Gas Sensor Array Drift Dataset (UCI ML Repository)
Abstract
"Benchmark dataset for gas sensor arrays showing drift over 36 months. Contains 13,910 measurements from 16 chemical sensors across 6 volatile organic compounds (VOCs)."
Description
Dataset Significance
Classic benchmark dataset in sensor research. Demonstrates critical challenge of sensor drift - degradation in sensor response over time due to aging and environmental factors. Essential for developing drift-robust detection algorithms.
Experimental Setup
- Duration: 36 months continuous operation
- Sensors: 16 chemical gas sensors
- Gas Types: 6 volatile organic compounds (VOCs)
- Concentrations: 10 different concentration levels
- Measurements: 13,910 total samples
Technical Parameters
- Sensor Type: Metal oxide semiconductor (MOS)
- Measurement: Sensor resistance (ohms)
- Sampling Frequency: 3.8 Hz
- Temperature: 20°C, 25°C (controlled)
- Humidity: 50%, 60%, 70% (varied)
Drift Characteristics
- Nonlinear sensor degradation over time
- Chemical sensitivity reduction
- Baseline drift patterns
- Seasonal and environmental influences
Applications
Sensor drift compensation, gas classification with aging sensors, robust feature extraction, concept drift detection, and transfer learning approaches.
Data Preview
| Batch_ID | Sensor_ID | Chemical_ID | Concentration | Measurement_Time_s | Sensor_Resistance_Ohms | Temperature_C |
|---|---|---|---|---|---|---|
| B001 | S01 | VOC_A | 50ppm | 0.26 | 4524.5 | 20 |
| B001 | S02 | VOC_A | 50ppm | 0.26 | 3850.2 | 20 |
| B001 | S03 | VOC_B | 100ppm | 0.52 | 2145.8 | 25 |
Showing first few rows for preview
Cite This Dataset
Academic (2026). Gas Sensor Array Drift Dataset (UCI ML Repository). [Dataset]. Academic. https://archive.ics.uci.edu/ml/datasets/Gas+Sensor+Array+Drift+Dataset
Select your preferred citation style above. The citation will automatically update and you can copy it to your clipboard.
Original source: Academic (2026). Visit official page for more details.
Indexed by IoTDataset.com on Jan 13, 2026
Ready to Start Your Research?
Download this dataset directly from the official repository and start building your next breakthrough project.