Abstract
Crop productivity is heavily impacted by inefficient fertilizer usage, improper fertilizer handling, and inappropriately chosen crops. To address these issues, this research work proposes an AI-powered Smart Agriculture Prediction System utilizing intelligent agents for carrying out soil classification, estimating soil parameters, crop suggestion, and fertilizer suggestion. The soil classifier module is trained with 1,563 images of black soils, red soils, clay soils, and alluvial soils using MobileNet-V2, ResNet, and Custom CNN, with Custom CNN resulting in a higher accuracy of 92.88%, which performed better in classifying soils based on textures. A soil parameter estimation agent utilizes regression models for estimating pH and NPK content of soils using images. For crop suggestion, a crop dataset with 2,200 samples with parameters such as N, P, K, T, H, pH, and rainfall is used, in which Random Forest model performed better with an accuracy of 92.4% when compared with CNN and DNN models. For fertilizer suggestion, XGBoost performed better with an accuracy of 94.7% in estimating fertilizers such as Urea, DAP, NPK, Potash, and Compost. Real-time climatic parameters are obtained using API in order to make dynamic updates for climatic parameters. Real-time weather data obtained through APIs enables dynamic updates of climatic parameters, while Explainable AI techniques such as SHAP and LIME enhance model transparency and user trust. Additionally, the system incorporates an interactive agent-based framework that processes user inputs, including location, soil images, and nutrient levels, to generate adaptive outputs such as weather alerts, yield potential, and personalized recommendations. The experimental results demonstrate that the proposed system effectively integrates deep learning, ensemble learning, and explainability to deliver a scalable, efficient, and sustainable decision-support solution for precision agriculture, promoting optimized resource utilization and environmental stewardship.
Data availability
The datasets used in this study are publicly available and can be accessed at the following sources:- Soil Classification Dataset (Dataset-1): 1,563 labeled soil images covering black, red, clay, and alluvial soil types. Available at: https://www.kaggle.com/datasets/jayaprakashpondy/soil-image-dataset/data- Crop Recommendation Dataset (Dataset-2): 2,200 structured instances with features such as N, P, K, pH, temperature, humidity, and rainfall, along with crop labels. Available at: https://www.kaggle.com/datasets/atharvaingle/crop-recommendation-dataset- Fertilizer Recommendation Dataset (Dataset-3): 1,200 samples including soil type, crop type, soil nutrients, and corresponding fertilizer labels. Available at: https://www.kaggle.com/code/mohitsingh1804/fertilizer-recommendation-system.
References
Tripathi, P., Kumar, N., Rai, M., Shukla, P. K. & Verma, K. N. Applications of Machine Learning in Agriculture, in Smart Village Infrastructure and Sustainable Rural Communities, IGI Global, pp. 99–118. (2023).
Akpenpuun, T. D. et al. Review of Temperature Management Strategies and Techniques in the Greenhouse Microenvironment, Adeleke Univ J Eng Technol. 6, 2, 126–147, (2023).
Allouhi, A. et al. Machine learning algorithms to assess the thermal behavior of a Moroccan agriculture greenhouse. Clean. Eng. Technol. 5, 100346 (2021).
Bayatvarkeshi, M. et al. Modeling soil temperature using air temperature features in diverse Climatic conditions with complementary machine learning models. Comput. Electron. Agric. 185, 106158 (2021).
Guillén-Navarro, M. A., Martínez-España, R., Llanes, A., Bueno-Crespo, A. & Cecilia, J. M. A deep learning model to predict lower temperatures in agriculture. J. Ambient Intell. Smart Environ. 12 (1), 21–34 (2020).
Mampitiya, L., Pahalawattaarachchi, P. & Abeynayake, S. AI-Based temperature prediction model for soil in agriculture. Sustainability 16 (1), 263 (2024).
Rani, S., Sinha, N. & Prakash, P. A crop recommendation system using optimization algorithms. Ecol. Inf. 75, 101383 (2023).
Monjezi, H., Khalilnejad, R. & Yousefi, A. Hybrid intelligent modeling for indoor greenhouse air temperature prediction. Energy Build. 258, 111876 (2023).
Sharma, A., Kumar, R. & Yadav, N. Smart farming using Cloud, Satellite, and AI. Comput. Electron. Agric. 213, 108123 (2024).
Mohan, R. J., Rayanoothala, P. S. & Sree, R. P. Next-gen agriculture: integrating AI and XAI for precision crop yield predictions. Front. Plant. Sci. 15, 1451607 (2025).
Dey, B., Ferdous, J. & Ahmed, R. Machine learning based recommendation of agricultural and horticultural crop farming in India under the regime of NPK, soil pH and three Climatic variables. Heliyon, 10, 3, (2024).
Reddy, G. V. et al. Precision farming practices with data-driven analysis and machine learning-based crop and fertiliser recommendation system, E3S Web of Conf., 507, 01078, (2024).
Liu, S. Y. Artificial intelligence (AI) in agriculture. IT Prof. 22 (3), 14–15 (2020).
Suganthi, S. U., Prinslin, L., Selvi, R. & Prabha, R. Generative AI in agri: sustainability in smart precision farming yield prediction mapping system based on GIS using deep learning and GPS. Procedia Comput. Sci. 252, 365–380 (2025).
Sai, S., Roy, M., Kumari, V. A., Ghosh, R. & Mehta, K. J. Unleashing the power of generative AI in agriculture 4.0 for smart and sustainable farming. Cogn. Comput. 17 (1), 63–78 (2025).
Crop, E. M. L. A. Sustainable food development based on ensemble machine learning assisted crop and fertilizer recommendation system, (2024).
Nandom, S. S., Abe, G. T. & Gambo, I. P. Application of random forest and hierarchical clustering models for crop and fertilizer recommendation to farmers. Nigerian J. Technol. 44 (1), 114–122 (2025).
Musanase, C., Vodacek, A., Hanyurwimfura, D., Uwitonze, A. & Kabandana, I. Data-driven analysis and machine learning-based crop and fertilizer recommendation system for revolutionizing farming practices. Agriculture 13 (11), 2141 (2023).
Tanaka, T. S., Heuvelink, G. B., Mieno, T. & Bullock, D. S. Can machine learning models provide accurate fertilizer recommendations? Precis Agric. 25 (4), 1839–1856 (2024).
Akhilesh, S., Abburi, B. T., Somya, P., Krishna, R. M. S. & Srihari, T. Fertilizer Recommendation for Agriculture using Machine Learning, (2025).
Khan, A. A., Faheem, M., Bashir, R. N., Wechtaisong, C. & Abbas, M. Z. Internet of things (IoT) assisted context aware fertilizer recommendation. IEEE Access. 10, 129505–129519 (2022).
Ndjuluwa, L. N. P., Adebisi, J. A. & Dayoub, M. Internet of things for crop farming: A review of technologies and applications. Commodities 2 (4), 367–381. https://doi.org/10.3390/commodities2040021 (2023).
Pawar, D., Rais Allauddin Mulla, D. S. H., Shikalgar, S., Jethva, H. B. & Patel, G. A. A novel hybrid AI federated ML/DL models for classification of soil components. Int. J. Recent. Innov. Trends Comput. Commun. 10, 190–199 (2022).
Godara, S. & Toshniwal, D. Deep Learning-based query-count forecasting using farmers’ helpline data. Comput. Electron. Agric. 196, 106875 (2022).
Folorunso, O. et al. GeaGrow: A mobile tool for soil nutrient prediction and fertilizer optimization using artificial neural networks. Front. Sustainable Food Syst. 9, 1533423 (2025).
Pallavi, V. N., Chaitanya, J., Rani, B. S. & Rohan, R. A machine learning-based fertilizer recommendation system for sustainable crop yield, (2024).
Panchbhai, K. G., Lanjewar, M. G. & Naik, A. V. Modified MobileNet with leaky ReLU and LSTM with balancing technique to classify the soil types. Earth Sci. Inf. 18, 77. https://doi.org/10.1007/s12145-024-01521- (2025).
Lanjewar, M. G. & Gurav, O. L. Convolutional neural networks based classifications of soil images. Multimed Tools Appl. 81, 10313–10336. https://doi.org/10.1007/s11042-022-12200-y (2022).
Shukla, A., Chouhan, S. S., Patel, R. K. & Singh, U. P. (2025) AgriCloud: Cloud-Based Framework for Scalable Crop. Monitoring and Intelligent Decision Support. In. Chouhan, S.S., Patel, R.K., Singh, U.P., Jain, S. (eds) AgriTech Revolution Springer, Singapore https://doi.org/10.1007/978-981-95-1268-3_6
Funding
Open access funding provided by Vellore Institute of Technology. This research was supported by the Vellore Institute of Technology, Chennai.
Author information
Authors and Affiliations
Contributions
N.L.P.S, V.G.S and D.N.S. done the conceptualization of this study, prepared the methodology, development of decision system. V.G.S and D.N.S prepared the figures and tables. N.L.P.S and V.G.S done the performance evaluation and documentation. L.R.P. supervised the research, done the performance evaluation and documentation support. All authors reviewed the manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Swati, N.L.P., Gupta, S.V., Duddela, N.S. et al. Agentic AI-driven autonomous decision support system for smart agriculture. Sci Rep (2026). https://doi.org/10.1038/s41598-026-39472-w
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-39472-w
