Wildlife poaching is one of the biggest battles mankind is fighting today. You’d be stunned if you look at the number of wild animals being hunted down for illegal trade. But here’s a piece of news that provides a glimmer of hope for the animals out there. A team of computer scientists may have developed a way to curb wildlife poaching with the help of artificial intelligence (AI).
Financially backed by the National Science Foundation (NSF), a team of computer scientists from the University of Southern California (USC) has developed the “Green Security Games”. Sounds cool, right? It is. With the use of mathematical equations, the game theory “predicts the behaviour of adversaries and plans optimal approaches for containment,” says the National Science Foundation (NSF). This would allow the national reserve patrol guards and park rangers to patrol the parks and wildlife sanctuaries a lot more effectively and efficiently.
Fei Fang, a Ph.D. candidate in the computer science department at USC, and researcher of the Green Security Games project says, “In most parks, ranger patrols are poorly planned, reactive rather than pro-active, and habitual. We need to provide actual patrol routes that can be practically followed. Fang, and the professor of computer science and systems engineering at USC, Milind Tambe, have created an artificial intelligence application called Protection Assistant for Wildlife Sanctuary or PAWS. Developed back in 2013, the last few years were spent testing the functionality of the system in the natural reserves of Uganda and Malaysia. Both these countries, in particular, have been quite badly affected by the poaching menace and were in desperate need for a solution. The Uganda Wildlife Authority admitted that the “killing of elephants for ivory has shot up over the last four years.” Malaysia too has seen three of the largest ivory seizures in the last few years.
According to the scientist duo, PAWS empowers the reserve guards to be more effective with their patrolling without requiring additional manpower. By creating patrol routes for the guards, keeping a check has become a lot more efficient. Along with this, the app also randomises routes to make them unpredictable.
We list all possible patrol routes and then determine which is the most effective, says Fang. For generally, when the poachers notice the patrols going to an area more often than others, they lay their snares elsewhere.
PAWS is quite intuitive that way, as it learns from the user experience, nkgering routes based on past successful efforts if need be. The system also incorporates the routes that experience the most animal traffic, where poachers are more likely to come, and modifies itself accordingly.
Interestingly, this isn’t the first time tech has been involved in catching poachers. The American wildlife law enforcement had also adopted a number of robotic animals to catch poachers red-handed, earlier this year. A number of engineers and conservationists have also been collaborating to develop a conservation drone that could monitor illegal activities from above and send signals to patrol parties. Fang and Tambe admitted that there were some shortcomings of the technology, but say PAWS has already been tried, tested and experienced success in a couple of the world’s most badly affected areas.
Talking to the NSF, Tambe said, This research is a step in demonstrating that AI can have a really significant positive impact on society, and allow us to assist humanity in solving some of the major challenges we face.
Scientists at USC are also exploring how artificial intelligence could help in curbing other environmental conflicts. Meanwhile, we could not be more excited about this.