Seeing biodiversity: perspectives in machine learning for wildlife conservation

Abstract

Data acquisition in animal ecology is rapidly accelerating due to inexpensive and accessible sensors such as smartphones, drones, satellites, audio recorders and bio-logging devices. These new technologies and the data they generate hold great potential for large-scale environmental monitoring and understanding, but are limited by current data processing approaches which are inefficient in how they ingest, digest, and distill data into relevant information. We argue that machine learning, and especially deep learning approaches, can meet this analytic challenge to enhance our understanding, monitoring capacity, and conservation of wildlife species. Incorporating machine learning into ecological workflows could improve inputs for population and behavior models and eventually lead to integrated hybrid modeling tools, with ecological models acting as constraints for machine learning models and the latter providing data-supported insights. In essence, by combining new machine learning approaches with ecological domain knowledge, animal ecologists can capitalize on the abundance of data generated by modern sensor technologies in order to reliably estimate population abundances, study animal behavior and mitigate human/wildlife conflicts. To succeed, this approach will require close collaboration and cross-disciplinary education between the computer science and animal ecology communities in order to ensure the quality of machine learning approaches and train a new generation of data scientists in ecology and conservation.

References in corpus (7)

• Deep learning in remote sensing: a review
• Deep Learning for Classification of Hyperspectral Data: A Comparative Review
• Detecting animals in African Savanna with UAVs and the crowds
• Efficient Pipeline for Camera Trap Image Review
• Perspectives on individual animal identification from biology and computer vision
• AcinoSet: A 3D Pose Estimation Dataset and Baseline Models for Cheetahs in the Wild
• Wildbook: Crowdsourcing, computer vision, and data science for conservation

Cited by in corpus (22)

• Machine Learning and Deep Learning -- A review for Ecologists
• SuperAnimal pretrained pose estimation models for behavioral analysis
• Novel community data in ecology -- properties and prospects
• The Impact of Imperfect XAI on Human-AI Decision-Making
• Automated wildlife image classification: An active learning tool for ecological applications
• Ensembles of Vision Transformers as a New Paradigm for Automated Classification in Ecology
• Elephants and Algorithms: A Review of the Current and Future Role of AI in Elephant Monitoring
• Conservation Tools: The Next Generation of Engineering--Biology Collaborations
• On the selection and effectiveness of pseudo-absences for species distribution modeling with deep learning
• Effects of shady environments on fish collective behavior
• Holstein-Friesian Re-Identification using Multiple Cameras and Self-Supervision on a Working Farm
• A benchmark for computational analysis of animal behavior, using animal-borne tags
• Designing Ocean Vision AI: An Investigation of Community Needs for Imaging-based Ocean Conservation
• A Power Management and Control System for Portable Ecosystem Monitoring Devices
• Characterizing and Modeling AI-Driven Animal Ecology Studies at the Edge
• A Bird Song Detector for improving bird identification through Deep Learning: a case study from Doñana
• Fourier-based Action Recognition for Wildlife Behavior Quantification with Event Cameras
• A Cost-Effective LLM-based Approach to Identify Wildlife Trafficking in Online Marketplaces
• Find Rhinos without Finding Rhinos: Active Learning with Multimodal Imagery of South African Rhino Habitats
• A drone-based framework for coral habitat mapping via weakly supervised segmentation
• Resource efficient data transmission on animals based on machine learning
• Advancing multivariate time series similarity assessment: an integrated computational approach