Two years ago, a post by James Özden and Neil Dullaghan in this forum, on Megaprojects for Animals, highlighted the significant gap in the evidence base to inform effective strategies for animal welfare. They estimated a growth rate of research to inform the animal welfare evidence base lower than 1% of the growth rate seen in global health. 

We argue that leveraging AI offers a promising solution to address this gap. Drawing inspiration from the success of AlphaFold in rapidly advancing the field of molecular biology, AI may similarly transform the mapping and quantification of animal suffering, helping convert existing scientific knowledge into structured, decision-relevant evidence. The Welfare Footprint Framework (WFF) is particularly well-suited to take advantage of this opportunity, as it provides a systematic way to translate diverse sources of evidence into estimates of animal welfare.

To illustrate what may already be possible, we introduce the Hedonic-Track AI Tool, which supports the structured description and quantification of negative and positive affective experiences in animals. This tool offers a starting point for generating welfare estimates in a consistent and transparent way.

Building on this foundation, we initially introduced the Pain Atlas Project as a way to systematically map sources of suffering across species.

As this work has evolved, we now see it as part of a broader objective: the development of a Welfare Footprint Atlas, a system capable of generating structured, comparable, and inspectable estimates of animal welfare across products, production systems, and species.

The key shift is not simply the use of AI, but the ability to produce first-pass, comparable estimates at scale, making it possible to identify where suffering is concentrated and where interventions may have the greatest impact.

Rather than being defined by a small number of components, this effort aims to combine:

• systematic identification of welfare-relevant conditions
• quantification of their impact using structured metrics
• translation of results into comparable outputs across systems and species

The objective is to move from fragmented and non-comparable evidence toward a situation where welfare impacts can be compared, prioritized, and improved in a more systematic way.

If successful, this approach could significantly expand the evidence base available for animal welfare prioritization — enabling faster and more systematic identification of high-impact interventions, while keeping assumptions explicit and open to revision.

For those interested, our blog post about the Welfare Footprint Atlas Project can be found here.