基於合成孔徑雷達數據建構卷積長短期記憶模型之洪水測繪技術;SAR-based change detection for flood mapping using a Convolutional LSTM-driven framework

NCUIR > Engineering College > Graduate Institute of Civil Engineering > Electronic Thesis & Dissertation > Item 987654321/88960

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/88960

Title:	基於合成孔徑雷達數據建構卷積長短期記憶模型之洪水測繪技術;SAR-based change detection for flood mapping using a Convolutional LSTM-driven framework
Authors:	武樂;Ulloa, Noel Ivan
Contributors:	土木工程學系
Keywords:	淹水;合成孔徑雷達;Flooding;Synthetic Aperture Radar;LSTM
Date:	2022-07-20
Issue Date:	2022-10-04 10:45:08 (UTC+8)
Publisher:	國立中央大學
Abstract:	利用合成孔徑雷達 (Synthetic Aperture Radar, SAR) 影像進行地表變遷偵測已廣泛應用於洪泛監測。然而利用變遷監測界定洪泛區域時，由於並非所有地表變化都由洪水引起，使得其應用有諸多限制，例如農田上的作物生長或收成、林地或地表植生的移除，以及都市內建物的變遷等，加之SAR訊號對這些變化十分敏感，往往導致監測結果產生錯誤。據此，本研究提出以深度學習為基礎之時空模擬框架—卷積長短期記憶模型 (Convolutional Long Short-Term Memory, ConvLSTM)來處理多時序影像地表變分析，並應用於Sentinel-1之多時序SAR影像，針對於洪水事件發生前進行影像模擬，並備妥合成影像（以下稱模擬影像），配合洪水事件後影像（以下稱觀測影像）進行變遷偵測來界定洪泛區域。具體之方法為透過設定閾值於差異Delta影像（模擬減去觀察影像），進而界定出模擬影像和觀察影像間有顯著差異之洪泛區域。針對極端天氣事件之洪災問題，能有效增進衛星影像偵測之效能。本研究為基於ConvLSTM框架，利用多時序SAR影像進行洪泛區域變遷偵測，並實際應用於三個地區之不同淹水事件：澳大利亞昆士蘭艾薩克地區的黛比颶風 (Cyclone Debbie)、莫三比克索法拉地區的伊代颶風(Cyclone Idai)、以及巴西貝洛奧里藏特都會區的布魯馬迪紐市潰壩事件 (Brumadinho Dam Collapse)。為量化結果之正確率，本研究將偵測之淹水潛勢圖與Sentinel 2和Planet Labs等光學影像進行比對；為進一步證實本模型之效能，本研究試驗了四種變遷偵測方案：(1)使用最接近事件的事後影像減事件前影像，(2)使用歷史平均值減事件後影像，(3)傳統LSTM以及(3)本研究使用之ConvLSTM。結果顯示，ConvLSTM的Delta影像閾值化結果在所有研究案例皆有最高的Cohen Kappa係數：艾薩克地區為0.92、索法拉省為0.78、以及貝洛奧里藏特地區為 0.68。其中於莫三比克以及貝洛奧里藏特都會區的試驗得到了較低的Kappa值，分析其主要因素可歸因於地表植生類型、土壤水含量以及地形對SAR影像造成之影響。綜合本研究成果可以發現，應用本研究提出之卷積運算變遷偵測框架，可針有效針對SAR影像進行空間相關性之時間序列分析，並提高變遷偵測在洪泛區域界定上之正確性。 ;Synthetic Aperture Radar (SAR) imagery has been widely applied for flooding mapping based on change detection approaches. However, errors in the mapping result are expected since not all land-cover changes are flood-induced, and those changes are sensitive to SAR data, such as crop growth or harvest over agricultural lands, clearance of forested areas, and/or modifications to the urban landscape. This study, therefore, incorporated historical SAR images to boost the detection of flood-induced changes during extreme weather events, by applying a deep learning-driven spatiotemporal simulation framework, Convolutional Long Short-Term Memory (ConvLSTM), for simulating a synthetic image using Sentinel 1 intensity time series. This synthetic image can be prepared in advance of flood events, and then it can be used to detect flood areas using change detection when the post-image is available. Practically, a significant difference between the simulated and observed image is expected over inundated zones, which can be mapped by applying cut-off values to the Delta image (simulated minus observed image). The proposed ConvLSTM-driven SAR-based change detection framework was applied to three different events from Isaac Region, Queensland Australia (Cyclone Debbie), Sofala Region, Mozambique (Cyclone Idai), and Belo Horizonte Metropolitan Area, Brazil (Brumadinho Dam Collapse). The generated Flood Proxy Maps were compared against reference data derived from Sentinel 2 and Planet Labs optical data. To corroborate the effectiveness of the proposed methods, Delta products were also generated for two baseline models (closest post-image minus pre-image and historical mean minus post-image) and two LSTM architectures: traditional LSTM and ConvLSTM. Results show that thresholding of ConvLSTM Delta yielded the highest Cohen’s Kappa coefficients in all study cases: 0.92 for Isaac Region, 0.78 for Sofala Province, and 0.68 for Belo Horizonte Metropolitan Area. Lower Kappa values obtained in the Mozambique case can be subject to the topographic effect on SAR imagery. These results still confirm the benefits in terms of classification accuracy that convolutional operations provide in time series analysis of Earth Observation satellite data employing spatially correlated information in a deep learning framework.
Appears in Collections:	[Graduate Institute of Civil Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	57	View/Open

社群 sharing

Loading...