首页|Studies from Peking University Have Provided New Data on Machine Learning (Groun d Passive Microwave Remote Sensing of Atmospheric Profiles Using Wrf Simulations and Machine Learning Techniques)
Studies from Peking University Have Provided New Data on Machine Learning (Groun d Passive Microwave Remote Sensing of Atmospheric Profiles Using Wrf Simulations and Machine Learning Techniques)
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-Current study results on Machine Learning have be en published. According to news reporting out of Beijing, People's Republic of C hina, by NewsRx editors, research stated, "Microwave radiometer (MWR) demonstrat es exceptional efficacy in monitoring the atmospheric temperature and humidity p rofiles. A typical inversion algorithm for MWR involves the use of radiosonde me asurements as the training dataset." Financial support for this research came from National Natural Science Foundatio n of China (NSFC). Our news journalists obtained a quote from the research from Peking University, "However, this is challenging due to limitations in the temporal and spatial res olution of available sounding data, which often results in a lack of coincident data with MWR deployment locations. Our study proposes an alternative approach t o overcome these limitations by harnessing the Weather Research and Forecasting (WRF) model's renowned simulation capabilities, which offer high temporal and sp atial resolution. By using WRF simulations that collocate with the MWR deploymen t location as a substitute for radiosonde measurements or reanalysis data, our s tudy effectively mitigates the limitations associated with mismatching of MWR me asurements and the sites, which enables reliable MWR retrieval in diverse geogra phical settings. Different machine learning (ML) algorithms including extreme gr adient boosting (XGBoost), random forest (RF), light gradient boosting machine ( LightGBM), extra trees (ET), and backpropagation neural network (BPNN) are teste d by using WRF simulations, among which BPNN appears as the most superior, achie ving an accuracy with a root-mean-square error (RMSE) of 2.05 K for temperature, 0.67 g m-3 for water vapor density (WVD), and 13.98% for relative humidity (RH). Comparisons of temperature, RH, and WVD retrievals between our a lgorithm and the sounding-trained (RAD) algorithm indicate that our algorithm re markably outperforms the latter."
BeijingPeople's Republic of ChinaAsiaAlgorithmsCyborgsEmerging TechnologiesMachine LearningRemote SensingPeking University
NETL
NSTL
