Machine Learning Based ENSO Prediction Using Multivariate Ocean Atmosphere Data

DOI

10.2991/978-94-6239-697-5_29How to use a DOI?

Keywords

ENSO; El Niño southern oscillation; machine learning; LSTM; random forest; gradient boosting; sea surface temperature; sea level pressure

Abstract

El Niño–Southern Oscillation (ENSO) is a major driver of global climate variability that influences extreme weather, agriculture, water resources, and socio-economic systems. Predicting ENSO is challenging because of the complex interactions between the ocean and atmosphere. This study assesses the ENSO prediction capabilities using a number of machine learning techniques applied to a wide range of oceanic and atmospheric variables spanning 1980–2023. These variables include, but are not limited to, surface and subsurface temperatures, pressures, depths, winds, heat content, and outgoing longwave radiation. To predict the Niño 3.4 index and Niño 4 index, six models are tested; they are Random Forest, Gradient Boosting, Support Vector Regression, XGBoost, LSTM, and 1D-CNN. The results show that deep learning models particularly the 1D-CNN and the LSTM are effective more than the conventional methods. Niño 3.4 SST, thermocline depth, and ocean heat content are also found as the most significant predictors through the feature analysis, to enhance the process of prediction of ENSO and climatic early-warning systems.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Dibyadarshini Maharatha
AU  - Prashant Kumar
AU  - Yukiharu Hiasaki
AU  - Rajni Rajni
PY  - 2026
DA  - 2026/06/04
TI  - Machine Learning Based ENSO Prediction Using Multivariate Ocean Atmosphere Data
BT  - Proceedings of the Conference on Bridging Engineering Disciplines with AI and Machine Learning (BEDAIML 2026)
PB  - Atlantis Press
SP  - 348
EP  - 356
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-697-5_29
DO  - 10.2991/978-94-6239-697-5_29
ID  - Maharatha2026
ER  -