FOREST FIRE DETECTION BASED ON GOOGLE EARTH ENGINE SEBANGAU NATIONAL PARK

Sebangau National Park, a peatland conservation area, is particularly vulnerable to forest fires. These conflagrations are most prevalent during the dry season. The objective of this research is to detect and analyze burned areas in Sebangau National Park using the Google Earth Engine (GEE) platform. The analysis will utilize Landsat 8 satellite imagery from 2015. The methods employed for detecting areas that have undergone combustion include the utilization of Normalized Burn Ratio (NBR) and Normalized Difference Vegetation Index (NDVI) indices. The analysis reveals that the burned area, as determined by the NBR index, encompasses 27,567.92 hectares. When assessed using NDVI, the burned area increases to 35,163.44 hectares. The accuracy assessment reveals that the NDVI index exhibits an Overall Accuracy (OA) value of 97.71% and Kappa Accuracy (KA) of 81.46%, which exceeds the NBR by 0.07% and 1.24%, respectively. This finding highlights the enhanced precision of NDVI in detecting vegetation changes resulting from fire events. Consequently, NDVI can serve as a crucial reference point in post-fire mitigation and rehabilitation efforts within peat conservation areas.

Abstract licence: CC BY

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.