wildfires vegetation recovery through satellite remote sensing and functional data analysis

• DOI: 10.48550/arxiv.2105.10050
• Publication Date: 2021-06-07
• Authors: Feliu Serra-Burriel; Pedro Delicado; Fernando M. Cucch...
• Keywords: FOS: Computer and information sciences; Teledetecció; landsat; NDVI; Àrees temàtiques de la UPC::Matemàtiques i estadística::Anàlisi matemàtica::Anàlisi funcional; Statistics - Applications; 01 natural sciences; Wildfires; Functional principal components analysis; QA1-939; Anàlisi multivariable; Applications (stat.AP); causal inference; Function-on-scalar regression; 0101 mathematics; :Matemàtiques i estadística::Anàlisi matemàtica::Anàlisi funcional [Àrees temàtiques de la UPC]; functional data analysis; Functional analysis; Remote sensing; 15. Life on land; Time series decomposition; functional principal components analysis; Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Radiocomunicació i exploració electromagnètica::Teledetecció; Functional data analysis; Multivariate analysis; :Enginyeria de la telecomunicació::Radiocomunicació i exploració electromagnètica::Teledetecció [Àrees temàtiques de la UPC]; 13. Climate action; Anàlisi funcional; Synthetic controls; function-on-scalar regression; causal inference; functional data analysis; functional principal components analysis; function-on-scalar regression; landsat; NDVI; remote sensing; synthetic controls; time series decomposition; wildfires; Landsat; Mathematics; Causal inference

In recent years, wildfires have caused havoc across the world, which are especially aggravated in certain regions due to climate change. Remote sensing has become a powerful tool for monitoring fires, as well as for measuring their effects on vegetation over the following years. We aim to explain the dynamics of wildfires’ effects on a vegetation index (previously estimated by causal inference through synthetic controls) from pre-wildfire available information (mainly proceeding from satellites). For this purpose, we use regression models from Functional Data Analysis, where wildfire effects are considered functional responses, depending on elapsed time after each wildfire, while pre-wildfire information acts as scalar covariates. Our main findings show that vegetation recovery after wildfires is a slow process, affected by many pre-wildfire conditions, among which the richness and diversity of vegetation is one of the best predictors for the recovery.