Perspectives in machine learning for wildlife conservation

Margaret C. Crofoot,Mackenzie W. Mathis,Tilo Burghardt,Silvia Zuffi,Holger Klinck,Benjamin Risse,Blair R. Costelloe,Grant van Horn,Alexander Mathis,Charles V. Stewart,Sara Beery,Martin Wikelski,Frank van Langevelde,Benjamin Kellenberger,Iain D. Couzin,Roland Kays,Tanya Berger-Wolf,Devis Tuia

doi:10.1038/s41467-022-27980-y

Abstract

Inexpensive and accessible sensors are accelerating data acquisition in animal ecology. These technologies hold great potential for large-scale ecological understanding, but are limited by current processing approaches which inefficiently distill data into relevant information. We argue that animal ecologists can capitalize on large datasets generated by modern sensors by combining machine learning approaches with domain knowledge. Incorporating machine learning into ecological workflows could improve inputs for ecological models and lead to integrated hybrid modeling tools. This approach will require close interdisciplinary collaboration to ensure the quality of novel approaches and train a new generation of data scientists in ecology and conservation.

Highlights

Inexpensive and accessible sensors are accelerating data acquisition in animal ecology
What can we focus on now? State-of-the-art Machine and deep learning (ML) models are being applied to many tasks in animal ecology and wildlife conservation
We describe the advances in research at the interface of ML, animal ecology, and wildlife conservation

Summary

Perspectives in machine learning for wildlife conservation

Devis Tuia 1,17 ✉, Benjamin Kellenberger[1,17], Sara Beery[2,17], Blair R. We urgently need tools for rapid assessment of wildlife diversity and population dynamics at large scale and high spatiotemporal resolution, from individual animals to global densities In this Perspective, we aim to build bridges across ecology and machine learning to highlight how relevant advances in technology can be leveraged to rise to this urgent challenge in animal conservation. The physical and cognitive limitations of humans unavoidably constrain the number of individual animals that can be observed simultaneously, the temporal resolution and complexity of data that can be collected, and the extent of physical area that can be effectively monitored[10,11] These limitations considerably hamper our understanding of geographic ranges, population densities, and community diversity globally, as well as our ability to assess the consequences of their decline. Tasks: Pose estimation and behavioral analysis Free and open-source pose estimation toolbox based on deep learning

URL URL GitHub GitHub

Classification detection identification

Conclusions

Findings

Additional information