Modelling calibration uncertainty in networks of environmental sensors

Networks of low-cost sensors are becoming ubiquitous, but often suffer from poor accuracies and drift. Regular colocation with reference sensors allows recalibration but is complicated and expensive. Alternatively the calibration can be transferred using low-cost, mobile sensors. However inferring t...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-05
Main Authors: Smith, Michael Thomas, Ross, Magnus, Ssematimba, Joel, Alvarado, Pablo A, Alvarez, Mauricio, Engineer Bainomugisha, Wilkinson, Richard
Format: Article
Language:English
Subjects:
Calibration
Insects
Low cost
Sensors
Uncertainty
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Networks of low-cost sensors are becoming ubiquitous, but often suffer from poor accuracies and drift. Regular colocation with reference sensors allows recalibration but is complicated and expensive. Alternatively the calibration can be transferred using low-cost, mobile sensors. However inferring the calibration (with uncertainty) becomes difficult. We propose a variational approach to model the calibration across the network. We demonstrate the approach on synthetic and real air pollution data, and find it can perform better than the state of the art (multi-hop calibration). We extend it to categorical data produced by citizen-scientist labelling. In Summary: The method achieves uncertainty-quantified calibration, which has been one of the barriers to low-cost sensor deployment and citizen-science research.
ISSN:2331-8422