Simulation-assisted machine learning for operational digital twins. (February 2022)

• Record Type: Journal Article
• Authors: Pylianidis, Christos; Snow, Val; Overweg, Hiske; Osinga, Sjoukje; Kean, John; Athanasiadis, Ioannis N.
• Is Part Of: Environmental modelling & software. Volume 148(2022)
• Publication Date: 2022-02
• Subjects: Machine learning -- Digital twin -- Data availability -- Data resolution -- APSIM -- Metamodel; Environmental monitoring -- Computer programs -- Periodicals; Ecology -- Computer simulation -- Periodicals; Digital computer simulation -- Periodicals; Computer software -- Periodicals; Environmental Monitoring -- Periodicals; Computer Simulation -- Periodicals; Environnement -- Surveillance -- Logiciels -- Périodiques; Écologie -- Simulation, Méthodes de -- Périodiques; Simulation par ordinateur -- Périodiques; Logiciels -- Périodiques; Computer software; Digital computer simulation; Ecology -- Computer simulation; Environmental monitoring -- Computer programs; Periodicals; Electronic journals; 363.70015118
• DOI: 10.1016/j.envsoft.2021.105274
• Languages: English
• ISSNs: 1364-8152

Abstract

Abstract: 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. Highlights: A method to develop operational digital twins with limited data, by combining machine learning with process-based models. . Simulation-assisted machine learning can reduce the amount of required input data. Simulation-assisted machine learning models generalize well in previously unseen conditions. Simulation-assisted machine learning models use lower resolution temporal inputs than process-based models.