Meet WaterCopilot: AI for Smarter Water Decisions in the Limpopo Basin
Meet WaterCopilot, an AI assistant co-created by IWMI and Microsoft Research to help manage the Limpopo River Basin. It turns scattered documents and live hydrology feeds into clear, actionable answers.
- Unifies policy files, reports, and sensor data in one chat.
- Answers with transparent source links you can verify.
- Provides live insights: environmental-flow alerts, rainfall trends, reservoir levels, irrigation stats.
- Performs quick calculations and shares simple visuals.
- Chats in English, Portuguese, and French.
Under the hood, it uses Retrieval-Augmented Generation and tool-calling. Two plugins power it: iwmi-doc-plugin (semantic search over indexed documents via Azure AI Search) and iwmi-api-plugin (queries live databases).
In evaluations, WaterCopilot scored 0.8043 on the RAGAS framework, with high answer relevancy (0.8571) and context precision (0.8009).
Why it matters: faster, more inclusive decisions for water security in data-scarce, cross-border settings. Today’s limits include some non-English technical documents and occasional API latency. It also connects to the LRB Digital Twin and scales to new basins.
Paper: https://arxiv.org/abs/2601.08559v1
Register: https://www.AiFeta.com
Water AI Climate WaterSecurity Sustainability DigitalTwin RAG Hydrology Governance Africa Limpopo IWMI MicrosoftResearch
