We enhance machine learning algorithms for learning model parameters in complex systems represented by differential equations with domain decomposition methods. The study evaluates the performance of two approaches, namely (vanilla) Physics-Informed Neural Networks (PINNs) and Finite Basis Physics-Informed Neural Networks (FBPINNs), in learning the dynamics of test models with a quasi-stationary longtime behavior. We test the approaches for data sets in different dynamical regions and with varying noise level. As results, the FBPINN approach better captures the overall dynamical behavior compared to the vanilla PINN approach, even in cases with data only from a time domain with quasi-stationary dynamics.

This publication is the result of an international and interdisciplinary expert meeting at Technische Universität Berlin, in March 2020. The aim of the expert meeting was to collaboratively write and publish a book, within five days, on the central question: Which organizational structures and processes at universities support a strategic as well as innovative campus development?

As experts with an interdisciplinary background including the social sciences, public real estate, urban planning, architecture and landscape architecture, we could examine the question from a holistic perspective and gain new insights.

The resulting manifesto states necessary steps and strategies to create innovative and sustainable hybrid environments for universities. It addresses all decision makers – executives, practitioners and contributors alike – as all of us face the challenge of limited resources and needing to do more with less.