A security guard wearing an electric fan on his neck wipes his sweat on a hot day in Beijing, July 3, 2023. The entire planet has sweltered in the past weeks amid a strong El Nino event. (PHOTO / AP)

BEIJING - Chinese researchers have developed an artificial intelligence (AI) model powered by deep learning algorithms to predict the development and pattern of central Pacific El Nino events.

Scientists believe that El Nino events in the central Pacific can have far-reaching impacts on global climate, making accurate predictions crucial for preparedness and risk reduction.

The research team plans to further leverage the power of deep learning to expand the application of AI models in seasonal climate forecasting, aiming to provide earlier and more accurate warnings of major weather events

Based on the convolutional neural network technology, researchers from the Institute of Atmospheric Physics (IAP) under the Chinese Academy of Sciences developed a deep learning model for predicting the spatial pattern of sea surface temperature anomalies in the equatorial Pacific.

ALSO READ: How El Nino is helping drive heatwaves and extreme weather

"This study demonstrates the potential of AI in improving predictions of significant climate events like El Nino that can have devastating effects around the globe," said Huang Ping, a researcher at IAP and the corresponding author of the study recently published in the journal Advances in Atmospheric Sciences.

According to the study, the AI model surpasses traditional dynamical models in accuracy, particularly in predicting sea surface temperature anomalies in the west-central equatorial Pacific.

READ MORE: Chinese researchers prove presence of ocean on Mars

The study also suggests that a hybrid model that combines predictions from both the AI model and dynamical models achieves even higher accuracy for central and east Pacific El Nino events.

The research team plans to further leverage the power of deep learning to expand the application of AI models in seasonal climate forecasting, aiming to provide earlier and more accurate warnings of major weather events.