CO₂-Based Occupancy Estimation with Efficient Deep Learning: A Step Towards Edge-Deployable Soft Sensors

Accurate occupancy estimation is a key enabler for intelligent building automation, affecting energy efficiency, HVAC control, and space utilization. While conventional sensors such as cameras or motion detectors are either intrusive or expensive, CO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf> concentration offers a non-intrusive and widely available alternative correlated with human presence. However, most CO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2-</inf>based approaches rely on limited real-world datasets and do not systematically evaluate different model architectures or input feature designs. In this study, we leverage synthetic data generated via EnergyPlus simulations to benchmark lightweight deep learning models for CO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf>-based occupancy estimation. We explore the effectiveness of incorporating temporal CO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf> derivatives into model inputs. Our evaluation includes six model architectures (LSTM, GRU, BiLSTM, TCN, Small MLP, and Separable CNN) assessed under three input configurations across diverse room sizes and occupancy patterns. Results show that adding CO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf> derivatives significantly improves performance across all models. GRU achieved the best balance between accuracy (MAE = 0.1048, R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> = 0.967) and inference efficiency, while Separable CNN offered a strong lightweight alternative with fast runtime and competitive accuracy. These findings demonstrate the viability of using DL-based ’soft sensors’ for real-time, non-intrusive occupancy estimation in edge environments.