Stay Ahead of Poachers: Illegal Wildlife Poaching Prediction and Patrol Planning Under Uncertainty with Field Test Evaluations (Short Version)

  title={Stay Ahead of Poachers: Illegal Wildlife Poaching Prediction and Patrol Planning Under Uncertainty with Field Test Evaluations (Short Version)},
  author={Shahrzad Gholami and Lily Xu and Sara Mc Carthy and Bistra N. Dilkina and Andrew J. Plumptre and Milind Tambe and Rohit Singh and Mustapha Nsubaga and Joshua Mabonga and Margaret Driciru and Fredrick O. Wanyama and Aggrey Rwetsiba and Tom Okello and Eric Enyel},
  journal={2020 IEEE 36th International Conference on Data Engineering (ICDE)},
Illegal wildlife poaching threatens ecosystems and drives endangered species toward extinction. However, efforts for wildlife protection are constrained by the limited resources of law enforcement agencies. To help combat poaching, the Protection Assistant for Wildlife Security (PAWS) is a machine learning pipeline that has been developed as a data-driven approach to identify areas at high risk of poaching throughout protected areas and compute optimal patrol routes. In this paper, we take an… 
Enhancing Poaching Predictions for Under-Resourced Wildlife Conservation Parks Using Remote Sensing Imagery
This work automates the entire data-to-deployment pipeline and finds that the inclusion of satellite imagery creates a robust system through which parks of any resource level can benefit from poaching risks for years to come.
Data-Driven Multimodal Patrol Planning for Anti-poaching
This paper first uses machine learning models to predict the poaching threats and then uses a novel mixed-integer linear programming-based algorithm to plan the patrol route, which can improve the efficiency of patrol and thus they can serve as the basis for future deployment in the field.
Learning, Optimization, and Planning Under Uncertainty for Wildlife Conservation
Wildlife poaching fuels the multi-billion dollar illegal wildlife trade and pushes countless species to the brink of extinction. To aid rangers in preventing poaching in protected areas around the
Dual-Mandate Patrols: Multi-Armed Bandits for Green Security
The algorithm, LIZARD, improves performance on real-world poaching data from Cambodia and shows a synergy between Lipschitz-continuity and decomposition as each aids the convergence of the other.
Dual-Mandate Patrols: Bandit-Based Learning in Green Security Domains
The problem is formulated as a multi-armed bandit with Lipschitz continuity to exploit smoothness, where each arm represents a patrol strategy, and a no-regret approach for arm selection that uses an integer program to exploit decomposability is presented.
Learning and Planning Under Uncertainty for Green Security
This research develops novel techniques in machine learning and game theory to enable the effective development and deployment of AI in these resource-constrained settings.
Ranked Prioritization of Groups in Combinatorial Bandit Allocation
This work proposes a novel combinatorial bandit objective that trades off between reward maximization and also accounts for prioritization over species, which is called ranked prioritization and shows this objective can be expressed as a weighted linear sum of Lipschitz-continuous reward functions.
Driven by data: Improved protected area effectiveness in Royal Manas National Park, Bhutan
The necessity of rangers and other frontline staff for ensuring the protection and effective management of protected areas is well documented. The Spatial Monitoring and Reporting Tool (SMART) was
Learning Opportunistic Adversarial Model on Global Wildlife Trade
Global illegal wildlife trade threatens biodiversity and acts as a potential crisis of invasive species and disease spread. Despite a wide range of national and international policies and regulations
Game Theory on the Ground: The Effect of Increased Patrols on Deterring Poachers
It is shown that increased patrols in one region deter poaching in the next timestep, but poachers then move to neighboring regions, offering guidance on how adversaries should be modeled in realistic game-theoretic settings.


Adaptive resource allocation for wildlife protection against illegal poachers
The Protection Assistant for Wildlife Security (PAWS) application is introduced - a joint deployment effort done with researchers at Uganda's Queen Elizabeth National Park with the goal of improving wildlife ranger patrols, with a behavioral model extension that captures the heterogeneity of poachers' decision making processes.
CAPTURE: A New Predictive Anti-Poaching Tool for Wildlife Protection
This paper presents the largest dataset of real-world defender-adversary interactions analyzed in the security games literature, and presents a new predictive anti-poaching tool, CAPTURE, which provides significant advances over previous models from behavioral game theory and conservation biology.
Cloudy with a Chance of Poaching: Adversary Behavior Modeling and Forecasting with Real-World Poaching Data
An adversary behavior modeling system, INTERCEPT (INTERpretable Classification Ensemble to Protect Threatened species), and the most extensive evaluation in the AI literature of one of the largest poaching datasets from Queen Elizabeth National Park (QENP) in Uganda, comparing INTERCEPT with its competitors are provided.
Taking It for a Test Drive: A Hybrid Spatio-Temporal Model for Wildlife Poaching Prediction Evaluated Through a Controlled Field Test
A hybrid spatio-temporal model that predicts poaching threat levels and results from a five-month field test of this model in Uganda’s Queen Elizabeth Protected Area (QEPA) demonstrate that these predictive models can aid rangers in focusing their efforts to prevent wildlife poaching and save animals.
Deploying PAWS: Field Optimization of the Protection Assistant for Wildlife Security
This paper reports on PAWS’s significant evolution from a proposed decision aid to a regularly deployed application, reporting on the lessons from the first tests in Africa in Spring 2014, through its continued evolution since then, to current regular use in Southeast Asia and plans for future worldwide deployment.
Optimal Patrol Planning for Green Security Games with Black-Box Attackers
Motivated by the problem of protecting endangered animals, there has been a surge of interests in optimizing patrol planning for conservation area protection. Previous efforts in these domains have
Improving Law‐Enforcement Effectiveness and Efficiency in Protected Areas Using Ranger‐collected Monitoring Data
Protected areas are fundamental for conservation, yet are constantly threatened by illegal activities, such as cattle encroachment and wildlife poaching, which reduce biodiversity. Law enforcement is
From Poachers to Protectors: Engaging Local Communities in Solutions to Illegal Wildlife Trade
Combating the surge of illegal wildlife trade (IWT) devastating wildlife populations is an urgent global priority for conservation. There are increasing policy commitments to take action at the local
Spatiotemporal trends of illegal activities from ranger‐collected data in a Ugandan national park
The results show the need to explicitly model ranger patrol effort to reduce biases from existing uncorrected or capture per unit effort analyses, and overall, ecological covariates, although significant, were not useful predictors for occurrence of illegal activities.
Adversary Models Account for Imperfect Crime Data: Forecasting and Planning against Real-world Poachers
iWare-E is a predictive model integrated into Protection Assistant for Wildlife Security system (PAWS) developed at the University of Southern California, which is designed to handle the uncertainty in crime information efficiently, which leads to superior accuracy for adversary behavior prediction compared to the previous state-of-the-art.