scholarly journals Pyramid Pooling Module-Based Semi-Siamese Network: A Benchmark Model for Assessing Building Damage from xBD Satellite Imagery Datasets

2020 ◽  
Vol 12 (24) ◽  
pp. 4055
Author(s):  
Yanbing Bai ◽  
Junjie Hu ◽  
Jinhua Su ◽  
Xing Liu ◽  
Haoyu Liu ◽  
...  
Keyword(s):  
Satellite Imagery ◽  
High Performance ◽  
Large Scale ◽  
Tohoku Earthquake ◽  
Building Damage ◽  
Damage Classification ◽  
The 2011 Tohoku Earthquake ◽  
Benchmark Model ◽  
Siamese Network ◽  
End To End

Most mainstream research on assessing building damage using satellite imagery is based on scattered datasets and lacks unified standards and methods to quantify and compare the performance of different models. To mitigate these problems, the present study develops a novel end-to-end benchmark model, termed the pyramid pooling module semi-Siamese network (PPM-SSNet), based on a large-scale xBD satellite imagery dataset. The high precision of the proposed model is achieved by adding residual blocks with dilated convolution and squeeze-and-excitation blocks into the network. Simultaneously, the highly automated process of satellite imagery input and damage classification result output is reached by employing concurrent learned attention mechanisms through a semi-Siamese network for end-to-end input and output purposes. Our proposed method achieves F1 scores of 0.90, 0.41, 0.65, and 0.70 for the undamaged, minor-damaged, major-damaged, and destroyed building classes, respectively. From the perspective of end-to-end methods, the ablation experiments and comparative analysis confirm the effectiveness and originality of the PPM-SSNet method. Finally, the consistent prediction results of our model for data from the 2011 Tohoku Earthquake verify the high performance of our model in terms of the domain shift problem, which implies that it is effective for evaluating future disasters.

Detecting building damage caused by the 2011 Tohoku earthquake tsunami using TerraSAR-X data

2014 ◽  
Author(s):  
Hideomi Gokon ◽  
Shunichi Koshimura ◽  
Joachim Post ◽  
Christian Geis ◽  
Enrico Stein ◽  
...  
Keyword(s):  
Tohoku Earthquake ◽  
Building Damage ◽  
2011 Tohoku Earthquake ◽  
The 2011 Tohoku Earthquake

scholarly journals Investigating beach erosion related with tsunami sediment transport at Phra Thong Island, Thailand, caused by the 2004 Indian Ocean tsunami

2020 ◽  
Vol 20 (10) ◽  
pp. 2823-2841
Author(s):  
Ryota Masaya ◽  
Anawat Suppasri ◽  
Kei Yamashita ◽  
Fumihiko Imamura ◽  
Chris Gouramanis ◽  
...  
Keyword(s):  
Indian Ocean ◽  
Large Scale ◽  
Tohoku Earthquake ◽  
Beach Erosion ◽  
Indian Ocean Tsunami ◽  
Human Populations ◽  
The 2011 Tohoku Earthquake ◽  
2004 Indian Ocean Tsunami ◽  
Quick Recovery ◽  
2004 Tsunami

Abstract. The 2004 Indian Ocean tsunami and the 2011 Tōhoku earthquake and tsunami caused large-scale topographic changes in coastal areas. Whereas much research has focused on coastlines that have or had large human populations, little focus has been paid to coastlines that have little or no infrastructure. The importance of examining erosional and depositional mechanisms of tsunami events lies in the rapid reorganization that coastlines must undertake immediately after an event. A thorough understanding of the pre-event conditions is paramount to understanding the natural reconstruction of the coastal environment. This study examines the location of sediment erosion and deposition during the 2004 Indian Ocean tsunami event on the relatively pristine Phra Thong Island, Thailand. Coupled with satellite imagery, we use numerical simulations and sediment transportation models to determine the locations of significant erosion and the areas where much of that sediment was redeposited during the tsunami inundation and backwash processes. Our modeling approach suggests that beaches located in two regions on Phra Thong Island were significantly eroded by the 2004 tsunami, predominantly during the backwash phase of the first and largest wave to strike the island. Although 2004 tsunami deposits are found on the island, we demonstrate that most of the sediment was deposited in the shallow coastal area, facilitating quick recovery of the beach when normal coastal processes resumed.

scholarly journals Interpretability in Convolutional Neural Networks for Building Damage Classification in Satellite Imagery

2021 ◽  
Author(s):  
Thomas Chen
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Satellite Imagery ◽  
Building Damage ◽  
Classification Model ◽  
Damage Classification ◽  
Humanitarian Crisis ◽  
Monthly Basis ◽  
Loss Of Life ◽  
Post Disaster

<p>Natural disasters ravage the world's cities, valleys, and shores on a monthly basis. Having precise and efficient mechanisms for assessing infrastructure damage is essential to channel resources and minimize the loss of life. Using a dataset that includes labeled pre- and post- disaster satellite imagery, the xBD dataset, we train multiple convolutional neural networks to assess building damage on a per-building basis. In order to investigate how to best classify building damage, we present a highly interpretable deep-learning methodology that seeks to explicitly convey the most useful information required to train an accurate classification model. We also delve into which loss functions best optimize these models. Our findings include that ordinal-cross entropy loss is the most optimal loss function to use and that including the type of disaster that caused the damage in combination with a pre- and post-disaster image best predicts the level of damage caused. We also make progress in the realm of qualitative representations of which parts of the images that the model is using to predict damage levels, through gradient class-activation maps. Our research seeks to computationally contribute to aiding in this ongoing and growing humanitarian crisis, heightened by climate change. Specifically, it advances the study of more interpretable machine learning models, which were lacking in previous literature and are important for the understanding of not only research scientists but also operators of such technologies in underserved regions.</p>

Object-Based Method for Estimating Tsunami-Induced Damage Using TerraSAR-X Data

2016 ◽  
Vol 11 (2) ◽  
pp. 225-235 ◽  
Author(s):  
Hideomi Gokon ◽  
◽  
Shunichi Koshimura ◽  
Masashi Matsuoka ◽  
◽  
...  
Keyword(s):  
Correlation Coefficient ◽  
Tohoku Earthquake ◽  
Ground Truth ◽  
Test Site ◽  
Damage Function ◽  
Building Damage ◽  
The 2011 Tohoku Earthquake ◽  
Ground Truth Data ◽  
Object Based ◽  
The Relationship

The object-based method we developed to estimate building damage uses high-resolution synthetic aperture radar (TerraSAR-X) data from the 2011 Tohoku earthquake and tsunami. The damage function we developed involves the relationship between changes in the sigma nought values of pre- and postevent TerraSAR-X data and the damage ratio of washed-away buildings. We confirmed that the function performed as expected by estimating the number of washed-away buildings in homogeneous areas, agreeing well with ground truth data verified by a Pearson fs correlation coefficient of 0.99. The same damage function applied at another test site yielded a Pearson's correlation coefficient of 0.98. These results are sufficient to ensure transferability. We then simplified and semiautomated these processes in an ArcGIS environment, estimating building damage in the city of Sendai within 26 minutes.

scholarly journals BIG IMAGERY AND HIGH PERFORMANCE COMPUTING AS RESOURCES TO UNDERSTAND CHANGING ARCTIC POLYGONAL TUNDRA

2020 ◽  
Vol XLIV-M-2-2020 ◽  
pp. 111-116
Author(s):  
C. Witharana ◽  
M. A. E. Bhuiyan ◽  
A. K. Liljedahl
Keyword(s):  
High Performance Computing ◽  
Satellite Imagery ◽  
High Performance ◽  
Large Scale ◽  
Image Interpretation ◽  
Accurate Estimate ◽  
Neural Nets ◽  
Ground Subsidence ◽  
The Arctic ◽  
Performance Computing

Abstract. Permafrost thaw has been observed at several locations across the Arctic tundra in recent decades; however, the pan-Arctic extent and spatiotemporal dynamics of thaw remains poorly explained. Thaw-induced differential ground subsidence and dramatic microtopographic transitions, such as transformation of low-centered ice-wedge polygons (IWPs) into high-centered IWPs can be characterized using very high spatial resolution (VHSR) commercial satellite imagery. Arctic researchers demand for an accurate estimate of the distribution of IWPs and their status across the tundra domain. The entire Arctic has been imaged in 0.5 m resolution by commercial satellite sensors; however, mapping efforts are yet limited to small scales and confined to manual or semi-automated methods. Knowledge discovery through artificial intelligence (AI), big imagery, and high performance computing (HPC) resources is just starting to be realized in Arctic science. Large-scale deployment of VHSR imagery resources requires sophisticated computational approaches to automated image interpretation coupled with efficient use of HPC resources. We are in the process of developing an automated Mapping Application for Permafrost Land Environment (MAPLE) by combining big imagery, AI, and HPC resources. The MAPLE uses deep learning (DL) convolutional neural nets (CNNs) algorithms on HPCs to automatically map IWPs from VHSR commercial satellite imagery across large geographic domains. We trained and tasked a DLCNN semantic object instance segmentation algorithm to automatically classify IWPs from VHSR satellite imagery. Overall, our findings demonstrate the robust performances of IWP mapping algorithm in diverse tundra landscapes and lay a firm foundation for its operational-level application in repeated documentation of circumpolar permafrost disturbances.

scholarly journals Numerical Simulations of Large-Scale Sediment Transport Caused by the 2011 Tohoku Earthquake Tsunami in Hirota Bay, Southern Sanriku Coast

2016 ◽  
Vol 58 (4) ◽  
pp. 1640015-1-1640015-28 ◽  
Author(s):  
Kei Yamashita ◽  
Daisuke Sugawara ◽  
Tomoyuki Takahashi ◽  
Fumihiko Imamura ◽  
Yuichi Saito ◽  
...  
Keyword(s):  
Sediment Transport ◽  
Numerical Simulations ◽  
Large Scale ◽  
Tohoku Earthquake ◽  
2011 Tohoku Earthquake ◽  
The 2011 Tohoku Earthquake ◽  
Sanriku Coast
Sign in / Sign up

Export Citation Format

Share Document