An interpretable machine learning model for seasonal precipitation forecasting.

Pinheiro, Enzo ORCID: https://orcid.org/0000-0002-7532-2210 et Ouarda, Taha B. M. J. ORCID: https://orcid.org/0000-0002-0969-063X (2025). An interpretable machine learning model for seasonal precipitation forecasting. Communications Earth & Environment , vol. 6 , nº 1. p. 222. DOI: 10.1038/s43247-025-02207-2.

Prévisualisation

PDF - Version publiée Télécharger (3MB) | Prévisualisation

Résumé

Seasonal climate forecasting is important for societal welfare, as it supports decision-makers in taking proactive steps to mitigate risks from adverse climate conditions or to take advantage of favorable ones. Here, we introduce TelNet, a sequence-to-sequence machine learning model for short-to-medium lead seasonal precipitation forecasting. The model takes past seasonal precipitation values and climate indices to predict an empirical precipitation distribution for every grid point of the target region for the next six overlapping seasons. TelNet has a simple encoder-decoder-head architecture, allowing the model to be trained with a limited amount of data, as is often the case in climate forecasting. Its deterministic and probabilistic performance is thoroughly evaluated and compared with state-of-the-art dynamical and deep learning models in a prominent region for seasonal forecasting studies due to its high climate predictability. The training, validation, and test sets are resampled multiple times to estimate the uncertainty associated with a small dataset. The results show that TelNet ranks among the most accurate and calibrated models across multiple initialization months and lead times, especially during the rainy season when the predictable signal is strongest. Moreover, the model allows instance- and lead-wise forecast interpretation through its variable selection weights.

Type de document:	Article
Mots-clés libres:	atmospheric dynamics; hydrology
Centre:	Centre Eau Terre Environnement
Date de dépôt:	26 mars 2025 18:34
Dernière modification:	26 mars 2025 18:34
URI:	https://espace.inrs.ca/id/eprint/16408

Gestion Actions (Identification requise)

Modifier la notice