# Variational Autoencoder for Calibration: A New Approach

arXiv: https://arxiv.org/abs/2511.00475 · HTML: https://mlsanity.com/paper/2511.00475/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 21 references that are in the map.
- First posted on arXiv 1 Nov 2025.

## Builds on (most cited first, 5 of 5)

- [Dynamical Variational Autoencoders: A Comprehensive Review](https://mlsanity.com/paper/2008.12595/) (2020)
- [A Deep Learning Approach for Blind Drift Calibration of Sensor Networks](https://mlsanity.com/paper/1707.03682/) (2017)
- [A Propagation-model Empowered Solution for Blind-Calibration of Sensors](https://mlsanity.com/paper/2308.02431/) (2023)
- [Agile Climate-Sensor Design and Calibration Algorithms Using Machine Learning: Experiments From Cape Point](https://mlsanity.com/paper/2503.06777/) (2025)
- [Statistical Study of Sensor Data and Investigation of ML-based Calibration Algorithms for Inexpensive Sensor Modules: Experiments from Cape Point](https://mlsanity.com/paper/2503.13487/) (2025)

## Abstract (arXiv)

In this paper we present a new implementation of a Variational Autoencoder (VAE) for the calibration of sensors. We propose that the VAE can be used to calibrate sensor data by training the latent space as a calibration output. We discuss this new approach and show a proof-of-concept using an existing multi-sensor gas dataset. We show the performance of the proposed calibration VAE and found that it was capable of performing as calibration model while performing as an autoencoder simultaneously. Additionally, these models have shown that they are capable of creating statistically similar outputs from both the calibration output as well as the reconstruction output to their respective truth data. We then discuss the methods of future testing and planned expansion of this work.