Low-Cost Sensor Calibration for Indoor Air Quality Monitoring: A Dataset, Evaluation Scenarios, and a Lightweight Model

Jinyong Yun; Seokho Ahn; Hyungjin Kim; Sungbok Shin; Young-Duk Seo

cs.LGOct 8, 2026

Low-Cost Sensor Calibration for Indoor Air Quality Monitoring: A Dataset, Evaluation Scenarios, and a Lightweight Model

Authors: Jinyong Yun, Seokho Ahn, Hyungjin Kim, Sungbok Shin, Young-Duk Seo

Organizations: Department of Electrical and Computer Engineering, Inha University, Incheon 22212, South Korea · Department of Computer Science and Engineering, Sogang University, Seoul 04107, South Korea

Abstract

Low-cost sensors enable scalable indoor air quality monitoring but require calibration because of nonlinear distortions, noise, and temporal drift. The conventional strict pairwise calibration setting requires a co-located reference sensor at each deployment location and does not account for spatial and temporal heterogeneity. To address these limitations, we introduce a six-month dataset comprising multivariate indoor air-quality measurements from low-cost and reference sensors with contextual metadata collected at five locations. Using this dataset, we define four evaluation scenarios. The reference-efficient and location-transfer scenarios evaluate spatial generalization, whereas the long-term drift and event-conditioned scenarios assess robustness to gradual and abrupt distribution shifts. Based on these scenarios, we derive design requirements and propose a lightweight temporal model that combines input-window compression with residual temporal and feature fusion. Experiments show strong calibration performance across all four scenarios with low edge-inference cost.

Figures & tables

Dataset (Calibration Study)	Modalities	Dataset Properties			Deployment Scenarios
Dataset (Calibration Study)	Modalities	Indoor.	MultiLoc.	Event.	S1	S2	S3	S4
UCI Air Quality ( Aula et al. 2022 )	CO, NO 2 , T., RH.	$\times$	$\times$	$\times$	$\times$	$\times$	$\checkmark$	$\times$
Author-collected ( Allka et al. 2023 )	O 3 , T.	$\times$	$\checkmark$	$\times$	$\times$	$\times$	$\times$	$\times$
Author-collected ( Ahn et al. 2024 )	PM 10	$\checkmark$	$\checkmark$	$\times$	$\times$	$\times$	$\times$	$\times$
Author-collected ( Bachechi et al. 2024 )	NO, NO 2 , O 3	$\times$	$\checkmark$	$\times$	$\times$	$\times$	$\checkmark$	$\times$
SensEURCity ( Ahn et al. 2025 )	PM 1 , PM 2.5 , PM 10	$\times$	$\checkmark$	$\times$	$\times$	$\times$	$\times$	$\times$

Table 1: Comparison of low-cost sensor calibration studies and datasets. T. and RH. denote temperature and relative humidity.

Figure 1: Comparison of standard sensor calibration and four deployment-oriented scenarios in terms of relaxed assumptions, calibration regimes, and world settings: Scenarios 1-4: reference-efficient, location-transfer, long-term drift, and event-condition.

Measured	Channel	East	West	South	North	Center
PM 1	L PPD42	22.2	21.9	23.6	25.7	23.4
( $\mu$ g/m 3 )	R PMS7003	20.2	18.9	21.4	21.8	19.6
CO	L MQ135	6.3	7.1	6.2	8.5	6.8
(ppm)	R MQ9	4.5	4.2	4.4	4.8	4.1
CO 2	L MQ135	552.8	540.0	548.0	584.0	556.2
(ppm)	R MG811	532.4	512.0	538.0	548.0	522.6

Table 2: Mean channel measurements across five locations after sanity filtering and 1-minute resampling.

Figure 2: Architecture of proposed model with initial temporal compression, temporal and feature fusion, and output head.

Model	Outdoor data			Indoor data (Ours)
	RMSE $\downarrow$			RMSE $\downarrow$					Inference $\downarrow$ $\left(\mathrm{ms}\right)$	Memory $\downarrow$ $\left(\mathrm{KB}\right)$
	$\mathrm{PM}_{10}$ $\left(\mu\mathrm{g}/\mathrm{m}^{3}\right)$	$\mathrm{PM}_{2.5}$ $\left(\mu\mathrm{g}/\mathrm{m}^{3}\right)$	$\mathrm{PM}_{1}$ $\left(\mu\mathrm{g}/\mathrm{m}^{3}\right)$	$\mathrm{CO}_{2}$ $\left(\mathrm{ppm}\right)$	$\mathrm{CO}$ $\left(\mathrm{ppm}\right)$	$\mathrm{PM}_{1}$ $\left(\mu\mathrm{g}/\mathrm{m}^{3}\right)$	T. $\left({}^{\circ}\mathrm{C}\right)$	RH. $\left(\%\right)$	Inference $\downarrow$ $\left(\mathrm{ms}\right)$	Memory $\downarrow$ $\left(\mathrm{KB}\right)$
iTransformer	15.92	7.36	4.07	9.80	4.92	8.54	2.43	5.24	2.32	41.20
TimeXer	15.12	6.31	3.31	9.05	7.73	9.77	3.75	5.63	2.99	186.60
DLinear	17.81	8.41	4.49	13.70	5.93	9.21	3.14	5.44	1.29	28.00
XLinear	19.05	11.64	8.48	14.71	5.92	8.71	3.23	6.20	2.12	152.00

Table 3: Performance comparison on the representative outdoor calibration dataset SensEURCity and our indoor dataset. The best result for each metric is marked in bold , and the second-best result is underlined . Lower values indicate better performance.

Model	RMSE $\downarrow$
Model	CO	CO 2	T.	RH.	PM 1
iTransformer	6.26	9.45	4.11	7.25	9.34
TimeXer	7.92	10.29	9.18	9.31	12.95
DLinear	7.71	10.13	5.02	11.91	14.45
XLinear	6.93	10.77	6.59	10.80	11.69
TimeMixer	9.51	10.65	6.91	10.71	12.54

Table 4: S1 reports the average RMSE on non-anchor locations across the five anchor-location settings.

Model	RMSE $\downarrow$
Model	CO	CO 2	T.	RH.	PM 1
iTransformer	7.63	10.45	4.79	9.02	10.27
TimeXer	9.35	11.18	6.66	10.34	11.88
DLinear	8.69	11.60	11.43	12.27	12.66
XLinear	8.44	11.81	7.62	10.06	12.56
TimeMixer	9.70	11.75	8.54	13.05	13.65

Table 5: S2 evaluates transfer from each source location to four unseen target locations without adaptation, averaged across the five source-location settings.

Model	Relative increase (%) $\downarrow$
Model	CO	CO 2	T.	RH.	PM 1
iTransformer	28.6	56.0	32.3	47.6	67.8
TimeXer	64.4	42.2	53.7	67.2	84.5
DLinear	63.8	84.9	49.2	65.1	108.8
XLinear	43.3	82.4	56.8	75.2	77.6
TimeMixer	64.2	73.5	61.1	60.1	97.5

Table 6: S3 average relative increase from the earliest to the latest deployment period across five locations.

Model	South (Window)		North (Door)		Avg.
Model	CO 2	T.	CO 2	T.	Avg.
iTransformer	18.48	7.97	19.26	7.29	13.25
TimeXer	21.69	9.49	24.33	10.68	16.55
DLinear	20.55	10.37	24.08	10.93	16.48
XLinear	23.74	8.05	26.55	10.48	17.20
TimeMixer	19.21	10.58	32.08	11.69	18.39

Table 7: S4 event-conditioned calibration results at the window/door-side locations. Each value reports RMSE during the corresponding event periods.

Figure 3: Performance on Arduino Nano 33 BLE Sense. The graphs show mean inference latency and FlatBuffer size across input windows of 15, 60, 360, 720, and 1440. Missing points indicate that on-device measurement was not possible.

Explore similar work

A temporal deep learning framework for calibration of low-cost air quality sensors
Apr 23, 2026Arindam Sengupta, Tony Bush, Ben Marner +2Model Calibration
1ETSI Aeronáutica y del Espacio, Universidad Politécnica de Madrid, Plaza Cardenal Cisneros, 3, Madrid, 28040, Spain · 2Air Quality Consultants Ltd., 3rd Floor, St. Augustine’s Court, St. Augustine’s Place,2026 Bristol, BS1 4UD, United Kingdom
PoHAR: Understanding Hyperlocal Human Activities with Pollution Sensor Networks
May 10, 2026Prasenjit Karmakar, Karthik Reddy, Sandip ChakrabortyHuman Activity Recognition Internet of Things
Department of Computer Science and Engineering, Indian Institute of Technology Kharagpur, India.
AirQualityBench: A Realistic Evaluation Benchmark for Global Air Quality Forecasting
May 7, 2026Xing Xu, Xu Wang, Yudong Zhang +3Benchmark Design Time Series Forecasting
University of Science and Technology of China (USTC), Hefei, Anhui, China · 2Suzhou Institute for Advanced Research, USTC, Suzhou, Jiangsu, China · 3The Hong Kong Polytechnic University, Hong Kong, China

Apr 23, 2026, cs.LGJ/K move · Enter open · S save

A temporal deep learning framework for calibration of low-cost air quality sensors

Arindam Sengupta, Tony Bush, Ben Marner, Jose Miguel Pérez+1

1ETSI Aeronáutica y del Espacio, Universidad Politécnica de Madrid, Plaza Cardenal Cisneros, 3, Madrid, 28040, Spain · 2Air Quality Consultants Ltd., 3rd Floor, St. Augustine’s Court, St. Augustine’s Place,2026 Bristol, BS1 4UD, United Kingdom

Model Calibration

Open paper AskPDF arXiv

Low-cost air quality sensors (LCS) provide a practical alternative to expensive regulatory-grade instruments, making dense urban monitoring networks possible. Yet their adoption is limited by calibration challenges, including sensor drift, environmental cross-sensitivity, and variability in performance from device to device. This work presents a deep learning framework for calibrating LCS measurements of PM

_{2.5}

, PM

_{10}

, and NO

_2

using a Long Short-Term Memory (LSTM) network, trained on co-located reference data from the OxAria network in Oxford, UK. Unlike the Random Forest (RF) baseline, which treats each observation independently, the proposed approach captures temporal dependencies and delayed environmental effects through sequence-based learning, achieving higher

R^2

values across training, validation, and test sets for all three pollutants. A feature set is constructed combining time-lagged parameters, harmonic encodings, and interaction terms to improve generalization on unseen temporal windows. Validation of unseen calibrated values against the Equivalence Spreadsheet Tool 3.1 demonstrates regulatory compliance with expanded uncertainties of 22.11% for NO

_2

, 12.42% for PM

_{10}

, and 9.1% for PM

_{2.5}

Abstract

Explore similar work

A temporal deep learning framework for calibration of low-cost air quality sensors

PoHAR: Understanding Hyperlocal Human Activities with Pollution Sensor Networks

AirQualityBench: A Realistic Evaluation Benchmark for Global Air Quality Forecasting