For all marine mammal science folks from the AI haters to the AI curious and AI practitioners —
We are pleased to share this new paper, as part of the MMS special issue stemming from the Perth 2024 workshop "Machine Learning and Artificial Intelligence in Marine Mammal Research" Be the Captain, Not the Crew: Effective Development and Deployment of Artificial Intelligence in Marine Mammal Science Ted Cheeseman, Brian Miller, Shyam Madhusudhana, Amanda Hodgson ABSTRACT: Machine learning (ML), particularly the availability of deep neural networks, has enabled the proliferation of modern artificial intelligence (AI) and has revolutionized data processing capacity in marine mammal science. The development and application of these systems has delivered 1000-fold increases in throughput for applications such as photo identification and orders of magnitude increases in performance for passive acoustic detection of calls. Some AI systems now exceed the performance of human experts. As marine environments face unprecedented and compounding pressures from climate change, habitat degradation, and anthropogenic disturbance, these technological advances offer powerful promise. However, the success of AI applications depends less on algorithm sophistication than on the underlying information systems that enable their functionality. Here, we argue that marine mammal scientists must approach AI development with intentional agency—as captains rather than crew— emphasizing system-level design, interpretability, human oversight, and collaborative frameworks. We examine the spectrum of AI capabilities today, from pattern recognition where ML excels to context judgments and value judgments which must remain defined and decided by humans. By designing AI systems that center domain expertise, prioritize accessibility, and facilitate community engagement, the marine mammal science community can harness computational power while maintaining scientific rigor and advancing equitable conservation outcomes. A free viewable (but not printable) version of the manuscript is available here: https://onlinelibrary.wiley.com/doi/full/10.1111/mms.70238 …and I am happy to share a PDF if you so desire. And if you like this, consider joining us in October in Puerto Rico for our full day workshop - Evolving AI Applications in Marine Mammal Science: From Computer Vision to Generative and Agentic AI - https://www.smmconference.org/workshops/#1776734911653-b9b75573-bd9e Yay whales! Ted — Dr. Ted Cheeseman Director, Happywhale // Research Fellow, University of California Santa Cruz [email protected] // www.Happywhale.com Support ocean conservation science! https://donorbox.org/donate-to-the-whales-of-guerrero-and-happy-whale Happywhale on NPR: https://n.pr/42W0vjI and https://www.wbur.org/hereandnow/2024/07/31/ai-whale-recognition Recent publications: Bellwethers of Change: North Pacific humpback whale climate response: https://doi.org/10.1098/rsos.231462 Humpback whale automated image recognition: https://rdcu.be/cCOtw Multi-species image recognition: https://besjournals.onlinelibrary.wiley.com/doi/full/10.1111/2041-210X.14167 ** know your whales :) ** — I live and play on unceded lands of the Ohlone.
smime.p7s
Description: S/MIME cryptographic signature
_______________________________________________ MARMAM mailing list [email protected] https://lists.uvic.ca/mailman/listinfo/marmam
