Data Analytics for a Changing Climate: Feature Engineering for the forecast of hydrometeorological events

• Caique S. Noboa Universidade Tecnológica Federal do Paraná (UTFPR)
• Daniel Pigatto Universidade Tecnológica Federal do Paraná (UTFPR)
• Elaiz M. Buffon Universidade Estadual do Oeste do Paraná (Unioeste)
• Luiz Gomes-Jr Universidade Tecnológica Federal do Paraná (UTFPR)

DOI: https://doi.org/10.5753/sbbd.2024.240251

Resumo

Floods are becoming increasingly frequent, and consequently, the number of people and infrastructure affected by these events has increased. It is essential to have accurate models for the prediction of such hydrometeorological events, improving preparedness and decision making for damage reduction. The goal of this work was to determine the variables (features) that contribute the most to predicting hydrometeorological events. Feature engineering techniques were used to understand which factors are most helpful in predicting floods. The features were composed based on data from rain gauges, altimetry, and location of rivers and lakes. It was observed that the variables that had the greatest impact on improving the model were the data from rain gauges and altitude data. The predictive model proposed is part of a larger system being developed in the context of Smart Cities called ICARUS. The system is aimed at improving response time and up-time of critical infrastructure during extreme events.

Palavras-chave: data analytics, feature engineering, floods

Referências

A, L. and M, W. (2002). Classification and regression by randomforest. R News, pages 18–22.

Breiman, L. (2001). Random forests. Machine learning, 45(1):5–32.

Buffon, E. A. M. (2020). Inundações Em Áreas Urbanas: Proposição Conceitual-Metodológica E Sua Aplicação Na RMC – Região Metropolitana De Curitiba.

Buffon, E. A. M. and de Sousa, M. S. (2018). Proposta Metodológica Para Avaliação Dos Registros Secundários De Alagamentos: Uma Abordagem A Partir De Curitiba-Paraná, Brasil.

Cemaden (2021). Pluviômetros Automáticos – Cemaden. Accessed: 2022-11-03.

de Curitiba, P. M. (2022). Dados Geográficos de Curitiba. Accessed: 2022-11-05.

Fernandez, H. G. and Splendore, P. R. (2021). Sistema De Identificação Automática De Riscos Hidrometeorológicos Com Retroalimentação E Reestruturação Autônoma Da Infraestrutura De Comunicação. Curitiba, Brasil.

IPPUC (2022). Registros Alagamentos. Accessed: 2022-11-07.

Kulldorff, M. (1997). A spatial scan statistic. Communications in Statistics-Theory and methods, 26(6):1481–1496.

Lohmann, M. (2011). Regressão Logística E Redes Neurais Aplicadas À Previsão Probabilística De Alagamentos No Município De Curitiba, PR. Curitiba, Brasil.

Matisziw, T. C. and Murray, A. T. (2009). Modeling s–t path availability to support disaster vulnerability assessment of network infrastructure. Computers & Operations Research, 36(1):16–26.

Noronha, G. (2021). Enchentes – O que são, características, causas e impacto urbano.

Quinlan, J. R. (1986). Induction of decision trees. Machine Learning, 1.

Wu, E., Liu, W., and Chawla, S. (2010). Spatio-temporal outlier detection in precipitation data. In Knowledge Discovery from Sensor Data, pages 115–133. Springer Berlin Heidelberg.