# Modelling calibration uncertainty in networks of environmental sensors

arXiv: https://arxiv.org/abs/2205.01988 · HTML: https://mlsanity.com/paper/2205.01988/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 72 references that are in the map.
- First posted on arXiv 4 May 2022.

## Builds on (most cited first, 7 of 7)

- [Variational Inference: A Review for Statisticians](https://mlsanity.com/paper/1601.00670/) (2016)
- [Gaussian Processes for Big Data](https://mlsanity.com/paper/1309.6835/) (2013)
- [Doubly Stochastic Variational Inference for Deep Gaussian Processes](https://mlsanity.com/paper/1705.08933/) (2017)
- [MCMC for Variationally Sparse Gaussian Processes](https://mlsanity.com/paper/1506.04000/) (2015)
- [Importance Sampling for Minibatches](https://mlsanity.com/paper/1602.02283/) (2016)
- [Adaptive machine learning strategies for network calibration of IoT smart air quality monitoring devices](https://mlsanity.com/paper/2003.12011/) (2020)
- [Efficient Learning of Harmonic Priors for Pitch Detection in Polyphonic Music](https://mlsanity.com/paper/1705.07104/) (2017)

## Built on by (most cited first, 1 of 1)

- [Gaussian Processes for Monitoring Air-Quality in Kampala](https://mlsanity.com/paper/2311.16625/) (2023)

## Abstract (arXiv)

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.