Demarcating High-Risk Zones of Human-Elephant Conflict in Sri Lanka Utilizing GIS and a Satellite Data Fusion Approach

Demarcating High-Risk Zones of Human-Elephant Conflict in Sri Lanka Utilizing GIS and a Satellite Data Fusion Approach

The escalating human-elephant conflict (HEC) in countries like Sri Lanka demands urgent attention due to several factors: rapid population growth, agricultural expansion, infrastructure development, and climate change impacts. From 2010 to 2022, human and elephant deaths have doubled, resulting in 1,208 human and 3,771 elephant fatalities. Globally, Sri Lanka ranked second in annual human deaths and had the highest per capita death rate from HEC between 2006 and 2021. This study aims to identify high-risk HEC zones through a comprehensive analysis to monitor changes in greenery utilising satellite remote sensing and GIS techniques. The study analysed multi-seasonal land cover and land use (LCLU) changes utilising Sentinel-2 satellite data. These were correlated with recorded HEC incidents to identify potential high-risk zones. The study relied on random forest (RF), support vector machine (SVM), and object-based image analysis methods for LCLU classification, conducted in two forest-dominated regions of southeast Sri Lanka from 2021 to 2022. According to the findings, the RF and SVM methods have higher accuracy. The overall accuracy of the classification was 97.31 and 94.62, and kappa was 0.95 and 0.90 for RF and SVM, respectively. Therefore, these two methods were selected for analysis in this study. Monthly greenery changes were further quantified using normalised difference vegetation index (NDVI) analysis and NDVI values derived from moderate-resolution imaging spectrometer data, identifying suitable regions where elephants forage frequently. Furthermore, using kernel density estimation, the study identified high-density areas for reported incidents of human and elephant deaths. This process involved assigning weight to conflict incidents within a 5 km radius, considering the proximity to the forest, and evaluating greenery changes using NDVI values. This revealed varying levels of HEC risk, ranging from very high to low. The LCLU map, created using the RF classifier, indicates that all identified hotspots for very high and high HEC risks are closely aligned with forest boundaries. The findings support HEC mitigation strategies through community awareness, HEC hotspots mapping and restoration practices to ensure a sustainable human-elephant coexistence. This method will help policymakers in wildlife conservation to identify high-risk HEC zones and support HEC mitigation. In conclusion, this study highlights the potential of integrating remote sensing and GIS techniques in demarcating HEC hotspots in Sri Lanka to support conflict mitigation efforts.

File reproduced in accordance with the copyright policy of the publisher/author/creator.