More Like this

1. AUTOMATED RECOGNITION OF PERMAFROST DISTURBANCES USING HIGH-SPATIAL RESOLUTION SATELLITE IMAGERY AND DEEP LEARNING MODELS

   https://doi.org/10.5194/isprs-archives-XLVI-M-2-2022-203-2022  

   Udawalpola, M. R.; Witharana, C.; Hasan, A.; Liljedahl, A.; Ward Jones, M.; Jones, B. (March 2022, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences)

   The accelerated warming conditions of the high Arctic have intensified the extensive thawing of permafrost. Retrogressive thaw slumps (RTSs) are considered as the most active landforms in the Arctic permafrost. An increase in RTSs has been observed in the Arctic in recent decades. Continuous monitoring of RTSs is important to understand climate change-driven disturbances in the region. Manual detection of these landforms is extremely difficult as they occur over exceptionally large areas. Only very few studies have explored the utility of very high spatial resolution (VHSR) commercial satellite imagery in the automated mapping of RTSs. We have developed deep learning (DL) convolution neural net (CNN) based workflow to automatically detect RTSs from VHRS satellite imagery. This study systematically compared the performance of different DLCNN model architectures and varying backbones. Our candidate CNN models include: DeepLabV3+, UNet, UNet++, Multi-scale Attention Net (MA-Net), and Pyramid Attention Network (PAN) with ResNet50, ResNet101 and ResNet152 backbones. The RTS modeling experiment was conducted on Banks Island and Ellesmere Island in Canada. The UNet++ model demonstrated the highest accuracy (F1 score of 87%) with the ResNet50 backbone at the expense of training and inferencing time. PAN, DeepLabV3, MaNet, and UNet, models reported mediocre F1 scores of 72%, 75%, 80%, and 81% respectively. Our findings unravel the performances of different DLCNNs in imagery-enabled RTS mapping and provide useful insights on operationalizing the mapping application across the Arctic. 

   more » « less
2. High-rate emphasized DeepLabV3Plus for Semantic Segmentation of Breast Cancer-related Hematoxylin and Eosin-stained Images

   https://doi.org/10.1109/EMBC53108.2024.10782325  

   Lee, Sanghoon; Zhao, Yanjun; Choi, Wookjin (July 2024, IEEE)

   Deep learning algorithms have been successfully adopted to extract meaningful information from digital images, yet many of them have been untapped in the semantic image segmentation of histopathology images. In this paper, we propose a deep convolutional neural network model that strengthens Atrous separable convolutions with a high rate within spatial pyramid pooling for histopathology image segmentation. A well-known model called DeepLabV3Plus was used for the encoder and decoder process. ResNet50 was adopted for the encoder block of the model which provides us the advantage of attenuating the problem of the increased depth of the network by using skip connections. Three Atrous separable convolutions with higher rates were added to the existing Atrous separable convolutions. We conducted a performance evaluation on three tissue types: tumor, tumor-infiltrating lymphocytes, and stroma for comparing the proposed model with the eight state-of-the-art deep learning models: DeepLabV3, DeepLabV3Plus, LinkNet, MANet, PAN, PSPnet, UNet, and UNet++. The performance results show that the proposed model outperforms the eight models on mIOU (0.8058/0.7792) and FSCR (0.8525/0.8328) for both tumor and tumor-infiltrating lymphocytes. 

   more » « less
3. Convolutional Neural Networks for Automated Built Infrastructure Detection in the Arctic Using Sub-Meter Spatial Resolution Satellite Imagery

   https://doi.org/10.3390/rs14112719  

   Manos, Elias; Witharana, Chandi; Udawalpola, Mahendra Rajitha; Hasan, Amit; Liljedahl, Anna K. (June 2022, Remote Sensing)

   Rapid global warming is catalyzing widespread permafrost degradation in the Arctic, leading to destructive land-surface subsidence that destabilizes and deforms the ground. Consequently, human-built infrastructure constructed upon permafrost is currently at major risk of structural failure. Risk assessment frameworks that attempt to study this issue assume that precise information on the location and extent of infrastructure is known. However, complete, high-quality, uniform geospatial datasets of built infrastructure that are readily available for such scientific studies are lacking. While imagery-enabled mapping can fill this knowledge gap, the small size of individual structures and vast geographical extent of the Arctic necessitate large volumes of very high spatial resolution remote sensing imagery. Transforming this ‘big’ imagery data into ‘science-ready’ information demands highly automated image analysis pipelines driven by advanced computer vision algorithms. Despite this, previous fine resolution studies have been limited to manual digitization of features on locally confined scales. Therefore, this exploratory study serves as the first investigation into fully automated analysis of sub-meter spatial resolution satellite imagery for automated detection of Arctic built infrastructure. We tasked the U-Net, a deep learning-based semantic segmentation model, with classifying different infrastructure types (residential, commercial, public, and industrial buildings, as well as roads) from commercial satellite imagery of Utqiagvik and Prudhoe Bay, Alaska. We also conducted a systematic experiment to understand how image augmentation can impact model performance when labeled training data is limited. When optimal augmentation methods were applied, the U-Net achieved an average F1 score of 0.83. Overall, our experimental findings show that the U-Net-based workflow is a promising method for automated Arctic built infrastructure detection that, combined with existing optimized workflows, such as MAPLE, could be expanded to map a multitude of infrastructure types spanning the pan-Arctic. 

   more » « less
4. Developing and Testing a Deep Learning Approach for Mapping Retrogressive Thaw Slumps

   https://doi.org/10.3390/rs13214294  

   Nitze, Ingmar; Heidler, Konrad; Barth, Sophia; Grosse, Guido (November 2021, Remote Sensing)

   null (Ed.)

   In a warming Arctic, permafrost-related disturbances, such as retrogressive thaw slumps (RTS), are becoming more abundant and dynamic, with serious implications for permafrost stability and bio-geochemical cycles on local to regional scales. Despite recent advances in the field of earth observation, many of these have remained undetected as RTS are highly dynamic, small, and scattered across the remote permafrost region. Here, we assessed the potential strengths and limitations of using deep learning for the automatic segmentation of RTS using PlanetScope satellite imagery, ArcticDEM and auxiliary datasets. We analyzed the transferability and potential for pan-Arctic upscaling and regional cross-validation, with independent training and validation regions, in six different thaw slump-affected regions in Canada and Russia. We further tested state-of-the-art model architectures (UNet, UNet++, DeepLabv3) and encoder networks to find optimal model configurations for potential upscaling to continental scales. The best deep learning models achieved mixed results from good to very good agreement in four of the six regions (maxIoU: 0.39 to 0.58; Lena River, Horton Delta, Herschel Island, Kolguev Island), while they failed in two regions (Banks Island, Tuktoyaktuk). Of the tested architectures, UNet++ performed the best. The large variance in regional performance highlights the requirement for a sufficient quantity, quality and spatial variability in the training data used for segmenting RTS across diverse permafrost landscapes, in varying environmental conditions. With our highly automated and configurable workflow, we see great potential for the transfer to active RTS clusters (e.g., Peel Plateau) and upscaling to much larger regions. 

   more » « less
5. Circum-Arctic Map of the Yedoma Permafrost Domain

   https://doi.org/10.3389/feart.2021.758360  

   Strauss, Jens; Laboor, Sebastian; Schirrmeister, Lutz; Fedorov, Alexander N.; Fortier, Daniel; Froese, Duane; Fuchs, Matthias; Günther, Frank; Grigoriev, Mikhail; Harden, Jennifer; et al (October 2021, Frontiers in Earth Science)

   Ice-rich permafrost in the circum-Arctic and sub-Arctic (hereafter pan-Arctic), such as late Pleistocene Yedoma, are especially prone to degradation due to climate change or human activity. When Yedoma deposits thaw, large amounts of frozen organic matter and biogeochemically relevant elements return into current biogeochemical cycles. This mobilization of elements has local and global implications: increased thaw in thermokarst or thermal erosion settings enhances greenhouse gas fluxes from permafrost regions. In addition, this ice-rich ground is of special concern for infrastructure stability as the terrain surface settles along with thawing. Finally, understanding the distribution of the Yedoma domain area provides a window into the Pleistocene past and allows reconstruction of Ice Age environmental conditions and past mammoth-steppe landscapes. Therefore, a detailed assessment of the current pan-Arctic Yedoma coverage is of importance to estimate its potential contribution to permafrost-climate feedbacks, assess infrastructure vulnerabilities, and understand past environmental and permafrost dynamics. Building on previous mapping efforts, the objective of this paper is to compile the first digital pan-Arctic Yedoma map and spatial database of Yedoma coverage. Therefore, we 1) synthesized, analyzed, and digitized geological and stratigraphical maps allowing identification of Yedoma occurrence at all available scales, and 2) compiled field data and expert knowledge for creating Yedoma map confidence classes. We used GIS-techniques to vectorize maps and harmonize site information based on expert knowledge. We included a range of attributes for Yedoma areas based on lithological and stratigraphic information from the source maps and assigned three different confidence levels of the presence of Yedoma (confirmed, likely, or uncertain). Using a spatial buffer of 20 km around mapped Yedoma occurrences, we derived an extent of the Yedoma domain. Our result is a vector-based map of the current pan-Arctic Yedoma domain that covers approximately 2,587,000 km 2 , whereas Yedoma deposits are found within 480,000 km 2 of this region. We estimate that 35% of the total Yedoma area today is located in the tundra zone, and 65% in the taiga zone. With this Yedoma mapping, we outlined the substantial spatial extent of late Pleistocene Yedoma deposits and created a unique pan-Arctic dataset including confidence estimates. 

   more » « less