Short-lead seasonal precipitation forecast in northeastern Brazil using an ensemble of artificial neural networks

• Published in: Scientific reports Vol. 13; no. 1; pp. 20429 - 14
• Main Authors: Pinheiro, Enzo, Ouarda, Taha B. M. J.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 22.11.2023; Nature Publishing Group; Nature Portfolio
• Subjects: 704/106/35/823; 704/829; Atmospheric dynamics; Climate prediction; ENVIRONMENTAL SCIENCES; Forecasting; Humanities and Social Sciences; Mathematical models; multidisciplinary; Neural networks; Ocean sciences; Science; Science & Technology; Science (multidisciplinary); Spatial analysis; Statistical analysis; Statistical models; Brazil
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-023-47841-y

This study assesses the deterministic and probabilistic forecasting skill of a 1-month-lead ensemble of Artificial Neural Networks (EANN) based on low-frequency climate oscillation indices. The predictand is the February-April (FMA) rainfall in the Brazilian state of Ceará, which is a prominent subject in climate forecasting studies due to its high seasonal predictability. Additionally, the study proposes combining the EANN with dynamical models into a hybrid multi-model ensemble (MME). The forecast verification is carried out through a leave-one-out cross-validation based on 40 years of data. The EANN forecasting skill is compared with traditional statistical models and the dynamical models that compose Ceará’s operational seasonal forecasting system. A spatial comparison showed that the EANN was among the models with the smallest Root Mean Squared Error (RMSE) and Ranked Probability Score (RPS) in most regions. Moreover, the analysis of the area-aggregated reliability showed that the EANN is better calibrated than the individual dynamical models and has better resolution than Multinomial Logistic Regression for above-normal (AN) and below-normal (BN) categories. It is also shown that combining the EANN and dynamical models into a hybrid MME reduces the overconfidence of the extreme categories observed in a dynamically-based MME, improving the reliability of the forecasting system.