The impact of environmental variables on surface Conductance: Advancing simulation with a nonlinear Machine learning model

Surface conductance (G_s) is a key factor in the Penman-Monteith (PM) equation; the interaction between environmental variables such as CO₂ concentration, air temperature (TA), vapor pressure deficit (VPD), soil water content (SWC), and net radiation (R) affects G_s, evapotranspiration and thus impacts the hydrological cycle. These interactions are highly nonlinear and vary among different vegetation types. However, conventional G_s simulation models use fixed interactions between environmental variables in their equations for all vegetation types. Moreover, the characterisation and parameterisation of conventional G_s models is highly uncertain due to the high spatiotemporal variability in key environmental variables and plant parameters, which inhibits their generalisation. This study investigates whether G_s could be estimated more accurately by nonlinear statistical techniques that capture the multiple interactions between the environmental variables that affect G_s for each vegetation type. We compare mixed generalized additive model (MGAM) for G_s simulation with semi-empirical and empirical models at 20 eddy covariance flux tower sites with four different vegetation types at daily and monthly timescales. The results show that the Nash-Sutcliffe Efficiency (NSE) in G_s simulation increased by up to 50% in MGAM model in comparison to the semi-empirical and empirical models. The MGAM model highlighted the interactive effects of CO₂, VPD, and SWC for crops and grasses. The interactive effects of CO₂, VPD, and TA were important for trees and grasses. The results from this study expand our understanding of the ability of G_s simulation models to identify and include the interactive effects of crucial environmental variables on plant transpiration and hydrological processes.