東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Applying Neural Networks for Avalanche Detection from Satellite Imagery.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Applying Neural Networks for Avalanche Detection from Satellite Imagery./
作者:	Delannoy, Constance.
面頁冊數:	1 online resource (25 pages)
附註:	Source: Masters Abstracts International, Volume: 83-12.
Contained By:	Masters Abstracts International83-12.
標題:	Statistics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29069135click for full text (PQDT)
ISBN:	9798819391419

Applying Neural Networks for Avalanche Detection from Satellite Imagery.
Delannoy, Constance.

Applying Neural Networks for Avalanche Detection from Satellite Imagery. - 1 online resource (25 pages)

Source: Masters Abstracts International, Volume: 83-12.

Thesis (M.S.)--University of Colorado at Boulder, 2022.

Includes bibliographical references

Avalanche detection is currently mainly performed by human observers going out into the field, leading to great bias in the collective database of known avalanche paths towards areas that are easily accessible or need to be surveyed because of the consequences of an avalanche (i.e., areas where an avalanche would block a highway or come into contact with dwellings). However, in recent years, a new way of detecting avalanches has emerged that uses satellite imagery. Using this data has the potential to remove the aforementioned bias from avalanche databases, and therefore make prediction more accurate and less human-dependent in the future. Unfortunately, predictions from these data, which rely on radar signal processing techniques for analysis, are typically much less accurate than manual detection by human experts. Some research teams in Norway and Switzerland have attempted to remedy this problem by applying state-of-the-art deep learning models. This thesis explores those methods by applying a Fully Convolutional Network (FCN) to satellite radar data to identify avalanches in Switzerland, and compares results to previous studies. Our results do not rise to our expectations based on previous studies. This may be due to the quantity and quality of the data, which is crucial in detecting such rare events, and differences in avalanche appearances in different regions based on, for example wetter versus drier snowpack.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798819391419Subjects--Topical Terms:

517247
Statistics.
Index Terms--Genre/Form:

542853
Electronic books.

Applying Neural Networks for Avalanche Detection from Satellite Imagery.
LDR:02670nmm a2200361K 4500 001 2353138
005 20221214062803.5
006 m o d
007 cr mn ---uuuuu
008 241011s2022 xx obm 000 0 eng d
020 $a 9798819391419
035 $a (MiAaPQ)AAI29069135
035 $a AAI29069135
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Delannoy, Constance. $3 3693474
245 1 0 $a Applying Neural Networks for Avalanche Detection from Satellite Imagery.
264 0 $c 2022
300 $a 1 online resource (25 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 83-12.
500 $a Advisor: Corcoran, Jem.
502 $a Thesis (M.S.)--University of Colorado at Boulder, 2022.
504 $a Includes bibliographical references
520 $a Avalanche detection is currently mainly performed by human observers going out into the field, leading to great bias in the collective database of known avalanche paths towards areas that are easily accessible or need to be surveyed because of the consequences of an avalanche (i.e., areas where an avalanche would block a highway or come into contact with dwellings). However, in recent years, a new way of detecting avalanches has emerged that uses satellite imagery. Using this data has the potential to remove the aforementioned bias from avalanche databases, and therefore make prediction more accurate and less human-dependent in the future. Unfortunately, predictions from these data, which rely on radar signal processing techniques for analysis, are typically much less accurate than manual detection by human experts. Some research teams in Norway and Switzerland have attempted to remedy this problem by applying state-of-the-art deep learning models. This thesis explores those methods by applying a Fully Convolutional Network (FCN) to satellite radar data to identify avalanches in Switzerland, and compares results to previous studies. Our results do not rise to our expectations based on previous studies. This may be due to the quantity and quality of the data, which is crucial in detecting such rare events, and differences in avalanche appearances in different regions based on, for example wetter versus drier snowpack.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Statistics. $3 517247
650 4 $a Computer science. $3 523869
650 4 $a Macroecology. $3 3188544
650 4 $a Remote sensing. $3 535394
650 4 $a Geographic information science. $3 3432445
650 4 $a Avalanches. $3 3217898
650 4 $a Snow. $3 569416
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0463
690 $a 0984
690 $a 0420
690 $a 0799
690 $a 0370
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a University of Colorado at Boulder. $b Applied Mathematics. $3 1030307
773 0 $t Masters Abstracts International $g 83-12.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29069135 $z click for full text (PQDT)