Methane is the second most important anthropogenic greenhouse gas after CO2. As a short-lived climate forcing agent (lifetime ~10 years), it provides a lever for slowing near-term climate change. Major anthropogenic sources of methane include oil/gas exploration and use, livestock, landfills, coal mining, and rice cultivation. Wetlands are the dominant natural source. The magnitude and spatial distribution of methane sources is highly uncertain and difficult to constrain.
Figure: Simulated methane concentrations using emissions constrained by satellite observations.
The hydroxyl radical (OH) is the primary oxidant for a number of non-CO2 greenhouse gases and CFCs. It also regulates the production of tropospheric ozone, a leading pollutant. As such, changes in tropospheric OH could have large implications for both future climate and air quality. However we currently lack a predictive understanding of OH on decadal-to-centennial timescales, evidenced by the disagreement between global models in their simulation of OH.
Figure: OH concentrations in a 6000 year equilibrium simulation with a coupled chemistry-climate model.
Inverse models quantify the state variables driving the evolution of a physical system by using observations of that system. This requires a physical model that relates a set of input variables (state vector) to a set of output variables (observation vector). Obtaining solutions to high dimensional inverse problems can be computationally expensive or intractable.
Figure: Comparison source-receptor footprints generated by a full-physics model (left) and our FootNet machine learning model (right).