Sustainability AI
Arxiv
Sustainability AI
Watershed’s approach to AI
Watershed takes a sustainability-centered approach to deploying artificial intelligence. Our climate and data scientists work side-by-side with engineers to embed sustainability data into AI models. You control your data and can use primary data to refine the model results, giving you the most granular and actionable results at an otherwise impossible speed.
Introducing AI-accelerated Product Footprints
Learn more
AI is only as good as the underlying data and the expert review that trains the system. Watershed’s science team has decades of experience on peer-reviewed data projects – including foundational work in the LCA field and open-data initiatives. We have published public evaluation data-sets for AI systems. Questions to evaluate Sustainability AI:
- What is the underlying data and how is it updated over time?
- What evaluation data sets are used? Are they peer-reviewed?
- How are sustainability experts involved in system development and validation?
- When using AI for Scope 3, how do you ensure consistency across materials and industries?
Watershed research
NEURips / Climate Change AI
ATLAS: A spend classification benchmark for estimating scope 3 carbon emissions
NeurIPS / Climate Change AI
An LLM-based approach to creating a carbon emissions reduction levers library at scale
AI product advisory groups
In developing AI for sustainability, we work closely with leading companies across a range of industries to better shape and test the direction of our AI features. By spending time with these companies, and understanding their use cases, we refine and better architect the AI for greater sustainability progress.
Decompose your supply chain for smarter procurement decisions
From fabrics to circuit boards to heavy machinery, Watershed’s AI model deconstructs every material and product into the components and processes that comprise them, measuring the emissions at each step.
- Build PCFs for your supply chain in a single click.
- Tie your product footprints back to your corporate footprint and report on overall progress.
Simulate the impact of potential decarbonization levers
Use AI to simulate how different product or procurement decisions would influence your overall product footprint.
- Easily override outputs with primary data.
- Compare suppliers, materials and other potential shifts.
- Compare versions to understand how changes trickle down the supply chain.
Accelerate reporting
Get AI-assisted first drafts of California SB 261 and other reports with AI. AI assisted drafts are informed by your company’s published reports, data from company peers, and other relevant information. Get a clear view into the AI decisions and assign reviewers and approvers to finalize the report.
In our use of AI, we optimize for performance and efficiency and regularly evaluate the field of technology options. We use various machine learning and generative AI techniques, from classical statistical methods like regression to recent models like LLMs, including Anthropic, OpenAI, and Google Gemini.