微脈衝差分吸收光達(MPD)可提供在對流層低層高時間及高垂直解析度連續水氣剖面觀測資料。在2022TAHOPE實驗期間MPD被置放於北台灣三個地點：宜蘭、中央大學及新竹。這篇研究第一個目的是利用實驗期間收集的觀測資料分析在夏季不同天氣系統下北台灣的水氣特徵。我們發現在宜蘭是發生午後熱對流事件時水氣會最高。我們還利用MPD觀測去計算500-2000公尺的總可降水量(TPW)，發現在三個地點的午後熱對流、颱風、低氣壓造成的降水事件中，總可降水量皆可達22.3mm以上，而最大值是在宜蘭的午後熱對流事件高達24.18mm。此外，還去查看水氣跟風場的關係，在宜蘭跟新竹的水氣大小跟風向風速較無關，但在中央大學的測站有發現到當風速越大可以出現較高的水氣。研究的第二個目標是探究同化MPD對初始場和降水預報的影響，我們使用WRF-LETKF同化系統做了幾組實驗去測試。研究發現同時同化地面測站加上MPD的水氣可以得到更好的初始場。在午後熱對流個案中，當同化MPD水氣的水平影響半徑設成48公里比設成100公里在定量降水估計預報更好預測到北台灣及南台灣跟觀測一樣的降雨位置，在performance diagram 也得到更高的POD分數。然而在梅雨個案中，定量降水預報並沒有明顯的改善。研究結果顯示，MPD所觀測的水氣垂直剖面能有效掌握局部熱力環境；當水平影響半徑設定為 48 公里時，能取得更佳的預報結果，並對中尺度系統產生正面影響。;Micropulse Differential Absorption Lidar (MPD) provides continuous vertical water vapor profiles with high vertical and temporal resolution in the lower troposphere. The MPDs were conducted at three sites during Taiwan-Area Heavy rain Observation and Prediction Experiment (TAHOPE). In this study， the first objective is to investigate the water vapor characteristics over northern Taiwan in different weather systems. We found that water vapor at 500m in afternoon cases consistently ranks first or second at three sites. In addition， when calculating Layered Precipitable Water (LPW) using MPD data， the results showed that the highest value of LPW exceeded 24 mm in the afternoon thunderstorm case at Yilan. Furthermore， by examining the diurnal variations， it was found that water vapor in Mei-Yu， afternoon thunderstorm， and typhoon cases was higher during afternoon period (12 to 20 LST). We subsequently conducted several experiments which assimilated reflectivity and radial wind from radar data， water vapor and temperature from surface data， and water vapor profiles from MPDs during different type of severe weather events: afternoon thunderstorm case (SOP3) and Mei-Yu case (IOP3) to examined the impact of assimilating water vapor. WRF-LETKF Radar Assimilation System was used. The result showed that additionally assimilating MPD and surface data provides better thermodynamic environment during both cases. Moreover， the localization of water vapor observed by MPD set to 48km better captured the rainfall area over northern and southern Taiwan in forecast during afternoon thunderstorm case (SOP3) compared to that set to 100km. However， Quantitative Precipitation Forecasts (QPF) had limited improvement in Mei-Yu case. Therefore， the results indicate that humidity profiles observed by MPD can capture the localized thermodynamic environment， leading to better results when the localization is set to 48 km， and having the positive impact on mesoscale system.
