AGRISENSE AI: A PRECISION AGRICULTURE PLATFORM LEVERAGING RAG, MULTI-MODEL AI ENSEMBLES AND MULTILINGUAL LOCALIZATION

Authors:

Sandeep Sharma,Ruhi Saxena,Navin Garg,Vanita Kshirsagar,Bipin Sule,Tanveer Ahmad Wani,Ashish Rayal,

DOI NO:

https://doi.org/10.26782/jmcms.2026.11.00001

Keywords:

Precision Agriculture,Retrieval-Augmented Generation,Large Language Models,Crop Recommend,Multilingual NLP,Agricultural Decision Support,Plant Disease Detection,Weather Intelligence,Qdrant,Generative AI.,

Abstract

Indian agriculture has a high level of spatial, climatic, soil, market, and linguistic diversity, which has a strong impact on agricultural decision-making. AgriSense AI is an integrated precision agriculture decision support platform that integrates Retrieval-Augmented Generation (RAG), real-time weather intelligence, agronomic reasoning, financial analytics, multilingual generation, conversational assistance, and image-based crop-health analysis. It fetches historical knowledge on agricultural topics from a Qdrant vector database and fuses it with Gemini 1.5 Flash-based weather intelligence and GPT-4o-mini to provide structured recommendations and constrained agronomic reasoning. AgriSense AI does not give one set of recommendations, but rather four different sets of recommendations based on climate fit, strategic opportunity, historical performance, and diversification. The recommendations include “actionable” estimates of NPK requirements, water usage, investment, expected profit, and return on investment (ROI). The multilingual module generates the advice directly in the selected language of India without any post hoc translation. In the controlled evaluation reported, the LLM with RAG-based models obtained around 87% accuracy in yielding the same responses as "ground-truth" data with less than 6% hallucination rates, versus 55% for the vanilla LLM, and less than 28% for the vanilla LLM. State-wise accuracy was 80 to 92%, and overall scores for the multilingual evaluation by the agricultural extension workers were in the range of 4.4–4.8 out of 5. The study covers the architecture, the retrieval and the recommendation mechanism, the evaluation results, case studies, limitations and future directions.

Refference:

I. Achiam, Josh, et al. “GPT-4 Technical Report.” arXiv, 2023, 10.48550/arXiv.2303.08774 .
II. Conneau, Alexis, et al. “Unsupervised Cross-Lingual Representation Learning at Scale.” Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020, pp. 8440–8451. 10.18653/v1/2020.acl-main.747 .
III. Devlin, Jacob, et al. “BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding.” Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1, 2019, pp. 4171–4186. 10.18653/v1/N19-1423 .
IV. Ferentinos, Konstantinos P. “Deep Learning Models for Plant Disease Detection and Diagnosis.” Computers and Electronics in Agriculture, vol. 145, 2018, pp. 311–318. 10.1016/j.compag.2018.01.009
V. Fountas, Spyros, et al. “Farm Management Information Systems: Current Situation and Future Perspectives.” Computers and Electronics in Agriculture, vol. 115, 2015, pp. 40–50. 10.1016/j.compag.2015.05.011 .
VI. Gebbers, Robin, and Viacheslav I. Adamchuk. “Precision Agriculture and Food Security.” Science, vol. 327, no. 5967, 2010, pp. 828–831. 10.1126/science.1183899 .
VII. Gemini Team, et al. “Gemini 1.5: Unlocking Multimodal Understanding across Millions of Tokens of Context.” arXiv, 2024, 10.48550/arXiv.2403.05530 .

VIII. Hu, Junjie, et al. “XTREME: A Massively Multilingual Multi-Task Benchmark for Evaluating Cross-Lingual Generalisation.” Proceedings of the 37th International Conference on Machine Learning, 2020, pp. 4411–4421. PMLR. https://proceedings.mlr.press/v119/hu20b.html .
IX. Hughes, David P., and Marcel Salathé. “An Open Access Repository of Images on Plant Health to Enable the Development of Mobile Disease Diagnostics.” arXiv, 2015. https://arxiv.org/abs/1511.08060
X. Jabed, Md. Abu, and Masrah Azrifah Azmi Murad. “Crop Yield Prediction in Agriculture: A Comprehensive Review of Machine Learning and Deep Learning Approaches, with Insights for Future Research and Sustainability.” Heliyon, vol. 10, no. 24, 2024, article e40836. 10.1016/j.heliyon.2024.e40836 .
XI. Jha, Kirtan, et al. “A Comprehensive Review on Automation in Agriculture Using Artificial Intelligence.” Artificial Intelligence in Agriculture, vol. 2, 2019, pp. 1–12. 10.1016/j.aiia.2019.05.004 .
XII. Kakwani, Divyanshu, et al. “IndicNLPSuite: Monolingual Corpora, Evaluation Benchmarks and Pre-Trained Multilingual Language Models for Indian Languages.” Findings of the Association for Computational Linguistics: EMNLP 2020, 2020, pp. 4948–4961. 10.18653/v1/2020.findings-emnlp.445 .
XIII. Kallenberg, M. G., et al. “Integrating Process-Based Models and Machine Learning for Crop Yield Prediction.” arXiv, 2023, https://arxiv.org/abs/2307.13466 .
XIV. Kamilaris, Andreas, and Francesc X. Prenafeta-Boldú. “Deep Learning in Agriculture: A Survey.” Computers and Electronics in Agriculture, vol. 147, 2018, pp. 70–90. 10.1016/j.compag.2018.02.016 .
XV. Khanuja, Simran, et al. “MuRIL: Multilingual Representations for Indian Languages.” arXiv, 2021. https://arxiv.org/abs/2103.10730 .
XVI. Klerkx, Laurens, Emma Jakku, and Pierre Labarthe. “A Review of Social Science on Digital Agriculture, Smart Farming and Agriculture 4.0: New Contributions and a Future Research Agenda.” NJAS: Wageningen Journal of Life Sciences, vols. 90–91, 2019, pp. 1–16. 10.1016/j.njas.2019.100315 .
XVII. Lewis, Patrick, et al. “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.” Advances in Neural Information Processing Systems, vol. 33, 2020, pp. 9459–9474. https://papers.neurips.cc/paper/2020/hash/6b493230205f780e1bc26945df7481e5-Abstract.html .
XVIII. Li, J., et al. “Label-Efficient Learning in Agriculture: A Comprehensive Review.” Computers and Electronics in Agriculture, vol. 215, 2023, article 108412.
XIX. Liakos, Konstantinos G., et al. “Machine Learning in Agriculture: A Review.” Sensors, vol. 18, no. 8, 2018, article 2674. 10.3390/s18082674 .
XX. Lowenberg-DeBoer, James, and Bruce Erickson. “Setting the Record Straight on Precision Agriculture Adoption.” Agronomy Journal, vol. 111, no. 4, 2019, pp. 1552–1569. 10.2134/agronj2018.12.0779 .
XXI. Mohanty, Sharada P., David P. Hughes, and Marcel Salathé. “Using Deep Learning for Image-Based Plant Disease Detection.” Frontiers in Plant Science, vol. 7, 2016, article 1419. 10.3389/fpls.2016.01419 .
XXII. Pathak, Deepak, et al. “Predicting Crop Yield with Machine Learning: An Extensive Analysis of Input Modalities and Models on a Field and Sub-Field Level.” IGARSS 2023–2023 IEEE International Geoscience and Remote Sensing Symposium, 2023, pp. 2767–2770. IEEE, 10.1109/IGARSS52108.2023.10282318 .
XXIII. Schick, Timo, et al. “Toolformer: Language Models Can Teach Themselves to Use Tools.” Advances in Neural Information Processing Systems, vol. 36, 2023, pp. 68539–68551. 10.52202/075280-2997 .
XXIV. Singh, Namita, et al. “Farmer.Chat: Scaling AI-Powered Agricultural Services for Smallholder Farmers.” arXiv, 2024. https://arxiv.org/abs/2409.08916 .
XXV. Sladojevic, Srdjan, et al. “Deep Neural Networks Based Recognition of Plant Diseases by Leaf Image Classification.” Computational Intelligence and Neuroscience, vol. 2016, 2016, article 3289801. 10.1155/2016/3289801 .
XXVI. Too, Edna Chebet, et al. “A Comparative Study of Fine-Tuning Deep Learning Models for Plant Disease Identification.” Computers and Electronics in Agriculture, vol. 161, 2019, pp. 272–279. 10.1016/j.compag.2018.03.032 .
XXVII. van Klompenburg, Thomas, Ayalew Kassahun, and Cagatay Catal. “Crop Yield Prediction Using Machine Learning: A Systematic Literature Review.” Computers and Electronics in Agriculture, vol. 177, 2020, article 105709. 10.1016/j.compag.2020.105709 .
XXVIII. Wolfert, Sjaak, et al. “Big Data in Smart Farming—A Review.” Agricultural Systems, vol. 153, 2017, pp. 69–80. 10.1016/j.agsy.2017.01.023 .
XXIX. Yao, Shunyu, et al. “ReAct: Synergizing Reasoning and Acting in Language Models.” arXiv, 2022. https://arxiv.org/abs/2210.03629 .
XXX. Zhang, Naiqian, Maohua Wang, and Ning Wang. “Precision Agriculture—A Worldwide Overview.” Computers and Electronics in Agriculture, vol. 36, nos. 2–3, 2002, pp. 113–132. 10.1016/S0168-1699(02)00096-0 .

View Download