Artificial Intelligence in Agricultural Extension: Transforming Farmer Advisory Systems, Decision Support and Knowledge Delivery

B. Neeraja

Government Polytechnic Nalgonda, Telangana, India.

Deepali Suryawanshi *

Department of Agricultural Extension & Communication, School of Agriculture, ITM University Gwalior, Madhya Pradesh, India.

Nibedita Taye

Department of Agribusiness Management and Food Technology (ABMFT), Nehu, Tura Campus, Meghalaya, India.

Rinkesh Kumar

Guru Kashi University, Talwandi Sabo, Bathinda, Punjab, India.

Surabhi Bharti

Guru Kashi University, Talwandi Sabo, Bathinda, Punjab, India.

Somdutt Tripathi

Department of Agricultural Extension, Banda University of Agriculture and Technology, Banda, Uttar Pradesh, India.

*Author to whom correspondence should be addressed.


Abstract

Agricultural extension services face a structural crisis characterised by acute shortages of trained advisors, declining public investment, and rapidly escalating agronomic complexity in an era of accelerating climate change. Artificial intelligence (AI) has emerged as a prominent technological response to these challenges, offering scalable, personalised, and continuously improving advisory capabilities across multiple modalities. This critical review examines the current state of AI applications within agricultural extension, synthesising evidence on farmer advisory systems, decision support tools, and knowledge delivery mechanisms drawn from a wide-ranging body of peer-reviewed literature and authoritative institutional sources. Key applications reviewed include machine learning-based crop management decision support, deep learning-powered pest and disease diagnostics, conversational chatbot advisory platforms, remote sensing-integrated recommendation systems, and natural language processing tools designed for multilingual, low-literacy contexts. The review finds that whilst technical capabilities have advanced substantially, the translation of these capabilities into demonstrated farm-level impact — particularly for smallholder farmers in low-income countries — remains limited and inadequately evidenced. Structural barriers, including the digital divide, data governance deficits, algorithmic opacity, gendered inequalities in digital access, and inadequate public extension infrastructure, continue to constrain equitable deployment at scale. The review argues that realising the transformative potential of AI in agricultural extension requires coherent policy frameworks addressing digital infrastructure, data rights, institutional capacity, and regulatory accountability. It concludes that AI-based advisory tools are most appropriately understood as augmenting rather than replacing human extension capacity, and that inclusive design, independent evaluation, and participatory development are essential prerequisites for equitable and effective deployment.

Keywords: Artificial Intelligence, agricultural extension, farmer advisory, machine learning, digital agriculture, knowledge delivery, smallholder farmers


How to Cite

Neeraja, B., Deepali Suryawanshi, Nibedita Taye, Rinkesh Kumar, Surabhi Bharti, and Somdutt Tripathi. 2026. “Artificial Intelligence in Agricultural Extension: Transforming Farmer Advisory Systems, Decision Support and Knowledge Delivery”. Journal of Experimental Agriculture International 48 (6):352-71. https://doi.org/10.9734/jeai/2026/v48i64288.

Downloads

Download data is not yet available.