Segmentation of RADARSAT-2 Dual-polarization Sea Ice Imagery
Segmentation of RADARSAT-2 Dual-polarization Sea Ice Imagery

Author: Peter Yu

Publisher:

Published: 2009

Total Pages: 93

ISBN-13:

DOWNLOAD EBOOK

The mapping of sea ice is an important task for understanding global climate and for safe shipping. Currently, sea ice maps are created by human analysts with the help of remote sensing imagery, including synthetic aperture radar (SAR) imagery. While the maps are generally correct, they can be somewhat subjective and do not have pixel-level resolution due to the time consuming nature of manual segmentation. Therefore, automated sea ice mapping algorithms such as the multivariate iterative region growing with semantics (MIRGS) sea ice image segmentation algorithm are needed. MIRGS was designed to work with one-channel single-polarization SAR imagery from the RADARSAT-1 satellite. The launch of RADARSAT-2 has made available two-channel dual-polarization SAR imagery for the purposes of sea ice mapping. Dual-polarization imagery provides more information for distinguishing ice types, and one of the channels is less sensitive to changes in the backscatter caused by the SAR incidence angle parameter. In the past, this change in backscatter due to the incidence angle was a key limitation that prevented automatic segmentation of full SAR scenes. This thesis investigates techniques to make use of the dual-polarization data in MIRGS.

Dual-polarization (HH/HV) RADARSAT-2 ScanSAR Observations of New, Young and First-year Sea Ice
Dual-polarization (HH/HV) RADARSAT-2 ScanSAR Observations of New, Young and First-year Sea Ice

Author: John Alexander Casey

Publisher:

Published: 2010

Total Pages: 135

ISBN-13:

DOWNLOAD EBOOK

Observations of sea ice from space are routinely used to monitor sea ice extent, concentration and type to support human marine activity and climate change studies. In this study, eight dual-polarization (dual-pol) (HH/HV) RADARSAT-2 ScanSAR images acquired over the Gulf of St. Lawrence during the winter of 2009 are analysed to determine what new or improved sea ice information is provided by dual-pol C-band synthetic aperture radar (SAR) data at wide swath widths, relative to single co-pol data. The objective of this study is to assess how dual-pol RADARSAT-2 ScanSAR data might improve operational ice charts and derived sea ice climate data records. In order to evaluate the dual-pol data, ice thickness and surface roughness measurements and optical remote sensing data were compared to backscatter signatures observed in the SAR data. The study found that: i) dual-pol data provide improved separation of ice and open water, particularly at steep incidence angles and high wind speeds; ii) the contrast between new, young and first-year (FY) ice types is reduced in the cross-pol channel; and iii) large areas of heavily deformed ice can reliably be separated from level ice in the dual-pol data, but areas of light and moderately ridged ice cannot be resolved and the thickness of heavily deformed ice cannot be determined. These results are limited to observations of new, young and FY ice types in winter conditions. From an operational perspective, the improved separation of ice and open water will increase the accuracy of ice edge and total ice concentration estimates while reducing the time required to produce image analysis charts. Further work is needed to determine if areas of heavily ridged ice can be separated from areas of heavily rafted ice based on knowledge of ice conditions in the days preceding the formation of high backscatter deformed ice. If rafted and ridged ice can be separated, tactical ridged ice information should be included on image analysis charts. The dual-pol data can also provide small improvements to ice extent and concentration data in derived climate data records. Further analysis of dual-pol RADARSAT-2 ScanSAR data over additional ice regimes and seasons is required.

Sea Ice Mapping in Labrador Coast with Sentinel-1 Synthetic Aperture Radar Imagery
Sea Ice Mapping in Labrador Coast with Sentinel-1 Synthetic Aperture Radar Imagery

Author: Weikai Tan

Publisher:

Published: 2017

Total Pages: 92

ISBN-13:

DOWNLOAD EBOOK

Sea ice mapping is crucial to Canadian coast, including marine transportation, environmental protection, resource management, disaster and emergency management, especially under current background of climate change. Canadian RADARSAT-2, like other synthetic aperture radar (SAR) sensors, is an essential source for current sea ice mapping in Canada, However, its limited revisiting makes daily ice chart generation challenging. The RADARSAT Constellation project is expected to be launched in 2018, the gap of data availability is expected to be filled with imagery from multiple sources. Sentinel-1, launched by European Space Agency (ESA) in late 2014, is an alternative source for sea ice mapping with comparable capability of RADARSAT-2 in wide swath mode. The main objective of this study is to examine the performance of Sentinel-1 imagery in sea ice mapping with a semi-automated image segmentation workflow. The methodology consists of two main steps. First, the most significant features in sea ice interpretation were determined using a random forest feature selection method. Second, an unsupervised graph-cut image segmentation is performed. The workflow was tested on 15 dual-polarized Sentinel-1A Extra Wide (EW) scenes in Labrador coast from December, 2015 to June, 2016, and the results were evaluated on the accuracy of water segmentation. The study found that: 1) GLCM features are effective in distinguishing different ice classes and 6 most important features were selected; 2) the proposed semi-automated workflow is able to segment Sentinel-1 imagery into 3 to 8 classes for water identification; and 3) generally Sentinel-1 imagery has similar responses from first-year ice compared with previous sensors, but with a different noise pattern in cross-polarized bands; and the overall accuracy of water identification reached close to 95%.

Sea Ice in the Arctic
Sea Ice in the Arctic

Author: Ola M. Johannessen

Publisher: Springer Nature

Published: 2019-11-12

Total Pages: 575

ISBN-13: 3030213013

DOWNLOAD EBOOK

This book provides in-depth information about the sea ice in the Arctic at scales from paleoenvironmental variability to more contemporary changes during the past and present centuries. The book is based on several decades of research related to sea ice in the Arctic and its variability, sea ice process studies as well as implications of the sea ice variability on human activities. The chapters provide an extensive overview of the research results related to sea ice in the Arctic at paleo-scales to more resent scales of variations as well as projections for changes during the 21st century. The authors have pioneered the satellite remote sensing monitoring of sea ice and used other monitoring data in order to study, monitor and model sea ice and its processes.

Towards Automated Lake Ice Classification Using Dual Polarization RADARSAT SAR Imagery
Towards Automated Lake Ice Classification Using Dual Polarization RADARSAT SAR Imagery

Author: Junqian Wang

Publisher:

Published: 2018

Total Pages: 108

ISBN-13:

DOWNLOAD EBOOK

Lake ice, as one of the most important component of the cryosphere, is a valuable indicator of climate change and variability. The Laurentian Great Lakes are the world's largest supply of freshwater and their ice cover has a major impact on regional weather and climate, ship navigation, and public safety. Monitoring detailed ice conditions on large lakes requires the use of satellite-borne synthetic aperture radar (SAR) data that provide all-weather sensing capabilities, high resolution, and large spatial coverage. Ice experts at the Canadian Ice Service (CIS) have been manually producing operational Great Lakes image analysis charts based on visual interpretation of the SAR images. Ice services such as the CIS would greatly benefit from the availability of an automated or semi-automated SAR ice classification algorithm. We investigated the performance of the unsupervised segmentation algorithm “glocal” iterative region growing with semantics (IRGS) for lake ice classification using dual polarized RADARSAT-2 imagery. Here, the segmented classes with arbitrary labels are manually labelled based on visual interpretation. IRGS was tested on 26 RADARSAT-2 scenes acquired over Lake Erie during winter 2014, and the results were validated against the manually produced CIS image analysis charts. Analysis of various case studies indicated that the “glocal” IRGS algorithm can provide a reliable ice-water classification using dual polarized images with a high overall accuracy of 90.2%. The improvement of using dual-pol as opposed to single-pol images for ice-water discrimination was also demonstrated. For lake ice type classification, most thin ice types were effectively identified but thick and very thick lake ice were often confused due to the ambiguous relation between backscatter and ice types. Texture features could be included for further improvement. Overall, our “glocal” IRGS classification results are close to visual interpretation by ice analysts and would have expected to be closer if they could draw ice charts at a more detailed level.

Sea Ice Image Processing with MATLAB®
Sea Ice Image Processing with MATLAB®

Author: Qin Zhang

Publisher: CRC Press

Published: 2018-02-13

Total Pages: 375

ISBN-13: 1351069187

DOWNLOAD EBOOK

Sea Ice Image Processing with MATLAB addresses the topic of image processing for the extraction of key sea ice characteristics from digital photography, which is of great relevance for Artic remote sensing and marine operations. This valuable guide provides tools for quantifying the ice environment that needs to be identified and reproduced for such testing. This includes fit-for-purpose studies of existing vessels, new-build conceptual design and detailed engineering design studies for new developments, and studies of demanding marine operations involving multiple vessels and operational scenarios in sea ice. A major contribution of this work is the development of automated computer algorithms for efficient image analysis. These are used to process individual sea-ice images and video streams of images to extract parameters such as ice floe size distribution, and ice types. Readers are supplied with Matlab source codes of the algorithms for the image processing methods discussed in the book made available as online material. Features Presents the first systematic work using image processing techniques to identify ice floe size distribution from aerial images Helps identify individual ice floe and obtain floe size distributions for Arctic offshore operations and transportation Explains specific algorithms that can be combined to solve various problems during polar sea ice investigations Includes MATLAB® codes useful not only for academics, but for ice engineers and scientists to develop tools applicable in different areas such as sustainable arctic marine and coastal technology research Provides image processing techniques applicable to other fields like biomedicine, material science, etc

Automated Ice-water Classification Using Dual Polarization Synthetic Aerture Radar Imagery
Automated Ice-water Classification Using Dual Polarization Synthetic Aerture Radar Imagery

Author: Steven Leigh

Publisher:

Published: 2013

Total Pages: 110

ISBN-13:

DOWNLOAD EBOOK

Mapping ice and open water in ocean bodies is important for numerous purposes including environmental analysis and ship navigation. The Canadian Ice Service (CIS) currently has several expert ice analysts manually generate ice maps on a daily basis. The CIS would like to augment their current process with an automated ice-water discrimination algorithm capable of operating on dual-pol synthetic aperture radar (SAR) images produced by RADARSAT-2. Automated methods can provide mappings in larger volumes, with more consistency, and in finer resolutions that are otherwise impractical to generate. We have developed such an automated ice-water discrimination system called MAGIC. The algorithm first classifies the HV scene using the glocal method, a hierarchical region-based classification method. The glocal method incorporates spatial context information into the classification model using a modified watershed segmentation and a previously developed MRF classification algorithm called IRGS. Second, a pixel-based support vector machine (SVM) using a nonlinear RBF kernel classification is performed exploiting SAR grey-level co-occurrence matrix (GLCM) texture and backscatter features. Finally, the IRGS and SVM classification results are combined using the IRGS approach but with a modified energy function to accommodate the SVM pixel-based information. The combined classifier was tested on 61 ground truthed dual-pol RADARSAT-2 scenes of the Beaufort Sea containing a variety of ice types and water patterns across melt, summer, and freeze-up periods. The average leave-one-out classification accuracy with respect to these ground truths is 95.8% and MAGIC attains an accuracy of 90% or above on 88% of the scenes. The MAGIC system is now under consideration by CIS for operational use.

Artificial Intelligence Oceanography
Artificial Intelligence Oceanography

Author: Xiaofeng Li

Publisher: Springer Nature

Published: 2023-02-03

Total Pages: 351

ISBN-13: 9811963754

DOWNLOAD EBOOK

This open access book invites readers to learn how to develop artificial intelligence (AI)-based algorithms to perform their research in oceanography. Various examples are exhibited to guide details of how to feed the big ocean data into the AI models to analyze and achieve optimized results. The number of scholars engaged in AI oceanography research will increase exponentially in the next decade. Therefore, this book will serve as a benchmark providing insights for scholars and graduate students interested in oceanography, computer science, and remote sensing.

Novel AI Applications for Advancing Earth Sciences
Novel AI Applications for Advancing Earth Sciences

Author: Yadav, Sudesh

Publisher: IGI Global

Published: 2023-12-29

Total Pages: 428

ISBN-13:

DOWNLOAD EBOOK

The Earth Sciences industry faces a new challenge - the need for accurate, efficient, and reliable methods to monitor and predict geological phenomena and environmental changes. As climate change, earthquakes, and other natural disasters become more frequent and severe, the necessity for advanced tools and techniques is paramount. Traditional methods often fall short in providing the precision and speed required to address these critical issues. Geologists and earth scientists who are grappling with the urgent problem of utilizing artificial intelligence (AI) to revolutionize their field, will find the solution within the pages of Novel AI Applications for Advancing Earth Sciences. This book offers the research community concepts expanding upon the fusion of AI technology with earth sciences. By leveraging advanced AI tools, such as convolutional neural networks, support vector machines, artificial neural networks, and the potential of remote sensing satellites, this book transforms the identification of geological features, geological mapping, soil classification, and gas detection. Scientists can now predict earthquakes and assess the probability of climate change with unprecedented accuracy. Additionally, the book explains how the optimization of algorithms for specific tasks substantially reduces the time complexity of earth observations, leading to an unprecedented leap in accuracy and efficiency.

Illumination and Noise-based Scene Classification - Application to SAR Sea Ice Imagery
Illumination and Noise-based Scene Classification - Application to SAR Sea Ice Imagery

Author: Namrata Bandekar

Publisher:

Published: 2011

Total Pages: 77

ISBN-13:

DOWNLOAD EBOOK

Spatial intensity variation introduced by illumination changes is a challenging problem for image segmentation and classification. Many techniques have been proposed which focus on removing this illumination variation by estimating or modelling it. There is limited research on developing an illumination invariant classification technique which does not use any preprocessing. A major focus of this research is on automatically classifying synthetic aperture radar (SAR) images. These are large satellite images which pose many challenges for image classification including the incidence angle effect which is a strong illumination variation across the image. Mapping of full scene satellite images of sea-ice is important for navigational purposes for ships and also for climate research. The images obtained from the RADARSAT-2 satellite are dual band, high quality images. Currently, sea ice chart are produced manually by ice analysts at the Canadian Ice Service. However, this process can be automated to reduce processing time and obtain more detailed pixel-level ice maps. An automated classification algorithm to achieve sea ice and open water separation will greatly help the ice analyst by providing sufficient guidance in the initial stages of creating an ice map. It would also help the analyst to improve the accuracy while finding ice concentrations and remove subjective bias. The existing Iterative Region Growing by Semantics (IRGS) algorithm is not effective for full scene segmentation because of the incidence angle effect. This research proposes a "glocal" (global as well as local) approach to solve this problem.