Fine Tuning MobileNet Neural Networks for Oil Spill Detection
The monitoring of open water and early identification of oil spills in the Alaska Arctic has become increasingly critical due to the rise in oil and gas exploration and shipping activities, facilitated by the increasing number of ice-free days resulting from global warming. This escalating risk of o...
Main Authors: | , |
---|---|
Format: | Text |
Language: | unknown |
Published: |
Purdue University
2023
|
Subjects: | |
Online Access: | https://docs.lib.purdue.edu/iguide/2023/presentations/16 https://docs.lib.purdue.edu/context/iguide/article/1010/viewcontent/Fine_Tuning_MobileNet_Neural_Networks_for_Oil_Spill_Detection_Wang_Coulson.pdf |
id |
ftpurdueuniv:oai:docs.lib.purdue.edu:iguide-1010 |
---|---|
record_format |
openpolar |
spelling |
ftpurdueuniv:oai:docs.lib.purdue.edu:iguide-1010 2023-12-17T10:25:15+01:00 Fine Tuning MobileNet Neural Networks for Oil Spill Detection Wang, Caixia Coulson, Andrew 2023-10-06T16:50:00Z application/pdf https://docs.lib.purdue.edu/iguide/2023/presentations/16 https://docs.lib.purdue.edu/context/iguide/article/1010/viewcontent/Fine_Tuning_MobileNet_Neural_Networks_for_Oil_Spill_Detection_Wang_Coulson.pdf unknown Purdue University https://docs.lib.purdue.edu/iguide/2023/presentations/16 https://docs.lib.purdue.edu/context/iguide/article/1010/viewcontent/Fine_Tuning_MobileNet_Neural_Networks_for_Oil_Spill_Detection_Wang_Coulson.pdf I-GUIDE Forum Other Civil and Environmental Engineering text 2023 ftpurdueuniv 2023-11-23T18:29:31Z The monitoring of open water and early identification of oil spills in the Alaska Arctic has become increasingly critical due to the rise in oil and gas exploration and shipping activities, facilitated by the increasing number of ice-free days resulting from global warming. This escalating risk of oil spills is further compounded by potential accidents in offshore operations, illicit oil discharges, and knowledge gaps in Arctic coastlines, rapidly changing due to rising seas, permafrost melting, and coastal erosion. To address these pressing challenges, we propose a deep learning model based on MobileNet neural networks to detect oil spills in remotely sensed images. Compared to traditional pattern recognition methods, the proposed model can learn from examples to map input new data into the design and automatically optimize the training objective without designing rules and specifying critical parameters to solve the inference task. The experiments demonstrated we were able to obtain an overall accuracy of 0.93 with our proposed methods. Text Arctic Global warming Ice permafrost Alaska Purdue University: e-Pubs Arctic |
institution |
Open Polar |
collection |
Purdue University: e-Pubs |
op_collection_id |
ftpurdueuniv |
language |
unknown |
topic |
Other Civil and Environmental Engineering |
spellingShingle |
Other Civil and Environmental Engineering Wang, Caixia Coulson, Andrew Fine Tuning MobileNet Neural Networks for Oil Spill Detection |
topic_facet |
Other Civil and Environmental Engineering |
description |
The monitoring of open water and early identification of oil spills in the Alaska Arctic has become increasingly critical due to the rise in oil and gas exploration and shipping activities, facilitated by the increasing number of ice-free days resulting from global warming. This escalating risk of oil spills is further compounded by potential accidents in offshore operations, illicit oil discharges, and knowledge gaps in Arctic coastlines, rapidly changing due to rising seas, permafrost melting, and coastal erosion. To address these pressing challenges, we propose a deep learning model based on MobileNet neural networks to detect oil spills in remotely sensed images. Compared to traditional pattern recognition methods, the proposed model can learn from examples to map input new data into the design and automatically optimize the training objective without designing rules and specifying critical parameters to solve the inference task. The experiments demonstrated we were able to obtain an overall accuracy of 0.93 with our proposed methods. |
format |
Text |
author |
Wang, Caixia Coulson, Andrew |
author_facet |
Wang, Caixia Coulson, Andrew |
author_sort |
Wang, Caixia |
title |
Fine Tuning MobileNet Neural Networks for Oil Spill Detection |
title_short |
Fine Tuning MobileNet Neural Networks for Oil Spill Detection |
title_full |
Fine Tuning MobileNet Neural Networks for Oil Spill Detection |
title_fullStr |
Fine Tuning MobileNet Neural Networks for Oil Spill Detection |
title_full_unstemmed |
Fine Tuning MobileNet Neural Networks for Oil Spill Detection |
title_sort |
fine tuning mobilenet neural networks for oil spill detection |
publisher |
Purdue University |
publishDate |
2023 |
url |
https://docs.lib.purdue.edu/iguide/2023/presentations/16 https://docs.lib.purdue.edu/context/iguide/article/1010/viewcontent/Fine_Tuning_MobileNet_Neural_Networks_for_Oil_Spill_Detection_Wang_Coulson.pdf |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Global warming Ice permafrost Alaska |
genre_facet |
Arctic Global warming Ice permafrost Alaska |
op_source |
I-GUIDE Forum |
op_relation |
https://docs.lib.purdue.edu/iguide/2023/presentations/16 https://docs.lib.purdue.edu/context/iguide/article/1010/viewcontent/Fine_Tuning_MobileNet_Neural_Networks_for_Oil_Spill_Detection_Wang_Coulson.pdf |
_version_ |
1785574891199660032 |