Loading...
Loading...
Contributors:
Dataset URI:
10.5281/zenodo.23105501This repository provides the reproducibility package accompanying the manuscript “Cross-fire transferability of four-year NBR-based spectral recovery after the 2021 wildfires in southwestern Türkiye”. The package contains the analysis-ready modelling sample, Google Earth Engine and Python analysis scripts, locked out-of-fold model predictions, model-selection records, sensitivity-analysis outputs, uncertainty and calibration results, derived tables and figures, random seeds, data dictionaries, provenance information, and supporting quality-control documentation. The study evaluates the transferability of four-year NBR-based spectral recovery across five 2021 wildfire complexes in southwestern Türkiye using outer leave-one-fire-out validation and spatially blocked inner cross-validation. The repository supports reproduction and auditing of the reported analyses. Source Sentinel-2, CORINE Land Cover, EFFIS, MODIS MCD64A1, and other third-party datasets remain subject to their original providers’ terms and licences. Spectral recovery reported in this study should not be interpreted as complete biomass, ecosystem, or restoration recovery. Version 1.1.0 adds two reviewer-motivated robustness analyses: direct prediction of NBR in 2025 to reduce dependence on the recovery-ratio formulation, and event-grouped inner cross-validation using leave-one-training-fire-out model selection.
Keyword(s):
forest monitoring; leave-one-fire-out validation; machine learning; NBR; remote sensing.
MeSH Term(s):
Grants and Funding:
No Grants or Funding Data Available
Associated Publication(s):
No Associated Publication Data Available
Supplementary Data:
No Supplementary Data Available
Related Dataset(s):
No Related Dataset Data Available
The National Library of Medicine (NLM) provides information about biomedical datasets. Inclusion on an NLM Web page does not imply endorsement of, or agreement with, the contents by NLM or the National Institutes of Health. Learn more: NLM Web Policies (nih.gov)