No abstract

When wildfires are controlled, they are integral to the existence of savannah ecosystems and play an intrinsic role in maintaining their structure and function. Ample studies on wildfire detection and severity mapping are available but what remains a challenge is the accurate mapping of burnt areas in heterogenous landscapes. In this study, we tested which spectral bands contributed most to burnt area detection when using Sentinel-2 and Landsat 8 multispectral sensors in two study sites. Post-fire Sentinel 2A and Landsat 8 images were classified using the Random Forest (RF) classifier. We found out that, the NIR, Red, Red-edge and Blue spectral bands contributed most to burned area detection when using Landsat 8 and Sentinel 2A. We found out that, Landsat 8 had a higher classification accuracy (OA = 0.92, Kappa = 0.85 and TSS = 0.84)) in study site 1 as compared to Sentinel-2 (OA = 0.86, Kappa = 0.74 and TSS = 0.76). In study site 2, Sentinel-2 had a slightly higher classification accuracy (OA = 0.89, Kappa = 0.67 and TSS = 0.64) which was comparable to that of Landsat 8 (OA = 0.85, Kappa = 0.50 and TSS = 0.41). Our study adds rudimentary knowledge on the most reliable sensor allowing reliable estimation of burnt areas and improved post-fire ecological evaluations on ecosystem damage and carbon emission.

This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Accurate land use and cover data are essential for effective land-use planning, hydrological modeling, and policy development. Since the Okavango Delta is a transboundary Ramsar site, managing natural resources within the Okavango Basin is undoubtedly a complex issue. It is often difficult to accurately map land use and cover using remote sensing in heterogeneous landscapes. This study investigates the combined value of climate-based regionalization and integration of spectral bands with spectral indices to enhance the accuracy of multi-temporal land use/cover classification using deep learning and machine learning approaches. Two experiments were set up, the first entailing the integration of spectral bands with spectral indices and the second involving the combined integration of spectral indices and climate-based regionalization based on Koppen–Geiger climate zones. Landsat 5 TM and Landsat 8 OLI images, machine learning classifiers (random forest and extreme gradient boosting), and deep learning (neural network and deep neural network) classifiers were used in this study. Supervised classification using a total of 5140 samples was conducted for the years 1996, 2004, 2013, and 2020. Average overall accuracy and Kappa coefficients were used to validate the results. The study found that the integration of spectral bands with indices improves the accuracy of land use/cover classification using machine learning and deep learning. Post-feature selection combinations yield higher accuracies in comparison to combinations of bands and indices. A combined integration of spectral indices with bands and climate-based regionalization did not significantly improve the accuracy of land use/cover classification consistently for all the classifiers (p < 0.05). However, post-feature selection combinations and climate-based regionalization significantly improved the accuracy for all classifiers investigated in this study. Findings of this study will improve the reliability of land use/cover monitoring in complex heterogeneous TDBs.