WaterCopilot: an AI-driven virtual assistant for water management

Sustainable water resource management in transboundary river basins is challenged by fragmented data, limited realtime access, and the complexity of integrating diverse information sources. This paper presents WaterCopilot—an AI-driven virtual assistant developed through collaboration between the In...

Descripción completa

Detalles Bibliográficos
Autores principales: Vickneswaran, Keerththanan, Garcia Andarcia, Mariangel, Retief, H., Dickens, Chris, Silva, Paulo
Formato: Preprint
Lenguaje:Inglés
Publicado: 2026
Materias:
Acceso en línea:https://hdl.handle.net/10568/180263
_version_ 1855521340821340160
author Vickneswaran, Keerththanan
Garcia Andarcia, Mariangel
Retief, H.
Dickens, Chris
Silva, Paulo
author_browse Dickens, Chris
Garcia Andarcia, Mariangel
Retief, H.
Silva, Paulo
Vickneswaran, Keerththanan
author_facet Vickneswaran, Keerththanan
Garcia Andarcia, Mariangel
Retief, H.
Dickens, Chris
Silva, Paulo
author_sort Vickneswaran, Keerththanan
collection Repository of Agricultural Research Outputs (CGSpace)
description Sustainable water resource management in transboundary river basins is challenged by fragmented data, limited realtime access, and the complexity of integrating diverse information sources. This paper presents WaterCopilot—an AI-driven virtual assistant developed through collaboration between the International Water Management Institute (IWMI) and Microsoft Research for the Limpopo River Basin (LRB) to bridge these gaps through a unified, interactive platform. Built on Retrieval-Augmented Generation (RAG) and tool-calling architectures, WaterCopilot integrates static policy documents and real-time hydrological data via two custom plugins: the iwmi-doc-plugin, which enables semantic search over indexed documents using Azure AI Search, and the iwmi-api-plugin, which queries live databases to deliver dynamic insights such as environmental-flow alerts, rainfall trends, reservoir levels, water accounting, and irrigation data. The system features guided multilingual interactions (English, Portuguese, French), transparent source referencing, automated calculations, and visualization capabilities. Evaluated using the RAGAS framework, WaterCopilot achieves an overall score of 0.8043, with high answer relevancy (0.8571) and context precision (0.8009). Key innovations include automated threshold-based alerts, integration with the LRB Digital Twin, and a scalable deployment pipeline hosted on AWS. While limitations in processing non-English technical documents and API latency remain, WaterCopilot establishes a replicable AI-augmented framework for enhancing water governance in data-scarce, transboundary contexts. The study demonstrates the potential of this AI assistant to support informed, timely decisionmaking and strengthen water security in complex river basins.
format Preprint
id CGSpace180263
institution CGIAR Consortium
language Inglés
publishDate 2026
publishDateRange 2026
publishDateSort 2026
record_format dspace
spelling CGSpace1802632026-01-21T04:29:28Z WaterCopilot: an AI-driven virtual assistant for water management Vickneswaran, Keerththanan Garcia Andarcia, Mariangel Retief, H. Dickens, Chris Silva, Paulo artificial intelligence water management digital twins natural language processing large language models river basins Sustainable water resource management in transboundary river basins is challenged by fragmented data, limited realtime access, and the complexity of integrating diverse information sources. This paper presents WaterCopilot—an AI-driven virtual assistant developed through collaboration between the International Water Management Institute (IWMI) and Microsoft Research for the Limpopo River Basin (LRB) to bridge these gaps through a unified, interactive platform. Built on Retrieval-Augmented Generation (RAG) and tool-calling architectures, WaterCopilot integrates static policy documents and real-time hydrological data via two custom plugins: the iwmi-doc-plugin, which enables semantic search over indexed documents using Azure AI Search, and the iwmi-api-plugin, which queries live databases to deliver dynamic insights such as environmental-flow alerts, rainfall trends, reservoir levels, water accounting, and irrigation data. The system features guided multilingual interactions (English, Portuguese, French), transparent source referencing, automated calculations, and visualization capabilities. Evaluated using the RAGAS framework, WaterCopilot achieves an overall score of 0.8043, with high answer relevancy (0.8571) and context precision (0.8009). Key innovations include automated threshold-based alerts, integration with the LRB Digital Twin, and a scalable deployment pipeline hosted on AWS. While limitations in processing non-English technical documents and API latency remain, WaterCopilot establishes a replicable AI-augmented framework for enhancing water governance in data-scarce, transboundary contexts. The study demonstrates the potential of this AI assistant to support informed, timely decisionmaking and strengthen water security in complex river basins. 2026-01-13 2026-01-21T03:31:55Z 2026-01-21T03:31:55Z Preprint https://hdl.handle.net/10568/180263 en Open Access Vickneswaran, K.; Garcia Andarcia, M.; Retief, H.; Dickens, C.; Silva, P. 2026. WaterCopilot: an AI-driven virtual assistant for water management. arXiv, 15p. doi: https://doi.org/10.48550/arXiv.2601.08559
spellingShingle artificial intelligence
water management
digital twins
natural language processing
large language models
river basins
Vickneswaran, Keerththanan
Garcia Andarcia, Mariangel
Retief, H.
Dickens, Chris
Silva, Paulo
WaterCopilot: an AI-driven virtual assistant for water management
title WaterCopilot: an AI-driven virtual assistant for water management
title_full WaterCopilot: an AI-driven virtual assistant for water management
title_fullStr WaterCopilot: an AI-driven virtual assistant for water management
title_full_unstemmed WaterCopilot: an AI-driven virtual assistant for water management
title_short WaterCopilot: an AI-driven virtual assistant for water management
title_sort watercopilot an ai driven virtual assistant for water management
topic artificial intelligence
water management
digital twins
natural language processing
large language models
river basins
url https://hdl.handle.net/10568/180263
work_keys_str_mv AT vickneswarankeerththanan watercopilotanaidrivenvirtualassistantforwatermanagement
AT garciaandarciamariangel watercopilotanaidrivenvirtualassistantforwatermanagement
AT retiefh watercopilotanaidrivenvirtualassistantforwatermanagement
AT dickenschris watercopilotanaidrivenvirtualassistantforwatermanagement
AT silvapaulo watercopilotanaidrivenvirtualassistantforwatermanagement