Caution is needed across Mediterranean ecosystems when interpreting wall-to-wall fire severity estimates based on spectral indices

• Published in: Forest ecology and management 2023-10, Vol.546, p.121383, Article 121383
• Main Authors: Fernández-Guisuraga, José Manuel, Fernandes, Paulo M., Marcos, Elena, Beltrán-Marcos, David, Sarricolea, Pablo, Farris, Massimiliano, Calvo, Leonor
• Format: Article
• Language: English
• Subjects: Broadleaf forest; Composite burn index; Conifer forest; dNBR; RdNBR; Spectral variability
• ISSN: 0378-1127; 1872-7042
• DOI: 10.1016/j.foreco.2023.121383

•Fire effects are strongly decoupled among strata in Mediterranean ecosystems.•Aggregated field severity metrics obscures ecologically relevant fire impacts.•Most CBI attributes are redundant in shaping the signal variation of spectral indices.•Fire impact on upper-strata photosynthetic material mainly drives spectral behavior.•Caution is needed when interpreting severity maps produced from aggregated metrics. The use of comprehensive, multi-strata fire severity metrics measured in the field, such as the composite burn index (CBI), is the most commonly used approach to calibrate remote sensing-based products and obtain wall-to-wall fire severity estimates. However, the extent to which specific ecological changes as measured by individual CBI attributes per stratum actually drive the spectral variability in Mediterranean fire-prone ecosystems has not been deciphered yet. In addition, it is not clear if these relationships are consistent across different Mediterranean ecosystems, particularly when fire effects across strata can be decoupled. To bridge these knowledge gaps, we examined the fire severity divergence among CBI strata in different types of Mediterranean forest (both conifer- and broadleaf-dominated) and shrubland ecosystems with 240 plots distributed across five wildfires in the westernmost part of the Mediterranean Basin and Chile. Then, we compared the relationship of two spectral fire severity indices with the CBI scores by strata. Finally, we used a wrapper algorithm (VSURF) around Random Forest regression to assess the potential contribution and redundancy of individual CBI attributes in shaping the spectral response of fire severity indices computed from multispectral Sentinel-2 data. The Relativized Burn Ratio (RBR) index fitted CBI field data better than the differenced Normalized Burn Ratio (dNBR). Fire effects were strongly decoupled and, for example, the substrate stratum experienced the lowest severity in conifer forests and shrublands, whereas the upper strata remained largely unaffected in broadleaf forests. This has substantial implications since we found differential responses of the RBR signal to fire effects by strata as measured by distinct individual CBI attributes. Specifically, the fire impact on the green vegetation fraction of upper strata in broadleaf and conifer forests, and on the substrate stratum in shrublands, were identified as non-redundant and most contributing fire effects shaping the spectral signal variability