A temporal deep learning framework for calibration of low-cost air quality sensors

2026-04-23

AI Summary

This study addresses the limitations of low-cost air quality sensors, which suffer from drift, cross-sensitivity to environmental factors, and inter-device variability, hindering their regulatory acceptance. The authors propose a novel LSTM-based temporal deep learning calibration framework that integrates time-lagged features, harmonic time encoding, and interaction terms, achieving strong generalization to unseen time periods for the first time. The model is trained and evaluated using reference measurements from the Oxford OxAria network for PM₂.₅, PM₁₀, and NO₂, significantly outperforming a random forest baseline. Validation with the Equivalence Spreadsheet Tool 3.1 demonstrates expanded uncertainties of 9.1% for PM₂.₅, 12.42% for PM₁₀, and 22.11% for NO₂, all meeting established regulatory standards.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Application Domains: Internet of Things, Sensor Networks & Smart Cities

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments

Abstract

Low-cost air quality sensors (LCS) provide a practical alternative to expensive regulatory-grade instruments, making dense urban monitoring networks possible. Yet their adoption is limited by calibration challenges, including sensor drift, environmental cross-sensitivity, and variability in performance from device to device. This work presents a deep learning framework for calibrating LCS measurements of PM$_{2.5}$, PM$_{10}$, and NO$_2$ using a Long Short-Term Memory (LSTM) network, trained on co-located reference data from the OxAria network in Oxford, UK. Unlike the Random Forest (RF) baseline, which treats each observation independently, the proposed approach captures temporal dependencies and delayed environmental effects through sequence-based learning, achieving higher $R^2$ values across training, validation, and test sets for all three pollutants. A feature set is constructed combining time-lagged parameters, harmonic encodings, and interaction terms to improve generalization on unseen temporal windows. Validation of unseen calibrated values against the Equivalence Spreadsheet Tool 3.1 demonstrates regulatory compliance with expanded uncertainties of 22.11% for NO$_2$, 12.42% for PM$_{10}$, and 9.1% for PM$_{2.5}$.

Problem

• low-cost air quality sensors
• calibration
• sensor drift
• cross-sensitivity
• performance variability

Innovation

• LSTM
• temporal deep learning
• low-cost air quality sensors
• sensor calibration
• time-series modeling