Ocean Colour Remote Sensing Of Case 2 Waters Using An Optimised Neural Network

Kajian ini memberi tumpuan pada pembangunan algoritma baru untuk mendapatkan produk warna laut di kawasan perairan kes 2 menggunakan model rangkain neural (NN) dari pelbagai jenis data penderiaan jauh sebagai input. Model NN dan parameter latihan dioptimumkan dengan input yang dipilih berdasarkan an...

Full description

Saved in:

Bibliographic Details
Main Author:	Anwar, Saumi Syahreza
Format:	Thesis
Language:	English
Published:	2016
Subjects:	QC1-999 Physics
Online Access:	http://eprints.usm.my/32007/1/SAUMI_SYAHREZA_24%28NN%29.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-usm-ep.32007
record_format	uketd_dc
spelling	my-usm-ep.320072019-04-12T05:25:22Z Ocean Colour Remote Sensing Of Case 2 Waters Using An Optimised Neural Network 2016-03 Anwar, Saumi Syahreza QC1-999 Physics Kajian ini memberi tumpuan pada pembangunan algoritma baru untuk mendapatkan produk warna laut di kawasan perairan kes 2 menggunakan model rangkain neural (NN) dari pelbagai jenis data penderiaan jauh sebagai input. Model NN dan parameter latihan dioptimumkan dengan input yang dipilih berdasarkan analisis korelasi (CA) dan analisis komponen utama (PCA). Di pesisiran pantai Kelantan, penggunaan data spektra pantulan in situ dan simulasi penderiaan jauh satelit telah dikaji untuk menganggar dua parameter kejelasan iaitu kekeruhan (TURB) dan cakera kedalaman Sechhi (SDD). Data simulasi Landsat TM dan AVNIR-2 diuji berdasarkan pengukuran spektra pantulan in situ menggunakan ASD spectroradiometer. Keputusan menunjukkan bahawa data simulasi Landsat TM dan AVNIR-2 membenarkan tafsiran TURB dan SDD. Di kawasan pesisiran pantai Pulau Pinang, penggunaan data satelit penderiaan jauh tunggal dan gabungan pelbagai tarikh telah dikaji untuk menganggar sediment terampai (Cs) dan kepekatan klorofil (Cchl). Pengukuran sampel air pelbagai tarikh telah dibuat selari dengan perolehan data satelit Landsat TM dan AVNIR-2 di lokasi terpilih dari Februari 1999 hingga Mac 2011. This study focused on the development of the new algorithm for retrieving ocean colour products of Case 2 water types using the neural network (NN) model and multiple types of remotely sensed data as inputs. The NN model architecture and training parameters were optimised, with inputs being selected based correlation analysis (CA) and principal component analysis (PCA). In Kelantan coastal waters, the use of in situ reflectance spectra and simulated satellite data for estimation of two water clarity parameters namely turbidity (TURB) and Secchi disk depth (SDD) have been studied. The simulated Landsat TM and AVNIR-2 data were tested against in situ reflectance spectra measurements using ASD Spectroradiometer. The results show that the simulated Landsat TM and AVNIR-2 data enables the interpretation of TURB and SDD. In Penang coastal area, the use of single and multitemporal remote sensing data for estimation of Cs and Cchl has been studied. Multidate in-situ water sample measurements concurrent with Landsat TM and AVNIR-2 satellite data were obtained in selected locations from February 1999 to March 2011. 2016-03 Thesis http://eprints.usm.my/32007/ http://eprints.usm.my/32007/1/SAUMI_SYAHREZA_24%28NN%29.pdf application/pdf en public phd doctoral Universiti Sains Malaysia Pusat Pengajian Sains Fizik (School of Physics)
institution	Universiti Sains Malaysia
collection	USM Institutional Repository
language	English
topic	QC1-999 Physics
spellingShingle	QC1-999 Physics Anwar, Saumi Syahreza Ocean Colour Remote Sensing Of Case 2 Waters Using An Optimised Neural Network
description	Kajian ini memberi tumpuan pada pembangunan algoritma baru untuk mendapatkan produk warna laut di kawasan perairan kes 2 menggunakan model rangkain neural (NN) dari pelbagai jenis data penderiaan jauh sebagai input. Model NN dan parameter latihan dioptimumkan dengan input yang dipilih berdasarkan analisis korelasi (CA) dan analisis komponen utama (PCA). Di pesisiran pantai Kelantan, penggunaan data spektra pantulan in situ dan simulasi penderiaan jauh satelit telah dikaji untuk menganggar dua parameter kejelasan iaitu kekeruhan (TURB) dan cakera kedalaman Sechhi (SDD). Data simulasi Landsat TM dan AVNIR-2 diuji berdasarkan pengukuran spektra pantulan in situ menggunakan ASD spectroradiometer. Keputusan menunjukkan bahawa data simulasi Landsat TM dan AVNIR-2 membenarkan tafsiran TURB dan SDD. Di kawasan pesisiran pantai Pulau Pinang, penggunaan data satelit penderiaan jauh tunggal dan gabungan pelbagai tarikh telah dikaji untuk menganggar sediment terampai (Cs) dan kepekatan klorofil (Cchl). Pengukuran sampel air pelbagai tarikh telah dibuat selari dengan perolehan data satelit Landsat TM dan AVNIR-2 di lokasi terpilih dari Februari 1999 hingga Mac 2011. This study focused on the development of the new algorithm for retrieving ocean colour products of Case 2 water types using the neural network (NN) model and multiple types of remotely sensed data as inputs. The NN model architecture and training parameters were optimised, with inputs being selected based correlation analysis (CA) and principal component analysis (PCA). In Kelantan coastal waters, the use of in situ reflectance spectra and simulated satellite data for estimation of two water clarity parameters namely turbidity (TURB) and Secchi disk depth (SDD) have been studied. The simulated Landsat TM and AVNIR-2 data were tested against in situ reflectance spectra measurements using ASD Spectroradiometer. The results show that the simulated Landsat TM and AVNIR-2 data enables the interpretation of TURB and SDD. In Penang coastal area, the use of single and multitemporal remote sensing data for estimation of Cs and Cchl has been studied. Multidate in-situ water sample measurements concurrent with Landsat TM and AVNIR-2 satellite data were obtained in selected locations from February 1999 to March 2011.
format	Thesis
qualification_name	Doctor of Philosophy (PhD.)
qualification_level	Doctorate
author	Anwar, Saumi Syahreza
author_facet	Anwar, Saumi Syahreza
author_sort	Anwar, Saumi Syahreza
title	Ocean Colour Remote Sensing Of Case 2 Waters Using An Optimised Neural Network
title_short	Ocean Colour Remote Sensing Of Case 2 Waters Using An Optimised Neural Network
title_full	Ocean Colour Remote Sensing Of Case 2 Waters Using An Optimised Neural Network
title_fullStr	Ocean Colour Remote Sensing Of Case 2 Waters Using An Optimised Neural Network
title_full_unstemmed	Ocean Colour Remote Sensing Of Case 2 Waters Using An Optimised Neural Network
title_sort	ocean colour remote sensing of case 2 waters using an optimised neural network
granting_institution	Universiti Sains Malaysia
granting_department	Pusat Pengajian Sains Fizik (School of Physics)
publishDate	2016
url	http://eprints.usm.my/32007/1/SAUMI_SYAHREZA_24%28NN%29.pdf
_version_	1747820516897456128

Ocean Colour Remote Sensing Of Case 2 Waters Using An Optimised Neural Network

Similar Items