DSpace community: 水文與海洋科學研究所

Source Reconstruction of the 2026 Northern Molucca Sea Tsunami from Coastal Tide Gauge Waveforms;Source Reconstruction of the 2026 Northern Molucca Sea Tsunami from Coastal Tide Gauge Waveforms

Tue, 20 Oct 2026 07:12:27 GMT

title: Source Reconstruction of the 2026 Northern Molucca Sea Tsunami from Coastal Tide Gauge Waveforms;Source Reconstruction of the 2026 Northern Molucca Sea Tsunami from Coastal Tide Gauge Waveforms abstract: 2026年4月1日22時48分13秒（UTC），印度尼西亞北馬魯古海發生規模 Mw 7.4 地震，引發近場海嘯，周邊沿岸潮位站均記錄到相關波形。北米納哈薩（North Minahasa）觀測到的海平面振幅達0.75 m，比通（含倫貝島 Lembeh Island）則觀測到0.20 m（BMKG， 2026a）。本研究由涵蓋北馬魯古海的9個沿岸潮位站中選取6站，以其海嘯波形逆推本次地震的同震滑移分布。其餘3站不參與滑移逆推，保留作為逆推之外的一致性檢核。斷層模型幾何由海嘯反向傳播時間分析（Backward Tsunami Travel-Time，BTTT）及主震後24小時內的餘震空間分布共同約束。初步正演模擬採用三種由地震學資料推導的震源模型，包括全球地震矩張量目錄（GCMT）提供的NP1與NP2，以及美國地質調查所（USGS）的有限斷層模型。三種模型均系統性高估海嘯振幅，顯示有必要進行分布式滑移逆推。波形擬合誤差與餘震幾何共同顯示，在所測試的斷層面中，向西傾斜的GCMT NP2較符合觀測結果。本研究以COMCOT模式結合Okada（1985）彈性位錯理論建立格林函數矩陣，將斷層面離散為20個子斷層，並採非負最小平方法進行海嘯波形逆推。主要逆推所用的單位滑移格林函數由COMCOT線性淺水波方程模擬產生，理論上滿足逆推所需的疊加與尺度縮放性質；然而如下文診斷比較所示，實際數值實作仍存在約10–12%之振幅正規化偏差，此一性質尚不應視為已於數值上完全驗證。另以非線性淺水波方程產生的格林函數進行對照逆推。所得大尺度滑移型態、主要高滑移區及總地震矩均與主要結果相近，可作為一致性檢核。逆推結果顯示，滑移主要集中於NP2定向震源網格中央部位的一個緊密高滑移區，最大滑移約為4.44 m。此空間特徵較符合由馬魯古海主要板塊邊界逆衝斷層分支出的向西傾斜分支斷層（splay fault），而非主要隱沒介面本身。本研究實際建立的NP2定向震源網格，與依52°傾角沿傾向正確投影所得的平面斷層離散網格有所差異。因此，精確滑移量、深度及高滑移區位置均應視為具有模型相依性。此外，圖4.15的診斷比較顯示，5個測站仍存在約10–12%的振幅正規化偏差，故本文所報告的滑移量應在所採用之格林函數正規化條件下解讀。此外，觀測潮位紀錄採用測站專屬之帶通濾波處理，格林函數波形則未經相同濾波，兩者所代表之觀測算子並不完全相同，故本文所報告之振幅相依量亦可能包含未單獨量化之系統性前處理不確定性。作為補充敏感度測試，本研究亦以相同的6站資料，採無約束最小平方法逆推另一種初始自由表面參數化，得到正負交錯且具空間振盪特徵的多網格分布，其大尺度特徵與斷層滑移震源大致相符。以逆推滑移模型進行正演傳播模擬後，3個未參與滑移逆推的測站（BITU、LKPN及MTHMI）波形均獲得合理重現，可作為逆推之外的驗證；惟三站先前皆曾用於斷層幾何評估，故均非嚴格意義上的獨立盲測。模擬亦顯示，蘇拉威西島東部沿岸約於地震發生後10分鐘受到首波影響。Kema潮位站的模擬首波到時約為15分鐘，略早於NOAA/NCTR報告的約17分鐘首波偵測時間。研究結果顯示，馬魯古海發散型雙重隱沒系統具有高度近場海嘯危害，並凸顯建置可靠且能快速反應之海嘯預警基礎設施的迫切需求。;On 1 April 2026 at 22:48:13 UTC， an Mw 7.4 earthquake occurred in the northern Molucca Sea， Indonesia， generating a near-field tsunami recorded by coastal tide gauges. A sea-level amplitude of 0.75 m was observed at North Minahasa， and 0.20 m at Bitung (including Lembeh Island)， based on BMKG tide-gauge records (BMKG， 2026a). This study estimated the coseismic slip distribution of the earthquake by inverting tsunami waveforms recorded at six coastal tide-gauge stations selected from a nine-station network spanning the northern Molucca Sea. The remaining three stations were excluded from the slip inversion and retained for subsequent forward-model evaluation. The fault geometry was constrained using backward tsunami travel-time (BTTT) analysis and the spatial distribution of aftershocks within 24 hours of the mainshock. Preliminary forward simulations were conducted using three seismologically derived source models: the Global Centroid Moment Tensor (GCMT; Dziewonski et al.， 1981) NP1 and NP2 nodal planes and the USGS finite-fault model. All three models systematically overestimated the observed tsunami amplitudes， indicating the need for a distributed slip inversion. The combined evidence from waveform misfits and aftershock geometry favored the west-dipping GCMT NP2 among the tested planar fault geometries. The primary tsunami waveform inversion employed non-negative least squares and a Green′s-function matrix constructed from unit-slip sources on 20 subfaults. Initial seafloor deformation for each source was calculated using the Okada (1985) elastic dislocation model， and tsunami propagation was simulated with COMCOT using the linear shallow-water equations. This formulation is theoretically consistent with the superposition and amplitude-scaling properties required for Green′s-function inversion， subject to the numerical-implementation caveat noted below. A parallel inversion using Green′s functions generated with the nonlinear shallow-water equations was also conducted as a consistency test. It produced a similar large-scale slip pattern， dominant high-slip area， and total seismic moment. The recovered source was dominated by a compact high-slip asperity， with a peak slip of approximately 4.44 m， located within the central portion of the implemented NP2-oriented source grid. This geometry is consistent with rupture on a west-dipping splay fault branching from the main Molucca Sea plate-boundary thrust and may be associated with the Maju Thrust. However， the results do not conclusively identify the mapped Maju Thrust as the causative fault. The implemented NP2-oriented source grid differs from a geometrically correct planar grid projected along a dip of 52°. Consequently， the precise slip magnitude， source depth， and asperity location should be regarded as model-dependent. A diagnostic comparison also revealed a residual amplitude-normalization offset of approximately 10–12% at five stations. The reported slip magnitudes should therefore be interpreted as conditional on the Green′s-function normalization adopted in this study. Station-specific bandpass filtering， not replicated in the synthetic waveforms， adds a further unquantified uncertainty. As a complementary sensitivity test， an alternative initial-free-surface parameterization was inverted from the same six-station dataset using unconstrained least squares. The resulting distribution contained alternating positive and negative displacements with spatial oscillations， although its large-scale characteristics were broadly consistent with those of the fault-slip source model. Forward propagation simulations using the inverted slip model reproduced the waveforms at the three stations excluded from the slip inversion with satisfactory agreement. BITU， LKPN， and MTHMI therefore provide out-of-inversion consistency checks， although all three had previously contributed to fault-geometry assessment. The simulations indicate that the first tsunami wave reached parts of the modeled coastal waters along eastern Sulawesi approximately 10 minutes after the earthquake. At the Kema tide gauge， the simulated first arrival occurred approximately 15 minutes after the origin time， slightly earlier than the approximately 17-minute first detection reported by NOAA/NCTR. These findings indicate the substantial near-field tsunami hazard associated with the divergent double-subduction system of the Molucca Sea and highlight the urgent need for reliable rapid-response tsunami-warning infrastructure.

應用物理資訊神經網路建立颱風氣象場預報模式及其於暴潮模擬之應用;Development of a Physics-Informed Neural Network Model for Typhoon Meteorological Field Forecasting and Its Application to Storm Surge Simulation

Tue, 20 Oct 2026 07:12:13 GMT

title: 應用物理資訊神經網路建立颱風氣象場預報模式及其於暴潮模擬之應用;Development of a Physics-Informed Neural Network Model for Typhoon Meteorological Field Forecasting and Its Application to Storm Surge Simulation abstract: 臺灣位於西北太平洋颱風主要侵襲路徑上，每年夏秋季經常受到颱風影響，伴隨強風、豪雨及風暴潮等災害。其中，風暴潮所造成之沿海淹水、港灣設施損壞及海岸侵蝕等問題，對沿岸地區之生命財產安全與經濟活動造成嚴重衝擊。因此，如何提升風暴潮預報之準確性與效率，已成為防災與海岸工程領域的重要研究課題。　　風暴潮模擬結果高度依賴海面風場與氣壓場之準確性。然而，目前常用之參數化風場模型多建立於理想化與軸對稱假設，難以描述颱風通過臺灣時受中央山脈地形阻擋、繞流及通道效應影響所產生之風場變形、強度削弱與局部增強等現象；另一方面，高解析度數值天氣模式雖可提供受地形影響後之氣象場資訊，但其計算成本高且不利於即時預報應用。因此，發展兼具計算效率與物理合理性之颱風氣象場重建方法，具有重要之研究與實務價值。　　本研究以ERA5再分析資料為基礎，建立臺灣周邊颱風氣象場資料庫，並利用颱風路徑、中心氣壓及最大風速等特徵作為模型輸入，學習臺灣地形影響下之颱風氣象場空間分布特徵。為評估不同機器學習方法於颱風氣象場重建之適用性，本研究首先建構卷積神經網路（Convolutional Neural Network， CNN）作為純資料驅動基準模型，並進一步發展物理資訊神經網路（Physics-Informed Neural Networks， PINNs）模型，進行颱風氣壓場以及風場重建。PINNs模型於訓練過程中結合觀測資料與物理約束條件，使模型在學習氣象場空間分布特徵之同時，亦能維持物理一致性，進而提升模型於極端條件下之穩定性與泛化能力。　　研究結果顯示，相較於純資料驅動模型，PINNs能較準確重建颱風中心附近之強梯度氣壓場與風場結構，並有效捕捉受臺灣地形影響所形成之非對稱分布特徵。在氣壓場、風場及暴潮空間分布等評估指標上，PINNs於各項評估指標中均呈現較低之誤差與較高之空間分布一致性。進一步將重建之氣象場輸入COMCOT風暴潮模式進行模擬，結果顯示PINNs所重建之氣壓場及風場能夠合理再現暴潮空間分布特徵，且與ERA5驅動之模擬結果呈現相近之空間分布與變化特徵。本研究證實，透過PINNs結合地形鎖定效應與物理約束之建模方法，可有效提升颱風風壓場重建能力，並具備快速重建氣象場之能力，可有效降低高解析度數值天氣模式所需之計算成本。未來可進一步精進，輔助於即時風暴潮預報系統，提供臺灣沿岸防災決策與風險管理之重要參考。;Taiwan is frequently affected by typhoons originating in the western North Pacific， which often bring strong winds， heavy rainfall， and storm surges. Among these hazards， storm surges can cause coastal flooding， damage to harbor facilities， and coastal erosion， posing serious threats to lives， property， and economic activities in coastal regions. Therefore， improving the accuracy and efficiency of storm surge forecasting is an important issue in disaster prevention and coastal engineering. The reliability of storm surge simulations strongly depends on the accuracy of surface wind and atmospheric pressure fields used as forcing inputs. However， conventional parametric typhoon wind field models are usually based on idealized and axisymmetric assumptions， making it difficult to represent the deformation， weakening， and localized enhancement of wind fields caused by the blocking， channeling， and flow-deflection effects of Taiwan’s Central Mountain Range. Although high-resolution numerical weather prediction models provide more realistic wind and pressure fields， their high computational cost limits their application in real-time forecasting. In this study， a typhoon wind and pressure field database was established using ERA5 reanalysis data over the Taiwan region. Typhoon track information， central pressure， and maximum wind speed were used as input features to reconstruct wind and pressure fields affected by Taiwan’s complex terrain. A Convolutional Neural Network (CNN) was first developed as a purely data-driven baseline model， followed by a Physics-Informed Neural Network (PINN) for typhoon wind and pressure field reconstruction. By incorporating physical constraints into the training process， the PINNs model improves physical consistency， model stability， and generalization capability under extreme typhoon conditions. The results show that the PINNs model outperforms the conventional CNN model in reconstructing strong pressure gradients and wind structures near the typhoon center， while also capturing asymmetric spatial patterns induced by Taiwan’s terrain. In terms of pressure field reconstruction， wind field reconstruction， and spatial structural similarity， the PINNs model achieves lower prediction errors and higher similarity. Furthermore， the reconstructed wind and pressure fields were used as forcing inputs for the COMCOT storm surge model. The resulting storm surge simulations reasonably reproduce the spatial distribution characteristics of storm surges and exhibit similar spatial distribution with simulations driven by ERA5 reanalysis data. Overall， this study demonstrates that integrating topography locking effects and physical constraints through PINNs can effectively improve the reconstruction of typhoon wind and pressure fields. The proposed framework enables rapid generation of physically consistent forcing fields and reduces the computational cost associated with high-resolution numerical weather prediction models. Therefore， it has strong potential for application in real-time storm surge forecasting and can support coastal disaster prevention， emergency response， and risk management in Taiwan.

以三維數值模式探討海嘯湧潮作用下結構物周圍之流場與沖刷特性暨前置犧牲結構之影響;Three-Dimensional Numerical Investigation of Flow Field and Scour Characteristics around Structures under Tsunami Bore Conditions: Effects of Front Sacrificial Structures

Tue, 20 Oct 2026 07:12:03 GMT

title: 以三維數值模式探討海嘯湧潮作用下結構物周圍之流場與沖刷特性暨前置犧牲結構之影響;Three-Dimensional Numerical Investigation of Flow Field and Scour Characteristics around Structures under Tsunami Bore Conditions: Effects of Front Sacrificial Structures abstract: 本研究以三維數值模式探討海嘯湧潮作用下圓柱結構物周圍之流場變化、自由液面抬升與局部沖刷特性，並分析前置犧牲結構對主圓柱周圍水流與床面沖淤型態之影響。研究內容分為兩部分：首先以穩態流作用下之單一圓柱作為基礎案例，分析圓柱迎水面壅高、滯流區、壓力集中與下游尾流等流場特徵；其次以潰壩流型態模擬海嘯湧潮入侵，建立可動床條件下之單一圓柱基準案例，並進一步比較不同前置犧牲結構配置之影響。本研究採用改良型 Truchas / Splash3D 三維數值模式，結合 VOF（Volume of Fluid）方法追蹤水體與空氣間之自由液面變化，並以非連續雙黏性模型（Discontinuous Bi-viscous Model， DBM）描述底床材料受高速水流作用後之變形與位移。潰壩流案例中，除單一圓柱基準案例外，另配置前置犧牲圓柱高度 0.3H_0、0.5H_0、0.8H_0，以及半徑 1.0D之單一前置圓球與雙前置圓球並排案例，以比較不同前置結構形式對主圓柱入流條件、近底床速度、壓力分布與床面沖淤之影響。數值結果顯示，潰壩流波前撞擊單一圓柱後，圓柱迎水面形成局部滯流區與壓力集中，使部分水平動量轉換為壓力能與垂向動量，進而造成自由液面壅高與非定常流場變化。配置前置犧牲結構後，前置結構物會優先承受波前衝擊並於其周圍形成局部沖刷；同時，其後方產生之遮蔽、分流與尾流作用亦會改變主圓柱前方入流條件，使主圓柱周圍床面沖淤型態產生變化。量化結果顯示，單一圓柱案例中主圓柱上游側平均床面變化為負值，呈現平均沖刷趨勢；加入前置犧牲圓柱後，該區域平均床面變化轉為正值，表示主圓柱上游側由平均沖刷趨勢轉為平均堆積趨勢。其中，前置圓柱高度由 0.3H_0增加至 0.5H_0時，平均堆積量增加；當高度進一步增加至 0.8H_0時，平均堆積量未再增加，而呈現略微下降或趨於平緩之趨勢，顯示前置圓柱高度增加所帶來之床面改善效果並非線性增強。整體而言，前置犧牲結構並非單純消除沖刷，而是透過改變入流條件、重新分配水流動量與轉移局部沖刷位置，進而影響主圓柱周圍床面沖淤型態。本研究以 S/D、Δz_b/D 與 h_s/H_0作為主要無因次量化指標，研究成果可作為潰壩流型海嘯湧潮條件下，理解前置犧牲結構對主圓柱周圍沖淤型態、流場調控與沖刷轉移機制影響之初步數值依據，並可供後續水槽實驗、模式驗證及參數化配置研究參考。;This study employs a three-dimensional numerical model to investigate flow-field variations， free-surface rise， and local scour characteristics around a circular cylinder under tsunami bore conditions， with emphasis on the influence of front sacrificial structures on the flow field and bed morphological changes around the main cylinder. The study consists of two parts. First， a single cylinder under steady flow conditions is used as a baseline case to examine upstream water-level rise， stagnation region， pressure concentration， and downstream wake characteristics. Second， a dam-break flow is adopted to simulate tsunami bore inundation， and a movable-bed single-cylinder case is established as the reference case for comparison with different front sacrificial structure configurations. The simulations are conducted using a modified Truchas / Splash3D three-dimensional numerical model. The Volume of Fluid (VOF) method is used to track the free-surface variation between water and air， while the Discontinuous Bi-viscous Model (DBM) is applied to describe bed deformation and displacement under high-speed flow conditions. In the dam-break cases， in addition to the single-cylinder baseline case， front sacrificial cylinders with heights of 0.3H_0， 0.5H_0， and 0.8H_0， as well as a single front sphere and a double-sphere side-by-side configuration with a radius of 1.0D， are considered to evaluate their effects on the inflow condition， near-bed velocity， pressure distribution， and bed morphological changes around the main cylinder. The numerical results show that when the dam-break bore impacts the single cylinder， a local stagnation region and pressure concentration form on the upstream face of the cylinder. Part of the horizontal momentum is converted into pressure energy and vertical momentum， resulting in local free-surface rise and unsteady flow-field variations. After front sacrificial structures are installed， the sacrificial structures directly receive the incoming bore impact and experience local scour around themselves. Meanwhile， the shielding， flow diversion， and wake effects formed behind the sacrificial structures modify the inflow conditions in front of the main cylinder and change the scour and deposition patterns around it. The quantitative results indicate that the mean bed elevation change upstream of the main cylinder is negative in the single-cylinder case， showing an average scouring trend. After installing front sacrificial cylinders， the mean bed elevation change in this region becomes positive， indicating a transition from average scour to average deposition. The mean deposition increases as the front-cylinder height increases from 0.3H_0 to 0.5H_0. However， when the height further increases to 0.8H_0， the mean deposition does not continue to increase and instead shows a slight decrease or a tendency to level off， suggesting that the bed-improvement effect of increasing front-cylinder height is not linear. Overall， the front sacrificial structures do not simply eliminate scour. Instead， they modify the inflow conditions， redistribute flow momentum， and transfer local scour locations， thereby influencing the bed morphological pattern around the main cylinder. In this study， S/D， Δz_b/D， and h_s/H_(0 )are used as the main dimensionless parameters. The findings provide preliminary numerical evidence for understanding how front sacrificial structures influence bed morphological patterns， local flow regulation， and scour-transfer mechanisms around the main cylinder under dam-break-type tsunami bore conditions， and may serve as a reference for future flume experiments， model validation， and parametric configuration studies.

應用雙段式參數化風場與近岸淺水海面拖曳係數校正提升暴潮模擬精度：以 2025 年丹娜絲颱風為例;應用雙段式參數化風場與近岸淺水海面拖曳係數校正提升暴潮模擬精度：以 2025 年丹娜絲颱風為例

Tue, 20 Oct 2026 07:11:39 GMT

title: 應用雙段式參數化風場與近岸淺水海面拖曳係數校正提升暴潮模擬精度：以 2025 年丹娜絲颱風為例;應用雙段式參數化風場與近岸淺水海面拖曳係數校正提升暴潮模擬精度：以 2025 年丹娜絲颱風為例 abstract: 2025 年 7 月，中度颱風丹娜絲以特殊路徑影響臺灣西南沿岸，並於臺南七股等低窪沿海地區造成海水倒灌。潮位觀測顯示，本次事件具有明顯之空間局部性與短延時特徵，其中東石潮位站出現暴潮偏差由負值快速轉為正值之「先降後昇」現象，將軍潮位站則出現短時間、高振幅之正暴潮尖峰。現行氣象署作業化 COMCOT-SS 暴潮預報設定雖可描述部分背景潮汐變化，但未能有效重現上述暴潮偏差之相位與振幅，顯示模式於近岸地形、颱風風場結構及海氣動量交換之描述仍有改善空間。本研究以 COMCOT-SS 暴潮模式為基礎，採分階段敏感度與交叉敏感度分析架構，依序檢驗地形解析度、參數化理想風場、最大風速及海表面拖曳係數對模擬結果之影響。首先，將臺灣西南沿岸巢狀網格解析度由公里級提高至約 200 m，以改善潮間帶、淺灘與局部岸線之地形表示；其次，建立 Two-Segment 參數化風場，分別描述內圈風速增長與外圈風速衰減，並進一步進行最大風速與拖曳係數敏感度試驗，其中拖曳係數係由 Charnock 關係、對數風速律及粗糙長度上限動態計算。結果顯示，提高地形解析度可改善近岸水深與測站格點之描述，但不足以單獨重現東石站之強烈負暴潮偏差與將軍站之正暴潮尖峰。Two-Segment 風場可使暴潮偏差歷線較為集中，並改善東石站負轉正之相位及將軍站整體模擬誤差；提高最大風速則可增強暴潮振幅，但仍無法單獨完整重現觀測極值。進一步調整拖曳係數後，海氣動量交換增強，使東石與將軍站之水位歷線及暴潮偏差獲得較一致之改善。研究結果顯示，丹娜絲颱風暴潮模擬誤差並非由單一因素造成，而是受到近岸地形、風場結構、颱風強度及海氣動量交換共同影響。本研究建立之控制變因分析流程與近岸拖曳係數敏感度架構，可作為臺灣西南沿岸暴潮預報系統在地化校正之事件型科學參考；惟相關參數仍需透過更多颱風案例及獨立觀測資料進一步驗證。;In July 2025， Typhoon Danas followed an atypical track toward southwestern Taiwan and caused coastal inundation in low-lying areas， including Qigu， Tainan. Tide-gauge observations revealed that the event exhibited highly localized and short-duration storm-surge characteristics. At the Dongshi tide gauge， the surge residual recorded a rapid transition from negative to positive， whereas the Jiangjun tide gauge recorded a brief， high-amplitude positive surge peak. Although the operational COMCOT-SS storm-surge forecasting configuration used by the Central Weather Administration could reproduce part of the background tidal variation， it failed to adequately capture the phase and amplitude of these surge residuals. This indicates that improvements are still needed in the representation of nearshore topography， typhoon wind-field structure， and air–sea momentum exchange. Based on the COMCOT-SS storm-surge model， this study employed a controlled sensitivity-analysis framework to sequentially examine the effects of topographic resolution， parametric wind-field structure， maximum wind speed， and sea-surface drag coefficient on the simulated storm surge. First， the resolution of the nested grids along the southwestern coast of Taiwan was increased from the kilometer scale to approximately 200 m to improve the representation of intertidal zones， shallow banks， and local shorelines. Second， a Two-Segment parametric wind-field model was developed to separately describe the increase in inner-core wind speed within the radius of maximum wind and the decay of the outer wind field beyond it. Sensitivity experiments were then conducted for the maximum wind speed and drag coefficient. The drag coefficient was dynamically calculated using the Charnock relation， the logarithmic wind profile， and an upper limit on aerodynamic roughness length. The results show that increasing topographic resolution improved the representation of nearshore bathymetry and tide-gauge grid locations， but was insufficient to independently reproduce the strong negative surge residual at Dongshi and the positive surge peak at Jiangjun. The Two-Segment wind field produced a more temporally concentrated surge response and improved the transition from negative to positive residuals at Dongshi， as well as the overall simulation error at Jiangjun. Increasing the maximum wind speed enhanced the surge amplitude， but could not independently reproduce the observed extreme values. Further adjustment of the drag coefficient strengthened air–sea momentum transfer and resulted in more consistent improvements in the simulated water-level and storm-surge residual time series at both stations. These findings indicate that the simulation errors during Typhoon Danas were not caused by a single factor， but were jointly influenced by nearshore topography， wind-field structure， typhoon intensity， and air–sea momentum exchange. The controlled sensitivity-analysis framework and nearshore drag-coefficient sensitivity approach developed in this study provide an event-based scientific reference for the localized calibration of storm-surge forecasting systems along the southwestern coast of Taiwan. However， the applicability of the proposed parameters requires further verification using additional typhoon cases and independent observational datasets.