Print Email Facebook Twitter Applying Machine Learning to Learn System Dynamics Models for Urban Systems Title Applying Machine Learning to Learn System Dynamics Models for Urban Systems Author Yin, Rukai (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Yorke-Smith, N. (mentor) Isufi, E. (graduation committee) Heijnen, P.W. (graduation committee) Voorburg, Arie (graduation committee) Degree granting institution Delft University of Technology Date 2020-07-08 Abstract System Dynamics (SD) is an approach to study the nonlinear behaviour of complex systems over time. SD models provide a highlevel understanding of the system and aid in designing policies to achieve specific system behaviours. Conventional SD modelling requires an intensive amount of time, human resources and effort. Applying Machine Learning (ML) techniques benefits the modelling process in saving on resources. It also has the potential to provide insights into the system and prevent subjective ness of the modeller. This work proposes two methodologies, EvoNN and EvoESN, to learn SD models automatically for the urban system from observations under different levels of prior knowledge. EvoNN solves the automated equation formulation task for a Causal Link Diagram (CLD) and annotates it with Shallow Neural Networks (SNNs) as surrogate equations. The annotated CLD can be further used in simulating the system behaviour. We provide experimental results on a realworld urban system in Amsterdam as well as the evaluation of the simulation results. The second methodology, EvoESN learns both the structure and the quantitative relations in the model without the prior knowledge about the structure. Trained using observation data, the EvoESN produces satisfactory results on the realworld urban system. We further incorporate the judgement from the domain expert to evaluate the learned model. Applied on a more complex system, EvoESN shows solid reliability and scalability to handle large datasets. Both EvoNN and EvoESN stand as promising supportive tools for SD modellers and remain robust even when lacking system observations. Subject system dynamicsautomated modellingmachine learningdeep learning To reference this document use: http://resolver.tudelft.nl/uuid:f0ff8178-d9bd-4265-bf9f-33ae188fd917 Part of collection Student theses Document type master thesis Rights © 2020 Rukai Yin Files PDF Master_Thesis_Rukai_Yin.pdf 3.11 MB Close viewer /islandora/object/uuid:f0ff8178-d9bd-4265-bf9f-33ae188fd917/datastream/OBJ/view