Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AQuaMoHo: Localized Low-Cost Outdoor Air Quality Sensing over a Thermo-Hygrometer

Prithviraj Pramanik, Prasenjit Karmakar, Praveen Kumar Sharma, Soumyajit Chatterjee, Abhijit Roy, Santanu Mandal, Subrata Nandi, Sandip Chakraborty, Mousumi Saha, Sujoy Saha

TL;DR

The paper tackles the problem of sparse, city-scale air quality annotation by introducing AQuaMoHo, a framework that combines low-cost THM sensing with publicly crawled spatio-temporal features to annotate AQI at a personal location. It builds city-specific pre-trained models and uses an LSTM with temporal attention to fuse meteorological, temporal, and spatial data, enabling real-time AQI annotation from minimal hardware. The authors validate the approach with in-house AQMD deployments in Durgapur and publicly sourced AQMS data in Delhi, achieving substantial gains over baselines (F1 > 0.60) and demonstrating the value of temporal features, while exploring device counts and progressive deployment effects. This work offers a practical, scalable path for personal-scale air quality monitoring in regions with limited AQMS density, with implications for citizen science, health exposure studies, and urban air management.

Abstract

Efficient air quality sensing serves as one of the essential services provided in any recent smart city. Mostly facilitated by sparsely deployed Air Quality Monitoring Stations (AQMSs) that are difficult to install and maintain, the overall spatial variation heavily impacts air quality monitoring for locations far enough from these pre-deployed public infrastructures. To mitigate this, we in this paper propose a framework named AQuaMoHo that can annotate data obtained from a low-cost thermo-hygrometer (as the sole physical sensing device) with the AQI labels, with the help of additional publicly crawled Spatio-temporal information of that locality. At its core, AQuaMoHo exploits the temporal patterns from a set of readily available spatial features using an LSTM-based model and further enhances the overall quality of the annotation using temporal attention. From a thorough study of two different cities, we observe that AQuaMoHo can significantly help annotate the air quality data on a personal scale.

AQuaMoHo: Localized Low-Cost Outdoor Air Quality Sensing over a Thermo-Hygrometer

TL;DR

The paper tackles the problem of sparse, city-scale air quality annotation by introducing AQuaMoHo, a framework that combines low-cost THM sensing with publicly crawled spatio-temporal features to annotate AQI at a personal location. It builds city-specific pre-trained models and uses an LSTM with temporal attention to fuse meteorological, temporal, and spatial data, enabling real-time AQI annotation from minimal hardware. The authors validate the approach with in-house AQMD deployments in Durgapur and publicly sourced AQMS data in Delhi, achieving substantial gains over baselines (F1 > 0.60) and demonstrating the value of temporal features, while exploring device counts and progressive deployment effects. This work offers a practical, scalable path for personal-scale air quality monitoring in regions with limited AQMS density, with implications for citizen science, health exposure studies, and urban air management.

Abstract

Efficient air quality sensing serves as one of the essential services provided in any recent smart city. Mostly facilitated by sparsely deployed Air Quality Monitoring Stations (AQMSs) that are difficult to install and maintain, the overall spatial variation heavily impacts air quality monitoring for locations far enough from these pre-deployed public infrastructures. To mitigate this, we in this paper propose a framework named AQuaMoHo that can annotate data obtained from a low-cost thermo-hygrometer (as the sole physical sensing device) with the AQI labels, with the help of additional publicly crawled Spatio-temporal information of that locality. At its core, AQuaMoHo exploits the temporal patterns from a set of readily available spatial features using an LSTM-based model and further enhances the overall quality of the annotation using temporal attention. From a thorough study of two different cities, we observe that AQuaMoHo can significantly help annotate the air quality data on a personal scale.
Paper Structure (39 sections, 17 figures, 10 tables)

This paper contains 39 sections, 17 figures, 10 tables.

Table of Contents

  1. Introduction
  2. Our Contributions
  3. Paper Organization
  4. Related work
  5. Cost Effective Ubiquitous Air Quality Sensing
  6. AQMD Calibration
  7. AQI-based Estimation
  8. Development of AQMD
  9. Device Development and Calibration
  10. Pre-Deployment Validation
  11. Post-Deployment Validation
  12. System Deployment
  13. Publicly Available Data
  14. Preliminary Study of the Data
  15. Asynchronous Sensor Polling
  16. ...and 24 more sections

Figures (17)

  • Figure 1: The AQMD device -(a) The system overview & (b) The internal layout of a device deployment at one of the sites in Durgapur
  • Figure 2: (a) Deployment of the AQMDs in Durgapur, (b) PM2.5 concentration measured by AQMS, CPCB station and AQMD
  • Figure 3: PM2.5 concentration measured by different AQMDs in a controlled fire event
  • Figure 4: The red dots and blue bounded figures represents the position of AQMDs and area of coverage respectively in (a) Durgapur & (b) Delhi
  • Figure 5: Correlation of THM based features with the AQI classes in (a) Durgapur & (b) Delhi.
  • ...and 12 more figures