Artificial Intelligence is helping catch wildlife poachers

Game theory is being use to protect wildlife by predicting poacher's behavior. 

The National Science Foundation (NSF) founded an investigation team at the University of Southern California (USC) to use game theory to help the patrol system catch wildlife poachers.

As human patrols serve as forms of protection specially in national parks, this technology will help them. Poaching is one of the main causes for wildlife endangerment protection agencies have limited resources for patrolling and animals are being killed for their skin or trophy hunting among other reasons.

"Game theory is the science of strategy," says the Library of Economics and Liberty.  It uses mathematical equations and logic to determine the actions players should take to reach the best outcome in a wide array of games. It also provides a plan an optimal approaches for containment.

Scientists developed a model for "green security games" to solve poaching, illegal logging and other problems around the globe. They've had the collaboration of conservationists from the US, Singapore, Netherlands and Malaysia.

PAWS (Protection Assistant for Wildlife Security) is the AI driven application, created in 2013 and tested in Uganda and Malaysia during 2014.

It uses data from past patrols and the evidence on poaching. Then as it receives more data the system "learns" and improve its planning. So far it has led to more observations of poacher activities per kilometer.

PAWS avoids falling into predictable patrol patterns by randomizing its patrols. And to be more practical, it incorporates the topography of protected areas, making it easier for patrols to find routes.

Also, it creates poaching street maps after taking into account the transit paths of animal traffic and poaching.

"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," said Milind Tambe, the leading professor of the project in an NSF press release.

Because of its success the team won the Innovative Applications of Artificial Intelligence award in 2015. They have also combined PAWS with CAPTURE (Comprehensive Anti-Poaching Tool with Temporal and Observation Uncertainty Reasoning) which gives even more accurate results of attacking probability.

These tools will not only help find poachers but also assist in the localization of trafficked wildlife products and other high risk cargo.

With an expected deploy of the system in Uganda, the team will be presenting more results in the International Conference on Autonomous Agents and Multi-agent Systems later this month.

Similar systems have been used by the Coast Guard and the Transportation Security Administration to protect airports and waterways. Also undercover taxidermied robots have been used by  North American wildlife agencies to catch unlawful hunters for over two decades.

 LatinAmerican Post 

We use cookies to improve our website. By continuing to use this website, you are giving consent to cookies being used. More details…