ENSO diversity forecasting method based on artificial intelligence

An artificial intelligence and diversity technology, applied in weather condition forecasting, calculation models, instruments, etc., can solve the problem that the forecasting ability of the Central Pacific El Niño is not high, the spatial type of El Niño is not well resolved, and the spatial diversity cannot be displayed and other issues to achieve the effect of improving forecasting skills, reducing personnel and property losses, and breaking through forecasting bottlenecks

Active Publication Date: 2022-04-12
INST OF ATMOSPHERIC PHYSICS CHINESE ACADEMY SCI
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • ENSO diversity forecasting method based on artificial intelligence
  • ENSO diversity forecasting method based on artificial intelligence
  • ENSO diversity forecasting method based on artificial intelligence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0023] This embodiment provides a method for forecasting ENSO diversity based on artificial intelligence, such as figure 1 shown, including the following steps:

[0024] S1. Using the EOF decomposition method, the first three main modes are extracted from the observed data of sea surface temperature anomalies in the equatorial Pacific Ocean: the zonal consistent type, the zonally inconsistent type, and the central warming type;

[0025] S2. Projecting the CMIP6 historical simulation data onto the three main modes EOF main mode, respectively obtaining three sets of historical simulation data PC values;

[0026] S3. Use the PC value of three sets of historical simulation data as the forecast value, and use the SSTA of the initial month and the two kinds of sea temperature data of the Tendency item as the input value of the training, and use the CMIP6 mode to train the improved deep learning model (VGG-11).

[0027] S4. Input the new observed data as the forecast input value int...

Embodiment 2

[0038] This embodiment provides a process of forecasting El Niño in the Central Pacific El Niño type occurrence area using the data of the equatorial Pacific Ocean surface from 1984 to 2017.

[0039] In this example, the warm pool index (WPI) is used to evaluate and compare the forecast results of the Central Pacific El Niño.

[0040] 1. Decompose the observed equatorial Pacific SSTA data using EOF to obtain the first three main modes (EOF1~3, such as figure 2 )

[0041] 2. Project the SSTA of 39 CMIP6 historical models (time: 1948–2014) into the three EOF main modes, and you can get the PC value of each month from 1948–2014; at the same time, you can get it from 39 historical models SSTA and Tendency items for each month.

[0042] 3. Use the initial month's SSTA and Tendency to input the deep learning model, and output 3 PC values ​​forecasted N months in advance (N=1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11); Due to the large amount of data in 39 modes, after deep learning traini...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

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...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F30/27G06N20/00G01W1/10G06F111/10G06F119/08
Inventor 黄平王听雨
Owner INST OF ATMOSPHERIC PHYSICS CHINESE ACADEMY SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap