Estimation of Spatially Continuous Near-Surface Relative Humidity Over Japan and South Korea

Abstract

Near-surface relative humidity (RHns) is an essential meteorological parameter for water, carbon, and climate studies. However, spatially continuous RHns estimation is difficult due to the spatial discontinuity of in-situ observations and the cloud contamination of satellite-based data. This study proposed machine learning-based models to estimate spatially continuous daily RHns at 1 km resolution over Japan and South Korea under all sky conditions and examined the spatiotemporal patterns of RHns. All sky estimation of RHns using machine learning has been rarely conducted, and it can be an alternative to the currently available RHns data mostly from numerical models, which have relatively low spatial resolution. We combined two schemes for clear sky conditions (scheme A, which uses satellite and reanalysis data) and cloudy sky conditions (scheme B, which uses reanalysis data solely). The relatively small numbers of data in extremely low and high RHns conditions (i.e., < 30% or > 70%, respectively) were augmented by applying an oversampling method to avoid biased training. The machine learning models based on random forest and XGBoost were trained and validated using 94 in-situ observation sites from meteorological administrations of both countries from 2012 to 2017. The results showed that XGBoost produced slightly better performance than random forest, and the spatially continuous RHns model combined based on XGBoost yielded the coefficient of determination of 0.72 and a root mean square error of 10.61%. Spatiotemporal patterns of the estimated RHns agreed with in-situ observations, reflecting the effect of topography on RHns. We expect that the proposed RHns model could be used in various environmental studies that require RHns under all sky conditions as input data.

Modeling primary production from carbon flux and satellite data

“…Considering sudden changes in Ta/VPD due to short-term rainfall smaller than the mesoscale is important for diurnal GPP estimation, but difficult even using the numerical model data. (Park et al, 2021;Yoo et al, 2022) or alternatively use of satellite products, such as LST. The recently proposed NIRvPbased estimation does not have a capability to incorporate the effects of diurnal stress into GPP estimation (Khan et al, 2022;Jeong et al, 2023).…”