AI-Driven Carbon Monitoring: Transformer-Based Reconstruction of Atmospheric CO2 in Canadian Poultry Regions
This enables more precise carbon monitoring for agricultural emissions, particularly in poultry farming, supporting policy and mitigation efforts, though it is incremental as it adapts existing transformer methods to a specific domain.
The paper tackles the problem of accurately mapping atmospheric CO2 concentrations over agricultural landscapes by developing a transformer-based framework (ST-ViWT) that reconstructs continuous CO2 fields from sparse satellite data, achieving R2 = 0.984 and RMSE = 0.468 ppm with 92.3% of predictions within +/-1 ppm error. It applies this to Canadian poultry regions, finding a moderate correlation (r = 0.43) between facility density and CO2 levels and revealing seasonal patterns.
Accurate mapping of column-averaged CO2 (XCO2) over agricultural landscapes is essential for guiding emission mitigation strategies. We present a Spatiotemporal Vision Transformer with Wavelets (ST-ViWT) framework that reconstructs continuous, uncertainty-quantified XCO2 fields from OCO-2 across southern Canada, emphasizing poultry-intensive regions. The model fuses wavelet time-frequency representations with transformer attention over meteorology, vegetation indices, topography, and land cover. On 2024 OCO-2 data, ST-ViWT attains R2 = 0.984 and RMSE = 0.468 ppm; 92.3 percent of gap-filled predictions lie within +/-1 ppm. Independent validation with TCCON shows robust generalization (bias = -0.14 ppm; r = 0.928), including faithful reproduction of the late-summer drawdown. Spatial analysis across 14 poultry regions reveals a moderate positive association between facility density and XCO2 (r = 0.43); high-density areas exhibit larger seasonal amplitudes (9.57 ppm) and enhanced summer variability. Compared with conventional interpolation and standard machine-learning baselines, ST-ViWT yields seamless 0.25 degree CO2 surfaces with explicit uncertainties, enabling year-round coverage despite sparse observations. The approach supports integration of satellite constraints with national inventories and precision livestock platforms to benchmark emissions, refine region-specific factors, and verify interventions. Importantly, transformer-based Earth observation enables scalable, transparent, spatially explicit carbon accounting, hotspot prioritization, and policy-relevant mitigation assessment.