Machine learning derived sub-seasonal to seasonal extremes

Resumo


Improving the accuracy of sub-seasonal to seasonal (S2S) extremes can significantly impact society. Providing S2S forecasts in the form of risk or extreme indices can aid in disaster response, especially for drought and flood events. Additionally, it can provide updates on disease outbreaks and aid in predicting the occurrence, duration, and decline of heatwaves. This work uses a transformer model to predict the daily temperature distributions in the S2S scale. We analyze how the model performs in extreme temperatures by comparing its output distributions with those obtained from ECMWF forecasts across different metrics. Our model produces better responses for temperatures in average and extreme regions. Also, we show how our model better captures the heatwave that hit Europe in the summer of 2019.

Palavras-chave: machine learning, transformer, extremes, subseasonal to seasonal

Referências

Akram Zaytar, M., Zadrozny, B., Watson, C., Salles Civitarese, D., Eben Vos, E., Mathonsi, T. M., and Lukhetho Mashinini, T. (2022). ML-based Probabilistic Prediction of 2m Temperature and Total Precipitation. In EGU General Assembly Conference Abstracts, EGU General Assembly Conference Abstracts, pages EGU22–11063.

Board, O. S., of Sciences Engineering, N. A., Medicine, et al. (2016). Next generation earth system prediction: strategies for subseasonal to seasonal forecasts. National Academies Press.

Civitarese, D. S., Szwarcman, D., Zadrozny, B., and Watson, C. (2021). Extreme precipitation seasonal forecast using a transformer neural network.

Lim, B., Arik, S. Ö., Loeff, N., and Pfister, T. (2021). Temporal fusion transformers for interpretable multi-horizon time series forecasting. International Journal of Forecasting, 37(4):1748–1764.

Patel, Z., Baloyi, G., Watson, C., Zaytar, A., Zadrozny, B., Civitarese, D., Makhanya, S., and Vos, E. (2022). S2S Extreme Weather Featurization: A Global Skill Assessment Study. In EGU General Assembly Conference Abstracts, EGU General Assembly Conference Abstracts, pages EGU22–12461.

Poppenga, S. K., Evans, G., Gesch, D., Stoker, J. M., Queija, V. R., Worstell, B., Tyler, D. J., Danielson, J., Bliss, N., and Greenlee, S. (2010). Topographic science. Technical report, US Geological Survey.

Robertson, A. and Vitart, F. (2018). Sub-seasonal to seasonal prediction: the gap between weather and climate forecasting. Elsevier.

Store, C. C. D. (2019). Land cover classification gridded maps from 1992 to present derived from satellite observations.
Publicado
25/09/2023
SALLES CIVITARESE, Daniel; ZADROZNY, Bianca. Machine learning derived sub-seasonal to seasonal extremes. In: WORKSHOP ON DATA-DRIVEN EXTREME EVENTS ANALYTICS (DEXEA) - SIMPÓSIO BRASILEIRO DE BANCO DE DADOS (SBBD), 38. , 2023, Belo Horizonte/MG. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2023 . p. 312-317. DOI: https://doi.org/10.5753/sbbd_estendido.2023.235209.