Field NotesWhat we're learning about AI and the environment

Project CETI: finding structure in sperm whale clicks

⚠ Not yet claimed by the project owner or their organization. This information may not be completely accurate. Is this your project? Claim it.

Project CETI analyzed about 9,000 sperm whale click patterns, called codas, recorded off Dominica over more than a decade. The team found that whales vary the rhythm and tempo of codas, stretch them to match each other, and add extra clicks, combining these features into a large set of distinct signals.

Why it mattersKnowing how sperm whales communicate could change how people protect them, and the methods may help researchers study other species.

What they learned

Surprise

Whale codas turned out to combine features, but what they mean is still unknown

From public sources: the team expected to find a fixed set of click patterns. Instead, whales combine rhythm, tempo, small timing shifts and extra clicks into many variations that depend on the conversation. The authors stress that this shows structure, not meaning: what most codas communicate is still unknown, and they plan field work to test it.

The problem

Sperm whale communication has been recorded for decades, but researchers lacked the tools to see the structure in it.

What the AI does

Project CETI uses machine learning to study sperm whale recordings. The sources for this finding do not say which methods this particular analysis used.

Papers, data and other outputs

Sources

This entry was summarized in our own words from these public sources.

Contact the team

We forward your message. We never show anyone's email address.