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.
