Research articleOpen accessVol. 14, Issue 10, October 2026
- Received
- 3 September 2026
- Accepted
- 16 September 2026
- Published
- 3 October 2026
- Licence
- CC BY 4.0
Abstract
Environmental sensors can indicate conditions associated with crop disease, but a sensor reading alone cannot confirm an infection. This methodological paper develops an explainable machine learning framework for assessing rice disease risk in Chhattisgarh using time-stamped Internet of Things (IoT) observations. It defines field–date observations, a seven-day warning horizon, expert-confirmed outcomes and predictors derived only from earlier measurements. Random Forest, a support vector machine and a seasonal baseline are specified for comparison. The evaluation design separates fields and later periods during validation and examines discrimination, probability calibration, alert burden and model explanations. The contribution is a reproducible protocol for evaluating a field warning system; no new Chhattisgarh field dataset or verified predictive performance is claimed.
Keywords: Chhattisgarh, rice disease, Internet of Things, Random Forest, explainable artificial intelligence, probability calibration, field validation
References
[1] Indian Council of Agricultural Research. “Chhattisgarh,” state agricultural profile. https://www.icar.gov.in/node/17261 (accessed 24 September 2026).
[2] S. P. Mohanty, D. P. Hughes, and M. Salathé, “Using Deep Learning for Image-Based Plant Disease Detection,” Frontiers in Plant Science, vol. 7, article 1419, 2016. doi:10.3389/fpls.2016.01419.
[3] S. M. Lundberg and S.-I. Lee, “A Unified Approach to Interpreting Model Predictions,” Advances in Neural Information Processing Systems, vol. 30, 2017. https://papers.nips.cc/paper/2017/hash/8a20a8621978632d76c43dfd28b67767-Abstract.html.
[4] scikit-learn developers, “Cross-validation: evaluating estimator performance,” documentation, section on grouped cross-validation. https://scikit-learn.org/stable/modules/cross_validation.html (accessed 24 September 2026).
[5] scikit-learn developers, “Probability calibration,” documentation. https://scikit-learn.org/stable/modules/calibration.html (accessed 24 September 2026).
[6] scikit-learn developers, “Permutation feature importance,” documentation. https://scikit-learn.org/stable/modules/permutation_importance.html (accessed 24 September 2026).
How to cite
Preeti Mishra, Dr. Anupa Sinha (2026). Explainable Prediction of Crop Disease Risk Using IoT Based Environmental Data: A Field Oriented Machine Learning Framework for Chhattisgarh. International Journal of Research in Modern Engineering & Emerging Technology, 14(10), 1-5. https://doi.org/10.63345/ijrmeet.org.v14.i10.1
Licence
This article is open access, published under the CC BY 4.0 licence. Copyright remains with the authors.