Exploiting Real-World Data and Human Knowledge for Predicting Wildlife Poaching

Published in ACM SIGCAS Conference on Computing and Sustainable Societies (COMPASS 2018), 2018

Swaminathan Gurumurthy, Lantao Yu, Chenyan Zhang, Yongchao Jin, Weiping Li, Xiaodong Zhang, Fei Fang. ACM SIGCAS Conference on Computing and Sustainable Societies. COMPASS 2018.

[PDF]

Abstract

Poaching continues to be a significant threat to the conservation of wildlife and the whole ecosystem. Estimating and predicting where the poachers have committed or would commit crimes is essential to designing a more effective allocation of patrolling resources. The real-world data in this domain is often sparse, noisy and incomplete, consisting of a small number of positive data (poaching signs), a large number of negative data with label uncertainty, and an even larger number of unlabeled data. Fortunately, domain experts such as the rangers can provide complementary information about the poaching activity patterns. However, such kind of prior knowledge is rarely used in previous approaches.

In this paper, we contribute solutions to the predictive analysis of poaching pattern based on very limited real-world data and human knowledge. We propose to elicit quantitative information from domain experts through clustering the data points based on geographical features and asking domain experts to provide an estimation for each cluster. In addition, we propose algorithms that exploits qualitative and quantitative information provided by the domain experts’ to augment the dataset and improve the learning. In collaboration with World Wild Fund for Nature, we show that incorporating human knowledge leads to better predictions in a conservation area in Northeastern China where the charismatic species is Siberian Tiger. The results show the importance of exploiting human knowledge when learning from limited real-world data.