In a recently published study, researchers from the Institute of Atmospheric Physics of the Chinese Academy of Sciences have developed an artificial intelligence (AI) model using deep learning algorithms that outperforms traditional dynamic models in predicting the development and pattern of El Niño events in the central Pacific Ocean.
The study, published in Advances in Atmospheric Scienceshighlights the potential for AI to improve seasonal forecasting and offers significant improvements in climate forecasting.
El Niño events in the central Pacific Ocean can have a large impact on the global climate, making accurate forecasts essential for preparedness and risk reduction. The new AI model, based on convolutional neural network technology, is trained on sea surface temperature (SST) produced by models participating in the Coupled Model Intercomparison Projects to predict the specific shape, location, and timing of SST anomalies associated with central Pacific El Niño events.
“This study shows the potential of artificial intelligence to improve predictions of important climate events such as El Niño that can have devastating effects around the world,” said Prof. Huang Ping, corresponding author of the study.
The AI model outperformed traditional dynamical models in accuracy, especially in predicting SST anomalies in the west-central equatorial Pacific. In addition, a hybrid model combining predictions from the AI model and dynamic models achieved higher accuracy for central and eastern Pacific El Niño events.
The research team plans to further use the power of deep learning to expand the use of AI models in seasonal climate forecasting, with the goal of providing earlier and more accurate warnings of major weather events.
The findings have important implications for disaster risk reduction efforts worldwide, as AI-driven predictions can contribute to better preparedness and mitigation strategies. By harnessing the potential of AI, scientists and policymakers can work together to increase global resilience to climate-related challenges.
More information:
Tingyu Wang et al, Superiority of a Convolutional Neural Network Model over Dynamical Models in Predicting Central Pacific ENSO, Advances in Atmospheric Sciences (2023). DOI: 10.1007/s00376-023-3001-1
Awarded by the Chinese Academy of Sciences
Citation: New AI model outperforms traditional methods to predict central Pacific El Niño (2023, July 24) retrieved on July 25, 2023 from https://phys.org/news/2023-07-ai-outperforms-traditional-methods-central.html
This document is subject to copyright. Except for any fair dealing for the purpose of private study or research, no part may be reproduced without written permission. Content is provided for informational purposes only.