Veli: Unsupervised Method and Unified Benchmark for Low-Cost Air Quality Sensor Correction

• URL: http://arxiv.org/abs/2508.02724v1
• Date: Fri, 01 Aug 2025 10:06:28 GMT
• Title: Veli: Unsupervised Method and Unified Benchmark for Low-Cost Air Quality Sensor Correction
• Authors: Yahia Dalbah, Marcel Worring, Yen-Chia Hsu,
• Abstract summary: Urban air pollution is a major health crisis causing millions of premature deaths annually.<n>Low-cost sensors offer a scalable alternative to expensive reference-grade stations.<n>Their readings are affected by drift, calibration errors, and environmental interference.
• Score: 13.58115155043779
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Urban air pollution is a major health crisis causing millions of premature deaths annually, underscoring the urgent need for accurate and scalable monitoring of air quality (AQ). While low-cost sensors (LCS) offer a scalable alternative to expensive reference-grade stations, their readings are affected by drift, calibration errors, and environmental interference. To address these challenges, we introduce Veli (Reference-free Variational Estimation via Latent Inference), an unsupervised Bayesian model that leverages variational inference to correct LCS readings without requiring co-location with reference stations, eliminating a major deployment barrier. Specifically, Veli constructs a disentangled representation of the LCS readings, effectively separating the true pollutant reading from the sensor noise. To build our model and address the lack of standardized benchmarks in AQ monitoring, we also introduce the Air Quality Sensor Data Repository (AQ-SDR). AQ-SDR is the largest AQ sensor benchmark to date, with readings from 23,737 LCS and reference stations across multiple regions. Veli demonstrates strong generalization across both in-distribution and out-of-distribution settings, effectively handling sensor drift and erratic sensor behavior. Code for model and dataset will be made public when this paper is published.

Related papers

• Provably Outlier-resistant Semi-parametric Regression for Transferable Calibration of Low-cost Air-quality Sensors [2.9079895220997294]
  We present a case study for the calibration of Low-cost air-quality (LCAQ) CO sensors from one of the largest multi-site-multi-season-multi-sensor-multi-pollutant mobile air-quality monitoring network deployments in India.<n>LCAQ sensors have been shown to play a critical role in the establishment of dense, expansive air-quality monitoring networks.
  arXiv  Detail & Related papers  (2025-11-25T00:33:26Z)
• DiffRegCD: Integrated Registration and Change Detection with Diffusion Features [74.3102451211493]
  We present DiffRegCD, an integrated framework that unifies dense registration and change detection in a single model.<n>Experiments on aerial (LEVIR-CD, DSIFN-CD, WHU-CD, SYSU-CD) and ground level (VL-CMU-CD) datasets show that DiffRegCD consistently surpasses recent baselines.
  arXiv  Detail & Related papers  (2025-11-11T07:32:19Z)
• Online Reliable Anomaly Detection via Neuromorphic Sensing and Communications [58.796149594878585]
  This paper proposes a low-power online anomaly detection framework based on neuromorphic wireless sensor networks.<n>In the considered system, a central reader node actively queries a subset of neuromorphic sensor nodes (neuro-SNs) at each time frame.<n>The neuromorphic sensors are event-driven, producing spikes in correspondence to relevant changes in the monitored system.
  arXiv  Detail & Related papers  (2025-10-16T13:56:54Z)
• In-field Calibration of Low-Cost Sensors through XGBoost $\&$ Aggregate Sensor Data [2.7832348184252056]
  Precision comes at a cost: highly accurate sensors are expensive, limiting the spatial deployments and thus their coverage.<n>Low-cost sensors have become popular, though they are prone to drift caused by environmental sensitivity and manufacturing variability.<n>This paper presents a model for in-field sensor calibration using XGBoost ensemble learning to consolidate data from neighboring sensors.
  arXiv  Detail & Related papers  (2025-06-18T19:40:32Z)
• Advancing Air Quality Monitoring: TinyML-Based Real-Time Ozone Prediction with Cost-Effective Edge Devices [0.0]
  This paper introduces a novel TinyML-based system designed to predict ozone concentration in real-time.<n>The system employs an Arduino Nano 33 BLE Sense microcontroller equipped with an MQ7 sensor for carbon monoxide (CO) detection and built-in sensors for temperature and pressure measurements.
  arXiv  Detail & Related papers  (2025-04-03T10:48:24Z)
• Efficient Unsupervised Domain Adaptation Regression for Spatial-Temporal Air Quality Sensor Fusion [6.963971634605796]
  We propose a novel unsupervised domain adaptation (UDA) method specifically tailored for regression tasks on graph-structured data. We incorporate spatial-temporal graph neural networks (STGNNs) to model the relationships between sensors. Our approach allows low-cost IoT sensors to learn calibration parameters from expensive reference sensors.
  arXiv  Detail & Related papers  (2024-11-11T12:20:57Z)
• Spatial-Temporal Graph Attention Fuser for Calibration in IoT Air Pollution Monitoring Systems [8.997596859735516]
  We propose a novel approach to enhance the calibration process by fusing data from sensor arrays. We demonstrate the effectiveness of our approach in significantly improving the calibration accuracy of sensors in IoT air pollution monitoring platforms.
  arXiv  Detail & Related papers  (2023-09-08T12:04:47Z)
• Environmental Sensor Placement with Convolutional Gaussian Neural Processes [65.13973319334625]
  It is challenging to place sensors in a way that maximises the informativeness of their measurements, particularly in remote regions like Antarctica. Probabilistic machine learning models can suggest informative sensor placements by finding sites that maximally reduce prediction uncertainty. This paper proposes using a convolutional Gaussian neural process (ConvGNP) to address these issues.
  arXiv  Detail & Related papers  (2022-11-18T17:25:14Z)
• Leveraging unsupervised data and domain adaptation for deep regression in low-cost sensor calibration [2.5845893156827158]
  Air quality monitoring is becoming an essential task with rising awareness about air quality. Low cost air quality sensors are easy to deploy but are not as reliable as the costly and bulky reference monitors. In this paper, we translate the task of sensor calibration into a semi-supervised domain adaptation problem.
  arXiv  Detail & Related papers  (2022-10-02T13:47:45Z)
• Bayesian Autoencoders for Drift Detection in Industrial Environments [69.93875748095574]
  Autoencoders are unsupervised models which have been used for detecting anomalies in multi-sensor environments. Anomalies can come either from real changes in the environment (real drift) or from faulty sensory devices (virtual drift)
  arXiv  Detail & Related papers  (2021-07-28T10:19:58Z)
• Real-time detection of uncalibrated sensors using Neural Networks [62.997667081978825]
  An online machine-learning based uncalibration detector for temperature, humidity and pressure sensors was developed. The solution integrates an Artificial Neural Network as main component which learns from the behavior of the sensors under calibrated conditions. The obtained results show that the proposed solution is able to detect uncalibrations for deviation values of 0.25 degrees, 1% RH and 1.5 Pa, respectively.
  arXiv  Detail & Related papers  (2021-02-02T15:44:39Z)
• Federated Learning in the Sky: Aerial-Ground Air Quality Sensing Framework with UAV Swarms [53.38353133198842]
  Air quality significantly affects human health, it is increasingly important to accurately and timely predict the Air Quality Index (AQI) This paper proposes a new federated learning-based aerial-ground air quality sensing framework for fine-grained 3D air quality monitoring and forecasting. For ground sensing systems, we propose a Graph Convolutional neural network-based Long Short-Term Memory (GC-LSTM) model to achieve accurate, real-time and future AQI inference.
  arXiv  Detail & Related papers  (2020-07-23T13:32:47Z)
• Learning Camera Miscalibration Detection [83.38916296044394]
  This paper focuses on a data-driven approach to learn the detection of miscalibration in vision sensors, specifically RGB cameras. Our contributions include a proposed miscalibration metric for RGB cameras and a novel semi-synthetic dataset generation pipeline based on this metric. By training a deep convolutional neural network, we demonstrate the effectiveness of our pipeline to identify whether a recalibration of the camera's intrinsic parameters is required or not.
  arXiv  Detail & Related papers  (2020-05-24T10:32:49Z)
• Adaptive machine learning strategies for network calibration of IoT smart air quality monitoring devices [1.957338076370071]
  Low cost chemical microsensors array have shown capable to provide relatively accurate air pollutant quantitative estimations. Their accuracy have shown limited in long term field deployments due to negative influence of several technological issues. In this work, we address this non stationary framework with adaptive learning strategies in order to prolong the validity of multisensors calibration models.
  arXiv  Detail & Related papers  (2020-03-24T10:26:51Z)
• Deep Soft Procrustes for Markerless Volumetric Sensor Alignment [81.13055566952221]
  In this work, we improve markerless data-driven correspondence estimation to achieve more robust multi-sensor spatial alignment. We incorporate geometric constraints in an end-to-end manner into a typical segmentation based model and bridge the intermediate dense classification task with the targeted pose estimation one. Our model is experimentally shown to achieve similar results with marker-based methods and outperform the markerless ones, while also being robust to the pose variations of the calibration structure.
  arXiv  Detail & Related papers  (2020-03-23T10:51:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.