DSpace community: 大氣物理研究所

優化掩星觀測資料同化對颱風預報效益的評估研究;優化掩星觀測資料同化對颱風預報效益的評估研究

title: 優化掩星觀測資料同化對颱風預報效益的評估研究;優化掩星觀測資料同化對颱風預報效益的評估研究 abstract: 全球導航衛星系統無線電掩星（Global Navigation Satellite System Radio Occultation， GNSSRO）資料在觀測不足的區域提供豐富的資料，並在資料同化過程中扮演相當重要的角色。由於在低對流層的空氣密度劇烈變化，無線電波在掩星觀測裡會發生不同路徑的偏折，偏折角頻譜中的局部頻譜寬（Local Spectral Width， LSW）可用以代表無線電掩星觀測的不確定性，改善資料同化後的初始場進而修正熱帶氣旋的預報路徑。本研究採用格點統計插值（Gridpoint Statistical Interpolation， GSI）混成(hybrid)系統進行資料同化，並結合全球跨尺度天氣預報模式（Model for Prediction Across Scales–Atmosphere， MPAS），模擬2019年至2024年之間的熱帶氣旋預報。 GSI同化系統裡預設的觀測誤差與高度和緯度有著高度的相關性，利用LSW的特性部分取代原本預設的觀測誤差，同化過後再利用動態渦旋初始化（DVI）改善熱帶氣旋的初始場狀態，使其更接近最佳路徑的位置。在資料同化循環過程中，在O-B和O-A的垂直剖面上BNDM1大部分比BND還要小，水平面上的分析增量相比於GTS實驗，BND和BNDM1都有很顯著的差異，而BND和BNDM1之間的差異在溫度與濕度增量上大多為顯著的正值。在預報路徑中，BND和BNDM1的路徑預報結果差異不大，但相對於GTS來說有些許的改善。為了深入了解BND和BNDM1之間的差異，分別選取2019年米塔和2021年璨樹往後一天模擬結果表明，在路徑預報中，BNDM1比BND還更接近最佳路徑，在熱力場以及動力場上，LSW同化可以調整中低對流層的溫度、濕度以及風場，對於颱風的整體結構上，BNDM1可以很明確地顯示出靠近地形時颱風結構的變化。由系集敏感度分析(Ensemble Sensitivity Analysis， ESA)也表明BNDM1對於系集成員的風場調整也可以改善颱風預報的路徑。基於LSW品質控管的無線電掩星觀測資料為資料同化提供更好的初始條件，並提高熱帶氣旋路徑的預報度。;Global Positioning System (GPS) radio occultation (RO) data provides abundant observation data for assimilation system over regions with insufficient observation. The radio waves give rise to the different path deflection due to moisture variability in the lower troposphere. The local spectral width (LSW) from bending angle spectrum represents the uncertainty of RO observation， and then improves the initial fields for data assimilation to predict the track of the tropical cyclone. In this study， the Gridpoint Statistical Interpolation (GSI) hybrid system for data assimilation with the Model for Prediction Across Scales–Atmosphere (MPAS) is implemented and simulates the forecasts of tropical cyclone from 2019 to 2024. The representative error is highly correlated with altitude and latitude in the GSI system; however， the part of LSW is used to replace the default setting in GSI system for assimilating the RO data. The dynamical vortex initialization (DVI) is applied to improve the initial fields and get closer to the best track position after assimilation cycles. Four experiments are conducted: no data assimilation (CTRL)， assimilating conventional data only (GTS)， and RO bending angle with default (BND) or RO bending angle with LSW (BNDM1). During the data assimilation cycles， the analysis increments of BNDM1 on the vertical profile mostly get smaller values. The increments of BND and BNDM1 show the significant differences on the horizontal field compared to GTS. The differences between BND and BNDM1 in temperature and humidity increments are mostly significant positive values. The track of BNDM1 is similar to BND in most cases， but the tracks have statistically significant difference in all experiments. To understand the differences between BND and BNDM1， simulations were conducted one day later in Mitag (2019) and Chanthu (2021). The results showed the track of BNDM1 was closer to the best track than the track of BND. In thermal and dynamic structures， The data assimilation with LSW can effectively modulate the temperature， humidity， and wind field in the middle and lower troposphere. Regarding the overall structure of the typhoon， BNDM1 clearly demonstrates structural variations as the typhoon approaches terrain. Furthermore， the Ensemble Sensitivity Analysis (ESA) indicates that the adjustments made by BNDM1 to the wind fields of the ensemble members also contribute to the improvement of the simulated typhoon tracks. The results demonstrate RO data with LSW-based quality control provides better initial condition for data assimilation and improves the track prediction of tropical cyclone.

臺灣不同季節中尺度對流系統結構特徵之綜觀尺度系集敏感度分析 Synoptic-scale Ensemble Sensitivity Analysis of Mesoscale Convective System Structural Characteristics across Different Seasons in Taiwan;臺灣不同季節中尺度對流系統結構特徵之綜觀尺度系集敏感度分析 Synoptic-scale Ensemble Sensitivity Analysis of Mesoscale Convective System Structural Characteristics across Different Seasons in Taiwan

title: 臺灣不同季節中尺度對流系統結構特徵之綜觀尺度系集敏感度分析 Synoptic-scale Ensemble Sensitivity Analysis of Mesoscale Convective System Structural Characteristics across Different Seasons in Taiwan;臺灣不同季節中尺度對流系統結構特徵之綜觀尺度系集敏感度分析 Synoptic-scale Ensemble Sensitivity Analysis of Mesoscale Convective System Structural Characteristics across Different Seasons in Taiwan abstract: 本研究探討不同季節下影響臺灣中尺度對流系統（Mesoscale Convective Systems， MCSs）特徵之環境因子。MCS 特徵包含位置、頻率及對流面積等指標，利用中央氣象署 QPESUMS 雷達資料搭配 SMART 對流追蹤演算法進行辨識與追蹤，並結合 2006 年至 2024 年 ERA5 再分析資料作為環境場資料。研究採用皮爾森相關分析（Pearson correlation analysis）及系集敏感度分析（Ensemble Sensitivity Analysis， ESA），量化不同環境變數與 MCS 特徵之間的關聯。此外，本研究亦結合中央氣象署地面測站降雨觀測資料，比較不同 MCS 特徵所對應之降雨分布，以建立 MCS 形態特徵與降雨影響之間的連結。研究結果顯示，不同 MCS 特徵對環境條件具有不同程度之敏感性。依據各季節 MCS 特徵之 Top 3 環境因子家族比較結果，本研究選取垂直積分水氣輸送（Integrated Vapor Transport， IVT）及 500 hPa 比濕作為跨季節比較之共同關鍵因子。物理機制結果顯示，MCS 強對流面積與頻率呈現相似之環境關聯特徵。IVT 方面，暖季主要與來自南海之低層水氣輸送有關，冷季則轉為與臺灣東側海域之水氣輸送關聯較為明顯；500 hPa 比濕方面，中層高水氣區大多分布於臺灣上空，其中春、冬季偏向臺灣北部，而梅雨季、夏季及秋季則主要位於臺灣上空至偏南區域。降雨分析結果亦顯示，頻率較長之 MCS 較強對流面積較大者更容易產生局部累積雨量較高之降雨。相較之下，MCS 主要對流位置之環境控制機制有所不同。IVT 主要反映中國華南沿岸低層水氣輸送之強弱與位置，偏北發展之 MCS 通常方向較北抑或是輸送較北之低層水氣輸送；500 hPa 比濕則顯示，中層高水氣區之延伸位置與範圍與 MCS 主要發展區域具有良好對應關係，其降雨分布亦呈現向臺灣北部偏移之趨勢。此外，代表極端強度個案之物理機制與降雨分布特徵，相較於 Top 10% 群體更為明顯，進一步支持平均背景環境場分析之代表性。;This study investigates the environmental factors influencing the characteristics of mesoscale convective systems (MCSs) over Taiwan across different seasons. The MCS characteristics examined include convective location， frequency， and convective area. MCSs were identified and tracked using the SMART convective tracking algorithm applied to QPESUMS radar data provided by the Central Weather Administration (CWA)， while environmental conditions were obtained from the ERA5 reanalysis dataset for the period 2006–2024. Pearson correlation analysis and Ensemble Sensitivity Analysis (ESA) were employed to quantify the relationships between environmental variables and MCS characteristics. In addition， rainfall observations from the CWA surface rain gauge network were analyzed to compare the rainfall distributions associated with different MCS characteristics， thereby establishing the relationship between MCS morphology and rainfall impacts. The results indicate that different MCS characteristics exhibit varying sensitivities to environmental conditions. Based on a comparison of the Top 3 environmental variable families for each MCS characteristic in each season， vertically integrated vapor transport (IVT) and 500-hPa specific humidity were identified as the common key factors for cross-seasonal analysis. The physical mechanism analysis reveals that MCS convective area and frequency exhibit similar environmental characteristics. In terms of IVT， warm-season MCSs are primarily associated with low-level moisture transport originating from the South China Sea， whereas cold-season MCSs are more strongly related to moisture transport from the ocean east of Taiwan. Regarding 500-hPa specific humidity， enhanced mid-level moisture is generally distributed over Taiwan， with the moisture maximum located over northern Taiwan during spring and winter， and over central to southern Taiwan during the mei-yu， summer， and autumn seasons. Rainfall analyses further show that MCSs with longer frequency are more likely to produce higher localized accumulated rainfall than those with larger convective areas. In contrast， the environmental controls governing MCS location differ from those influencing convective area and duration. IVT primarily reflects the intensity and position of low-level moisture transport along the southern coast of China， with northward-developing MCSs generally corresponding to a more northward moisture transport pathway. Meanwhile， the spatial extent and position of enhanced 500-hPa specific humidity closely correspond to the preferred regions of MCS development， with the associated rainfall distribution also shifting northward over Taiwan. Furthermore， the physical mechanisms and rainfall characteristics of the most extreme cases are more pronounced than those represented by the Top 10% composites， further supporting the representativeness of analyses based on mean background environmental fields.

利用區域MPAS對侵臺並發生打轉路徑之颱風凱米（2024）的數值研究;A Numerical Study of the Track-Looping Typhoon Gaemi (2024) Impinging Taiwan Using Regional MPAS

title: 利用區域MPAS對侵臺並發生打轉路徑之颱風凱米（2024）的數值研究;A Numerical Study of the Track-Looping Typhoon Gaemi (2024) Impinging Taiwan Using Regional MPAS abstract: 颱風凱米生成於西太平洋，並由東側接近臺灣，在登陸前於臺灣東北部近海呈現迴轉路徑。本研究使用具20–2公里可變水平解析度之區域性跨尺度預報模式（Model for Prediction Across Scales， MPAS），探討凱米颱風接近臺灣期間的路徑演變及其相關降雨響應。控制組（CTL）實驗顯示，中央山脈（Central Mountain Range， CMR）會在臺灣東側誘發明顯的氣流通道效應，增強北風，進而促使凱米初期向南偏折，之後快速轉向北移。為找出較適合重現凱米迴轉路徑的模式設定，本研究針對不同微物理參數化方案進行敏感度實驗，並進一步利用系集模擬進行波數一（wavenumber-one， WN-1）位渦（potential vorticity， PV）收支分析，以探討迴轉期間路徑改變的動力機制。PV收支分析結果顯示，水平平流項在迴轉期間對颱風路徑改變具有主要貢獻，而垂直平流項則對後續向北轉向具有調節作用。模擬與觀測結果皆顯示，凱米迴轉期間臺灣西南部出現顯著強降雨。進一步以兩組採用不同微物理方案、各包含30個成員的系集進行系集敏感度分析（Ensemble Sensitivity Analysis， ESA），分別針對臺灣累積降雨與颱風中心駛流指標，辨識與降雨及路徑變異相關的前期環境特徵。降雨ESA結果顯示，臺灣西北側的比濕與風場呈現相互對應的敏感度分布，顯示颱風環流可能將暖濕空氣輸送至所選定的迎風面降雨區域。駛流ESA則顯示，最明顯的有利敏感度出現在臺灣西北側500 hPa緯向風分量，並向中國東南沿海延伸，顯示上游環境氣流對颱風移動具有重要調節作用。局地化多變量ESA在降雨與駛流響應中皆呈現空間上較一致的敏感度分布，其敏感度量值約為單變量ESA的三分之一，顯示局地化處理能有效抑制遠端雜訊的影響。;Typhoon Gaemi formed over the western Pacific and approached Taiwan from the east， exhibiting a looping track offshore of northeastern Taiwan before landfall. This study uses the regional Model for Prediction Across Scales (MPAS) with a variable horizontal resolution of 20–2 km to investigate the track evolution of Gaemi near Taiwan and the associated rainfall response. The CTL experiment shows that the Central Mountain Range (CMR) induces strong flow channeling east of Taiwan， enhancing northerly winds that contribute to the initial southward deflection of Gaemi before its rapid northward turn. Sensitivity experiments with different microphysics parameterization schemes were conducted to identify suitable configurations for reproducing the looping track， and ensemble simulations were further analyzed using wavenumber-one (WN-1) potential vorticity (PV) budgets. The PV budget analysis indicates that horizontal advection provides the dominant contribution to the track change during the looping period， while vertical advection modulates the subsequent northward turn. Both simulations and observations show heavy rainfall over southwestern Taiwan during this period. Ensemble Sensitivity Analysis (ESA)， based on two 30-member ensembles using different microphysics schemes， was applied to accumulated rainfall and storm-centered steering-flow metrics to identify precursor environmental features associated with rainfall and track variability. The rainfall ESA reveals corresponding sensitivity patterns in specific humidity and winds northwest of Taiwan， suggesting that the typhoon circulation transports warm and moist air toward the selected windward rainfall region. The steering-flow ESA identifies the strongest favorable sensitivity to the 500-hPa zonal wind component northwest of Taiwan， extending toward the southeastern coast of China， indicating the importance of the upstream environmental flow in modulating storm motion. A localized multivariate ESA produces spatially more coherent sensitivity patterns for both rainfall and steering-flow responses， with sensitivity magnitudes approximately one-third of those obtained from the univariate ESA， consistent with the suppression of remote noise through localization.

北臺灣微脈衝差分吸收光達資料分析與同化水氣及雷達之影響：TAHOPE SOP3及IOP3 個案分析;Analysis of MPD Lidar Data from Northern Taiwan and the Effects of Humidity and Radar Data Assimilation： Case Studies of TAHOPE SOP3 and IOP3

title: 北臺灣微脈衝差分吸收光達資料分析與同化水氣及雷達之影響：TAHOPE SOP3及IOP3 個案分析;Analysis of MPD Lidar Data from Northern Taiwan and the Effects of Humidity and Radar Data Assimilation： Case Studies of TAHOPE SOP3 and IOP3 abstract: 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.