Few-shot calibration of low-cost air pollution (PM2.5) sensors using meta-learning

TL;DR

This paper introduces a meta-learning approach, specifically MAML, for rapid calibration of low-cost PM2.5 sensors using minimal reference data, improving calibration efficiency and reducing deployment costs.

Contribution

It proposes a novel transfer learning method based on MAML for quick sensor calibration with limited reference data, outperforming existing baselines.

Findings

MAML-based transfer learning outperforms other methods.

The approach reduces calibration time and data requirements.

It enhances the practicality of deploying low-cost sensors.

Abstract

Low-cost particulate matter sensors are transforming air quality monitoring because they have lower costs and greater mobility as compared to reference monitors. Calibration of these low-cost sensors requires training data from co-deployed reference monitors. Machine Learning based calibration gives better performance than conventional techniques, but requires a large amount of training data from the sensor, to be calibrated, co-deployed with a reference monitor. In this work, we propose novel transfer learning methods for quick calibration of sensors with minimal co-deployment with reference monitors. Transfer learning utilizes a large amount of data from other sensors along with a limited amount of data from the target sensor. Our extensive experimentation finds the proposed Model-Agnostic- Meta-Learning (MAML) based transfer learning method to be the most effective over other competitive baselines.