RT info:eu-repo/semantics/article
T1 Enhanced burn severity estimation using fine resolution ET and MESMA fraction images with machine learning algorithm
A1 Quintano, Carmen
A1 Fernández-Manso, Alfonso
A1 Roberts, Dar
K1 Evapotranspiration
K1 Energy balance
K1 MESMA
K1 Burn severity
K1 Random forest
AB Successful post-fire management depends on accurate burn severity maps that are increasingly derived from satellitedata, replacing field-based estimates. Post-fire vegetation and soil changes, besides modifying the reflectedand emitted radiation recorded by sensors onboard satellites, strongly alters water balance in the fire affectedarea. While fire-induced spectral changes can be well represented by fraction images from Multiple EndmemberSpectral Mixture Analysis (MESMA), changes in water balance are mainly registered by evapotranspiration (ET).As both types of variables have a clear physical meaning, they can be easily understood in terms of burn severity,providing a clear advantage compared to widely-used spectral indices. In this research work, we evaluate the potentialof Landsat-derived ET to estimate burn severity, together with MESMA derived Sentinel-2 fraction imagesand important environment variables (pre-fire vegetation, climate, topography). In this study, we use the randomforest (RF) classifier, which provides information on variable importance allowing us to identify the combinationof input variables that provided the most accurate estimate. Our study area is located in Central Portugal, wherea mega-fire burned >450 km2 from 17 to 24 June 2017. We used the official burn severity map as ground reference.The RF algorithm identified ET as the most important variable in the burn severity model, followed byMESMA char fractions. When both ET and MESMA char fraction image were used as RF inputs, burn severityestimates reached higher accuracy than if only one of them was used, which suggests their potential synergeticinteraction. In particular, when environmental variables were used in addition to ET and char fraction, the highestaccuracy for burn severity was reached (κ = 0.79). Our main conclusion is that post-fire fine resolution ETis a useful and easily understandable indicator of burn severity in Mediterranean ecosystems, in particular whenused in combination with a MESMA char fraction image. This novel approach to estimate burn severity may helpto develop successful post-fire management strategies not only in Mediterranean ecosystems but also in otherecosystems, due to ease of generalization.
PB Elsevier
YR 2020
FD 2020
LK https://uvadoc.uva.es/handle/10324/67787
UL https://uvadoc.uva.es/handle/10324/67787
LA spa
NO Remote Sensing of Environment, Julio 2020, 244, 111815.
DS UVaDOC
RD 24-nov-2024