AI-driven point source estimation for future satellite missions

To support the goals of the Paris Agreement, monitoring and verification support (MVS) capacities focussing on anthropogenic greenhouse gas emissions are being developed, such as the EU’s emerging Copernicus CO₂ Service and Germany’s ITMS (Integriertes Treibhausgas-Monitoringsystem). Satellite concepts capable of measuring atmospheric CO₂ and CH₄ concentrations on small spatial scales (10s of meters) have emerged as potential contributors to such MVS systems, through their ability to image the exhaust plumes of individual facilities. To quantify emissions based on these plume images, traditional mass balance methods require an accurate knowledge of the effective speed of the wind that transports the detected CO₂ or CH₄ plume. Uncertainty in the wind speed is the largest source of uncertainty in the estimated emissions. It has been proposed, however, that machine learning approaches might be able to estimate emission rates directly from the turbulent plume images without the need to impose wind speeds from external sources.

Here, we present our progress on developing a deep-learning-based emission rate estimator for plume images using convolutional neural networks. Our main focus lies on the improvement of the quality and certainty of deep learning models. Therefore, we provide a model that is capable of providing estimates with, on average, little to no bias over a large scale of flux rates. We present a feasible solution to existing biases, leading to a Pearson correlation coefficient of 97.98% for true and estimated fluxes. In addition, our model provides error estimates alongside its flux predictions, making a first step towards improving the certainty of estimated predictions. Further, we present our progress on making the model more stable across different wind speed situations, and potentially extracting effective wind speed information directly from image data. Thus, we are working towards applying deep-learning-based methods in a more stable and powerful approach that is capable of efficiently analyzing large amounts of incoming data.