Short-term forecasting of Amazon rainforest fires based on ensemble decomposition model

TL;DR

This paper introduces a novel ensemble decomposition model for short-term forecasting of Amazon rainforest fires, improving accuracy and aiding decision-making amidst rising fire incidents.

Contribution

The paper develops a new heterogeneous decomposition-ensemble model combining Seasonal and Trend decomposition with algorithms for multi-month-ahead fire forecasting.

Findings

Proposed models achieve higher forecasting accuracy.

Diebold-Mariano test shows models outperform others statistically.

Models are statistically comparable to the best existing methods.

Abstract

Accurate forecasting is important for decision-makers. Recently, the Amazon rainforest is reaching record levels of the number of fires, a situation that concerns both climate and public health problems. Obtaining the desired forecasting accuracy becomes difficult and challenging. In this paper were developed a novel heterogeneous decomposition-ensemble model by using Seasonal and Trend decomposition based on Loess in combination with algorithms for short-term load forecasting multi-month-ahead, to explore temporal patterns of Amazon rainforest fires in Brazil. The results demonstrate the proposed decomposition-ensemble models can provide more accurate forecasting evaluated by performance measures. Diebold-Mariano statistical test showed the proposed models are better than other compared models, but it is statistically equal to one of them.