首页|Hong Kong University of Science and Technology Researchers Have Published New Da ta on Machine Learning (Estimation of groundlevel NO [ [2] ] and its spatiotemporal variations in China using GEMS measurements and a nested machine learning model)
Hong Kong University of Science and Technology Researchers Have Published New Da ta on Machine Learning (Estimation of groundlevel NO [ [2] ] and its spatiotemporal variations in China using GEMS measurements and a nested machine learning model)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators discuss new findings in artificial intelligence. According to news originating from Hong Kong, People’s Republic of China, by NewsRx editors, the research stated, “The major link betwe en satellite-derived vertical column densities (VCDs) of nitrogen dioxide (NO [ [2] ] ) and ground-leve l concentrations is theoretically the NO [ [2] ] mixing height (NMH). Various meteorol ogical parameters have been used as a proxy for NMH in existing studies.” Our news editors obtained a quote from the research from Hong Kong University of Science and Technology: “This study developed a nested XGBoost machine learning model to convert VCDs of NO [ [2] ] into ground-level NO [ [2] ] concentrations across China using Geo stationary Environmental Monitoring Spectrometer (GEMS) measurements. This neste d model was designed to directly incorporate NMH into the methodological framewo rk to estimate satellite-derived ground-level NO [ [2] ] concentrations. The inner machine lea rning model predicted the NMH from meteorological parameters, which were then in put into the main XGBoost machine learning model to predict the ground-level NO [ [2] ] concentrations from its VCDs. The inclusion of NMH significantly enhanced the ac curacy of ground-level NO [ [2] ] concentration estimates; i.e., the * * R* * 2 values were improved from 0.73 to 0.93 in 10-fold crossvalidation and from 0.8 8 to 0.99 in the fully trained model. Furthermore, NMH was identified as the sec ond most important predictor variable, following the VCDs of NO [ [2] ]. Subsequently, th e satellitederived ground-level NO [ [2] ] data were analyzed across subregions with varying geographi c locations and urbanization levels.”
NETL
NSTL
