Estimation of Spatially Continuous Near-Surface Relative Humidity Over Japan and South Korea
Haemi Park, Junghee Lee, Cheolhee Yoo, Seongmun Sim, Jungho Im
Abstract
Near-surface relative humidity (RH <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ns</sub> ) is an essential meteorological parameter for water, carbon, and climate studies. However, spatially continuous RH <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ns</sub> estimation is difficult due to the spatial discontinuity of in situ observations and the cloud contamination of satellite-based data. This article proposed machine learning-based models to estimate spatially continuous daily RH <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ns</sub> at 1 km resolution over Japan and South Korea under all sky conditions and examined the spatiotemporal patterns of RH <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ns</sub> . All sky estimation of RH <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ns</sub> using machine learning has been rarely conducted, and it can be an alternative to the currently available RH <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ns</sub> 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 RH <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ns</sub> 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 (RF) 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 RF, and the spatially continuous RH <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ns</sub> 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 RH <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ns</sub> agreed with in situ observations, reflecting the effect of topography on RH <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ns</sub> . We expect that the proposed RH <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ns</sub> model could be used in various environmental studies that require RH <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ns</sub> under all sky conditions as input data.