Exploring Machine Learning, Deep Learning, and Explainable AI Methods for Seasonal Precipitation Prediction in South America

2025-12-15

AI Summary

This study addresses the challenge of seasonal precipitation prediction over South America. We systematically evaluate purely data-driven models—including Random Forest, XGBoost, 1D-CNN, LSTM, and GRU—and benchmark them against the conventional dynamical model BAM. To our knowledge, this is the first unified, continent-wide, and seasonally comprehensive assessment of diverse machine learning and deep learning methods for South American precipitation forecasting. We further innovate by integrating SHAP and LIME—state-of-the-art explainable AI (XAI) techniques—to quantitatively disentangle the contributions of key meteorological predictors. Results show that LSTM achieves the highest accuracy for heavy-precipitation events, while XGBoost offers the best trade-off between computational efficiency and predictive skill; BAM performs worst across metrics. The study demonstrates that data-driven approaches hold significant operational potential for climate prediction in resource-constrained settings—particularly where high-resolution initial conditions and extensive computational capacity are unavailable—thereby establishing a novel paradigm for seasonal precipitation forecasting over South America.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Humans and AI: Human-in-the-loop Machine Learning
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Forecasting meteorological variables is challenging due to the complexity of their processes, requiring advanced models for accuracy. Accurate precipitation forecasts are vital for society. Reliable predictions help communities mitigate climatic impacts. Based on the current relevance of artificial intelligence (AI), classical machine learning (ML) and deep learning (DL) techniques have been used as an alternative or complement to dynamic modeling. However, there is still a lack of broad investigations into the feasibility of purely data-driven approaches for precipitation forecasting. This study aims at addressing this issue where different classical ML and DL approaches for forecasting precipitation in South America, taking into account all 2019 seasons, are considered in a detailed investigation. The selected classical ML techniques were Random Forests and extreme gradient boosting (XGBoost), while the DL counterparts were a 1D convolutional neural network (CNN 1D), a long short-term memory (LSTM) model, and a gated recurrent unit (GRU) model. Additionally, the Brazilian Global Atmospheric Model (BAM) was used as a representative of the traditional dynamic modeling approach. We also relied on explainable artificial intelligence (XAI) to provide some explanations for the models behaviors. LSTM showed strong predictive performance while BAM, the traditional dynamic model representative, had the worst results. Despite presented the higher latency, LSTM was most accurate for heavy precipitation. If cost is a concern, XGBoost offers lower latency with slightly accuracy loss. The results of this research confirm the viability of DL models for climate forecasting, solidifying a global trend in major meteorological and climate forecasting centers.

Problem

• Evaluating machine and deep learning for South American precipitation forecasting
• Comparing data-driven models with traditional dynamic climate modeling
• Assessing model performance and explainability across seasonal conditions

Innovation

• Used machine learning and deep learning models for precipitation prediction
• Applied explainable AI to interpret model behaviors and decisions
• Compared data-driven approaches with traditional dynamic atmospheric modeling