Methane is a powerful greenhouse gas and is one of the most significant drivers of global warming. It has an impact on climate change 84 times greater than CO2 (per unit mass, over 20 year). It is also a precursor to the formation of tropospheric ozone, which can have a number of indirect effects on agriculture productivity, crop yields and human help.

Methane is one of the key targets of Sentinel-5P’s TROPospheic Monitoring Instrument (TROPOMI).

Current methods of tracking methane perform well but have a large computation cost. Scientists are using Raditative Transfer Model simulations which allow faster and less computationally demanding retrievals.

A Neural Network was trained on a synthetic spectra database of TROPOMI Shortwave InfraRed (SWIR) spectra, based on simulations from the LINTRAN RTM, implemented within the current Methane retrieval algorithm. Different NN architectures were tested to find the best performing emulator. The resulting NN-based emulator can effectively replicate spectra simulated by LINTRAN, explaining 99% of the variance and to within ~3% uncertainty, with a speed up of up 10000 times faster than the RTM. Additional effort is placed on uncertainty characterisation of the emulator, which is a key requirement for S5P-TROPOMI Greenhouse Gas products.

Featured Educator

• Jennifer Adams