EUVIMEDEUVIMED entdecken
Crossref

Science-Guided Multi-Task Deep Learning for Emulating APSIM Simulations for Root-zone Soil Moisture Forecasting

Tanjim Bin Faruk, Abdul Matin, Rupasree Dey, Andrei Bachinin, Shrideep Pallickara, Sangmi Lee Pallickara

Proceedings of the AAAI Symposium Series · 23.06.2026 · 9 (1) · 143-147

DOI: 10.1609/aaaiss.v9i1.42916 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Symposium Series, online erschienen am 23.06.2026. Verfasst von Tanjim Bin Faruk und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Soil moisture is a critical variable for water management, drought monitoring, and crop risk management, yet direct measurements below the surface are sparse and difficult to scale. We present a deep learning framework that forecasts root-zone soil moisture generated with a process-based agroecosystem simulation model, APSIM. Our approach forecasts multi-layer soil moisture profiles down to 1m using static site descriptors and daily meteorological forcings. Our approach unifies (i) large-scale physics-based simulation data generation over diverse counterfactual soil properties, irrigation strategies, and weather information, (ii) a controlled benchmark spanning Temporal Convolutional Networks, and Mamba-style state space models, and (iii) a multi-task training objective that predicts both absolute moisture levels and step-wise changes (deltas). The deltas formulation anchors forecasts to the last observed state and focuses learning on day-to-day process rates, improving stability across depths and forecast steps. Experiments on a large APSIM-derived dataset with 11 depth layers evaluate accuracy under a standard held-out test split, spatial generalization to unseen stations, and temporal generalization to a future year. Across architectures, delta-aware training consistently improves forecasting performance relative to direct level prediction and simple baselines, with the strongest gains appearing under distribution shift.

Zitieren

APA

Faruk, T. B., Matin, A., Dey, R., Bachinin, A., Pallickara, S., & Pallickara, S. L. (2026). Science-Guided Multi-Task Deep Learning for Emulating APSIM Simulations for Root-zone Soil Moisture Forecasting. Proceedings of the AAAI Symposium Series, 9(1), 143-147. https://doi.org/10.1609/aaaiss.v9i1.42916

Vancouver

Faruk TB, Matin A, Dey R, Bachinin A, Pallickara S, Pallickara SL. Science-Guided Multi-Task Deep Learning for Emulating APSIM Simulations for Root-zone Soil Moisture Forecasting. Proceedings of the AAAI Symposium Series. 2026;9(1):143-147. doi:10.1609/aaaiss.v9i1.42916

BibTeX
@article{Faruk2026,
  author = {Faruk, Tanjim Bin and Matin, Abdul and Dey, Rupasree and Bachinin, Andrei and Pallickara, Shrideep and Pallickara, Sangmi Lee},
  title = {Science-Guided Multi-Task Deep Learning for Emulating APSIM Simulations for Root-zone Soil Moisture Forecasting},
  journal = {Proceedings of the AAAI Symposium Series},
  year = {2026},
  volume = {9},
  number = {1},
  pages = {143--147},
  doi = {10.1609/aaaiss.v9i1.42916}
}
Kostenlos starten →