Forecasting the El Niño Southern Oscillation (ENSO) is crucial for mitigating the impacts of extreme weather events on ecosystems and human activities. Researchers from Kent State University evaluated the performance of six machine-learning models in predicting two types of ENSO. The study, published in Physica Scripta, found that deep learning models, specifically the Feed Forward Neural Network (FFNN) and Long Short-term Memory (LSTM), provided the most accurate 6-month lead-time forecasts. These two models captured the complex relationships in historical ENSO data more effectively than the other models, demonstrating their potential for more reliable ENSO forecasting. These findings can help advance proactive planning and risk management in agriculture, water resources, and disaster preparedness.
The Climate Program Office’s Modeling, Analysis, Predictions, and Projections (MAPP) program supported this work through a grant to develop new model-based monitoring products addressing key climate impact areas. Lead author Chibuike Ibebuchi, a postdoctoral researcher at Kent State University, works with MAPP-funded scientist Cameron Lee on a project aimed at monitoring hazardous temperature conditions in North America.
For more information, contact Clara Deck.