ENSO diversity forecasting method based on artificial intelligence

Abstract

The invention discloses an ENSO diversity forecasting method based on artificial intelligence, and the method comprises the steps: extracting first three main modes from equatorial Pacific Ocean SSTA observation data through employing an EOF decomposition method, enabling CMIP6 historical simulation data to be projected on the three main modes, and obtaining three groups of PC values; three groups of PC values are used as forecast values, SSTA of an initial month and two sea temperature data of a Tendency item are used as training input values, and a CMIP6 mode is used for training VGG-11; and inputting observation data into the trained model to obtain PC values at three future moments, and combining the PC values with the three EOF main modes to reconstruct the SSTA spatial form of the equatorial pacific region at the future moments. According to the method, the forecasting skill of the El Nino of the middle-pacific ocean type is improved, and the forecasting bottleneck of the previous power mode in the middle-pacific ocean region is broken through. According to the method, the forecasting skill of ENSO is improved, forecasting and early warning of climate disasters are facilitated, and personnel and property loss can be reduced.

Description

technical field [0001] The invention relates to the technical field of climate forecasting, in particular to an artificial intelligence-based ENSO diversity forecasting method. Background technique [0002] The El Niño-Southern Oscillation (ENSO) has a major impact on the global climate and can cause severe flooding. Therefore, improving ENSO forecasting skills is beneficial to disaster prevention and mitigation for all countries. Existing artificial intelligence-based forecasting models refer to the El Niño phenomenon over the entire equatorial Pacific Ocean by forecasting the Nino3.4 index, but such forecasting techniques are not sufficient to solve the El Niño forecasting problem. Because El Niño is manifested as an anomaly of sea surface temperature (SST) in the equatorial Pacific Ocean, and there is spatial diversity in temperature anomalies, but the Nino3.4 index cannot show spatial diversity. Spatial diversity of El Niño In addition to the common East Pacific El Niñ...

AI Technical Summary

Problems solved by technology

Existing artificial intelligence-based forecasting models refer to the El Niño phenomenon in the entire equatorial Pacific by forecasting the Nino3.4 index, but such forecasting techniques are not sufficient to solve the El Niño forecasting problem

Because El Niño is manifested as an anomaly of sea surface temperature (SST) in the equatorial Pacific, and there is spatial diversity in temperature anomalies, but the Nino3.4 index cannot show spatial diversity

Spatial diversity of El Niño In addition to the common East Pacific El Niño, there is also a Central Pacific El Niño, the impact of the two types on the global climate is quite different; The forecasting ability of the Central Pacific El Niño is not high, so the problem of forecasting the spatial type of El Niño has not been well resolved

Images