A data-based model for predicting wildfires in Chapada das Mesas National Park in the State of Maranhão

Abstract

Chapada das Mesas National Park extends over an area of 160,046 ha in the municipalities of Carolina, Riachão, Estreito and Imperatriz in the south central region of the state of Maranhão, northeast Brazil, in a savanna-like biome known as the Cerrado. The park has a rich biodiversity, making the need for conservation all the more important. The weather conditions in the region increase the likelihood of wildfires, so that a monitoring and control system for the area is needed to help conservation efforts. This article proposes a methodology that uses data-mining techniques to predict outbreaks of wildfires in the park some hours in advance. Predictive models using wildfire records and a meteorology dataset for 11 months in 2010 were built. Two different classification techniques for predicting wildfires were used: artificial neural networks and classification rules. The two models built with these techniques showed good accuracy when tested with the validation samples and could be used as additional tools for predicting the risk of fires in the area.

Machine learning to predict final fire size at the time of ignition

“…Also, classification techniques have rarely been evaluated in the context of fire prediction. One example is a study in Brazil that used machine learning classification to predict the risk of ignitions in different areas, but similarly did not attempt to identify which ignitions were most likely to become large ( de Souza et al 2015 ).…”

Global Wildfire Outlook Forecast with Neural Networks

“…The mean R-square is 0.59, 0.51, and 0.41, the mean index of agreement (IOA) is 0.74, 0.65, and 0.54, the mean normalized root-mean-square deviation (NRMSD) is 0.15, 0.3, and 0.4, the mean normalized mean error (NME) is 54%, 62%, and 70%, the mean normalized mean bias (NMB) is 33%, 42%, and 54%, for the neural network, regression tree, and GLM, respectively. This reflects the nonlinear dependence of wildfires on meteorological parameters and demonstrates the ability of the neural network method to resolve nonlinear and highly variable events like wildfires [32,70,74,75]. Consequently, we show only the neural network prediction results in the following sections.…”

“…Remote Sens. 2020, 12, x FOR PEER REVIEW 6 of 21 highly variable events like wildfires [32,70,74,75]. Consequently, we show only the neural network prediction results in the following sections.…”

“…In comparison to linear regression, the regression tree method can deal with the nonlinear relationship between independent and dependent variables [19,23,24], but it may have a poor resolution with continuous expectation variables and tends to be sensitive to small perturbations in the data [25,26]. Recently, more advanced data-driven models, created through data-adaptive machine learning methods from a large set of spatiotemporal datasets, have been employed in predicting wildfires and PM2.5 [27][28][29][30][31][32], and have obtained encouraging results. In recent years, machine learning methods have been applied to satellite fire image recognition [33], such as artificial neural network (ANN [34]), Bayesian (BN [35]), convolutional neural network (CNN [36]), Depp neural network (DNN [37]), decision tree (DT [38]), K-means clustering (KM [39]), recurrent neural network (RNN [40]).…”

COVID-19 morbidity and mortality forecast in megalopolis: a data approach to public health management in São Paulo, Brazil

“…This article proposes a methodological approach that has been used to support decision making in several areas 30,31,32 , including recently in urban health 33 . Although such an approach has been little used, it is a potential tool in the context of the current health crisis caused by COVID-19 and can contribute to decision-making in facing the virus and other epidemic diseases.…”