Generative AI Against Poaching: Latent Composite Flow Matching for Poaching Prediction
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (47) · 40279-40286
DOI: 10.1609/aaai.v40i47.41466 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Lingkai Kong und 5 weiteren Autor:innen.
Abstract (Originalsprache)
Poaching poses significant threats to biodiversity. A valuable step in reducing poaching is to forecast poacher behavior, which can inform patrol deployment and other conservation interventions. Existing poaching prediction methods based on linear models or decision trees lack the expressivity to capture complex, nonlinear spatiotemporal patterns. Recent advances in generative modeling, particularly flow matching, offer a more flexible alternative. However, training such models on real-world poaching data faces two central obstacles: imperfect detection of poaching events and limited data. To address imperfect detection, we integrate flow matching with an occupancy-based detection model and train the flow in latent space to infer the underlying occupancy state. To mitigate data scarcity, we adopt a composite flow initialized from a linear-model prediction rather than random noise which is the standard in diffusion models, injecting prior knowledge and improving generalization. Evaluations on datasets from two national parks in Uganda show consistent gains in predictive accuracy.
Zitieren
APA
Kong, L., Wang, H., Emogor, C. A., Böersch-Supan, V., Xu, L., & Tambe, M. (2026). Generative AI Against Poaching: Latent Composite Flow Matching for Poaching Prediction. Proceedings of the AAAI Conference on Artificial Intelligence, 40(47), 40279-40286. https://doi.org/10.1609/aaai.v40i47.41466
Vancouver
Kong L, Wang H, Emogor CA, Böersch-Supan V, Xu L, Tambe M. Generative AI Against Poaching: Latent Composite Flow Matching for Poaching Prediction. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(47):40279-40286. doi:10.1609/aaai.v40i47.41466
BibTeX
@article{Kong2026,
author = {Kong, Lingkai and Wang, Haichuan and Emogor, Charles A. and Böersch-Supan, Vincent and Xu, Lily and Tambe, Milind},
title = {Generative AI Against Poaching: Latent Composite Flow Matching for Poaching Prediction},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {47},
pages = {40279--40286},
doi = {10.1609/aaai.v40i47.41466}
}
EUVIMED