Tropical deforestation monitoring using Landsat time series and breakpoint detection

Michael Schultz

doi:10.18174/454885

Tropical deforestation monitoring using Landsat time series and breakpoint detection

Michael Schultz

Research output: Thesis › internal PhD, WU

Abstract

Landsat time series Breaks For Additive Season and Trend (BFAST) breakpoint detection was identified as an accurate and generic deforestation monitoring device for the tropics. Suitability for time series pre-processing while varying sites and response signals was researched across different study sites in south America, Asia and Africa. Extensive reference data composed of ground truth data and very high resolution data was used to describe error sources and calculate performance accuracies. Machine learning was used to fuse results to create best maps.

Original language	English
Qualification	Doctor of Philosophy
Awarding Institution	Wageningen University
Supervisors/Advisors	Herold, Martin, Promotor Clevers, Jan, Co-promotor Verbesselt, J., Co-promotor
Award date	15 Oct 2018
Place of Publication	Wageningen
Publisher	Wageningen University
Print ISBNs	9789463434669
DOIs	https://doi.org/10.18174/454885
Publication status	Published - 15 Oct 2018

Access to Document

10.18174/454885

Files and links

Download PDF

Multi-resolution time series analysis using spatial/temporal segments to support REDD.
Schultz, M. (PI), Clevers, J. (CoI), Herold, M. (CoI), Verbesselt, J. (CoI), Schultz, M. (PhD candidate), Herold, M. (Promotor), Clevers, J. (Co-promotor) & Verbesselt, J. (Co-promotor)
1/01/11 → 15/10/18
Project: PhD

Cite this

@phdthesis{bde3cc6d510447ceb3273ce39248d7da,

title = "Tropical deforestation monitoring using Landsat time series and breakpoint detection",

abstract = "Landsat time series Breaks For Additive Season and Trend (BFAST) breakpoint detection was identified as an accurate and generic deforestation monitoring device for the tropics. Suitability for time series pre-processing while varying sites and response signals was researched across different study sites in south America, Asia and Africa. Extensive reference data composed of ground truth data and very high resolution data was used to describe error sources and calculate performance accuracies. Machine learning was used to fuse results to create best maps.",

author = "Michael Schultz",

note = "WU thesis 7051 Includes bibliographical references. - With summary in English",

year = "2018",

month = oct,

day = "15",

doi = "10.18174/454885",

language = "English",

isbn = "9789463434669",

publisher = "Wageningen University",

address = "Netherlands",

type = "internal PhD, WU",

school = "Wageningen University",

}

TY - THES

T1 - Tropical deforestation monitoring using Landsat time series and breakpoint detection

AU - Schultz, Michael

N1 - WU thesis 7051 Includes bibliographical references. - With summary in English

PY - 2018/10/15

Y1 - 2018/10/15

N2 - Landsat time series Breaks For Additive Season and Trend (BFAST) breakpoint detection was identified as an accurate and generic deforestation monitoring device for the tropics. Suitability for time series pre-processing while varying sites and response signals was researched across different study sites in south America, Asia and Africa. Extensive reference data composed of ground truth data and very high resolution data was used to describe error sources and calculate performance accuracies. Machine learning was used to fuse results to create best maps.

AB - Landsat time series Breaks For Additive Season and Trend (BFAST) breakpoint detection was identified as an accurate and generic deforestation monitoring device for the tropics. Suitability for time series pre-processing while varying sites and response signals was researched across different study sites in south America, Asia and Africa. Extensive reference data composed of ground truth data and very high resolution data was used to describe error sources and calculate performance accuracies. Machine learning was used to fuse results to create best maps.

UR - https://edepot.wur.nl/454885

U2 - 10.18174/454885

DO - 10.18174/454885

M3 - internal PhD, WU

SN - 9789463434669

PB - Wageningen University

CY - Wageningen

ER -

Tropical deforestation monitoring using Landsat time series and breakpoint detection

Abstract

Access to Document

Files and links

Fingerprint

Projects

Multi-resolution time series analysis using spatial/temporal segments to support REDD.

Cite this