Previsão de Focos de Calor na Região Metropolitana de Maceió Utilizando Rede Neural Artificial

Abstract

O objetivo deste estudo é o de analisar a previsão de focos de calor (FC) na Região Metropolitana de Maceió (RMM) utilizando Rede Neural Artificial (RNA). Foram usados neste estudo os dados de focos de calor no período de 1999 a 2019, disponíveis no Banco de Dados de Queimadas (BDQueimadas). A previsão foi feita com base na RNA não linear autorregressiva (NAR) com os FC sendo dados de entrada e alvo. As previsões se basearam na função de ativação Tangente Hiperbólica e Sigmoide, para averiguar qual função se adaptaria melhor ao modelo de previsão de FC na RMM. O desempenho do modelo foi verificado pelo diagrama de espalhamento (1:1), com destaque para Regressão Linear Simples (RLS), os coeficientes de determinação (R2) e de Pearson (r), seguido dos indicadores de erros (EM - Erro Médio, REQM – Raiz do Erro Quadrático Médio, EPAM – Erro Percentual Absoluto Médio). O EM variou entre -0,47 a 1,49 focos, o REQM (1,16 a 7,02 focos) e o EPAM (14,45 a 24,66%). Os coeficientes r (0,08 a 0,52) e R2 (1 a 58%). Os modelos com base nas funções de ativação foram similares entre observado e previsto, sendo satisfatória na maioria dos municípios. Os modelos não tiveram sucesso na previsão de FC elevados, principalmente nos anos 2008, 2012, 2015 e 2016, período de seca extrema. Os resultados obtidos indicam que a aplicação de RNA na previsão de FC pode auxiliar nas tomadas de decisões dos gestores públicos e no monitoramento de queimadas e incêndios em áreas urbanas.Palavras-chave: incêndios, inteligência artificial, monitoramento ambiental. Forecast of Fire Foci in the Metropolitan Region of Maceió Using Artificial Neural NetworkABSTRACTThe aim of this study is to analyze the forecast of fire foci (FF) in the Maceió Metropolitan Region (MMR) using Artificial Neural Network (ANN). It was used in the study fire foci data available in the Burning Database (BDQueimadas) in the period from 1999 to 2019. The forecast was made based on the ANN non-linear autoregressive (NAR) with the FF, being input and target data. The forecast was based Hyperbolic Tangent and Sigmoid activation function, to find out which function would best adapt to the forecast model of FF in the MMR. The model performance was based on the Scatter Diagram (1:1), with emphasis on Simple Linear Regression (SLR), the coefficients of determination (R2) and Pearson’s (r), followed by the error indicators (ME – Mean Error, RMSE – Root Mean Square Error, MAPE – Mean Absolute Percentage Error). The ME ranged from -0.47 to 1.49 foci, RMSE (1.16 to 7.02 foci), MAPE (14.45 to 24.66%). The coefficients r (0.08 to 0.52) and R2 (1 to 58%). The models based on activation function were similar between observed and predicted, being satisfactory in most municipalities. The models were not successful in forecast high FF, especially in the years 2008, 2012, 2015 and 2016, a period of extreme drought. These results obtained in the study indicate that the application of ANN in the forecast of FF can help in the decision-making of public managers and in the monitoring of burnings and fires in urban areas.Keywords: Fire foci, Artificial Intelligence, Environmental Monitoring.

Rede neural artificial aplicada aos casos notificados de dengue cases em Maceió – Alagoas

“…Maceió is in ENEB between latitudes 9.40º to 9.70º S, and longitudes 35.80º to 35.60º W, with altitudes that vary between 0 and 100 m above mean sea level (NMM), located in the Atlantic Forest biome. (Santos, et al, 2022;Batista, et al, 2021), as shown in Figure 1. According to the Köppen-Geiger classification, it is categorized as tropical hot and humid 'As', with variations in temperature throughout the year.…”

“…This ANN is characterized by the variable Z, which is the time delay. The Z factor works as a memory that provides current and previous input values (Santos, et al, 2022;Santos, et al, 2020;Samet, et al, 2019).…”

“…( 2)), as it does not propagate negative values, since there are no negative NDC records. It is a continuously differentiable and nonlinear activation function with the shape of S that serve as input to the next layer, they reduce the effect of extreme input values, with a better functioning of the ANN-NAR (Santos, et al, 2022). Figure 2 shows the Sigmoid activation function in the Cartesian plane x and f(x) with emphasis on the ordered pair (0,0.5) which is the inflection point of the curve.…”

“…Table 2 shows the final configuration of the ANN-NAR training phase, the architecture was configured to provide the NDC prediction based on the input/target values in the study period. The configuration of the parameters used was based on studies Santos, et al, 2020;Santos, et al, 2022).…”