Search

Menu
Search
in Ecology

Reinforcement learning based dynamic vegetation index formulation for rice crop stress detection using satellite and mobile imagery

50 Views


Abstract

Timely crop stress detection is essential for safeguarding yields and promoting sustainable agriculture. Traditional vegetation indices (e.g., NDVI, EVI) are widely used but remain static, crop-agnostic, and often insensitive to early stress signals. This study proposed RL-VI, a reinforcement learning-based framework that dynamically formulates vegetation indices optimized for rice stress detection. Unlike existing methods, RL-VI integrates Sentinel-2 multispectral imagery with smartphone-captured RGB data, creating the first cross-platform environment where vegetation indices are learned rather than predefined. The reinforcement learning agent adaptively selects stress-sensitive spectral band combinations guided by classification rewards. Experiments on real-world rice fields in Tamil Nadu, India, and benchmark datasets (Indian Pines, wheat salt stress) show that RL-VI achieves an overall accuracy of 89.4% and F1-score of 0.88, outperforming static and machine-learned indices by up to 12%. Importantly, RL-VI enables early stress detection up to 10 14 days before visible symptoms, providing actionable lead time for intervention. The proposed framework is computationally lightweight and scalable to UAV or edge devices, offering a farmer-ready tool for precision agriculture, bridging field-level mobile sensing with satellite monitoring for low-cost, real-time crop health management. Statistical validation using ANOVA (F = 88.24, p < 0.001) and pairwise t-tests (p < 0.001) confirmed RL-VI’s superiority, while SHAP analyses emphasized the physiological significance of red-edge and SWIR bands in stress discrimination.

Similar content being viewed by others

Refining grapevine vegetation status by utilizing grassland and remote sensing data

Article
Open access
27 August 2025

Beyond the traditional NDVI index as a key factor to mainstream the use of UAV in precision viticulture

Article
Open access
01 February 2021

Hyperspectral discrimination of vegetable crops grown under organic and conventional cultivation practices: a machine learning approach

Article
Open access
06 March 2025

Data availability

All datasets used in this study are openly accessible. The Mobile RGB dataset, consisting of field-captured rice canopy images collected by the authors at Polur, Tamil Nadu, India, is publicly available on Kaggle under a CC BY-NC 4.0 license (DOI: [https://doi.org/10.34740/kaggle/dsv/14105754](https:/doi.org/10.34740/kaggle/dsv/14105754)). Sentinel-2 multispectral imagery was obtained from the European Space Agency Copernicus Open Access Hub via Google Earth Engine. Benchmark hyperspectral datasets (Indian Pines and Wheat Salt Stress) are publicly available from their respective repositories. All processed data generated during this study are available from the corresponding author upon reasonable request.

Code availability

All custom code developed for this work including the RL-VI (Reinforcement Learning–based Vegetation Index) formulation algorithm, image preprocessing scripts, vegetation index computation modules, model training pipelines, and evaluation routines is openly accessible in a public GitHub repository. The code is available without restriction for non-commercial research use and fully available at Github Repository (https://github.com/Poornisrm/Vegetation-Index.git).

References

  1. Moharrami, M., Attarchi, S., Gloaguen, R. & Alavipanah, S. K. Integration of Sentinel-1 and Sentinel-2 Data for Ground Truth Sample Migration for Multi-Temporal Land Cover Mapping. Remote Sens., 16(9). https://doi.org/10.3390/rs16091566 (2024).

  2. Reis Pereira, M. et al. Plant disease diagnosis based on hyperspectral sensing: comparative analysis of parametric spectral vegetation indices and nonparametric Gaussian process classification approaches. Agronomy 14 (3), https://doi.org/10.3390/agronomy14030493 (2024).

  3. Fan, L. et al. A temporal-spatial deep learning network for winter wheat mapping using time-series Sentinel-2 imagery. ISPRS J. Photogrammetry Remote Sens. 214, 4864. https://doi.org/10.1016/j.isprsjprs.2024.06.005 (2024).

    Google Scholar 

  4. Jiang, X. et al. An automatic rice mapping method based on an integrated time-series gradient boosting tree using GF-6 and sentinel-2 images. GIScience Remote Sens. 61 (1), https://doi.org/10.1080/15481603.2024.2367807 (2024).

  5. Xu, H., Song, J. & Zhu, Y. Evaluation and Comparison of Semantic Segmentation Networks for Rice Identification Based on Sentinel-2 Imagery. Remote Sens. 15(6), https://doi.org/10.3390/rs15061499 (2023).

  6. Yu, L. et al. Research on machine Learning-Based extraction and classification of crop planting information in arid irrigated areas using Sentinel-1 and Sentinel-2 Time-Series data. Agric. (Switzerland). 15 (11), https://doi.org/10.3390/agriculture15111196 (2025).

  7. Herzig, P. et al. Evaluation of Rgb and multispectral unmanned aerial vehicle (Uav) imagery for high-throughput phenotyping and yield prediction in barley breeding. Remote Sens. 13 (14), https://doi.org/10.3390/rs13142670 (2021).

  8. Sun, Y., Wang, B. & Zhang, Z. Improving leaf area index Estimation with chlorophyll insensitive multispectral Red-Edge vegetation indices. IEEE J. Sel. Top. Appl. Earth Observations Remote Sens. 16, 35683582. https://doi.org/10.1109/JSTARS.2023.3262643 (2023).

    Google Scholar 

  9. Aslan, M. F., Sabanci, K. & Aslan, B. Artificial Intelligence Techniques in Crop Yield Estimation Based on Sentinel-2 Data: A Comprehensive Survey. In Sustainability (Switzerland) (Vol. 16, Issue 18). Multidisciplinary Digital Publishing Institute (MDPI). (2024). https://doi.org/10.3390/su16188277

  10. Samsuddin Sah, S., Abdul Maulud, K. N., Sharil, S., Karim, A., Pradhan, B. & O., & Monitoring of three stages of paddy growth using multispectral vegetation index derived from UAV images. Egypt. J. Remote Sens. Space Sci. 26 (4), 989998. https://doi.org/10.1016/j.ejrs.2023.11.005 (2023).

    Google Scholar 

  11. Sulaiman, N. et al. N., W. F. The Application of Hyperspectral Remote Sensing Imagery (HRSI) for Weed Detection Analysis in Rice Fields: A Review. In Applied Sciences (Switzerland) (12 (5), MDPI. https://doi.org/10.3390/app12052570 (2022).

  12. Zhang, G., Xu, T. & Tian, Y. Hyperspectral imaging-based classification of rice leaf blast severity over multiple growth stages. Plant. Methods. 18 (1), https://doi.org/10.1186/s13007-022-00955-2 (2022).

  13. Farmonov, N. et al. Crop Type Classification by DESIS Hyperspectral Imagery and Machine Learning Algorithms, in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 16, 1576–1588, https://doi.org/10.1109/JSTARS.2023.3239756 (2023).

  14. Singh, G. & Sharma, S. Enhancing precision agriculture through cloud based transformative crop recommendation model. Sci. Rep. 15, 9138. https://doi.org/10.1038/s41598-025-93417-3 (2025).

    Google Scholar 

  15. Singh, S. et al. A predictive framework using advanced machine learning approaches for measuring and analyzing the impact of synthetic agrochemicals on human health. Sci. Rep. 15, 15544. https://doi.org/10.1038/s41598-025-00509-1 (2025).

    Google Scholar 

  16. Singh, G. & Sharma, S. Revolutionizing cloud-IoT and UAV-assisted framework to analyze soil for cultivation in agricultural landscapes. Proc. Indian Natl. Sci. Acad. https://doi.org/10.1007/s43538-025-00489-w (2025).

    Google Scholar 

  17. Upadhyay, N. & Gupta, N. Detecting fungi-affected multi-crop disease on heterogeneous region dataset using modified resnext approach. Environ. Monit. Assess. 196, 610. https://doi.org/10.1007/s10661-024-12790-0 (2024).

    Google Scholar 

  18. Upadhyay, N. & Bhargava, A. Artificial intelligence in agriculture: applications, approaches, and adversities across pre-harvesting, harvesting, and post-harvesting phases. Iran. J. Comput. Sci. 8, 749772. https://doi.org/10.1007/s42044-025-00264-6 (2025).

    Google Scholar 

  19. Upadhyay, N., Gupta, N. & SegLearner A segmentation based approach for predicting disease severity in infected leaves. Multimed Tools Appl. 84, 42523 42546. https://doi.org/10.1007/s11042-025-20838-7 (2025).

    Google Scholar 

  20. Upadhyay, N., Sharma, D. K. & Bhargava, A. 3SW-Net: A feature fusion network for semantic weed detection in precision agriculture. Food Anal. Methods. 18, 2241 2257. https://doi.org/10.1007/s12161-025-02852-5 (2025).

    Google Scholar 

  21. Kurihara, J., Nagata, T. & Tomiyama, H. Rice yield prediction in different growth environments using unmanned aerial Vehicle-Based hyperspectral imaging. Remote Sens. 15 (8), https://doi.org/10.3390/rs15082004 (2023).

  22. Karmakar, P. et al. Crop monitoring by multimodal remote sensing: A review. In Remote Sensing Applications: Society and Environment (Vol. 33). Elsevier B.V. https://doi.org/10.1016/j.rsase.2023.101093 (2024).

  23. Albahar, M. A Survey on Deep Learning and Its Impact on Agriculture: Challenges and Opportunities. In Agriculture (Switzerland) (Vol. 13, Issue 3). MDPI. https://doi.org/10.3390/agriculture13030540 (2023).

  24. Mou, L. et al. Deep reinforcement learning for band selection in hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 60 https://doi.org/10.1109/TGRS.2021.3067096 (2022).

  25. Wu, B. et al. Challenges and opportunities in remote sensing-based crop monitoring: a review. In National Science Review (10 (4)). Oxford University Press. https://doi.org/10.1093/nsr/nwac290 (2023).

  26. Zhang, J. et al. UAV as a bridge: mapping key rice growth stage with Sentinel-2 imagery and novel vegetation indices. Remote Sens. 17 (13), 2180. https://doi.org/10.3390/rs17132180 (2025).

    Google Scholar 

  27. Virnodkar, S. S., Pachghare, V. K., Patil, V. C. & Jha, S. K. Remote sensing and machine learning for crop water stress determination in various crops: a critical review. In Precision Agriculture (21 (5), 1121 1155). Springer. (2020). https://doi.org/10.1007/s11119-020-09711-9

  28. Liu, L. et al. A disease index for efficiently detecting wheat fusarium head blight using Sentinel-2 multispectral imagery. IEEE Access. 8, 5218152191. https://doi.org/10.1109/ACCESS.2020.2980310 (2020).

    Google Scholar 

  29. Zhao, D. et al. Early detection of rice leaf blast disease using unmanned aerial vehicle remote sensing: A novel approach integrating a new spectral vegetation index and machine learning. Agronomy 14 (3), https://doi.org/10.3390/agronomy14030602 (2024).

  30. Sato, Y., Tsuji, T. & Matsuoka, M. Estimation of rice plant coverage using Sentinel-2 based on UAV-Observed data. Remote Sens. 16 (9), https://doi.org/10.3390/rs16091628 (2024).

  31. Yu, Y. et al. Early mapping method for different planting types of rice based on planet and Sentinel-2 satellite images. Agronomy 14 (1), https://doi.org/10.3390/agronomy14010137 (2024).

  32. Tian, H. et al. A novel spectral index for automatic Canola mapping by using Sentinel-2 imagery. Remote Sens. 14 (5). https://doi.org/10.3390/rs14051113 (2022).

  33. Choshi, T. J., Dhau, I. & Mashao, F. Enhancing maize streak virus detection: a comparative analysis of Sentinel-2 MSI and Landsat 9 OLI data across vegetative and reproductive growth stages. Geocarto Int. 40 (1). https://doi.org/10.1080/10106049.2025.2480701 (2025).

  34. Baldin, C. M. & Casella, V. M. Comparison of planetscope and Sentinel-2 spectral channels and their alignment via linear regression for enhanced index derivation. Geosci. (Switzerland). 15 (5). https://doi.org/10.3390/geosciences15050184 (2025).

  35. Liu, L., Xie, Y., Zhu, B. & Song, K. Rice leaf chlorophyll content Estimation with different crop coverages based on Sentinel-2. Ecol. Inf. 81 https://doi.org/10.1016/j.ecoinf.2024.102622 (2024).

  36. Cong, C. et al. Research on Monitoring Methods for the Appropriate Rice Harvest Period Based on Multispectral Remote Sensing. Discrete Dynamics in Nature and Society, 2022. https://doi.org/10.1155/2022/1519667 (2022).

  37. Zhang, H. et al. A novel red-edge spectral index for retrieving the leaf chlorophyll content. Methods Ecol. Evol. 13 (12), 27712787. https://doi.org/10.1111/2041-210X.13994 (2022).

    Google Scholar 

  38. Tian, J., Tian, Y., Cao, Y., Wan, W. & Liu, K. Research on rice fields extraction by NDVI difference method based on Sentinel data. Sensors 23 (13), https://doi.org/10.3390/s23135876 (2023).

  39. Luo, S. et al. Remotely sensed prediction of rice yield at different growth durations using UAV multispectral imagery. Agric. (Switzerland). 12 (9), https://doi.org/10.3390/agriculture12091447 (2022).

  40. Sharma, V., Honkavaara, E., Hayden, M. & Kant, S. UAV remote sensing phenotyping of wheat collection for response to water stress and yield prediction using machine learning. Plant. Stress. 12 https://doi.org/10.1016/j.stress.2024.100464 (2024).

  41. Ren, C., Kim, D. K. & Jeong, D. A survey of deep learning in agriculture: techniques and their applications. J. Inform. Process. Syst. 16 (5), 10151033. https://doi.org/10.3745/JIPS.04.0187 (2020).

    Google Scholar 

  42. Liao, Z. Q. et al. A double-layer model for improving the Estimation of wheat canopy nitrogen content from unmanned aerial vehicle multispectral imagery. J. Integr. Agric. 22 (7), 22482270. https://doi.org/10.1016/j.jia.2023.02.022 (2023).

    Google Scholar 

  43. Banerjee, B. P., Sharma, V., Spangenberg, G. & Kant, S. Machine learning regression analysis for Estimation of crop emergence using multispectral UAV imagery. Remote Sens. (Basel). 13 (15), 2918 (2021). https://www.mdpi.com/2072-4292/13/15/2918

    Google Scholar 

  44. Yu, W. et al. Evaluation of red-edge features for identifying subtropical tree species based on Sentinel-2 and Gaofen-6 time series. Int. J. Remote Sens. 43 (8), 3003. https://doi.org/10.1080/01431161.2022.2079018 (2022).

    Google Scholar 

  45. Qiu, Z. et al. Accurate prediction of 327 rice variety growth period based on unmanned aerial vehicle multispectral remote sensing. Drones 8 (11), 665. https://doi.org/10.3390/drones8110665 (2024).

    Google Scholar 

  46. Li, Z., Feng, X., Li, J., Wang, D., Hong, W., Qin, J., … Chen, S. (2024). Time Series Field Estimation of Rice Canopy Height Using an Unmanned Aerial Vehicle-Based RGB/Multispectral Platform. Agronomy, 14(5), 883. https://doi.org/10.3390/agronomy14050883.

  47. Brinkhoff, J. et al. Forecasting field rice grain moisture content using Sentinel-2 and weather data. Precision Agric. 26, 28. https://doi.org/10.1007/s11119-025-10228-2 (2025).

    Google Scholar 

  48. Sári-Barnácz, F. E. et al. Monitoring Helicoverpa armigera damage with PRISMA hyperspectral imagery: first experience in maize and comparison with Sentinel-2 imagery. Remote Sens. 16 (17), 3235. https://doi.org/10.3390/rs16173235 (2024).

    Google Scholar 

  49. Darra, N., Espejo-Garcia, B., Psiroukis, V., Psomiadis, E. & Fountas, S. Spectral bands vs. Vegetation indices: an automl approach for processing tomato yield predictions based on Sentinel-2 imagery. Smart Agricultural Technol. 100805. https://doi.org/10.1016/j.atech.2025.100805 (2025).

  50. Khosravi, I. Towards sustainable agriculture in Iran using a machine learning-driven crop mapping framework. Eur. J. Remote Sens. 58 (1), https://doi.org/10.1080/22797254.2025.2490787 (2025).

  51. Botero-Valencia, J. et al. Machine learning in sustainable agriculture: systematic review and research perspectives. Agriculture 15 (4), 377. https://doi.org/10.3390/agriculture15040377 (2025).

    Google Scholar 

  52. Sumantra Chatterjee, G. S., Baath, B. R., Sapkota, K. C., Flynn, D. R. & Smith Enhancing LAI estimation using multispectral imagery and machine learning: A comparison between reflectance-based and vegetation indices-based approaches, Computers and Electronics in Agriculture, 230, 2025, 109790,ISSN 0168–1699,https://doi.org/10.1016/j.compag.2024.109790

  53. Ou, C. et al. Using machine learning methods combined with vegetation indices and growth indicators to predict seed yield of Bromus inermis. Plants 13 (6), 773. https://doi.org/10.3390/plants13060773 (2024).

    Google Scholar 

  54. Yang Xu, Y. et al. A deep learning model based on RGB and hyperspectral images for efficiently detecting tea green leafhopper damage symptoms. Smart Agricultural Technol. Volume. 10, 2772–3755. https://doi.org/10.1016/j.atech.2025.100817 (2025).

    Google Scholar 

  55. Patel, U. & Patel, V. Active learning-based hyperspectral image classification: a reinforcement learning approach. J. Supercomput. 80, 2461 2486. https://doi.org/10.1007/s11227-023-05568-7 (2024).

    Google Scholar 

  56. Fu, B., Sun, X., Cui, C., Zhang, J. & Shang, X. Structure-preserved and weakly redundant band selection for hyperspectral imagery. IEEE J. Sel. Top. Appl. Earth Observations Remote Sens. https://doi.org/10.1109/JSTARS.2024.3425906 (2024).

    Google Scholar 

  57. Yang, J. X., Zhou, J., Wang, J., Tian, H. & Liew, A. W. C. LiDAR-Guided Cross-Attention Fusion for Hyperspectral Band Selection and Image Classification, in IEEE Transactions on Geoscience and Remote Sensing, 62, 1–15, 5515815, https://doi.org/10.1109/TGRS.2024.3389651 (2024).

Download references

Acknowledgements

The authors would like to thank their supervisor for the guidance and constructive suggestions that significantly contributed to this work. The authors also acknowledge SRM Institute of Science and Technology, VADAPALANI campus for providing institutional support and research facilities essential for conducting this research.

Funding

This research received no specific grant from any funding agency in the public, commercial, or not-for-profit sectors.

Author information

Authors and Affiliations

  1. Department of Electronics and Communication Engineering, Faculty of Engineering and Technology, SRM Institute of Science and Technology, Vadapalani Campus, Chennai, 600026, India

    Poornima Seralathan & A. Shirly Edward

Authors

  1. Poornima Seralathan
    View author publications

    Search author on:PubMed Google Scholar

  2. A. Shirly Edward
    View author publications

    Search author on:PubMed Google Scholar

Contributions

S.P conceived the study and developed the RL-VI framework and contributed to data collection, analysis, and validation. A.S assisted in implementation, visualization, and manuscript preparation. All authors reviewed and approved the final manuscript.

Corresponding author

Correspondence to
Poornima Seralathan.

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/.

Reprints and permissions

About this article

Cite this article

Seralathan, P., Edward, A.S. Reinforcement learning based dynamic vegetation index formulation for rice crop stress detection using satellite and mobile imagery.
Sci Rep (2025). https://doi.org/10.1038/s41598-025-33386-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1038/s41598-025-33386-9

Keywords

  • Reinforcement learning
  • Vegetation index (VI)
  • Sentinel-2
  • Crop stress detection
  • Precision agriculture
  • Hyperspectral/Multispectral remote sensing

Source: Ecology - nature.com

Widespread heat stress will become the norm in a warming Southeast Asia

Flora and vegetation of fallow lands invaded by the black Cherry Padus serotina (Ehrh.) Borkh. in Lower Silesia (SW Poland)

This portal is not a newspaper as it is updated without periodicity. It cannot be considered an editorial product pursuant to law n. 62 of 7.03.2001. The author of the portal is not responsible for the content of comments to posts, the content of the linked sites. Some texts or images included in this portal are taken from the internet and, therefore, considered to be in the public domain; if their publication is violated, the copyright will be promptly communicated via e-mail. They will be immediately removed.

Back to Top
Close