome-BGC ecological process model as a core, and integrating a graph neural network to construct a carbon sink-climate index-terrain coupling model; setting various climatic change scenes, and predicting a carbon sink spatial and temporal distribution pattern under different scenes based on a carbon sink-climatic index-terrain coupling model. The space-time pattern prediction method based on the forest carbon sink climate change is adopted, and the prediction precision is improved.

The invention discloses a southwest wine grape climate zoning method based on multi-source data, and relates to the technical field of agrometeorological information, and the method comprises the following steps: collecting and preprocessing multi-source basic data; key climate and growth indexes are calculated; spatial interpolation analysis; generating a zoning map; analyzing and verifying the trend; according to the method, by integrating multi-source meteorological data and high-precision topographic data, a more comprehensive southwest wine grape climate zoning index system is established; according to the method, multiple factors such as heat, moisture and terrain are comprehensively considered, the limitation of single climate index analysis is made up, the zoning result can more accurately reflect the difference of microclimate under the complex terrain, a scientific basis with more regional pertinence is provided for planting layout, and the zoning practicability and guidance value are improved.

The invention belongs to the technical field of informatization agriculture, and particularly relates to a climate-soil synergistic effect-based apple quality multi-index prediction model construction method, which comprises the following steps of: data collection and preprocessing: collecting climate indexes, soil chemical indexes and quality index data corresponding to apple samples, carrying out standardization processing on all continuous variables, and carrying out calculation on the standard variables; dividing a training set and a test set according to a preset proportion; feature engineering: high-order features are constructed based on agronomy knowledge, an engineering feature pool is formed, and the high-order features comprise an interaction feature, a seasonal aggregation feature, a soil-climate balance feature and a ratio feature; according to the method, a systematic basic statistical analysis-high-order feature engineering-two-stage modeling research framework is constructed, the limitation of traditional single-factor linear analysis is broken through, the nonlinear synergistic effect of climate-soil factors is effectively captured, and high-quality feature input and a scientific modeling thought are provided for apple quality prediction.

The invention discloses a medium and long term prediction method and system for regional thunder and lightning climate, and the method enables the interannual change of thunder and lightning activity to be objectively predicted in the future 2-12 months through building the quantitative mapping relation between the thunder and lightning occurrence frequency distance level and the multi-source climate factor and the large-scale climate index. Therefore, thunder and lightning approaching early warning which is originally limited to a minute-to-hour level is expanded to seasonal and annual climate scales, and a thunder and lightning-oriented climate service prediction link is formed by uniformly utilizing historical thunder and lightning observation, air temperature, rainfall, an El Nino index and other data. The large-scale air-sea abnormal signals can be converted into quantitative judgment of too much and too little regional thunder and lightning, and the defect that in the prior art, only empirical correlation analysis stays is overcome. And meanwhile, by performing standardized grading on the lightning frequency interval, the grading results of'more, more, normal, less and less' and the like are directly output, so that the prediction product can be directly called and applied by the lightning protection and disaster reduction department, the planning and design department and the like.

This invention discloses a method for quantifying the coupling degree of drought-heat wave and decomposing its driving forces based on a time-varying moment model (PMOE). It constructs a time-varying moment-constrained maximum entropy distribution (POME) model for heat wave and drought sequences, expressing the key Lagrange multipliers of the PMOE model as a linear function of climate indices and urbanization factors to characterize the time-varying characteristics of univariate marginal distributions. Based on pseudo-observations, a time-varying Copula model considering physical driving factors is constructed. Through the optimal combination of various parameter structures, the dynamic evolution of the interdependent structure between drought and heat waves is characterized. By calculating and comparing risk impact indicators under multiple models, the influence of climate change and human activities on the coupling degree of drought-heat waves is quantified and separated. This invention achieves simultaneous characterization of the dynamic evolution and non-stationary characteristics of complex extreme events, and effectively identifies and decomposes the contributions of key physical driving factors, providing a scientific basis for dynamic risk assessment and adaptive countermeasure formulation for regional complex events.

The invention relates to a convolutional neural network-based drought and flood sudden change event grading early warning method. The method comprises the steps of performing objective clustering-based drought and flood sudden change event grading definition and label construction; constructing a multi-source climate-driven feature set based on nonlinear dynamic optimization; a GDFAA-CNN prediction model with time sequence perception and cost sensitive characteristics is constructed; the invention relates to medium-and-long-term multi-scale rolling forecasting application of drought and flood sudden turning events. According to the method, the specific one-dimensional convolution and pooling layer structure of the convolutional neural network is utilized, time sequence accumulation and mutation characteristics can be automatically extracted from high-dimensional and complex input climate data, a data-driven model training mode is adopted, only current climate index data needs to be input in practical application, and the time sequence accumulation and mutation characteristics can be automatically extracted. According to the method, prediction results of 1-3 months in the future are output within second-level time, prediction time consumption is greatly shortened, uncertainty accumulation caused by physical model parameter calibration is avoided, and precious advance is gained for formulating emergency plans for flood and drought disaster prevention departments.

The application provides a runoff prediction method and device, a storage medium and a computer device, and comprises the following steps: obtaining historical hydro-meteorological data, historical climate index data, historical runoff return data of a plurality of preset historical periods and historical runoff data of a target basin; the historical runoff return data is runoff data of the preset historical period simulated by a plurality of different runoff simulation models according to the historical hydro-meteorological data and the historical climate index data; the historical runoff data is measured runoff data of the historical period corresponding to the historical runoff return data; training a plurality of initial runoff prediction models according to the historical hydro-meteorological data, the historical climate index data, the historical runoff return data and the historical runoff data to obtain a plurality of runoff prediction models; inputting basin hydro-meteorological data, basin climate index data and a plurality of runoff return data of the target basin into the plurality of runoff prediction models to obtain runoff data prediction data.

The application discloses a method, system, device and medium for medium and long term runoff prediction based on multi-source climate factors and deep learning. The method comprises: obtaining historical runoff time series data and multi-source climate factor data, wherein the multi-source climate factors are divided into three-dimensional space climate field factors and two-dimensional climate index factors; based on an initial space window scale, the three-dimensional space climate field factors are cropped and traversed at different space positions, a runoff prediction model is trained in a first stage, and candidate space driving region centers are determined by comparing prediction performance; taking the candidate space driving region centers as space window centers, a plurality of different space window scales are traversed, a runoff prediction model is trained in a second stage, the optimal space window scale corresponding to each candidate space driving region center and the final parameters of the model are determined by prediction performance, a plurality of candidate runoff prediction models are constructed, and the optimal model for final runoff prediction is determined by comprehensive comparison. The application can improve the prediction accuracy, stability and reliability of runoff prediction.