A team of computer scientists from the University of Southern California (USC) have been successful in developing a new method to alleviate wildlife poaching. The National Science Foundation (NSF) funded the project that has created a model for ‘green security games’.
This model is based on game theory to safeguard wildlife from poachers. Game theory involves predicting the actions of enemy using mathematical equations and subsequently formulating the best possible restrain moves. This model will enable more efficient patrolling of parks and wildlife by park rangers.
An artificial intelligence (AI) application, known as Protection Assistant for Wildlife Sanctuary (PAWS) was developed by Fei Fang, a Ph.D. candidate in the computer science department at USC and Milind Tambe, a professor of computer science and systems engineering at USC, in 2013. The team has since then spent a couple of years to test the effectiveness of the application in Uganda and Malaysia.
The two countries desperately require patrolling assistance since during the last four years, the number of elephants that have been killed for ivory has increased drastically, according to the Uganda Wildlife Authority. Malaysia witnessed the three biggest ivory seizures in the past few years.
Fang stated that in majority of the parks, patrols undertaken by rangers are formulated inadequately. Their approach is reactive, while it should be pro-active and habitual. Rangers will have to be provided with proper patrol routes that are feasible.
“These routes need to go back to a base camp and the patrols can’t be too long. We list all possible patrol routes and then determine which is the most effective. If the poachers observe that patrols go to some area more often than others, then the poachers place their snares elsewhere”, said Fang. Tambe, the lead researcher, and Fang also developed random routes that cannot be predicted by poachers.
