東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Satellite Imagery Interpretation for...

Aravena Mesias , Ricardo Agustin,

Linked to FindBook

Google Book

Amazon

博客來

Satellite Imagery Interpretation for Environmental Mapping and Monitoring /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Satellite Imagery Interpretation for Environmental Mapping and Monitoring // Ricardo Agustin Aravena Mesias.
Author:	Aravena Mesias , Ricardo Agustin,
Description:	1 electronic resource (133 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-08, Section: B.
Contained By:	Dissertations Abstracts International86-08B.
Subject:	Ontology. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31863051
ISBN:	9798302891037

Satellite Imagery Interpretation for Environmental Mapping and Monitoring /
Aravena Mesias , Ricardo Agustin,

Satellite Imagery Interpretation for Environmental Mapping and Monitoring /Ricardo Agustin Aravena Mesias. - 1 electronic resource (133 pages)

Source: Dissertations Abstracts International, Volume: 86-08, Section: B.

Recent applications of Remote Sensing have tended to implement more automated approaches, for example with Machine Learning (ML) or Artificial Intelligence (AI) approaches that are implemented without, or with limited geovisualization of the multivariate data. This poses challenges to the interpretability of patterns and the explainability of classifications. Although such approaches can work consistently over large areas, limitations on interpretation have led to perceptions of the approaches as black boxes that typically require very large amounts of training data and processing power. Conversely, approaches founded on operator-interpreted ecological relationships, such as traditional Aerial Photography Interpretation (API), lack reproducibility and cannot be implemented across large areas. These trade-offs have stimulated the development of complementary approaches, with the development of explainable ontologies for landscape geovisualization.In an era increasingly dominated by AI derived solutions, this thesis aims to formalize Satellite Imagery Interpretation (SII) as a quantitative multispectral extension to API and to demonstrate its application for environmental mapping. The motivation is to develop a Remote Sensing approach built on the understanding of ecological relationships that is both communicable and logistically feasible across scales for global monitoring efforts.SII places emphasis on extracting existing knowledge from landscape ecology in the form of indices for environmental gradients and colourimetric indicators of physiognomic properties with the evidential reasoning from perceptual cues, Gestalt principles and cognitive attributes. These indices are intended to enable interpreters to classify land classes in their simplest semantic form (such as forest, water or snow) to facilitate efficient classifications with holistic reduction analyses that are intended to test and help mitigate the effects of the Modifiable Spatial Temporal Unit Problem (MSTUP). The MSTUP combines the scaling effects that may result from inadequate spatial extents and temporal ranges for analysis.By applying gradient theory, geospatial holistic reduction is essentially chorologic, deducing the causal relations between biophysical geographic phenomena occurring within, but also across regions and modelling them systematically. Combining holistic and parametric procedures is possible since gradient analyses provide scalability by avoiding the need to redefine entities and interactions across spatial and temporal scales which is important for global monitoring.SII achieves communicability and replicability through three key steps: 1) development of false colour RGB composite interpretation keys, 2) colourimetric ontologies for training references and/or direct measurement when applicable, and 3) chorologic classification to infer and validate causality of the classes created. Taking these approaches, gradient-directed sampling was applied with ecological colourimetric deductions of pseudo invariant features from gradient extremes to significantly reduce sampling intensity without compromising classification performance.Following an introductory literature review and background to the concepts that comprise the SII approach, this thesis has four core chapters that develop the approach and methods with case studies:Chapter 2(A Colourimetric Approach to Ecological Remote Sensing: Case Study for the Rainforests of South-Eastern Australia) introduces colourimetric ontologies, holistic analysis, Satellite Imagery Interpretation keys and eco-regionalization. The direct measurement of the hue angle from a new band ratio RGB produced the best overall accuracy across a diverse range of ecoregions, only slightly higher than a new conventional index based on a band ratio subtraction.

English

ISBN: 9798302891037Subjects--Topical Terms:

530874
Ontology.
Subjects--Index Terms:

Satellite Imagery Interpretation

Satellite Imagery Interpretation for Environmental Mapping and Monitoring /
LDR:05235nmm a22004093i 4500 001 2431810
005 20250624130456.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798302891037
035 $a (MiAaPQD)AAI31863051
035 $a AAI31863051
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Aravena Mesias , Ricardo Agustin, $e author. $3 3820792
245 1 0 $a Satellite Imagery Interpretation for Environmental Mapping and Monitoring / $c Ricardo Agustin Aravena Mesias.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (133 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: Dissertations Abstracts International, Volume: 86-08, Section: B.
500 $a Advisors: Keith, David; Lyons, Mitchell.
502 $b Ph.D. $c University of New South Wales (Australia) $d 2024.
520 $a Recent applications of Remote Sensing have tended to implement more automated approaches, for example with Machine Learning (ML) or Artificial Intelligence (AI) approaches that are implemented without, or with limited geovisualization of the multivariate data. This poses challenges to the interpretability of patterns and the explainability of classifications. Although such approaches can work consistently over large areas, limitations on interpretation have led to perceptions of the approaches as black boxes that typically require very large amounts of training data and processing power. Conversely, approaches founded on operator-interpreted ecological relationships, such as traditional Aerial Photography Interpretation (API), lack reproducibility and cannot be implemented across large areas. These trade-offs have stimulated the development of complementary approaches, with the development of explainable ontologies for landscape geovisualization.In an era increasingly dominated by AI derived solutions, this thesis aims to formalize Satellite Imagery Interpretation (SII) as a quantitative multispectral extension to API and to demonstrate its application for environmental mapping. The motivation is to develop a Remote Sensing approach built on the understanding of ecological relationships that is both communicable and logistically feasible across scales for global monitoring efforts.SII places emphasis on extracting existing knowledge from landscape ecology in the form of indices for environmental gradients and colourimetric indicators of physiognomic properties with the evidential reasoning from perceptual cues, Gestalt principles and cognitive attributes. These indices are intended to enable interpreters to classify land classes in their simplest semantic form (such as forest, water or snow) to facilitate efficient classifications with holistic reduction analyses that are intended to test and help mitigate the effects of the Modifiable Spatial Temporal Unit Problem (MSTUP). The MSTUP combines the scaling effects that may result from inadequate spatial extents and temporal ranges for analysis.By applying gradient theory, geospatial holistic reduction is essentially chorologic, deducing the causal relations between biophysical geographic phenomena occurring within, but also across regions and modelling them systematically. Combining holistic and parametric procedures is possible since gradient analyses provide scalability by avoiding the need to redefine entities and interactions across spatial and temporal scales which is important for global monitoring.SII achieves communicability and replicability through three key steps: 1) development of false colour RGB composite interpretation keys, 2) colourimetric ontologies for training references and/or direct measurement when applicable, and 3) chorologic classification to infer and validate causality of the classes created. Taking these approaches, gradient-directed sampling was applied with ecological colourimetric deductions of pseudo invariant features from gradient extremes to significantly reduce sampling intensity without compromising classification performance.Following an introductory literature review and background to the concepts that comprise the SII approach, this thesis has four core chapters that develop the approach and methods with case studies:Chapter 2(A Colourimetric Approach to Ecological Remote Sensing: Case Study for the Rainforests of South-Eastern Australia) introduces colourimetric ontologies, holistic analysis, Satellite Imagery Interpretation keys and eco-regionalization. The direct measurement of the hue angle from a new band ratio RGB produced the best overall accuracy across a diverse range of ecoregions, only slightly higher than a new conventional index based on a band ratio subtraction.
546 $a English
590 $a School code: 0423
650 4 $a Ontology. $3 530874
650 4 $a Topography. $3 3561794
650 4 $a Seasons. $3 523975
650 4 $a Biodiversity. $3 627066
650 4 $a Color. $3 533870
650 4 $a Winter. $3 603950
650 4 $a Ecosystems. $3 595401
650 4 $a Summer. $3 800184
650 4 $a Ice. $3 566597
650 4 $a Vegetation. $3 3560047
650 4 $a Aerial photography. $3 549923
650 4 $a Rainforests. $3 3540340
650 4 $a Autumn. $3 800407
650 4 $a Phase transitions. $3 3560387
650 4 $a Satellites. $3 924316
650 4 $a Remote sensing. $3 535394
653 $a Satellite Imagery Interpretation
653 $a Landscape ecology
653 $a Machine Learning
690 $a 0800
690 $a 0799
710 2 $a University of New South Wales (Australia). $e degree granting institution. $3 3815488
720 1 $a Keith, David $e degree supervisor.
720 1 $a Lyons, Mitchell $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-08B.
790 $a 0423
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31863051