集水區空間貿訊萃取及坡面泥砂產量推估之研究

Automated Watershed Delineation for Spatial Information Extraction and Slopeland Sediment Yield Evaluation

林文賜(Wen-Tzu Lin) ； 林昭遠(Chao-Yuan Lin) ； 周天穎(Tien-Yin Chou)

《航測及遙測學刊》 8卷3期 (2003/09) Pp. 33-58

https://doi.org/10.6574/JPRS.2003.8(3).3

摘要

水土保持之理論基礎及實務應用多以集水區為評估單元，往昔集水區資訊之萃取主要以人工方式量測，近年來隨電腦科技之進步，數值高程模型資料於集水區自動劃分及水系網萃取的技術已臻成熟，利用電腦量化集水區資訊應用於坡地災害分析為時勢所趨。本研究以集水區自動劃分理論為主軸，針對窪地出口、流向迴路、集水區門檻值劃分及水系網萃取等項目提出改進方法，以石門、德基及曾文水庫集水區為驗證樣區，自動萃取集水區範圍及水系網分布。另由集水區自動劃分理論，結合通用土壤流失公式(USLE)及泥砂遞移率(SDR)之計算，建立集水區坡面泥砂產量推估模式，以石門、德基、曾文水庫及二仁溪上游集水區為驗證區域，推估集水區土壤沖蝕量及坡面泥砂產量之空間分布，其結果分述如下：
藉由高差法(Jenson and Domlngue,1988)及本研究所推導之斜面法能計算集水區之初始流向，輔以窪地集水區法結合PROMETHEE理論計算建立集水區之無窪地流向。石門、德基及曾文水庫集水區之流向計算，與傳統方法（高程平滑化法、窪地填高法及逐步填高法）比較，以窪地集水區法最為精確。以石門、德基及曾文水庫集水區之水庫大壩為出流口，動態萃取之集水區面積為75634 ha、52367 ha及48395 ha。而真實水系網之萃取，由於集水區之地形、地質、土壤及氣候為非均一性，單一門檻值所萃取水系網無法代表真實水系網，本研究以多重門檻值取代傳統單一門檻值，其結果可確實反應水系網分布現況。
集水區坡面泥砂產量之推估結果，石門、德基、曾文水庫及二仁溪上游集水區之年泥砂產量分別為1928168 tons/yr、1793742 tons/yr、4807205 tons/yr及5074396 tons/yr，年平均沖蝕深度分別為1.82mm、2.45mm、7.10mm及25.81mm，以有泥岩分布之曾文水庫及二仁溪上游集水區較為嚴重。集水區坡面泥砂產量推估以Nash and Sutcliffe (1970)公式所計算之模式效率(ME)為81.21%，另由集水區泥砂產量推估值(Ŷ)與實測值(Y)相關分析結果，呈顯著正相關Ŷ=1.15Y(R^2=0.96*，n=4)。

關鍵字

集水區自動劃分 ； 窪地集水區 ； 多重門檻值 ； 泥砂遞移率 ； 泥砂產量

並列摘要

Watershed unit has been regarded as an analyzed object for slopeland disaster assessment. With the fast growing progress of computer technologies, instead of manual operation, there is a trend of applying Digital Elevation Model (DEM) in automated watershed delineating and drainage network design. This study first focused on improving extraction method for automated watershed delineating. The concepts for depression outlets decision, looped drainage direction calculation, reasonable watersheds area delineation, and simulation of realistic drainage networks are all revised to propose a new approach for more reasonable and efficient in watershed delineation. Three major reservoir watersheds (Shihmen, Techi and Tsenwen) were chosen to calculate watershed geomorphologic and hydrologic information for verifying the suitability of proposed approach. Universal Soil Loss Equation (USLE) and Sediment Delivery Ratio (SDR) coupled with automated watershed delineation theory is applied to estimate watershed sediment yield. The system shows good performance for Shihmen, Techi, Tsenwen reservoir and Erzen creek watersheds. The results are summarized as follows:
This study proposed surface-inclining approach to couple with elevation-differencing approach (Jenson and Domingue, 1988) for determining incipient drainage directions. The calculation of optimal outlet and drainage direction in the depressions can be performed using watershed depression approach with PROMETHEE theory. Compared with elevation-smoothing, depression-filling and repeatedly elevation-incrementing approaches, the drainage directions for Shihmen, Techi and Twensen reservoir watersheds calculated by watershed depression approach show more reasonable and realistic outcomes. The watershed area extracted for Shihmen, Techi and Twensen reservoir with the outlet located at the site of dam is 75634 ha, 52367 ha and 48396 ha, respectively. Due to inhomogeneous characteristics of geomorphology, geology, soil and/or climates of a watershed, the real drainage networks can not be delineated properly using single-threshold approach. Instead, a multiple-threshold approach is developed to cope with the real spatial distribution of streams in a watershed.
Annual watershed sediment yield calculated for Shihmen, Techi, Twensen reservoirs and Erzen creek is 1928168 tons/yr, 1793742 tons/yr, 4807205 tons/yr and 5074396 tons/yr, and the corresponding annual erosion depth is 1.82mm, 2.45mm, 7.10mm and 25.81mm, respectively. Tsenwen reservoir and Erzen creek show higher erosion depth because of moderate mudstone distribution in the watershed. Model efficiency calculated using Nash and Sutcliffe (1970) for sediment yield estimation is 81.21%, the model (Ŷ=1.15Y, R^2=0.96*) shows significant correlation between estimated (Ŷ) and measured (Y) data.

並列關鍵字

Automated watershed delineation ； Depression watershed ； Multiple-threshold method ； Sediment Delivery Ratio (SDR) ； Sediment Yield