Loading...
Uncertainty Aware Crop Yield Forecasting Under Extreme Weather Conditions Using Hybrid Temporal Models


Journal of Smart and Sustainable Farming

Received On : 01 March 2026

Revised On : 18 April 2026

Accepted On : 30 May 2026

Published On : 22 June 2026

Volume 02, 2026

Pages : 122-138


Abstract

The challenge of forecasting yields is increased and complicated by extreme weather events like heatwaves, droughts, floods and cold snaps, as a forecast that is true on average becomes highly misleading in the seasons when it is needed most by those who need it most: farmers, insurers and planners. A framework for uncertainty-aware forecasting that combines a one-dimensional convolutional front-end, a heteroscedastic Gaussian output, a bidirectional gated recurrent unit and temporal attention, as well as normalizing with split-conformal prediction is presented, followed by presenting five members in a deep ensemble, and calibrating the prediction intervals with normalized split-conformal prediction. The evaluation of the framework is done on a dataset of simulated extreme events over 30 years and 100 regions with a strict temporal split (3000 region-seasons, 24 weekly steps, the number of events increasing with the simulation period). The ensemble outperforms the six point-forecast baselines with a test RMSE of 0.557 t/ha (R² = 0.890) and error in extreme seasons of 0.587 t/ha (gradient boosting = 0.671 t/ha). The 90% intervals of its 90% intervals cover 92.7% of the seasons, compared to 83–84% for constant-width conformal gradient boosting for seasons corresponding to heatwave, drought and compound seasons. The calibrated ensemble maintains 90.2% coverage under the same type of intensified extremes it didn't see in training, compared to 87.5% for the uncalibrated ensemble and 79.7% for gradient boosting. The gains are found primarily in the heteroscedastic output and the ensemble but not the convolutional, bidirectional or attention components and conclusions are constrained by simulated data.

Keywords

Crop Yield Forecasting, Extreme Weather, Uncertainty Quantification, Deep Ensembles, Conformal Prediction, Climate Adaptation.

  1. D. B. Lobell, W. Schlenker, and J. Costa-Roberts, “Climate Trends and Global Crop Production Since 1980,” Science, vol. 333, no. 6042, pp. 616–620, Jul. 2011, doi: 10.1126/science.1204531.
  2. C. Lesk, P. Rowhani, and N. Ramankutty, “Influence of extreme weather disasters on global crop production,” Nature, vol. 529, no. 7584, pp. 84–87, Jan. 2016, doi: 10.1038/nature16467.
  3. E. DeLucia, “Faculty Opinions recommendation of Nonlinear temperature effects indicate severe damages to U.S. crop yields under climate change.,” Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature. H1 Connect, Nov. 27, 2009. doi: 10.3410/f.1168375.630551.
  4. C. Zhao et al., “Temperature increase reduces global yields of major crops in four independent estimates,” Proceedings of the National Academy of Sciences, vol. 114, no. 35, pp. 9326–9331, Aug. 2017, doi: 10.1073/pnas.1701762114.
  5. M. F. Haikal and M. A. Furqon, “Systematic Literature Review : Machine Learning and Deep Learning Aproaches for Crop Yield Prediction Using Remote Sensing Data,” Media Informatika, vol. 25, no. 2, pp. 126–137, Jul. 2026, doi: 10.37595/mediainfo.v25i2.496.
  6. S. Khaki, L. Wang, and S. V. Archontoulis, “A CNN-RNN Framework for Crop Yield Prediction,” Frontiers in Plant Science, vol. 10, Jan. 2020, doi: 10.3389/fpls.2019.01750.
  7. J. You, X. Li, M. Low, D. Lobell, and S. Ermon, “Deep Gaussian Process for Crop Yield Prediction Based on Remote Sensing Data,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31, no. 1, Feb. 2017, doi: 10.1609/aaai.v31i1.11172.
  8. George H. Hargreaves and Zohrab A. Samani, “Reference Crop Evapotranspiration from Temperature,” Applied Engineering in Agriculture, vol. 1, no. 2, pp. 96–99, 1985, doi: 10.13031/2013.26773.
  9. V. Sharma and S. Irmak, “Mapping Spatially Interpolated Precipitation, Reference Evapotranspiration, Actual Crop Evapotranspiration, and Net Irrigation Requirements in Nebraska: Part II. Actual Crop Evapotranspiration and Net Irrigation Requirements,” Transactions of the ASABE, vol. 55, no. 3, pp. 923–936, 2012, doi: 10.13031/2013.41524.
  10. R. Genuer and J.-M. Poggi, “Random Forests,” Random Forests with R, pp. 33–55, 2020, doi: 10.1007/978-3-030-56485-8_3.
  11. J. H. Friedman, “Greedy function approximation: A gradient boosting machine.,” The Annals of Statistics, vol. 29, no. 5, pp. 1189–1232, Oct. 2001, doi: 10.1214/aos/1013203451.
  12. A. Mateo-Sanchis, J. E. Adsuara, M. Piles, J. Munoz-Marí, A. Perez-Suay, and G. Camps-Valls, “Interpretable Long Short-Term Memory Networks for Crop Yield Estimation,” IEEE Geoscience and Remote Sensing Letters, vol. 20, pp. 1–5, 2023, doi: 10.1109/lgrs.2023.3244064.
  13. K. Cho et al., “Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation,” Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1724–1734, 2014, doi: 10.3115/v1/d14-1179.
  14. L. Hussein, P. Johri, A. A. Priya, R. Ramya, J. Karpagam, and A. Devendran, “Crop Yield Forecasting Using Bidirectional Gated Recurrent Unit (Bi-GRU) Networks,” 2025 International Conference on Automation and Computation (AUTOCOM), pp. 224–228, Mar. 2025, doi: 10.1109/autocom64127.2025.10957465.
  15. J. Song, S. Kim, and S. Yoon, “AligNART: Non-autoregressive Neural Machine Translation by Jointly Learning to Estimate Alignment and Translate,” Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 1–14, 2021, doi: 10.18653/v1/2021.emnlp-main.1.
  16. S. Vishwakarma, X. Zhang, and V. Lyubchich, “Unveiling the drivers contributing to global wheat yield shocks through quantile regression,” Artificial Intelligence in Agriculture, vol. 15, no. 3, pp. 564–572, Sep. 2025, doi: 10.1016/j.aiia.2025.03.004.
  17. C. Lee and K. K.-H. Park, “Representing Uncertainty in Property Valuation Through a Bayesian Deep Learning Approach,” Real Estate Management and Valuation, vol. 28, no. 4, pp. 15–23, Dec. 2020, doi: 10.1515/remav-2020-0028.
  18. J. Chen, R. Chen, Y. Feng, M. Tan, P. Chen, and Y. Wu, “On variance estimation of target population created by inverse probability weighting,” Journal of Biopharmaceutical Statistics, vol. 34, no. 5, pp. 661–679, Aug. 2023, doi: 10.1080/10543406.2023.2244593.
  19. B. Klein, D. Meissner, H.-U. Kobialka, and P. Reggiani, “Predictive Uncertainty Estimation of Hydrological Multi-Model Ensembles Using Pair-Copula Construction,” Water, vol. 8, no. 4, p. 125, Mar. 2016, doi: 10.3390/w8040125.
  20. H. Li, “Enhancing Cardiovascular Disease Prediction with Machine Learning: A Comparative Study Using the UCI Heart Disease Dataset,” Proceedings of the 2nd International Conference on Data Analysis and Machine Learning, pp. 295–300, 2024, doi: 10.5220/0013516000004619.
  21. L. Cella, “Distribution-free Inferential Models: Achieving finite-sample valid probabilistic inference, with emphasis on quantile regression,” International Journal of Approximate Reasoning, vol. 170, p. 109211, Jul. 2024, doi: 10.1016/j.ijar.2024.109211.
  22. T. Kaiser and P. Herzog, “A tutorial on distribution-free uncertainty quantification using conformal prediction,” Sep. 2025, doi: 10.31234/osf.io/xzqgt_v1.
  23. S. ABARNA and D. KESAVARAJA, “Dynamic parameter calibration based deep network for paddy yield prediction,” European Journal of Agronomy, vol. 174, p. 127929, Mar. 2026, doi: 10.1016/j.eja.2025.127929.
  24. J. Zheng and S. Zhang, “Decomposing the total uncertainty in wheat modeling: an analysis of model structure, parameters, weather data inputs, and squared bias contributions,” Agricultural Systems, vol. 224, p. 104215, Mar. 2025, doi: 10.1016/j.agsy.2024.104215.
  25. Ms. L. M., “Implementation Using Multiple Linear Regressions with ADAM Optimizer Technique in Neural Network for Crop Prediction-MLRAONN,” International Conference On Contemporary Researches in Engineering, Science, Management & Arts, 2020, p. 12, Feb. 2020, doi: 10.9756/bp2020.1002/12.
  26. S. Sui, J. Zhang, H. Gu, and Y. Chang, “PANet: A multi-scale temporal decoupling network and its high-resolution benchmark dataset for detecting pseudo changes in cropland non-agriculturalization,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 233, pp. 126–143, Mar. 2026, doi: 10.1016/j.isprsjprs.2026.01.029.
  27. M. Singh Boori, K. Choudhary, R. Paringer, and A. Kupriyanov, “Machine learning for yield prediction in Fergana valley, Central Asia,” Journal of the Saudi Society of Agricultural Sciences, vol. 22, no. 2, pp. 107–120, Feb. 2023, doi: 10.1016/j.jssas.2022.07.006.
  28. S. Boppudi and S. Jayachandran, “Improved feature ranking fusion process with hybrid model for crop yield prediction,” Biomedical Signal Processing and Control, vol. 93, Art. no. 106121, Jul. 2024, doi: 10.1016/j.bspc.2024.106121.
CRediT Author Statement

The authors confirm contribution to the paper as follows:

Conceptualization: Zhang Wang and Anandakumar Haldorai; Methodology: Zhang Wang and Anandakumar Haldorai; Software: Zhang Wang; Data Curation: Zhang Wang and Anandakumar Haldorai; Writing- Original Draft Preparation: Zhang Wang and Anandakumar Haldorai; Visualization: Zhang Wang and Anandakumar Haldorai; Investigation: Anandakumar Haldorai; Supervision: Zhang Wang and Anandakumar Haldorai; Validation: Zhang Wang and Anandakumar Haldorai; Writing- Reviewing and Editing: Anandakumar Haldorai; All authors reviewed the results and approved the final version of the manuscript.

Acknowledgements

The authors would like to express their appreciation to the institution for providing a supportive research environment.

Funding

No funding was received to assist with the preparation of this manuscript.

Ethics Declarations

Conflict of interest

The authors have no conflicts of interest to declare that are relevant to the content of this article.

Availability of Data and Materials

The simulator, the experiment code and the generated dataset can be obtained from the corresponding author on reasonable request.

Author Information

Contributions

All authors have equal contribution in the paper and all authors have read and agreed to the published version of the manuscript.

Corresponding Author



Rights and permissions

This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0).
https://creativecommons.org/licenses/by/4.0/.

This license permits unrestricted use, sharing, distribution, reproduction, and adaptation in any medium or format, including for commercial purposes, provided that appropriate credit is given to the original author(s) and the source, a link to the license is provided, and any changes made are indicated.

Copyright

© 2026 Zhang Wang and Anandakumar Haldorai. The author(s) retain copyright of the work. The author(s) grant the Journal of Smart and Sustainable Farming (JSSF) and its publisher, Ansis Publications, the right of first publication and the right to identify itself as the original publisher of the article.

Cite this Article

Zhang Wang and Anandakumar Haldorai, “Uncertainty Aware Crop Yield Forecasting Under Extreme Weather Conditions Using Hybrid Temporal Models”, Journal of Smart and Sustainable Farming, pp. 122-138, 2026, doi: 10.64026/JSSF/2026011.