首页|Data from Colorado State University Advance Knowledge in Machine Learning (Retri eval of boundary layer precipitable water from GOES ABI using machine learning t echniques)
Data from Colorado State University Advance Knowledge in Machine Learning (Retri eval of boundary layer precipitable water from GOES ABI using machine learning t echniques)
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 – Researchers detail new data in artific ial intelligence. According to news originating from Fort Collins, Colorado, by NewsRx correspondents, research stated, “Low-level moisture is an important ingr edient for forecasting severe storms, especially over the Great Plains where sev ere storms often develop along the dryline.” Our news journalists obtained a quote from the research from Colorado State Univ ersity: “Although ground-based observation systems such as lidar or radiosondes on weather balloons provide accurate information on low-level moisture, data are provided at limited locations, and the low temporal resolution of radiosondes m akes it difficult to track a rapidly developing dryline. Geostationary satellite s provide high spatial and temporal observation, but the channels of current geo stationary satellites are mostly sensitive to water vapor at mid to upper levels . However, the split window difference (SWD) between the “clean” window channel (10.3 mm) and the “dirty” window channel (12.3 mm) is commonly used for estimati ng low-level water vapor. However, this estimation is complicated by surface tem perature contributions, dependence on the lapse rate, and nonlinear relationship s between SWD and moisture. This study applies machine learning techniques to in fer boundary layer precipitable water (BLPW) from Geostationary Operational Envi ronmental Satellite (GOES) Advanced Baseline Imager (ABI) data. Since there are few observations that cover wide regions for training convolutional neural netwo rks, especially for the atmosphere above the surface, High-Resolution Rapid Refr esh (HRRR) model outputs are used as the truth for training.”
Colorado State UniversityFort CollinsColoradoUnited StatesNorth and Central AmericaCyborgsEmerging Technolog iesMachine Learning
NETL
NSTL
