Scalable computing for earth observation - Application on Sea Ice analysis
In recent years, Deep learning (DL) networks have shown considerable improvements and have become a preferred methodology in many different applications. These networks have outperformed other classical techniques, particularly in large data settings. In earth observation from the satellite field, for example, DL algorithms have demonstrated the ability to learn complicated nonlinear relationships in input data accurately. Thus, it contributed to advancement in this field. However, the training process of these networks has heavy computational overheads. The reason is two-fold: The sizable complexity of these networks and the high number of training samples needed to learn all parameters comprising these architectures. Although the quantity of training data enhances the accuracy of the trained models in general, the computational cost may restrict the amount of analysis that can be done. This issue is particularly critical in satellite remote sensing, where a myriad of satellites generate an enormous amount of data daily, and acquiring in-situ ground truth for building a large training dataset is a fundamental prerequisite.
This dissertation considers various aspects of deep learning based sea ice monitoring from SAR data. In this application, labeling data is very costly and time-consuming. Also, in some cases, it is not even achievable due to challenges in establishing the required domain knowledge, specifically when it comes to monitoring Arctic Sea ice with Synthetic Aperture Radar (SAR), which is the application domain of this thesis. Because the Arctic is remote, has long dark seasons, and has a very dynamic weather system, the collection of reliable in-situ data is very demanding. In addition to the challenges of interpreting SAR data of sea ice, this issue makes SAR-based sea ice analysis with DL networks a complicated process.
We propose novel DL methods to cope with the problems of scarce training data and address the computational cost of the training process. We analyze DL network capabilities based on self-designed architectures and learn strategies, such as transfer learning for sea ice classification. We also address the scarcity of training data by proposing a novel deep semi-supervised learning method based on SAR data for incorporating unlabeled data information into the training process. Finally, a new distributed DL method that can be used in a semi-supervised manner is proposed to address the computational complexity of deep neural network training.
Paper 1: Khaleghian, S., Ullah, H., Kræmer, T., Hughes, N., Eltoft, T. & Marinoni, A. (2021). Sea Ice Classification of SAR Imagery Based on Convolution Neural Networks. Remote Sensing, 13, 1734. Also available in Munin at https://hdl.handle.net/10037/21716.
Paper 2: Khaleghian, S., Ullah, H., Kræmer, T., Eltoft, T. & Marinoni, A. (2021). Deep Semisupervised Teacher–Student Model Based on Label Propagation for Sea Ice Classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, 10761-10772. Also available in Munin at https://hdl.handle.net/10037/24319.
Paper 3: Khaleghian, S., Ullah, H., Johnsen, E.B., Andersen, A. & Marinoni, A. (2022). AFSD: Adaptive Feature Space Distillation for Distributed Deep Learning. IEEE Access, 10, 84569-84578. Also available in Munin at https://hdl.handle.net/10037/27512.
Related research dataKhaleghian, S., Lohse, J.P. & Kræmer, T. (2020). Synthetic-Aperture Radar (SAR) based Ice types/Ice edge dataset for deep learning analysis. DataverseNO, V1, https://doi.org/10.18710/QAYI4O.
PublisherUiT Norges arktiske universitet
UiT The Arctic University of Norway
The following license file are associated with this item:
Showing items related by title, author, creator and subject.
Nikolaisen, Trygg Einar (Mastergradsoppgave; Master thesis, 2018-05-15)Introduction: Liposomes as drug delivery systems has been widely studied as a way to solubilize poorly soluble drugs, reduce side effects of chemotherapeutics and increase circulation time in vivo. Since the first descriptions of liposomes over 60 years ago, they have shown tendencies to shrink and swell when the external environment of the liposomes is altered. This phenomenon has been studied in ...
Implementing an electronic health record in a Nigerian secondary healthcare facility. Prospects and challenges Attah, Ambrose Ojadale (Master thesis; Mastergradsoppgave, 2017-11-02)Nigeria is witnessing continuing advocacy and increase in number of individuals yearning for computerization of health information and healthcare processes. However, little is known about the opinions of the diverse healthcare providers who would ensure the successful implementation and meaningful use of health information technology in the country (Adeleke, Erinle et al. 2015). This study explores ...
Pedersen, Aleksander (Doctoral thesis; Doktorgradsavhandling, 2020-10-20)In applications for technical problems, Geometric modeling and sensor technology are key in both scientific and industrial development. Simulations and visualization techniques are the next step after defining geometry models and data types. This thesis attempts to combine different aspects of geometric modeling and sensor technology as well as to facilitate simulation and visualization. It includes ...