# Utilizing Domain Knowledge: Robust Machine Learning for Building Energy Prediction with Small, Inconsistent Datasets

arXiv: https://arxiv.org/abs/2302.10784 · HTML: https://mlsanity.com/paper/2302.10784/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 45 references that are in the map.
- First posted on arXiv 23 Jan 2023.

## Builds on (most cited first, 8 of 8)

- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [Object Detection with Deep Learning: A Review](https://mlsanity.com/paper/1807.05511/) (2018)
- [Data and its (dis)contents: A survey of dataset development and use in machine learning research](https://mlsanity.com/paper/2012.05345/) (2020)
- [Natural Language Processing: State of The Art, Current Trends and Challenges](https://mlsanity.com/paper/1708.05148/) (2017)
- [Physics-constrained Deep Learning of Multi-zone Building Thermal Dynamics](https://mlsanity.com/paper/2011.05987/) (2020)
- [Introducing causal inference in the energy-efficient building design process](https://mlsanity.com/paper/2203.10115/) (2022)
- [A hybrid-model approach for reducing the performance gap in building energy forecasting](https://mlsanity.com/paper/2206.00460/) (2022)
- [Explainable AI for Engineering Design: A Unified Approach of Systems Engineering and Component- Based Deep Learning Demonstrated by Energy- Efficient Building Design](https://mlsanity.com/paper/2108.13836/) (2021)

## Built on by (most cited first, 2 of 2)

- [Pathway toward prior knowledge-integrated machine learning in engineering](https://mlsanity.com/paper/2307.06950/) (2023)
- [Machine Learning in Proton Exchange Membrane Water Electrolysis -- Part I: A Knowledge-Integrated Framework](https://mlsanity.com/paper/2404.03660/) (2024)

## Abstract (arXiv)

The demand for a huge amount of data for machine learning (ML) applications is currently a bottleneck in an empirically dominated field. We propose a method to combine prior knowledge with data-driven methods to significantly reduce their data dependency. In this study, component-based machine learning (CBML) as the knowledge-encoded data-driven method is examined in the context of energy-efficient building engineering. It encodes the abstraction of building structural knowledge as semantic information in the model organization. We design a case experiment to understand the efficacy of knowledge-encoded ML in sparse data input (1% - 0.0125% sampling rate). The result reveals its three advanced features compared with pure ML methods: 1. Significant improvement in the robustness of ML to extremely small-size and inconsistent datasets; 2. Efficient data utilization from different entities' record collections; 3. Characteristics of accepting incomplete data with high interpretability and reduced training time. All these features provide a promising path to alleviating the deployment bottleneck of data-intensive methods and contribute to efficient real-world data usage. Moreover, four necessary prerequisites are summarized in this study that ensures the target scenario benefits by combining prior knowledge and ML generalization.