Data for Change

Creating a more effective model for CO2 flux in North America based on regional variables and inversely estimated target data

Can we create a carbon flux model that uses inverse model estimates of carbon flux to train a neural network? Instead of using scaled-up carbon flux data, we can use inverse model estimates that capture large-scale carbon flux features because they are directly linked to the atmospheric CO2 data. This differs from other models because instead of using site-level data for carbon flux, our model is using region-wide averages to provide a better idea of the activity of carbon flux over broader areas. But unlike site-level estimates, inverse fluxes lack some of the detailed information like the temporal resolution. …

Ashwin Kuppahally

High Schooler from Silicon Valley

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store