KRISHI-SAKHI: AN AI-POWERED PERSONAL FARMING ASSISTANT FOR KERALA FARMERS

Main Article Content

Somya Agarwal

Abstract

This paper describes an intelligent agricultural chatbot to help farmers make data-driven decisions. The chatbot is built off two machine-learning models: A crop recommendation model with an accuracy level of 93% and a crop price prediction model with a 95% level of accuracy. The chatbot integrates both models into a multilingual chatbot with support for the Malayalam language primarily targeted at farmers in Kerala. The chatbot shows strong linguistic capabilities, with a BLEU score of over 95, which provides for accurate responses in context. The user interface is simple and easy to use, allowing users to submit inquiries and get responses quickly and easily. The proposed solution provides seamless and easy-to-use access to predictive analytics using natural language input to assist users in making informed decisions about their farming operations. This demonstrates the potential of AI-driven conversational technology to improve agricultural productivity by providing increased access to agriculture.   

Article Details

Section

Articles

Author Biography

Somya Agarwal

Assistant Professor

Geetanjali Institute of Technical Studies

         Udaipur

References

[1] P. S. Birthal et al., “Sources of growth in Indian agriculture,” Agricultural Economics Research Review, 2015.

[2] Y. Zhang, L. Wang, and S. Wang, “Application of artificial intelligence in agriculture: A review,” Information Processing in Agriculture, vol. 8, no. 1, pp. 1–12, 2021.

[3] S. Shanila and S. Helen, “Development of a scale to assess Kerala farmers’ attitude towards digital technologies in agriculture,” Indian Journal of Extension Education, vol. 61, no. 4, pp. 165–169, 2025.

[4] “A study on adoption of IoT-based smart agricultural practices in Kerala using Analytic Hierarchy Process,” 2024.

[5] Agmarknet, “Agricultural market information system,” 2025. [Online]. Available: https://agmarknet.gov.in/home

[6] Nirmalgaud, “Crop recommendation system using machine learning,” Kaggle, 2026. [Online]. Available: https://www.kaggle.com/code/nirmalgaud/crop

[7] P. I. Devi, S. S. Solomon, and M. G. Jayasree, “Green technologies for sustainable agriculture: Policy options towards farmer adoption,” 2015.

[8] S. Wolfert, L. Ge, C. Verdouw, and M. J. Bogaardt, “Big data in smart farming: A review,” Agricultural Systems, vol. 153, pp. 69–80, 2017.

[9] K. G. Liakos, P. Busato, D. Moshou, S. Pearson, and D. Bochtis, “Machine learning in agriculture: A review,” Sensors, vol. 18, no. 8, p. 2674, 2018.

[10] “A study on adoption of IoT-based smart agricultural practices in Kerala using Analytic Hierarchy Process,” 2024.

[11] K. P. Ferentinos, “Deep learning models for plant disease detection and diagnosis,” Computers and Electronics in Agriculture, vol. 145, pp. 311–318, 2018.

[12] S. Mittal, S. Gandhi, and G. Tripathi, “Socio-economic impact of mobile phones on Indian agriculture,” ICRIER Working Paper, 2010.