Monthly Burned-Area Mapping using Multi-Sensor Integration of Sentinel-1 and Sentinel-2 and machine learning: Case Study of 2019's fire events in South Sumatra Province, Indonesia

Abstract

Indonesia has experienced massive historical land and forest fire events, creating transnational environmental and socioeconomic issues. The extent of burned areas (BAs) is one of many indicators that reflect the magnitudes and impacts from fire events, and such information is also used for planning the response and recovery steps after the fire events. This information is usually derived using remote sensing (RS) data. However, the assessment on the performance using available RS data, possible RS data combinations, and existing methods is needed to regularly monitor the BA extent. This study aims to assess the performance from Sentinel-1 synthetic aperture radar polarization (Pol.) and gray-level of co-occurrence matrix (GLCM) textural features and the integration with Sentinel-2 spectral data (Spec.) for the monthly mapping of BA extent using machine learning algorithms, such as random forests (RFs) and extreme gradient boosting (XGB). The study took place in the parts of Ogan Komering Ilir Regency and Banyuasin in South Sumatra Province, Indonesia. This area has complex land-use classes, such as natural vegetation and plantations (pulpwood and oil palm), which were affected by the 2019's fire events. Our study demonstrated that the combination between Pol. from Sentinel-1 and spectral data from Sentinel-2 (Diff.Pol + Spec.) yielded the best classification accuracy with the overall accuracy (OA) values ranging from 91.80% (XGB) to 95.80% (RF) with the producer's accuracy (PA) from 73.33% to 97.66% and user's accuracy (UA) from 76.69% to 89.80% for the BA class. The integration of spectral data using Sentinel-2 reduced the source of misclassification of BAs from false detection from the non-fire-related land-cover conversion, such as logging activities.