快拆式淹水感測器之開發與應用(ECOMSNet)是以短延時強降雨為目標，期望降低都市受災的影響，進行具有邊際運算技術能力、方便安裝，與低廉維運成本之感測器開發。在創新分散式淹水預警系統架構下，感測器可快速從點的觀測推估到面之淹水預測。混合型快速淹水模型發展(HIM)整合細胞自動機(Cellular Automata)、數值高程模型開發(Digitial Elevation Model)以及一維下水道St. Venant控制方程式之都市快速淹水模式。結合衛星影像快速評估淹水範圍與深度透過Google Earth Engine（GEE）擷取衛星影像並判斷淹水範圍，接著使用 自行開發之SPM-GEE模式估計範圍內之淹水深度
Previous slide
Next slide
論文發表
1
2
A Novel Multimodal Large Language Model-Based Approach for Urban Flood Detection Using Open-Access Closed Circuit Television in Bandung, Indonesia
・Water, 17(18), 2739. (N/M=40/128=31.25%, WATER RESOURCES, 2023)
・Water, 17(18), 2739. (N/M=40/128=31.25%, WATER RESOURCES, 2023)
3
4
Combination of Large Language Models and Portable Flood Sensors for Community Flood Response: A Preliminary Study
・Water 2025, 17(7), 1055. (N/M=40/128=31.25%, WATER RESOURCES, 2023)
・Water 2025, 17(7), 1055. (N/M=40/128=31.25%, WATER RESOURCES, 2023)
