Neural Networks with LSTM and GRU in Modeling Active Fires in the Amazon

TL;DR

This paper introduces a combined LSTM and GRU neural network model to accurately forecast active fire spots in the Amazon, demonstrating deep learning's effectiveness in environmental time series prediction.

Contribution

It presents a novel mixed RNN approach that effectively captures seasonality and complex patterns in fire data, advancing machine learning applications in environmental monitoring.

Findings

The combined LSTM and GRU model achieved high forecasting accuracy.

The model successfully captured seasonal patterns in fire data.

Deep learning models can be effectively applied to environmental time series forecasting.

Abstract

This study presents a comprehensive methodology for modeling and forecasting the historical time series of active fire spots detected by the AQUA\_M-T satellite in the Amazon, Brazil. The approach employs a mixed Recurrent Neural Network (RNN) model, combining Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) architectures to predict the monthly accumulations of daily detected active fire spots. Data analysis revealed a consistent seasonality over time, with annual maximum and minimum values tending to repeat at the same periods each year. The primary objective is to verify whether the forecasts capture this inherent seasonality through machine learning techniques. The methodology involved careful data preparation, model configuration, and training using cross-validation with two seeds, ensuring that the data generalizes well to both the test and validation sets for both seeds. The results indicate that the combined LSTM and GRU model delivers excellent forecasting performance, demonstrating its effectiveness in capturing complex temporal patterns and modeling the observed time series. This research significantly contributes to the application of deep learning techniques in environmental monitoring, specifically in forecasting active fire spots. The proposed approach highlights the potential for adaptation to other time series forecasting challenges, opening new opportunities for research and development in machine learning and prediction of natural phenomena. Keywords: Time Series Forecasting; Recurrent Neural Networks; Deep Learning.