상세정보
Export to Refworks부가기능
Machine Learning Algorithms for Spatio-Temporal Scaling of Remotely Sensed Data
상세 프로파일
| 자료유형 | 학위논문 |
|---|---|
| 서명/저자사항 | Machine Learning Algorithms for Spatio-Temporal Scaling of Remotely Sensed Data. |
| 개인저자 | Chakrabarti, Subit. |
| 단체저자명 | University of Florida. Electrical and Computer Engineering. |
| 발행사항 | [S.l.]: University of Florida., 2017. |
| 발행사항 | Ann Arbor: ProQuest Dissertations & Theses, 2017. |
| 형태사항 | 181 p. |
| 기본자료 저록 | Dissertation Abstracts International 79-12B(E). Dissertation Abstract International |
| ISBN | 9780438165601 |
| 학위논문주기 | Thesis (Ph.D.)--University of Florida, 2017. |
| 일반주기 |
Source: Dissertation Abstracts International, Volume: 79-12(E), Section: B.
|
| 요약 | Over the last decade, machine learning algorithms have been extensively studied for their ability to estimate non-linear and dynamic mappings among sets of variables with high accuracies, even for large datasets. With satellite sensors providing |
| 요약 | This dissertation develops novel machine learning algorithms to downscale RS observations of soil moisture (SM) and microwave brightness temperatures (TB) utilizing spatial and temporal correlations among other disparate RS and in-situ datasets. |
| 요약 | The algorithms use kernel methods, information theoretic learning and ensemble learning to provide estimates of high resolution SM and TB satisfying different conditions of variable complexities, data availabilities and expected computational pe |
| 일반주제명 | Electrical engineering. Hydrologic sciences. Remote sensing. |
| 언어 | 영어 |
| 바로가기 | 
: 이 자료의 원문은 한국교육학술정보원에서 제공합니다. |
