Improvements of AI-driven emission estimation for point sources applied to high resolution 2-D methane-plume imagery

Kurzfassung

Anthropogenic methane (CH4) sources have had a considerable impact on the Earth's changing radiation budget since pre-industrial times. Localized sources such as those resulting from the fossil fuel industry and waste treatment have been shown to make up a substantial fraction of the emission total, and CH4 plumes from such sources are detectable through airborne and space-based hyperspectral imaging techniques. Here, we further develop a machine learning technique to estimate CH4 emission rates from such plume images without the need for auxiliary data such as local wind speed information. We directly build upon the idea of previous research which used a convolutional neural network (CNN) called MethaNet and a library of large-eddy-simulations (LES) of turbulent CH4 plumes as our synthetic data environment. Here we suggest appropriate error metrics and changes to the training procedure that reduce systematic biases present in previous studies. Our improved setup has a mean absolute percentage error (MAPE) of 10% for sources with flux rates above 40 kgCH4/h, a Pearson correlation coefficient of 98% and is capable of providing meaningful error estimates for its predictions. This is a significant improvement to MethaNet and other studies and can be used as an efficient method for point source quantification in the future.