Low-cost sensors (LCS) are becoming popular for air quality monitoring (AQM). They promise high spatial and temporal resolutions at low-cost. In addition, citizen science applications such as personal exposure monitoring can be implemented effortlessly. However, the reliability of the data is questionable due to various error sources involved in the LCS measurement. Furthermore, sensor performance drift over time is another issue. Hence, the adoption of LCS by regulatory agencies is still evolving. Several studies have been conducted to improve the performance of low-cost sensors. This article summarizes the existing studies on the state-of-the-art of LCS for AQM. We conceptualize a step by step procedure to establish a sustainable AQM setup with LCS that can produce reliable data. The selection of sensors, calibration and evaluation, hardware setup, evaluation metrics and inferences, and end user-specific applications are various stages in the LCS-based AQM setup we propose. We present a critical analysis at every step of the AQM setup to obtain reliable data from the low-cost measurement. Finally, we conclude this study with future scope to improve the availability of air quality data.
Low-cost sensors (LCS) are affordable, compact, and often portable devices designed to measure various environmental parameters, including air quality. These sensors are intended to provide accessible and cost-effective solutions for monitoring pollution levels in different settings, such as indoor, outdoor and moving vehicles. However, the data produced by LCS is prone to various sources of error that can affect accuracy. Calibration is a well-known procedure to improve the reliability of the data produced by LCS, and several developments and efforts have been made to calibrate the LCS. This work proposes a novel Estimated Error Augmented Two-phase Calibration ( EEATC ) approach to calibrate the LCS in stationary and mobile deployments. In contrast to the existing approaches, the EEATC calibrates the LCS in two phases, where the error estimated in the first phase calibration is augmented with the input to the second phase, which helps the second phase to learn the distributional features better to produce more accurate results. We show that the EEATC outperforms well-known single-phase calibration models such as linear regression models (single variable linear regression (SLR) and multiple variable linear regression (MLR)) and Random forest (RF) in stationary and mobile deployments. To test the EEATC in stationary deployments, we have used the Community Air Sensor Network (CAIRSENSE) data set approved by the United States Environmental Protection Agency (USEPA), and the mobile deployments are tested with the real-time data obtained from SensurAir, an LCS device developed and deployed on moving vehicle in Chennai, India.
Low-cost sensors (LCS) are crucial for high-resolution air quality monitoring, but their inherent noise poses challenges for wide-scale adoption. Typically, LCS are calibrated alongside reference stations to develop learning-based calibration models for accurate air quality estimation. However, existing learning-based calibration works are sensor and location-specific, requiring frequent re-calibration. The re-calibration also needs massive data, as required in the initial calibration, which is an unviable solution in practical scenarios. This work introduces Sens-BERT , a BERT-inspired deep learning approach for LCS calibration. It comprises two phases: self-supervised pre-training of Sens-BERT on LCS data alone to learn data features and embeddings and supervised fine-tuning of a neural network model for calibration. Sens-BERT offers several advantages: It requires paired data only for fine-tuning and is transferable across sensors of the same type without explicit training on them. We extensively tested our approach on diverse sensors using the CAIRSENSE and SensEURcity datasets. We demonstrated superior performance compared to traditional calibration models such as single-variable linear regression, multiple-variable linear regression, random forest, LSTM (long short-term memory), and a recently developed calibration model, estimated error augmented two-phase calibration ( EEATC ). Further, we empirically validate Sens-BERT ’s transferability and re-calibration capabilities under reference measurement scarcity, a required scenario to establish a sensor network in remote locations.
In vehicular mobility applications, sensor devices are exposed to rapidly varying concentrations of pollutants. Therefore, more than a conventional data set containing features such as sensor output, temperature and humidity is required to calibrate mobile sensors. We propose a new data set having additional features to address possible error sources encountered in vehicular-mobility LCS applications. We show that the proposed data set is a better choice for calibrating mobile LCS devices when compared to the conventional data set. Further, we propose and investigate two different tandem configurations involving a two-phase calibration approach to improve the calibration accuracy of mobile sensors. The calibration is done with real-time data obtained from an LCS device, SensurAir, which we developed and deployed in Chennai, India.