Using input feature information to improve ultraviolet retrieval in neural networks

Zhibin Sun, Ni Bin Chang, Wei Gao, Maosi Chen, Melina Zempila

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In neural networks, the training/predicting accuracy and algorithm efficiency can be improved significantly via accurate input feature extraction. In this study, some spatial features of several important factors in retrieving surface ultraviolet (UV) are extracted. An extreme learning machine (ELM) is used to retrieve the surface UV of 2014 in the continental United States, using the extracted features. The results conclude that more input weights can improve the learning capacities of neural networks.

Original languageEnglish
Title of host publicationRemote Sensing and Modeling of Ecosystems for Sustainability XIV
EditorsJinnian Wang, Wei Gao, Ni-Bin Chang
PublisherSPIE
ISBN (Electronic)9781510612679
DOIs
StatePublished - 2017
Externally publishedYes
EventRemote Sensing and Modeling of Ecosystems for Sustainability XIV 2017 - San Diego, United States
Duration: 9 Aug 2017 → …

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume10405
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceRemote Sensing and Modeling of Ecosystems for Sustainability XIV 2017
Country/TerritoryUnited States
CitySan Diego
Period9/08/17 → …

Keywords

  • Extreme learning machine
  • Input feature
  • Neural network
  • Ultraviolet retrieval

Fingerprint

Dive into the research topics of 'Using input feature information to improve ultraviolet retrieval in neural networks'. Together they form a unique fingerprint.

Cite this