# Calibration of Low-Cost Sensors for PM10 and PM2.5 Based on Artificial Intelligence for Smart Cities

## TL;DR

This study shows how low-cost air quality sensors can be calibrated using AI to provide accurate, cost-effective data for monitoring particulate matter in cities like Bogotá.

## Contribution

The paper introduces a novel LCS calibration approach using FastDTW and machine learning models for street-scale PM monitoring.

## Key findings

- FastDTW preprocessing significantly improves LCS calibration accuracy.
- Random Forest and XGBoost outperformed other models in LCS calibration.
- Incorporating RH, temperature, and absorption flow enhances calibration results.

## Abstract

What are the main findings?
Improved calibration results using Fast DTW for data preprocessing.Comparative analysis of LCS calibration performance using statistical methods, machine learning models and deep learning.

Improved calibration results using Fast DTW for data preprocessing.

Comparative analysis of LCS calibration performance using statistical methods, machine learning models and deep learning.

What are the implications of the main findings?
Determination of the feasibility of using calibrated LCS as a complement to traditional RMCA in the city of Bogotá.Application of machine learning models for LCS calibration.

Determination of the feasibility of using calibrated LCS as a complement to traditional RMCA in the city of Bogotá.

Application of machine learning models for LCS calibration.

Exposure to Particulate Matter (PM) is linked to respiratory and cardiovascular diseases, certain types of cancer, and accounts for approximately seven million premature deaths globally. While governments and organizations have implemented various strategies for Air Quality (AQ) such as the deployment of Air Quality Monitoring Networks (AQMN), these networks often suffer from limited spatial coverage and involve high installation and maintenance costs. Consequently, the implementation of networks based on Low-Cost Sensors (LCS) has emerged as a viable alternative. Nevertheless, LCS systems have certain drawbacks, such as lower reading precision, which can be mitigated through specific calibration models and methods. This paper presents the results and conclusions derived from simultaneous PM10 and PM2.5 monitoring comparisons between LCS nodes and a T640X reference sensor. Additionally, Relative Humidity (RH), temperature, and absorption flow measurements were collected via an Automet meteorological station. The monitoring equipment was installed at the Faculty of Environment of the Universidad Distrital in Bogotá. The LCS calibration process began with data preprocessing, which involved filtering, segmentation, and the application of FastDTW. Subsequently, calibration was performed using a variety of models, including two statistical approaches, three Machine Learning algorithms, and one Deep Learning model. The findings highlight the critical importance of applying FastDTW during preprocessing and the necessity of incorporating RH, temperature, and absorption flow factors to enhance accuracy. Furthermore, the study concludes that Random Forest and XGBoost offered the highest performance among the methods evaluated. While satellites map city-wide patterns and MAX-DOAS enables hourly source attribution, our calibrated LCS network supplies continuous, street-scale data at low CAPEX/OPEX—forming a practical backbone for sustained micro-scale monitoring in Bogotá.