首页|Research from University of Canterbury in the Area of Machine Learning Published (Supercooled liquid water cloud classification using lidar backscatter peak pro perties)
Research from University of Canterbury in the Area of Machine Learning Published (Supercooled liquid water cloud classification using lidar backscatter peak pro perties)
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 – A new study on artificial intelligence is now available. According to news reporting from Christchurch, New Zealand, b y NewsRx journalists, research stated, “The use of depolarization lidar to measu re atmospheric volume depolarization ratio (VDR) is a common technique to classi fy cloud phase (liquid or ice).” The news journalists obtained a quote from the research from University of Cante rbury: “Previous work using a machine learning framework, applied to peak proper ties derived from co-polarized attenuated backscatter data, has been demonstrate d to effectively detect supercooled-liquid-water-containing clouds (SLCCs). Howe ver, the training data from Davis Station, Antarctica, include no warm liquid wa ter clouds (WLWCs), potentially limiting the model’s accuracy in regions where W LWCs are present. In this work, we apply the same framework used on the Davis da ta to a 9-month micro-pulse lidar dataset collected in Otautahi / Christchurch, Aotearoa / New Zealand, a location which includes WLWC. We then evaluate the res ults relative to a reference VDR cloud-phase mask. We found that the Davis model performed relatively poorly at detecting SLCC with a recall score of 0.18, ofte n misclassifying WLWC as SLCC. The performance of our new model, trained using d ata from Otautahi / Christchurch, displays recall scores as high as 0.88 for ide ntification of SLCC, although it generally underestimates SLCC occurrence.”
University of CanterburyChristchurchNew ZealandAustralia and New ZealandCyborgsEmerging TechnologiesMachine Learning
NETL
NSTL
