CO2 Analysis (Zertiair)
Explore Zertiair resources for CO2 monitoring and analysis. This section offers access to both raw datasets for independent research and advanced Compute-to-Data algorithms that allow extracting environmental intelligence—from temporal and regional patterns to anomaly detection—without compromising data privacy.
Outdoor CO2 Dataset (Raw)
ZertiAir provides a downloadable dataset of continuous outdoor CO₂ measurements collected from sensors deployed across multiple farms and regions. The dataset can be accessed “as is” and contains time-series CO₂ observations suitable for independent analysis, research, and integration into external systems.
It serves as a reliable environmental boundary condition that can be combined with other datasets (agricultural operations, ventilation, production) to support environmental monitoring and benchmarking.
Multi-Farm CO2 Analytics (Compute-to-Data)
Exclusive access to outdoor CO₂ measurements from multiple farms via Compute-to-Data algorithms. Instead of downloading raw sensor data, users obtain privacy-secure analysis, including sensor health metrics, regional CO₂ footprints, day-night temporal behavior, and anomaly detection.
This approach allows outdoor CO₂ to function as a reliable boundary condition for advanced models without exposing raw measurements, enabling the safe reuse and monetization of environmental intelligence.
Zertiair Algorithms
Sensor Analytics
Analyzes the sensor population, sampling behavior, battery performance, and detects abnormal discharge patterns, all completely within a Compute-to-Data environment.
Temporal Analytics
Analysis of day-night temporal behavior of CO₂, identifying cyclic patterns and trends over time.
Regional Analytics
Generation of regional CO₂ footprints to compare and contrast environmental conditions between different geographical locations.
Local Analytics
Detailed local analysis to understand microclimatic variations and site-specific effects on CO₂ measurements.
Anomalies Analytics
Advanced anomaly detection to identify instability, outliers, and potential data quality issues or extreme environmental conditions.