Zum Inhalt springen
Technische Universität München
Foto von Xia Chen

Dr.-Ing. Xia Chen

About

Dr.-Ing. Xia Chen is a Postdoctoral Fellow at the TUM Georg Nemetschek Institute (GNI), supported by the GNI Postdoc Program. His research lies at the intersection of human-AI alignment, knowledge-integrated machine learning, and bio-inspired adaptive intelligence, aiming to develop AI systems that enhance—rather than replace—human decision-making, creativity, and autonomy in engineering and scientific contexts. His work explores how artificial systems can dynamically align with human cognition, values, and the evolving complexity of real-world environments. He applies this approach to domains such as energy-efficient design, symbolic neural networks for physical modeling, and causal decision support in engineering workflows.

Dr. Chen earned his Ph.D. with summa cum laude distinction from Leibniz University Hannover and TU Berlin. His dissertation, “Beyond Predictions: Alignment between Prior Knowledge and Machine Learning for Human-Centered Augmented Intelligence”, laid the theoretical and methodological groundwork for alignment across decision processes, methodological paradigms, and interaction patterns. As a Visiting Scholar at UC Berkeley’s Center for the Built Environment (CBE), he investigated how causal inference and AI can jointly support energy-aware design and system-level reasoning.

He has contributed to several national research initiatives (DFG, BMBF), with projects ranging from component-based machine assistance to forecasting frameworks for energy systems. Earlier, at the E.ON Energy Research Center (RWTH Aachen), he worked on meta-neural network ensembles for renewable prediction and economic evaluations of the German Energy Transition. He also brings experience from industry and startup collaborations in sustainable infrastructure, and actively serves as a reviewer and committee member for venues such as Advanced Engineering Informatics, Energy and Buildings, EG-ICE, and IBPSA.

Research

  • Human-AI Alignment
  • Knowledge Representation and Reasoning
  • Machine Learning
  • AI in the Built Environment

Further information

2026

  • Chen, X. and Sun, R. and Geyer, P. and Borrmann, A. and Schiavon S.: From ‘What-is’ to ‘What-if’ in human-factor analysis: A post-occupancy evaluation case. Building and Environment 292, 2026, / mehr…
  • Chen, Xia: Dynamical alignment: a principle for adaptive neural computation. Neuromorphic Computing and Engineering 6 (1), 2026, / mehr…
  • Dalach, A. And Chen, X. And Borrmann, A.: Workflow-Oriented Convex Decomposition of 2D Building Geometry. Proc. of the 33rd International Workshop on Intelligent Computing in Engineering, 2026 mehr…
  • Jang, S., Chen, X.,; Borrmann, A.: Front-Loading Cost Estimation in Early-Stage BIM Design. Proceedings of Computing in Civil Engineering 2026, 2026 mehr…
  • Napps, D.; Staudt, J.; Saluz, U.; Chen, X.; Steiner, D.; Zong, C.; Deghim, F.; Lang, W.; Geyer, P.; Schnellenbach-Held, M.; Petzold, F.; Borrmann, A.; König, M.: Evaluation of Building Design Variants in Early Phases on the Basis of Adaptive Detailing Strategies. Buildings 16 (4), 2026, 685 mehr…

[D] Chen, X. (2024). Beyond predictions: alignment between prior knowledge and machine learning for human-centric augmented intelligence, Doctoral dissertation. https://doi.org/10.15488/17976

 

[J11] Chen, X., Lv, G., Zhuang, X., Duarte, C., Schiavon, S., & Geyer, P. (2025). Integrating symbolic neural networks with building physics: A study and proposal. Journal of Building Engineering, 113033. https://doi.org/10.1016/j.jobe.2025.113033

[J10] Chen, X., Rex, A., Woelke, J., Eckert, C., Bensmann, B., Hanke-Rauschenbach, R., & Geyer, P. (2024). Machine learning in proton exchange membrane water electrolysis — A knowledge-integrated framework. Applied Energy, 371, 123550. https://doi.org/10.1016/j.apenergy.2024.123550

[J9] Chen, X., Singh, M.M. & Geyer, P., (2024). Utilizing domain knowledge: robust machine learning for building energy performance prediction with small, inconsistent datasets. Knowledge-Based Systems, p.111774. https://doi.org/10.1016/j.knosys.2024.111774

[J8] Chen, X., Teng, X., Chen, H., Pan, Y., & Geyer, P. (2024). Toward reliable signals decoding for electroencephalogram: A benchmark study to EEGNeX. Biomedical Signal Processing and Control, 87, 105475. https://doi.org/10.1016/j.bspc.2023.105475

[J7] Geyer, P., Singh, M. M., & Chen, X. (2024). Explainable AI for engineering design: A unified approach of systems engineering and component-based deep learning demonstrated by energy-efficient building design. Advanced Engineering Informatics, 62, 102843. https://doi.org/10.1016/j.aei.2024.102843

[J6] Chen, X., Sun, R., Saluz, U., Schiavon, S., & Geyer, P. (2023). Using causal inference to avoid fallouts in data-driven parametric analysis: A case study in the architecture, engineering, and construction industry. Developments in the Built Environment, 100296. https://doi.org/10.1016/j.dibe.2023.100296

[J5] Chen, X., Abualdenien, J., Singh, M. M., Borrmann, A., & Geyer, P. (2022). Introducing causal inference in the energy-efficient building design process. Energy and Buildings, 277, 112583. https://doi.org/10.1016/j.enbuild.2022.112583

[J4] Chen, X., & Geyer, P. (2022). Machine assistance in energy-efficient building design: A predictive framework toward dynamic interaction with human decision-making under uncertainty. Applied Energy, 307, 118240. https://doi.org/10.1016/j.apenergy.2021.118240

[J3] Chen, X., Guo, T., Kriegel, M., & Geyer, P. (2022). A hybrid-model forecasting framework for reducing the building energy performance gap. Advanced Engineering Informatics, 52, 101627. https://doi.org/10.1016/j.aei.2022.101627

[J2] Chen X., Zhang Y., & Cai X. (2022). Frontiers of carbon neutrality in EU-German building sector, Heating Ventilating & Air Conditioning, TU-023; X322. 

[J1] Zong, C., Chen, X., Fatma, D., Johannes, S., Geyer, P., & Werner, L. (2023). A holistic two-stage decision-making methodology of passive and active building design strategies under uncertainty. Building and Environment, 111211. https://doi.org/10.1016/j.buildenv.2024.111211

 

[C8] Chen, X., & Geyer, P. (2023). Sustainability recommendation system for building design alternatives under multi-objective scenarios. In 30th International Workshop on Intelligent Computing in Engineering, EG-ICE 2023, London, UK.

[C7] Chen, X., & Geyer, P. (2023). Pathway toward prior knowledge-integrated machine learning in engineering. In 18th International IBPSA conference and Exhibition, Building Simulation 2023, Shanghai, China. https://doi.org/10.26868/25222708.2023.1481

[C6] Guo, T., Chen, X., Geyer, P., & Kregel, M. (2023). Performance investigation of different topology organizations in district heating systems with component-based machine learning. In 18th International IBPSA conference and Exhibition, Building Simulation 2023, Shanghai, China. https://doi.org/10.26868/25222708.2023.1188

[C5] Wang, S., Chen, X., & Geyer, P. (2023). Feasibility Analysis of POD and Deep-autoencoder for Indoor Environment CFD Prediction. In 18th International IBPSA conference and Exhibition, Building Simulation 2023, Shanghai, China. https://doi.org/10.26868/25222708.2023.1227

[C4] Chen X., Cai X., Kümpel A., Müller D., & Geyer P., (2022). Dynamic Feedforward Strategy Development for Building Heating System based on AI Forecasting and Simulation. In Passive and Low Energy Architecture, PLEA 2022, Santiago de Chile, Chile. https://doi.org/10.48550/arXiv.2302.10179

[C3] Chen X., Saluz U., Staudt J., Margesin M., Lang W., & Geyer P. (2022). Integrated data-driven and knowledge-based performance evaluation for machine assistance in building design decision support, In 29th International Workshop on Intelligent Computing in Engineering, EG-ICE 2022. Aarhus, Denmark. https://doi.org/10.7146/aul.455.c202

[C2] Chen, X., Guo, T., & Geyer, P. (2021). A hybrid-model forecasting framework for reducing the building energy performance gap. In 28th International Workshop on Intelligent Computing in Engineering, EG-ICE 2021. Berlin, Germany, 2021, special issue on Advanced Engineering Informatics. https://doi.org/10.14279/depositonce-12021

[C1] Chen, X., Singh, M.M. & Geyer, P. (2021). Component-based machine learning for predicting representative time-series of energy performance in building design. In 28th International Workshop on Intelligent Computing in Engineering, EG-ICE 2021. Berlin, Germany. https://doi.org/10.14279/depositonce-12021

To top