PNNL

Abstract

Soil CO2 efflux is commonly measured monthly or seasonally, leaving daily dynamics poorlyresolved and contributing to global estimation uncertainty. We trained a single Long Short-Term Memory(LSTM) model to predict daily soil CO2 efflux across 82 globally distributed sites in COSORE, with0.2%–46.9% daily data coverage from 2003 to 2020. Despite using far fewer sites than are typically used to traina single deep learning model, with observations biased toward temperate mesic sites, the LSTM modelperformed well at approximately one-third of sites, reconstructed nearly 2 decades of daily efflux, andoutperformed commonly used approaches for estimating daily efflux when applied to the same data set.Performance was weakest at pronounced peaks and troughs and at non-temperate sites with