Explainable AI in Smart Agriculture: A Survey of Intelligent Farmer Advisory Systems for Loans, Insurance, and Market Support

Authors:

Yuvan B, T Ranadeep, V Bhuvan Chandu, Shreyas R V, Punitha M R

Department of Computer Science and Engineering

K S School of Engineering and Management, Bengaluru, India

1KG23CS125, 1KG23CS109, 1KG23CS115, 1KG23CS103

yuvanb@kssem.edu.in, ranadeept@kssem.edu.in, vasanthbc@kssem.edu.in, shreyasrv@kssem.edu.in, punithamr@kssem.edu.in

Punitha M R – Assistant Professor, Department of Computer Science and Engineering

Abstract—Getting farm loans, state subsidies, and reliable crop insurance is often a frustrating experience for everyday farmers. Most digital tools available today only look at one isolated prob- lem and rarely explain why they make specific recommendations. Because of this missing communication, farmers are frequently left confused and hesitate to trust automated platforms.

To fix this gap, this paper presents a unified advisory platform built on Explainable Artificial Intelligence (XAI). By linking environmental conditions, financial histories, and market shifts, our system offers clear and transparent guidance. It uses robust machine learning models paired with explainability layers to show farmers exactly why they qualify for specific programs, alongside future crop price estimates.

The system continuously tracks overall farming safety by calculating a custom risk score derived from real-time weather feeds, soil health images, and market indexes. To ensure language is never a barrier, the platform integrates the Gemini API to provide complete advice natively in Kannada, Hindi, and English. Early tests with simulated data prove that this transparent approach builds strong user trust, removes administrative confusion, and helps rural communities make highly secure, profitable choices.

Index Terms—Explainable Artificial Intelligence, Smart Agriculture, Farmer Advisory System, Agricultural Risk Analysis, Subsidy Recommendation, Welfare Optimization