A Hybrid Modeling Framework for Crop Prediction Tasks via Dynamic Parameter Calibration and Multi-Task Learning

Solow, William; Pesantez-Cabrera, Paola; Keller, Markus; Khot, Lav; Saisubramanian, Sandhya; Fern, Alan

doi:10.24963/ijcai.2026/826

A Hybrid Modeling Framework for Crop Prediction Tasks via Dynamic Parameter Calibration and Multi-Task Learning

William Solow, Paola Pesantez-Cabrera, Markus Keller, Lav Khot, Sandhya Saisubramanian, Alan Fern

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. AI and Social Good. Pages 7428-7436.

https://doi.org/10.24963/ijcai.2026/826

Keywords

Machine Learning: Machine Learning
Multidisciplinary Topics and Applications: Multidisciplinary Topics and Applications

Abstract

Accurate prediction of crop states (e.g., phenology stages and cold hardiness) is essential for timely farm management decisions such as irrigation, fertilization, and canopy management to optimize crop yield and quality. While traditional biophysical models can be used for season-long predictions, they lack the precision required for site-specific management. Deep learning methods are a compelling alternative, but can produce biologically unrealistic predictions and require large-scale data. We propose a hybrid modeling approach that uses a neural network to parameterize a differentiable biophysical model and leverages multi-task learning for efficient data sharing across crop cultivars in data limited settings. By predicting the parameters of the biophysical model, our approach improves the prediction accuracy while preserving biological realism. Empirical evaluation using real-world and synthetic datasets demonstrates that our method improves prediction accuracy by 60% for phenology and 40% for cold hardiness compared to deployed biophysical models. Project site: https://tinyurl.com/DMC-MTL-Site.

William Solow, Paola Pesantez-Cabrera, Markus Keller, Lav Khot, Sandhya Saisubramanian, and Alan Fern. 2026. A Hybrid Modeling Framework for Crop Prediction Tasks via Dynamic Parameter Calibration and Multi-Task Learning. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 7428–7436. https://doi.org/10.24963/ijcai.2026/826

@inproceedings{ijcai2026p826,
  title     = {A Hybrid Modeling Framework for Crop Prediction Tasks via Dynamic Parameter Calibration and Multi-Task Learning},
  author    = {Solow, William and Pesantez-Cabrera, Paola and Keller, Markus and Khot, Lav and Saisubramanian, Sandhya and Fern, Alan},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {7428--7436},
  year      = {2026},
  month     = {8},
  note      = {AI and Social Good},
  doi       = {10.24963/ijcai.2026/826},
  url       = {https://doi.org/10.24963/ijcai.2026/826},
}

TY  - CPAPER
TI  - A Hybrid Modeling Framework for Crop Prediction Tasks via Dynamic Parameter Calibration and Multi-Task Learning
AU  - Solow, William
AU  - Pesantez-Cabrera, Paola
AU  - Keller, Markus
AU  - Khot, Lav
AU  - Saisubramanian, Sandhya
AU  - Fern, Alan
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 7428
EP  - 7436
DO  - 10.24963/ijcai.2026/826
UR  - https://doi.org/10.24963/ijcai.2026/826
ER  -