Design and Implementation of a Machine Learning-Driven Crop Advisory System for Precision Agriculture

Abstract

Precision agriculture is being adopted as a game-changer to boost crop production, resource utilization efficiency and sustainable agriculture. Climatic variability, soil degradation, water scarcity and land fragmentation are emerging issues in Indian agriculture, which is a major occupation of nearly half of the country\'s workforce. These are more severe in areas of tribal dominated and rain fed agriculture sectors of the state Odisha where smallholder farmers are still highly exposed to agro climatic risks. In the context of precision farming in the Koraput&Rayagada district of Odisha, India, this paper discusses the design and implementation of a Machine Learning Based Crop Advisory System. The proposed system uses multi-source datasets such as soil properties (N, P, K, pH, texture), historical crop yield data, rainfall, temperature data and satellite derived vegetation indices (NDVI, EVI) to provide intelligent crop recommendations and advisories. The implemented supervised ML techniques are RF, SVM, DT, KNN, LR, AdaBoost, Gradient Boosting, Bagging Classifier, and Extra Trees which were comparatively evaluated. Experimental results show that the RF model is the most accurate prediction model at 99.5%, significantly enhancing the crop suitability decision making process from that of standard advising. The system developed gives predictions of crops recommendations on time, place and evidence basis. So, it minimises risk, boosts productivity and supports sustainable agriculture in tribal and rain-fed areas of the state\'s south.

Introduction

The text describes a machine learning–based crop recommendation system designed for climate-vulnerable agricultural regions in Odisha, India, specifically Koraput and Rayagada districts. Agriculture in this region is largely rain-fed and affected by erratic rainfall, poor soil fertility, and limited extension services, making data-driven decision support important.

The study aims to build a geospatial agricultural database combining soil, climate, satellite (NDVI/EVI), and yield data, and then use multiple ML models (such as Random Forest, SVM, KNN, and ensemble methods) to recommend suitable crops and provide guidance on fertiliser use and irrigation.

A major focus is comparing different machine learning algorithms for crop classification. The dataset includes around 2,200 records with soil nutrients, weather variables, and vegetation indices. After preprocessing and feature engineering, several models were trained and evaluated using accuracy, precision, recall, F1-score, and cross-validation.

Results show that ensemble methods—especially Random Forest—perform best, achieving about 99.5% accuracy, followed closely by Extra Trees and Gradient Boosting. Rainfall, humidity, and soil nitrogen were found to be the most important features influencing crop suitability. The system also generates practical crop recommendations that align well with agronomic knowledge (e.g., rice for high rainfall conditions, millets for low rainfall and acidic soils).

Conclusion

This work has highlighted the development, deployment and evaluation of a Machine Learning–assisted Crop Advisory System for precision agriculture in tribal and rain-fed districts of Koraput and Rayagada, Odisha. Main findings are: • There ensemble ML methods (RF and ET) are superior than individual classifiers and linear classifiers in multi-class crop recommendation. Random Forest demonstrated a good performance of 99.5% accuracy and 99.3% cross-validation accuracy, which shows that it has good generalisation ability. • Fusion of multistream data (satellite derived vegetation indices and soil and climatic variables) for enhancing the discriminative power of ML models. The contribution of satellite indices to basic environmental observations is not very large, but satellite indices combined have led to a good increase of the accuracy of the models. • The accuracy of the operational forecast in the agro-climatic condition of the south region of Odisha is highly sensitive to location specific model calibration using target region data. • The importance of rainfall as the sole most important driving factor for crop suitability (0.192) is a key indicator of the critical role water availability plays in the selection of suitable crops in rain-fed farming. • The web-based, bilingual (English/Odia) decision support interface is an example of the ways in which ML-based crop advice can be made accessible to agricultural extension staff and educated farmers, thus democratizing precision agriculture in tribal contexts.

References

[1] Doshi, Z.; Nadkarni, S.; Agrawal, R.; Shah, N. AgroConsultant: Intelligent crop recommendation system using machine learning algorithms. Proceedings of the 2018 ICCUBEA Conference, Pune, India, 2018. [2] Thilakarathne, N.N.; Bakar, M.S.A.; Abas, P.E.; Yassin, H. A cloud enabled crop recommendation platform for machine learning driven precision farming. Sensors 2022, 22, 6299. [3] Rajak, R.K.; Pawar, A.; Pendke, M.; Shinde, P.; Rathod, S.; Devare, A. Crop recommendation system to maximize crop yield using machine learning technique. Int. Res. J. Eng. Technol. 2017, 4, 950–953. [4] Panigrahi, B.; Kathala, K.C.R.; Sujatha, M. A machine learning-based comparative approach to predict the crop yield using supervised learning with regression models. Procedia Comput. Sci. 2023, 218, 2684–2693. [5] Bhatnagar, K.; Jaahnavi, M.; Barathi, B.A. Agriculture Crop Recommendation System using Machine-Learning. Math. Stat. Eng. Appl. 2022, 71, 626–637. [6] Senapaty, M.K.; Ray, A.; Padhy, N. A Decision Support System for Crop Recommendation Using Machine Learning Classification Algorithms. Proceedings of International Conference on Machine Learning and Data Engineering, 2023. [7] Khatua, R.; Nanda, A.; Mohapatra, A.K.B.; et al. District Level Crop Weather Calendars and Advisories for Kharif Rice in Odisha, India. Agricultural Research, 2022. [8] Liakos, K.G.; Busato, P.; Moshou, D.; Pearson, S.; Bochtis, D. Machine learning in agriculture: A review. Sensors 2018, 18, 2674. [9] Vandana, B.; Kumar, S.S. A novel approach using big data analytics to improve the crop yield in precision agriculture. Proceedings of the 2018 IEEE RTEICT, Bangalore, India, 2018. [10] Mohanty, S.P.; Hughes, D.P.; Salathé, M. Using deep learning for image-based plant disease detection. Frontiers in Plant Science 2016, 7, 1419. [11] Doshi, Z.; Nadkarni, S.; Agrawal, R.; Shah, N. AgroConsultant: Intelligent crop recommendation system using machine learning algorithms. In Proceedings of the 2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA), Pune, India, 16–18 August 2018; pp. 1–6. [12] Fonthal, F. Design and implementation of WSN for precision agriculture in white cabbage crops. In Proceedings of the 2017 IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing (INTERCON), Cusco, Peru, 15–18 August 2017; pp. 1–4. [13] Thilakarathne, N.N.; Bakar, M.S.A.; Abas, P.E.; Yassin, H. A cloud enabled crop recommendation platform for machine learning driven precision farming. Sensors 2022, 22, 6299. [14] Vandana, B.; Kumar, S.S. A novel approach using big data analytics to improve the crop yield in precision agriculture. In Proceedings of the 2018 3rd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT), Bangalore, India, 18–19 May 2018; pp. 824–827. [15] Rajak, R.K.; Pawar, A.; Pendke, M.; Shinde, P.; Rathod, S.; Devare, A. Crop recommendation system to maximize crop yield using machine learning technique. Int. Res. J. Eng. Technol. 2017, 4, 950–953. [16] Panigrahi, B.; Kathala, K.C.R.; Sujatha, M. A machine learning-based comparative approach to predict the crop yield using supervised learning with regression models. Procedia Comput. Sci. 2023, 218, 2684–2693. [17] Bhatnagar, K.; Jaahnavi, M.; Barathi, B.A. Agriculture Crop Recommendation System using Machine-Learning. Math. Stat. Eng. Appl. 2022, 71, 626–637. [18] Senapaty, M.K.; Ray, A.; Padhy, N. A Decision Support System for Crop Recommendation Using Machine Learning Classification Algorithms. In Proceedings of International Conference on Machine Learning and Data Engineering, 2023. [19] Khatua, R.; Nanda, A.; Mohapatra, A.K.B.; Mahapatra, A.; Guhan, V.; Praveenkumar, P. District Level Crop Weather Calendars and Advisories for Kharif Rice in Odisha, India. Agricultural Research, 2022. [20] Liakos, K.G.; Busato, P.; Moshou, D.; Pearson, S.; Bochtis, D. Machine learning in agriculture: A review. Sensors 2018, 18, 2674. [21] Goldstein, A.; Fink, L.; Meitin, A.; Bohadana, S.; Lutenberg, O.; Lalazar, G. Applying machine learning on sensor data for irrigation recommendations: Revealing the agronomist\'s rule of thumb. Precision Agriculture 2018, 19, 421–444. [22] Pantazi, X.E.; Moshou, D.; Alexandridis, T.; Whetton, R.L.; Mouazen, A.M. Wheat yield prediction using machine learning and advanced sensing techniques. Computers and Electronics in Agriculture 2016, 121, 57–65. [23] Filippi, P.; Jones, E.J.; Wimalathunge, N.S.; Somarathna, P.D.S.N.; Pozza, L.E.; Ugbaje, S.U.; Jephcott, T.G.; Paterson, S.E.; Whelan, B.M.; Bishop, T.F.A. An approach to forecast grain crop yield using multi-layered, multi-farm data sets and machine learning. Precision Agriculture 2019, 20, 1015–1029. [24] Mohanty, S.P.; Hughes, D.P.; Salathé, M. Using deep learning for image-based plant disease detection. Frontiers in Plant Science 2016, 7, 1419. [25] Veenadhari, S.; Misra, B.; Singh, C.D. Machine learning approach for forecasting crop yield based on climatic parameters. In Proceedings of the 2014 International Conference on Computer Communication and Informatics, Coimbatore, India, 3–5 January 2014; pp. 1–5. [26] Dahikar, S.S.; Rode, S.V. Agricultural crop yield prediction using artificial neural network approach. International Journal of Innovative Research in Electrical, Electronics, Instrumentation and Control Engineering 2014, 2, 683–686. [27] Basak, J.K.; Titumir, R.A.M.; Dey, N.C. Climate change in Bangladesh: A historical analysis of temperature and rainfall data. Journal of Environment 2013, 2, 41–46. [28] Government of India, Ministry of Agriculture and Farmers\' Welfare. State of Indian Agriculture, Annual Report. Department of Agriculture, Cooperation and Farmers Welfare: New Delhi, India, 2022. [29] ICAR. Annual Report 2022–23. Indian Council of Agricultural Research: New Delhi, India, 2023. [30] Directorate of Agriculture & Food Production, Odisha. District-wise Area, Production and Productivity of Crops. Government of Odisha: Bhubaneswar, India, 2023.

Copyright

Copyright © 2026 Like Mohanty. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.