Accurate measurement of methane emissions is crucial for improvement, but the Oil and Gas industry faces significant discrepancies in reporting. Uncovering the reasons behind these discrepancies requires a closer look at industry dynamics, methane properties, and existing practices.

Methane emissions, as a topic, has gone from relative obscurity to a unilateral agreement in the form of the Global Methane Pledge (GMP) at COP26 in a matter of years.

A review of several use-cases where machine learning could play a role in reducing greenhouse gas emissions, with recommendations around needed research questions to be asked and promising business opportunities.

There is a need to understand which technologies and methods are appropriate for measuring methane emissions in different scenes. This paper provides a systematic comparison and summary of the different technologies and methods for data analysis and uncertainty estimation.

According to current estimates from official US GHG inventories methane emissions are estimated to contribute 3% of national GHG emissions. However these estimates are fraut with uncertainty, data gaps, and inconsistency with alternative approaches has suggested a need for further evidence.