Eintrag weiter verarbeiten
Deep multi-scale learning for automatic tracking of internal layers of ice in radar data
Gespeichert in:
| Zeitschriftentitel: | Journal of Glaciology |
|---|---|
| Personen und Körperschaften: | , , , , |
| In: | Journal of Glaciology, 67, 2021, 261, S. 39-48 |
| Format: | E-Article |
| Sprache: | Englisch |
| veröffentlicht: |
Cambridge University Press (CUP)
|
| Schlagwörter: |
| author_facet |
Rahnemoonfar, Maryam Yari, Masoud Paden, John Koenig, Lora Ibikunle, Oluwanisola Rahnemoonfar, Maryam Yari, Masoud Paden, John Koenig, Lora Ibikunle, Oluwanisola |
|---|---|
| author |
Rahnemoonfar, Maryam Yari, Masoud Paden, John Koenig, Lora Ibikunle, Oluwanisola |
| spellingShingle |
Rahnemoonfar, Maryam Yari, Masoud Paden, John Koenig, Lora Ibikunle, Oluwanisola Journal of Glaciology Deep multi-scale learning for automatic tracking of internal layers of ice in radar data Earth-Surface Processes |
| author_sort |
rahnemoonfar, maryam |
| spelling |
Rahnemoonfar, Maryam Yari, Masoud Paden, John Koenig, Lora Ibikunle, Oluwanisola 0022-1430 1727-5652 Cambridge University Press (CUP) Earth-Surface Processes http://dx.doi.org/10.1017/jog.2020.80 <jats:title>Abstract</jats:title><jats:p>In this study, our goal is to track internal ice layers on the Snow Radar data collected by NASA Operation IceBridge. We examine the application of deep learning methods on radar data gathered from polar regions. Artificial intelligence techniques have displayed impressive success in many practical fields. Deep neural networks owe their success to the availability of massive labeled data. However, in many real-world problems, even when a large dataset is available, deep learning methods have shown less success, due to causes such as lack of a large labeled dataset, presence of noise in the data or missing data. In our radar data, the presence of noise is one of the main obstacles in utilizing popular deep learning methods such as transfer learning. Our experiments show that if the neural network is trained to detect contours of objects in electro-optical imagery, it can only track a low percentage of contours in radar data. Fine-tuning and further training do not provide any better results. However, we show that selecting the right model and training it on the radar imagery from the start yields far better results.</jats:p> Deep multi-scale learning for automatic tracking of internal layers of ice in radar data Journal of Glaciology |
| doi_str_mv |
10.1017/jog.2020.80 |
| facet_avail |
Online Free |
| finc_class_facet |
Geologie und Paläontologie Geographie |
| format |
ElectronicArticle |
| fullrecord |
blob:ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTAxNy9qb2cuMjAyMC44MA |
| id |
ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTAxNy9qb2cuMjAyMC44MA |
| institution |
DE-D275 DE-Bn3 DE-Brt1 DE-Zwi2 DE-D161 DE-Gla1 DE-Zi4 DE-15 DE-Pl11 DE-Rs1 DE-105 DE-14 DE-Ch1 DE-L229 |
| imprint |
Cambridge University Press (CUP), 2021 |
| imprint_str_mv |
Cambridge University Press (CUP), 2021 |
| issn |
0022-1430 1727-5652 |
| issn_str_mv |
0022-1430 1727-5652 |
| language |
English |
| mega_collection |
Cambridge University Press (CUP) (CrossRef) |
| match_str |
rahnemoonfar2021deepmultiscalelearningforautomatictrackingofinternallayersoficeinradardata |
| publishDateSort |
2021 |
| publisher |
Cambridge University Press (CUP) |
| recordtype |
ai |
| record_format |
ai |
| series |
Journal of Glaciology |
| source_id |
49 |
| title |
Deep multi-scale learning for automatic tracking of internal layers of ice in radar data |
| title_unstemmed |
Deep multi-scale learning for automatic tracking of internal layers of ice in radar data |
| title_full |
Deep multi-scale learning for automatic tracking of internal layers of ice in radar data |
| title_fullStr |
Deep multi-scale learning for automatic tracking of internal layers of ice in radar data |
| title_full_unstemmed |
Deep multi-scale learning for automatic tracking of internal layers of ice in radar data |
| title_short |
Deep multi-scale learning for automatic tracking of internal layers of ice in radar data |
| title_sort |
deep multi-scale learning for automatic tracking of internal layers of ice in radar data |
| topic |
Earth-Surface Processes |
| url |
http://dx.doi.org/10.1017/jog.2020.80 |
| publishDate |
2021 |
| physical |
39-48 |
| description |
<jats:title>Abstract</jats:title><jats:p>In this study, our goal is to track internal ice layers on the Snow Radar data collected by NASA Operation IceBridge. We examine the application of deep learning methods on radar data gathered from polar regions. Artificial intelligence techniques have displayed impressive success in many practical fields. Deep neural networks owe their success to the availability of massive labeled data. However, in many real-world problems, even when a large dataset is available, deep learning methods have shown less success, due to causes such as lack of a large labeled dataset, presence of noise in the data or missing data. In our radar data, the presence of noise is one of the main obstacles in utilizing popular deep learning methods such as transfer learning. Our experiments show that if the neural network is trained to detect contours of objects in electro-optical imagery, it can only track a low percentage of contours in radar data. Fine-tuning and further training do not provide any better results. However, we show that selecting the right model and training it on the radar imagery from the start yields far better results.</jats:p> |
| container_issue |
261 |
| container_start_page |
39 |
| container_title |
Journal of Glaciology |
| container_volume |
67 |
| format_de105 |
Article, E-Article |
| format_de14 |
Article, E-Article |
| format_de15 |
Article, E-Article |
| format_de520 |
Article, E-Article |
| format_de540 |
Article, E-Article |
| format_dech1 |
Article, E-Article |
| format_ded117 |
Article, E-Article |
| format_degla1 |
E-Article |
| format_del152 |
Buch |
| format_del189 |
Article, E-Article |
| format_dezi4 |
Article |
| format_dezwi2 |
Article, E-Article |
| format_finc |
Article, E-Article |
| format_nrw |
Article, E-Article |
| _version_ |
1792346200677023752 |
| geogr_code |
not assigned |
| last_indexed |
2024-03-01T17:35:35.735Z |
| geogr_code_person |
not assigned |
| openURL |
url_ver=Z39.88-2004&ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fvufind.svn.sourceforge.net%3Agenerator&rft.title=Deep+multi-scale+learning+for+automatic+tracking+of+internal+layers+of+ice+in+radar+data&rft.date=2021-02-01&genre=article&issn=1727-5652&volume=67&issue=261&spage=39&epage=48&pages=39-48&jtitle=Journal+of+Glaciology&atitle=Deep+multi-scale+learning+for+automatic+tracking+of+internal+layers+of+ice+in+radar+data&aulast=Ibikunle&aufirst=Oluwanisola&rft_id=info%3Adoi%2F10.1017%2Fjog.2020.80&rft.language%5B0%5D=eng |
| SOLR | |
| _version_ | 1792346200677023752 |
| author | Rahnemoonfar, Maryam, Yari, Masoud, Paden, John, Koenig, Lora, Ibikunle, Oluwanisola |
| author_facet | Rahnemoonfar, Maryam, Yari, Masoud, Paden, John, Koenig, Lora, Ibikunle, Oluwanisola, Rahnemoonfar, Maryam, Yari, Masoud, Paden, John, Koenig, Lora, Ibikunle, Oluwanisola |
| author_sort | rahnemoonfar, maryam |
| container_issue | 261 |
| container_start_page | 39 |
| container_title | Journal of Glaciology |
| container_volume | 67 |
| description | <jats:title>Abstract</jats:title><jats:p>In this study, our goal is to track internal ice layers on the Snow Radar data collected by NASA Operation IceBridge. We examine the application of deep learning methods on radar data gathered from polar regions. Artificial intelligence techniques have displayed impressive success in many practical fields. Deep neural networks owe their success to the availability of massive labeled data. However, in many real-world problems, even when a large dataset is available, deep learning methods have shown less success, due to causes such as lack of a large labeled dataset, presence of noise in the data or missing data. In our radar data, the presence of noise is one of the main obstacles in utilizing popular deep learning methods such as transfer learning. Our experiments show that if the neural network is trained to detect contours of objects in electro-optical imagery, it can only track a low percentage of contours in radar data. Fine-tuning and further training do not provide any better results. However, we show that selecting the right model and training it on the radar imagery from the start yields far better results.</jats:p> |
| doi_str_mv | 10.1017/jog.2020.80 |
| facet_avail | Online, Free |
| finc_class_facet | Geologie und Paläontologie, Geographie |
| format | ElectronicArticle |
| format_de105 | Article, E-Article |
| format_de14 | Article, E-Article |
| format_de15 | Article, E-Article |
| format_de520 | Article, E-Article |
| format_de540 | Article, E-Article |
| format_dech1 | Article, E-Article |
| format_ded117 | Article, E-Article |
| format_degla1 | E-Article |
| format_del152 | Buch |
| format_del189 | Article, E-Article |
| format_dezi4 | Article |
| format_dezwi2 | Article, E-Article |
| format_finc | Article, E-Article |
| format_nrw | Article, E-Article |
| geogr_code | not assigned |
| geogr_code_person | not assigned |
| id | ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTAxNy9qb2cuMjAyMC44MA |
| imprint | Cambridge University Press (CUP), 2021 |
| imprint_str_mv | Cambridge University Press (CUP), 2021 |
| institution | DE-D275, DE-Bn3, DE-Brt1, DE-Zwi2, DE-D161, DE-Gla1, DE-Zi4, DE-15, DE-Pl11, DE-Rs1, DE-105, DE-14, DE-Ch1, DE-L229 |
| issn | 0022-1430, 1727-5652 |
| issn_str_mv | 0022-1430, 1727-5652 |
| language | English |
| last_indexed | 2024-03-01T17:35:35.735Z |
| match_str | rahnemoonfar2021deepmultiscalelearningforautomatictrackingofinternallayersoficeinradardata |
| mega_collection | Cambridge University Press (CUP) (CrossRef) |
| physical | 39-48 |
| publishDate | 2021 |
| publishDateSort | 2021 |
| publisher | Cambridge University Press (CUP) |
| record_format | ai |
| recordtype | ai |
| series | Journal of Glaciology |
| source_id | 49 |
| spelling | Rahnemoonfar, Maryam Yari, Masoud Paden, John Koenig, Lora Ibikunle, Oluwanisola 0022-1430 1727-5652 Cambridge University Press (CUP) Earth-Surface Processes http://dx.doi.org/10.1017/jog.2020.80 <jats:title>Abstract</jats:title><jats:p>In this study, our goal is to track internal ice layers on the Snow Radar data collected by NASA Operation IceBridge. We examine the application of deep learning methods on radar data gathered from polar regions. Artificial intelligence techniques have displayed impressive success in many practical fields. Deep neural networks owe their success to the availability of massive labeled data. However, in many real-world problems, even when a large dataset is available, deep learning methods have shown less success, due to causes such as lack of a large labeled dataset, presence of noise in the data or missing data. In our radar data, the presence of noise is one of the main obstacles in utilizing popular deep learning methods such as transfer learning. Our experiments show that if the neural network is trained to detect contours of objects in electro-optical imagery, it can only track a low percentage of contours in radar data. Fine-tuning and further training do not provide any better results. However, we show that selecting the right model and training it on the radar imagery from the start yields far better results.</jats:p> Deep multi-scale learning for automatic tracking of internal layers of ice in radar data Journal of Glaciology |
| spellingShingle | Rahnemoonfar, Maryam, Yari, Masoud, Paden, John, Koenig, Lora, Ibikunle, Oluwanisola, Journal of Glaciology, Deep multi-scale learning for automatic tracking of internal layers of ice in radar data, Earth-Surface Processes |
| title | Deep multi-scale learning for automatic tracking of internal layers of ice in radar data |
| title_full | Deep multi-scale learning for automatic tracking of internal layers of ice in radar data |
| title_fullStr | Deep multi-scale learning for automatic tracking of internal layers of ice in radar data |
| title_full_unstemmed | Deep multi-scale learning for automatic tracking of internal layers of ice in radar data |
| title_short | Deep multi-scale learning for automatic tracking of internal layers of ice in radar data |
| title_sort | deep multi-scale learning for automatic tracking of internal layers of ice in radar data |
| title_unstemmed | Deep multi-scale learning for automatic tracking of internal layers of ice in radar data |
| topic | Earth-Surface Processes |
| url | http://dx.doi.org/10.1017/jog.2020.80 |