A new project is exploring the power of Generative Artificial Intelligence (GenAI) technology to support smallholder farmers in India and Kenya and enhance their overall agricultural productivity and sustainability.

The project, funded by the Bill & Melinda Gates Foundation, aims to localize digital advisory messages and increase the accessibility of such messages to reduce the digital divide compared to traditional, non-AI communication methods.

Using natural language processing (NLP) and large language models (LLMs) offers new potential to disseminate complex scientific information more widely, in local dialects and through various formats, transforming accessibility.

The project aims to localize digital advisory messages and increase the accessibility of such messages to reduce the digital divide compared to traditional, non-AI communication methods (Credit: CABI).

CABI’s highly curated and expert-validated resources

This project will explore the potential to deliver advisories based on CABI’s highly curated and expert-validated resources to plant doctors and other agriculture advisors via Generative AI chatbot technology, and the data governance and licensing necessary to ensure the quality of such advisories.

Will Holland, Product Manager at CABI, said access to reliable, effective agricultural advice is challenging for many farmers in low- and middle-income countries where face-to-face extension services have limited capacity and reach, leaving farmers with little support.

Mr Holland said, ″Many digital tools exist to try to combat this problem by delivering advice via mobile devices, but these can be challenging to access due to the digital divide – access to digital devices, language and digital illiteracy can cause barriers.

″GenAI has the potential to bridge the gap through more streamlined and accessible access to the vast amount of information and tools that are often siloed and difficult to access.

″However, there are significant unknowns and risks related to exclusion, bias, transparency, and potential misuse of AI. More investigation, evaluation and testing are required to understand these implications.″

GenAI use cases in agricultural advisory

The project, which includes partners such as the International Food Policy Research Institute (IFPRI) and the MS Swaminathan Research Foundation, will explore GenAI use cases in agricultural advisory.

CABI’s role will be to investigate how the use of our comprehensive range of crop health content and products, such as the PlantwisePlus Knowledge Bank, can be integrated into GenAI chatbots, both through investigations via our networks of plant doctors and agricultural advisors, and partnerships with other organizations within the project team.

CABI will explore the governance and licencing arrangements needed to prevent misuse of AI and put in place measures to ensure transparency in message outputs, enabling users to verify the quality of advice.

Priority information needs for a GenAI-powered agricultural advisory tool

Mr Holland added, ″The overarching goal of this project, Generative AI for Agriculture Advisory (GAIA), is to enhance the efficacy, reliability, and contextual relevance of AI-generated agricultural advisories.

″So far, CABI has conducted user engagement research with plant doctors in Kenya and India and identified their priority information needs for a GenAI-powered agricultural advisory tool. These have been mapped against CABI’s extensive agricultural information resources.

″Licensing agreements have been drafted for sharing CABI content with other use case partners and the technical options for delivery of content to partners. RAG-based systems are being defined.″

He said the project will contribute to outcomes including addressing the potential risk of using LLMs in agricultural advisory services and provide more nuanced, context-aware, and reliable agricultural advisories grounded in up-to-date information.

Part of the work will also involve CABI piloting the development of a CABI agricultural chatbot in India and Kenya.

Source:AgNews