AgResearch
Browse

Simulation-assisted machine learning for operational digital twins

Download (11.02 MB)
journal contribution
posted on 2023-05-03, 20:17 authored by Christos Pylianidis, Val SnowVal Snow, Hiske Overweg, Sjoukje Osinga, John KeanJohn Kean, Ioannis Athanasiadis
In the environmental sciences, there are ongoing efforts to combine multiple models to assist the analysis of complex systems. Combining process-based models, which have encoded domain knowledge, with machine learning models, which can flexibly adapt to input data, can improve modeling capabilities. However, both types of models have input data limitations. We propose a methodology to overcome these issues by using a process-based model to generate data, aggregating them to a lower resolution to mimic real situations, and developing machine learning models using a fraction of the process-based model inputs. We showcase this method with a case study of pasture nitrogen response rate prediction. We train models of different scales and test them in sampled and unsampled location experiments to assess their practicality in terms of accuracy and generalization. The resulting models provide accurate predictions and generalize well, showing the usefulness of the proposed method for tactical decision support.

History

Rights statement

© 2021 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/)

Language

  • English

Does this contain Māori information or data?

  • No

Publisher

Elsevier

Journal title

Environmental Modelling & Software

ISSN

1364-8152

Citation

Pylianidis, C., Snow, V., Overweg, H., Osinga, S., Kean, J., & Athanasiadis, I. N. (2022). Simulation-assisted machine learning for operational digital twins. Environmental Modelling & Software, 148, 105274. https://doi.org/10.1016/j.envsoft.2021.105274

Usage metrics

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC