For nearly a decade, there has been a trend to reduce greenhouse gas (GHG) emissions…that is, until now. According to the World Meteorological Organization, atmospheric levels of three major greenhouse gases—carbon dioxide, methane, and nitrous oxide—reached new records in 2021. In addition, these emissions increased by almost an additional 1% in the United States in 2022. Although While the reason for this increase is not entirely clear, it is likely the result of both biological and human processes, including increased gasoline use and the rebound in air travel after the COVID-19 pandemic.
While the United States has made great strides in reducing greenhouse gas emissions, one of the challenges it faces today is identifying the sources of these emissions and determining how much they produce. Traditionally, regulators have relied on different industries and others in the regulated community to collect information about greenhouse gas emissions, such as air emissions inventories and other self-reported data, for each source separately. Unfortunately, due to limited reporting requirements, incomplete and/or outdated inventories, and underreported emissions, these sources of information do not accurately portray what really happens to greenhouse gas emissions.
In fact, the new data indicates that among the major countries that report emissions from their oil and gas production to the United Nations, these emissions are actually three times higher than self-reported data. Where did this seemingly “fresh” information come from? The answer lies in artificial intelligence (AI). Using satellite coverage, remote sensing, machine learning, and artificial intelligence, it is now possible to identify and analyze sources of greenhouse gas emissions that were previously invisible to the human eye and undetectable by conventional modeling methods.
For example, ClimateTrace, a global nonprofit coalition created to independently track greenhouse gas emissions, uses more than 300 satellites, more than 11,100 sensors in the air, land, and sea, and additional public information to build models for estimates of greenhouse gas emissions. These models are then used to train the AI to spot subtle differences in satellite imagery and data patterns.
Last week, Climate TRACE released the most detailed global facility-level inventory of greenhouse gas emissions to date, including emissions data for more than 70,000 individual sources worldwide. These sources include power plants, steel mills, urban road networks, oil and gas production and refining, shipping, aviation, mining, waste, agriculture, transportation, and steel, cement and aluminum production. With the ability now to access and track information about millions of major sources of greenhouse gas emissions at our fingertips, the next question is whether and how this data can be used in the future to regulate greenhouse gas emissions. As it turns out, here in the States, we may not have to wait long for the answer.
In the wake of the Climate TRACE findings, the Biden-Harris administration announced a proposal to reduce methane pollution by 87% below 2005 levels by 2030. As part of their proposal, the administration would create a “super-emitter response program” that would use data from regulatory agencies or accredited third parties with expertise in Remote methane detection technology to identify large-scale emissions for immediate action.
Therefore, it is very likely that regulators will soon use artificial intelligence developed by third parties, such as Climate TRACE, in some capacity to monitor and/or enforce greenhouse gas emissions. At the very least, others across the country and around the world will almost certainly use this information to monitor the companies they work with now or consider engaging in business activities in the future.