Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Faculty of Construction and Environment | en_US |
| dc.contributor | Department of Land Surveying and Geo-Informatics | en_US |
| dc.contributor.advisor | Wong, Man-sing Charles (LSGI) | - |
| dc.creator | Ding, Ning | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/10528 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | - |
| dc.rights | All rights reserved | en_US |
| dc.title | Dust aerosol optical thickness retrieval based on neural network using geostationary satellite images (Himawari 8) | en_US |
| dcterms.abstract | Dust storms are known to have adverse effects on human health and significant impact on weather, air quality, hydrological cycle, and ecosystem. Atmospheric dust loading is also one of the major uncertainties in global climatic modeling as it is known to have a significant impact on the radiation budget and atmospheric stability. This dissertation develops an integrated model for dust storm detection and retrieval based on the geostationary satellite, Himaeari-8. The proposed model consists of two components: (i) using the threshold of Brightness Temperature Difference (BTD), Three-band Volcanic Ash Product (TVAP), the Infrared Difference Dust Index (IDDI), Reverse Absorption Technique (RAT) index to obtain dust storm pixels; (ii) a feed-forward Multilayer Perceptron (MLP) neural network, trained using Back Propagation (BP) algorithm, was used for dust Aerosol Optical Depth (AOT) retrieval. Multi-angle Imaging SpectroRadiometer (MISR) level 2 Aerosol parameters-MIL2ASAE product and Advanced Himawari Imager (AHI) was used in MLP neural network training. Four Himawari-8 channels (band 8, band 13, band 15), as well as pre-processed (BTD, TVAP, and IDDI) from Himawari-8 satellite data are adopted in the MLP-BP neural model. The correlation and root mean squared error (RMSE) of trained MLP-BP model are 98.4% and 0.0283 respectively. In order to assess the performance of the model, daytime AOT at 550 nm derived from MISR aerosol product were compared with AOT retrieved from MLP-BP NN model at 05:00 (UTC) March 5, 2016. The RMSE is 0.4807 and the correlation coefficient is 0.9561. | en_US |
| dcterms.extent | x, 60 pages : color illustrations | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2017 | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.LCSH | Dust storms -- Remote sensing | en_US |
| dcterms.LCSH | Aerosols -- Remote sensing | en_US |
| dcterms.LCSH | Atmosphere -- Remote sensing | en_US |
| dcterms.LCSH | Artificial satellites | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 991022385850103411.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 3.5 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/10528