國立虎尾科技大學 |

Machine Learning Algorithms for Automated Satellite Snow and Sea Ice Detection.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Machine Learning Algorithms for Automated Satellite Snow and Sea Ice Detection./
作者:	Bonev, George.
面頁冊數:	1 online resource (98 pages)
附註:	Source: Dissertation Abstracts International, Volume: 79-04(E), Section: B.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9780355351446

Machine Learning Algorithms for Automated Satellite Snow and Sea Ice Detection.
Bonev, George.

Machine Learning Algorithms for Automated Satellite Snow and Sea Ice Detection. - 1 online resource (98 pages)

Source: Dissertation Abstracts International, Volume: 79-04(E), Section: B.

Thesis (Ph.D.)--City University of New York, 2017.

Includes bibliographical references

The continuous mapping of snow and ice cover, particularly in the arctic and poles, are critical to understanding the earth and atmospheric science. Much of the world's sea ice and snow covers the most inhospitable places, making measurements from satellite-based remote sensors essential. Despite the wealth of data from these instruments many challenges remain. For instance, remote sensing instruments reside on-board different satellites and observe the earth at different portions of the electromagnetic spectrum with different spatial footprints. Integrating and fusing this information to make estimates of the surface is a subject of active research.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780355351446Subjects--Topical Terms:

573171
Computer science.
Index Terms--Genre/Form:

554714
Electronic books.

Machine Learning Algorithms for Automated Satellite Snow and Sea Ice Detection.
LDR:03762ntm a2200361K 4500 001 912417
005 20180608141653.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9780355351446
035 $a (MiAaPQ)AAI10635023
035 $a (MiAaPQ)minarees:14839
035 $a AAI10635023
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Bonev, George. $3 1184766
245 1 0 $a Machine Learning Algorithms for Automated Satellite Snow and Sea Ice Detection.
264 0 $c 2017
300 $a 1 online resource (98 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: Dissertation Abstracts International, Volume: 79-04(E), Section: B.
500 $a Adviser: Irina Gladkova.
502 $a Thesis (Ph.D.)--City University of New York, 2017.
504 $a Includes bibliographical references
520 $a The continuous mapping of snow and ice cover, particularly in the arctic and poles, are critical to understanding the earth and atmospheric science. Much of the world's sea ice and snow covers the most inhospitable places, making measurements from satellite-based remote sensors essential. Despite the wealth of data from these instruments many challenges remain. For instance, remote sensing instruments reside on-board different satellites and observe the earth at different portions of the electromagnetic spectrum with different spatial footprints. Integrating and fusing this information to make estimates of the surface is a subject of active research.
520 $a In response to these challenges, this dissertation will present two algorithms that utilize methods from statistics and machine learning, with the goal of improving on the quality and accuracy of current snow and sea ice detection products. The first algorithm aims at implementing snow detection using optical/infrared instrument data. The novelty in this approach is that the classifier is trained using ground station measurements of snow depth that are collocated with the reflectance observed at the satellite. Several classification methods are compared using this training data to identify the one yielding the highest accuracy and optimal space/time complexity. The algorithm is then evaluated against the current operational NASA snow product and it is found that it produces comparable and in some cases superior accuracy results. The second algorithm presents a fully automated approach to sea ice detection that integrates data obtained from passive microwave and optical/infrared satellite instruments. For a particular region of interest the algorithm generates sea ice maps of each individual satellite overpass and then aggregates them to a daily composite level, maximizing the amount of high resolution information available. The algorithm is evaluated at both, the individual satellite overpass level, and at the daily composite level. Results show that at the single overpass level for clear-sky regions, the developed multi-sensor algorithm performs with accuracy similar to that of the optical/infrared products, with the advantage of being able to also classify partially cloud-obscured regions with the help of passive microwave data. At the daily composite level, results show that the algorithm's performance with respect to total ice extent is in line with other daily products, with the novelty of being fully automated and having higher resolution.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
650 4 $a Environmental science. $3 1179128
650 4 $a Remote sensing. $3 557272
650 4 $a Artificial intelligence. $3 559380
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0768
690 $a 0799
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a City University of New York. $b Computer Science. $3 1184450
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10635023 $z click for full text (PQDT)