|
Registro Completo |
|
Biblioteca(s): |
Embrapa Arroz e Feijão; Embrapa Pantanal. |
|
Data corrente: |
28/06/2023 |
|
Data da última atualização: |
04/09/2023 |
|
Tipo da produção científica: |
Artigo em Anais de Congresso |
|
Autoria: |
SANTOS, B. Z.; SORIANO, B. M. A.; NARCISO, M. G.; SILVA, D. F.; CERRI, R. |
|
Afiliação: |
BRUNA ZAMITH SANTOS, UNIVERSIDADE FEDERAL DE SÃO CARLOS; BALBINA MARIA ARAUJO SORIANO, CPAP; MARCELO GONCALVES NARCISO, CNPAF; DIEGO FURTADO SILVA, USP; RICARDO CERRI, UNIVERSIDADE FEDERAL DE SÃO CARLOS. |
|
Título: |
A new time series framework for forest fire risk forecasting and classification. |
|
Ano de publicação: |
2023 |
|
Fonte/Imprenta: |
In: INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2023, Queensland, Australia. Proceedings. Illinois: International Neural Network Society, 2023. |
|
Idioma: |
Inglês |
|
Conteúdo: |
There's an increasing concern about the occurrence and spread of forest fires across the globe, as they contribute to greenhouse gas emissions and play a major influential role in economics and public health. Thus, there's a need for accurate methods to predict and classify forest fire risk. The main known forest fire risk indexes have limitations, such as not taking into account the unique characteristics of the biome in study, and not being able to predict forest fire risk for a given number of days in the future. This last aspect, in particular, is of utmost relevance. Addressing it allows for coordinated planning and action by proper authorities with adequate anticipation. Aiming to solve this problem, we present a new framework that applies Machine Learning methods for: (1) climatic variables forecasting; and (2) forest fire risk classification. For the first objective, different time series forecasting algorithms were tested. The forecasted variables are then used as input for the second objective, for which different classification algorithms were also tested. We evaluated our proposal using Brazilian Pantanal regional biome data from 1999 to 2019, where climatic variables were collected from ground meteorological stations, and fire occurrences (hotspots) were obtained from satellite images. The experiments considered 4 climatic variables and 5 forest fire risk classes. The results were evaluated based on the average correlation between (i) the prediction of forest fire risk classes and (ii) the observation of hotspots. Our proposal proved to be better or competitive with the main forest fire risk indexes, with the advantage of predicting fire risk for a given number of days in the future. MenosThere's an increasing concern about the occurrence and spread of forest fires across the globe, as they contribute to greenhouse gas emissions and play a major influential role in economics and public health. Thus, there's a need for accurate methods to predict and classify forest fire risk. The main known forest fire risk indexes have limitations, such as not taking into account the unique characteristics of the biome in study, and not being able to predict forest fire risk for a given number of days in the future. This last aspect, in particular, is of utmost relevance. Addressing it allows for coordinated planning and action by proper authorities with adequate anticipation. Aiming to solve this problem, we present a new framework that applies Machine Learning methods for: (1) climatic variables forecasting; and (2) forest fire risk classification. For the first objective, different time series forecasting algorithms were tested. The forecasted variables are then used as input for the second objective, for which different classification algorithms were also tested. We evaluated our proposal using Brazilian Pantanal regional biome data from 1999 to 2019, where climatic variables were collected from ground meteorological stations, and fire occurrences (hotspots) were obtained from satellite images. The experiments considered 4 climatic variables and 5 forest fire risk classes. The results were evaluated based on the average correlation between (i) the prediction of forest fi... Mostrar Tudo |
|
Thesagro: |
Análise de Risco; Fogo; Incêndio Florestal; Previsão do Tempo. |
|
Thesaurus Nal: |
Classification; Forest fires; Weather forecasting. |
|
Categoria do assunto: |
P Recursos Naturais, Ciências Ambientais e da Terra |
|
Marc: |
LEADER 02530nam a2200241 a 4500
001 2154743
005 2023-09-04
008 2023 bl uuuu u00u1 u #d
100 1 $aSANTOS, B. Z.
245 $aA new time series framework for forest fire risk forecasting and classification.$h[electronic resource]
260 $aIn: INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2023, Queensland, Australia. Proceedings. Illinois: International Neural Network Society$c2023
520 $aThere's an increasing concern about the occurrence and spread of forest fires across the globe, as they contribute to greenhouse gas emissions and play a major influential role in economics and public health. Thus, there's a need for accurate methods to predict and classify forest fire risk. The main known forest fire risk indexes have limitations, such as not taking into account the unique characteristics of the biome in study, and not being able to predict forest fire risk for a given number of days in the future. This last aspect, in particular, is of utmost relevance. Addressing it allows for coordinated planning and action by proper authorities with adequate anticipation. Aiming to solve this problem, we present a new framework that applies Machine Learning methods for: (1) climatic variables forecasting; and (2) forest fire risk classification. For the first objective, different time series forecasting algorithms were tested. The forecasted variables are then used as input for the second objective, for which different classification algorithms were also tested. We evaluated our proposal using Brazilian Pantanal regional biome data from 1999 to 2019, where climatic variables were collected from ground meteorological stations, and fire occurrences (hotspots) were obtained from satellite images. The experiments considered 4 climatic variables and 5 forest fire risk classes. The results were evaluated based on the average correlation between (i) the prediction of forest fire risk classes and (ii) the observation of hotspots. Our proposal proved to be better or competitive with the main forest fire risk indexes, with the advantage of predicting fire risk for a given number of days in the future.
650 $aClassification
650 $aForest fires
650 $aWeather forecasting
650 $aAnálise de Risco
650 $aFogo
650 $aIncêndio Florestal
650 $aPrevisão do Tempo
700 1 $aSORIANO, B. M. A.
700 1 $aNARCISO, M. G.
700 1 $aSILVA, D. F.
700 1 $aCERRI, R.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Pantanal (CPAP) |
|
