Poaching Hotspot Identification Using Satellite Imagery

Abstract: Elephant Poaching in African countries has been a decade-old problem. So much so that African Forest Elephants are now listed as an endangered species, and African Savannah Elephants as critically endangered by the IUCN (International Union for Conservation of Nature). [1] Elephants are hunted primarily for their ivory tusks which caused many elephants to be born tuskless as a genetic modification for survival. [2] Data gathered by recent studies shows that though poaching methods remain the same, the poaching grounds are rather dynamic. Poachers have shifted to areas with less ranger patrols and several other factors like watering holes, seasons, altitude etc. cause constant shifts in poaching hotspot locations. [3] After a period of low poaching from 2000-2014, poaching numbers in African countries are now on the rise again -- WWF (World Wildlife Foundation) says there are 20,000 elephants poached annually [4]. In African countries, anti-poaching efforts are concentrated near towns, while a majority of poaching occurs in the deserted regions. All of these factors result in the need for a Computer Vision Model to identify poaching hotspots through locating the geographic indicators of favorable poaching regions. A CV model eliminates the need to manually track poachers and account for the environmental factors to deploy resources and its combination with satellite imagery allows us to survey large areas without disturbing local species or cross border aviation restrictions.