Crop Price Prediction Using Machine Learning and Remote Sensing Technology

Abstract

Supply market volatility, climatic variability, and the absence of timely, reliable data for forecasting present serious obstacles for the agriculture industry. the vital role of precise crop price predictions in maintaining global food security and optimising supply chain efficiency. To achieve this, the authors propose a hybrid forecasting model that combines advanced machine learning algorithms with data from remote sensing technologies. By testing this framework across diverse geographic regions and seasons, the study proves that incorporating satellite data significantly enhances the reliability of financial projections. Ultimately, the source highlightshow technological integration provides more robust insights for stakeholders in the agricultural market. This approach aims to provide the predictive accuracy necessary for navigating complex international economic landscapes. The suggested framework is adaptable to various crop types and geographical locations. It offers a decision-support tool for farmers, traders, policymakers, and agribusinesses to make data-driven, informed choices regarding cultivation, storage, and market engagement.

Introduction

Accurate crop price forecasting is essential for helping farmers make informed decisions on crop selection, harvest timing, storage, and market negotiations. However, over 80% of smallholder farmers in developing countries lack access to reliable market forecasts, leading to overproduction, food waste, and income instability. Traditional forecasting methods based on historical averages and econometric models struggle to capture the non-linear, dynamic, and climate-sensitive nature of agricultural systems.

Recent advances in machine learning (ML) and remote sensing provide effective alternatives. ML algorithms such as Random Forest, XGBoost, and LSTM can uncover complex relationships in large datasets, often outperforming conventional statistical approaches. Remote sensing technologies—using satellite imagery, UAVs, and indices like NDVI, rainfall, and temperature—offer valuable insights into crop health and environmental conditions that directly influence yields and market prices.

This study proposes a Crop Price Prediction System that integrates machine learning with simulated remote sensing data to predict whether crop prices will rise, fall, or remain stable. Using historical price data and environmental variables, a Random Forest Classifier achieved 91% prediction accuracy, demonstrating strong performance and interpretability. The system is designed to be low-cost, modular, and deployable on cloud platforms or edge devices, making it suitable for data-scarce regions.

The framework also includes a real-time visualization dashboard that displays predicted price trends alongside environmental context, supporting proactive and data-driven decision-making. Overall, the proposed system provides a scalable foundation for intelligent agricultural advisory services, capable of supporting multiple crops, regions, and data sources while reducing risk and improving economic outcomes for farmers.

Conclusion

The experiment demonstrated that crop prices can be accurately predicted using machine learning models and remote sensing data. Gradient Boosting outperformed Random Forest and Support Vector Machine among the models that were tested in terms of accuracy. By removing superfluous features, dimensionality reduction decreased errors and training time while improving model performance. Notwithstanding the small dataset, the findings show that combining crop and environmental data can help improve agricultural decision-making and is useful for predicting prices.

References

[1] Chen, Z., Goh, H. S., Sin, K. L., Lim, K., Chung, N. K. H., & Liew, X. Y. (2021). Automated Agriculture Commodity Price Prediction System with Machine LearningTechniques.arXiv. HTTPS://ARXIV.ORG/ABS/2106.12747 [2] Bhardwaj, M. R., Pawar, J., Bhat, A., Deepanshu, Enaganti, I., Sagar, K., & Narahari, Y. (2023). An innovative Deep Learning Based Approach for Accurate Agricultural Crop Price Prediction. arXiv. HTTPS://ARXIV.ORG/ABS/2304.09761 [3] Mateo-Sanchis, A., Piles, M., Muñoz-Marí, J., Adsuara, J. E., Pérez-Suay, A., & Camps-Valls, G. (2020). Synergistic Integration of Optical and Microwave Satellite Data for Crop Yield Estimation. arXiv. HTTPS://ARXIV.ORG/ABS/2012.05905 [4] Ko, J., Shin, T., Kang, J., Baek, J., Sang, W.-G. (2024). Combining machine learning and remote sensing-integrated crop modeling for rice and soybean crop simulation.Frontiers in Plant Science. https://www.frontiersin.org/articles/10.3389/fpls.2024.1320969/full [5] Oikonomidis, A., Catal, C., & Kassahuna, A. (2022). Deep learning for crop yield prediction: a systematic literature review. New Zealand Journal of Crop and Horticultural Science. https://www.tandfonline.com/doi/full/10.1080/01140671.2022.2032213 [6] Riza, S. L., Yudianita, A. H., Nugraha, E., et al. (2022). Remote sensing and machine learning for yield prediction of lowland paddy crops. F1000Research. https://f1000research.com/articles/11-682 [7] Tzenios, N., & Reddy, M. (2023). Predicting Crop Yield Using Deep Learning and Remote Sensing. Journal of Engineering Research and Reports. https://journaljerr.com/index.php/JERR/article/view/858 [8] Catal, C., & Oikonomidis, A. (2022). Review on Crop Prediction Using Deep Learning Techniques. IOP Conference Series: Materials Science and Engineering. https://iopscience.iop.org/article/10.1088/1742-6596/1767/1/012026 [9] You, J., Li, X., Low, M., Lobell, D., & Ermon, S. (2017). Deep Gaussian Process for Crop Yield Prediction Based on Remote Sensing Data. AAAI Conference on Artificial Intelligence. https://ojs.aaai.org/index.php/AAAI/article/view/10597 [10] Pantazi, X. E., Moshou, D., & Alexandridis, T. (2016). Wheat Yield Prediction Using Machine Learning and Remote Sensing Data. Computers and Electronics in Agriculture,121,57–65. https://doi.org/10.1016/j.compag.2015.11.006 [11] Khaki, S., Khalilzadeh, Z., & Wang, L. (2020). Crop Yield Prediction Using Deep Neural Networks. Frontiers in Plant Science, 11, 633168. https://doi.org/10.3389/fpls.2020.633168 [12] Li, W., Gong, P., & Biging, G. S. (2016). Remote Sensing of Crop Yield: A Review of Applications and Methods. International Journal of Remote Sensing, 37(13),3064-3094. https://doi.org/10.1080/01431161.2016.1172489 [13] Jain, M., & Panigrahi, S. (2018). Machine Learning-Based Crop Yield Prediction: A Case Study of Wheat. IEEE International Conference on Data Mining Workshops. https://doi.org/10.1109/ICDMW.2018.00026 [14] Kamilaris, A., & Prenafeta-Boldú, F. X. (2018). Deep Learning in Agriculture: A Survey. Computers and ElectronicsinAgriculture,147,70–90. https://doi.org/10.1016/j.compag.2018.02.016 [15] Pantazi, X. E., Moshou, D., & Alexandridis, T. (2018). Crop Yield Prediction via Machine Learning: An Application on Maize. Agricultural Systems, 160, 1–10. https://doi.org/10.1016/j.agsy.2017.12.009 [16] Qin, Z., Wang, J., Yang, G., & Zhang, Q. (2021). A Review of Machine Learning for Crop Yield Prediction Using Remote Sensing Data. Remote Sensing,13(17), 3302. https://doi.org/10.3390/rs13173302 [17] S. Moraboena, G. Ketepalli, and P. Ragam, “A deep learning approach to network intrusion detection using deep autoencoder,” Revue d\'Intell. Artif., vol. 34, no. 4, pp. 457–463, 2020, doi: 10.18280/ria.340410. [18] M. S. Yadav and R. Kalpana, “Data preprocessing for intrusion detection system using encoding and normalization approaches,” in Proc. 11th Int. Conf. Adv. Comput. (ICoAC), Chennai, India, 2019, pp. 265–269, doi: 10.1109/ICoAC48765.2019.246851. [19] H. K. Bhuyan, V. Ravi, and M. S. Yadav, “Multi-objective optimization-based privacy in data mining,” Cluster Comput., vol. 25, pp. 4275–4287, 2022, doi: 10.1007/s10586-022-03667-3. [20] V. Naralasetti, R. K. Shaik, G. Katepalli, and J. D. Bodapati, “Deep learning models for pneumonia identification and classification based on X-ray images,” Traitement du Signal, vol. 38, no. 3, pp. 903–909, Jun. 2021. [21] G. Ketepalli and P. Bulla, “Data preparation and pre-processing of intrusion detection datasets using machine learning,” in Proc. Int. Conf. Inventive Comput. Technol. (ICICT), Lalitpur, Nepal, 2023, pp. 257–262, doi: 10.1109/ICICT57646.2023.10134025. [22] M. S. Yadav and R. Kalpana, “Recurrent nonsymmetric deep auto encoder approach for network intrusion detection system,” Measurement: Sensors, vol. 24, 100527, 2022, doi: 10.1016/j.measen.2022.100527. [23] M. S. Yadav and R. Kalpana, “A survey on network intrusion detection using deep generative networks for cyber-physical systems,” in Artif. Intell. Paradigms Smart Cyber-Physical Syst., A. K. Luhach and A. Elçi, Eds. IGI Global, 2021, pp. 137–159, doi: 10.4018/978-1-7998-5101-1.ch007. [24] M. C. P. Saheb, M. S. Yadav, S. Babu, J. J. Pujari, and J. B. Maddala, “A review of DDoS evaluation dataset: CICDDoS2019 dataset,” in Energy Syst., Drives Automations (ESDA 2021), J. R. Szymanski et al., Eds. Springer, 2023, pp. 417–429, doi: 10.1007/978-981-99-3691-5_34. [25] G. Ketepalli, S. Tata, S. Vaheed, and M. S. Yadav, “Anomaly detection in credit card transactions using deep learning techniques,” in Proc. 7th Int. Conf. Commun. Electron. Syst. (ICCES), Coimbatore, India, 2022, pp. 1207–1214, doi: 10.1109/ICCES54183.2022.9835921. [26] D. Yaswanth, S. S. Manoj, M. S. Yadav, and E. D. Chowdary, “Plant leaf disease detection using transfer learning approach,” in Proc. IEEE Int. Students’ Conf. Elect., Electron. Comput. Sci. (SCEECS), Bhopal, India, 2024, pp. 1–6, doi: 10.1109/SCEECS61402.2024.10482053. [27] K. Sujatha, K. Gayatri, M. S. Yadav, N. C. S. Rao, and B. S. Rao, “Customized deep CNN for foliar disease prediction based on features extracted from apple tree leaves images,” in Proc. Int. Interdisciplinary Humanitarian Conf. Sustainab. (IIHC), Bengaluru, India, 2022, pp. 193–197, doi: 10.1109/IIHC55949.2022.10060555. [28] G. Ketepalli and P. Bulla, “Review on generative deep models and datasets for intrusion detection systems,” Revue d\'Intell. Artif., vol. 34, no. 2, pp. 215–226, Apr. 2020, doi: 10.18280/ria.340213. [29] G. Ketepalli and P. Bulla, “Feature extraction using LSTM autoencoder in network intrusion detection system,” in Proc. 7th Int. Conf. Commun. Electron. Syst. (ICCES), 2022, pp. 744–749, doi: 10.1109/ICCES54183.2022.9835788. [30] M. S. Yadav and R. Kalpana, “Effective dimensionality reduction techniques for network intrusion detection systems based on deep learning,” in Data Intell. Cogn. Informatics (Algorithms for Intelligent Systems), Springer, 2022, pp. 527–538, doi: 10.1007/978-981-16-6460-1_39. [31] K. Gayatri, P. Bulla, and M. S. Yadav, “A two-level hybrid intrusion detection learning method,” in Mach. Intell. Soft Comput. (Advances in Intelligent Systems and Computing, vol. 1280), Springer, 2021, pp. 251–261, doi: 10.1007/978-981-15-9516-5_21. [32] M. S. Yadav, K. Sushma, and K. Gayatri, “Enhanced network intrusion detection using LSTM RNN,” Int. J. Adv. Sci. Technol., vol. 29, no. 5, pp. 7210–7220, 2020. [33] A. Patil and S. Yada, “Performance analysis of anomaly detection of KDD cup dataset in R environment,” Int. J. Appl. Eng. Res., vol. 13, no. 6, pp. 4576–4582, 2018. [34] S. Eeday, S. Goteti, and S. P. Anne, “Experimental investigation of thermal properties of Borassus flabellifer reinforced composites and effect of addition of fly ash,” Int. J. Eng. Trends Technol., vol. 15, no. 8, pp. 379–382, 2014. [35] A. Patil and M. S. Yadav, “Performance analysis of misuse attack data using data mining classifiers,” Int. J. Eng. Technol., vol. 7, no. 4, pp. 261–263, 2018. [36] R. Padmaja and P. R. Challagundla, “Exploring a two-phase deep learning framework for network intrusion detection,” in Proc. IEEE Int. Students’ Conf. Elect., Electron. Comput. Sci. (SCEECS), Bhopal, India, 2024, pp. 1–5, doi: 10.1109/SCEECS61402.2024.10482198.

Copyright

Copyright © 2026 Sireesha Goli, B. Jaya Sujitha, P. Kavitha. 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.