GAM4water: An R-based method for extracting wetted areas from remote sensed images

Matteo Redana; Lesley Lancaster; Chris Gibbins

doi:10.1016/j.mex.2024.102955

GAM4water: An R-based method for extracting wetted areas from remote sensed images

Matteo Redana^* (Corresponding Author), Lesley Lancaster, Chris Gibbins

^*Corresponding author for this work

Aberdeen Centre For Environmental Sustainability

Research output: Contribution to journal › Article › peer-review

4 Downloads (Pure)

Abstract

We present ‘GAM4water,’ a R-based method to classify wetted and non-wetted (dry) areas within remotely sensed images and indices derived from such images and derived indexes of various types of wetlands. The GAM4water classification algorithm is built around a Generalized Additive Model (GAM) capable of accounting for non-linear responses. GAM4water can use any type of radiometric data, whether from drones, satellites or other platforms, and can be used with data of different spatial resolutions, geographic extents and with different spatial reference systems. It is a supervised tool that uses pixel information to distinguish between wetted and dry areas within an image set, extract them and produce a rich output that includes a binary raster, polygons of wetted areas, and a classification performance report. We tested it in two case-studies, one using high resolution drone images and another using satellite images. The tests show that GAM4water can produce highly accurate classifications of wetted and non-wetted areas, and has the additional benefit of being easily customizable and not requiring complex implementation procedures.

•This paper introduces the first R based method of wetted area extraction within remotely-sensed images.

•The method is based on Generalized Additive Models and is applicable to any remotely-sensed data.

Original language	English
Article number	102955
Journal	MethodsX
Volume	13
Early online date	10 Sept 2024
DOIs	https://doi.org/10.1016/j.mex.2024.102955
Publication status	Published - 1 Dec 2024

Bibliographical note

A special Thanks to The NERC Filed Spectroscopy facility (FSF) of Edinburgh for providing UAV equipment used in the study case 1. We thank Sarawak Energy Berhad for part-funding the work described in this paper.

CRediT author statement
MR, CG, and LL collected the data presented. MR designed and implemented the GAM4Water function. MR, LL, and CG wrote the manuscript.

Funding

MR was supported by NERC with studentship A15775

Keywords

wetted areas
dry areas
rivers
lakes
GAM

Access to Document

10.1016/j.mex.2024.102955Licence: CC BY

Redana_etal_M_GAM4water_An_R_VoR
© 2024 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/)
Final published version, 2.17 MBLicence: CC BY

Cite this

@article{b45c2a7b80834763ad10c362c6d5cd6f,

title = "GAM4water: An R-based method for extracting wetted areas from remote sensed images",

abstract = "We present {\textquoteleft}GAM4water,{\textquoteright} a R-based method to classify wetted and non-wetted (dry) areas within remotely sensed images and indices derived from such images and derived indexes of various types of wetlands. The GAM4water classification algorithm is built around a Generalized Additive Model (GAM) capable of accounting for non-linear responses. GAM4water can use any type of radiometric data, whether from drones, satellites or other platforms, and can be used with data of different spatial resolutions, geographic extents and with different spatial reference systems. It is a supervised tool that uses pixel information to distinguish between wetted and dry areas within an image set, extract them and produce a rich output that includes a binary raster, polygons of wetted areas, and a classification performance report. We tested it in two case-studies, one using high resolution drone images and another using satellite images. The tests show that GAM4water can produce highly accurate classifications of wetted and non-wetted areas, and has the additional benefit of being easily customizable and not requiring complex implementation procedures.•This paper introduces the first R based method of wetted area extraction within remotely-sensed images.•The method is based on Generalized Additive Models and is applicable to any remotely-sensed data.",

keywords = "wetted areas, dry areas, rivers, lakes, GAM",

author = "Matteo Redana and Lesley Lancaster and Chris Gibbins",

note = "A special Thanks to The NERC Filed Spectroscopy facility (FSF) of Edinburgh for providing UAV equipment used in the study case 1. We thank Sarawak Energy Berhad for part-funding the work described in this paper. CRediT author statement MR, CG, and LL collected the data presented. MR designed and implemented the GAM4Water function. MR, LL, and CG wrote the manuscript.",

year = "2024",

month = dec,

day = "1",

doi = "10.1016/j.mex.2024.102955",

language = "English",

volume = "13",

journal = "MethodsX",

publisher = "Elsevier",

}

TY - JOUR

T1 - GAM4water

T2 - An R-based method for extracting wetted areas from remote sensed images

AU - Redana, Matteo

AU - Lancaster, Lesley

AU - Gibbins, Chris

N1 - A special Thanks to The NERC Filed Spectroscopy facility (FSF) of Edinburgh for providing UAV equipment used in the study case 1. We thank Sarawak Energy Berhad for part-funding the work described in this paper. CRediT author statement MR, CG, and LL collected the data presented. MR designed and implemented the GAM4Water function. MR, LL, and CG wrote the manuscript.

PY - 2024/12/1

Y1 - 2024/12/1

N2 - We present ‘GAM4water,’ a R-based method to classify wetted and non-wetted (dry) areas within remotely sensed images and indices derived from such images and derived indexes of various types of wetlands. The GAM4water classification algorithm is built around a Generalized Additive Model (GAM) capable of accounting for non-linear responses. GAM4water can use any type of radiometric data, whether from drones, satellites or other platforms, and can be used with data of different spatial resolutions, geographic extents and with different spatial reference systems. It is a supervised tool that uses pixel information to distinguish between wetted and dry areas within an image set, extract them and produce a rich output that includes a binary raster, polygons of wetted areas, and a classification performance report. We tested it in two case-studies, one using high resolution drone images and another using satellite images. The tests show that GAM4water can produce highly accurate classifications of wetted and non-wetted areas, and has the additional benefit of being easily customizable and not requiring complex implementation procedures.•This paper introduces the first R based method of wetted area extraction within remotely-sensed images.•The method is based on Generalized Additive Models and is applicable to any remotely-sensed data.

AB - We present ‘GAM4water,’ a R-based method to classify wetted and non-wetted (dry) areas within remotely sensed images and indices derived from such images and derived indexes of various types of wetlands. The GAM4water classification algorithm is built around a Generalized Additive Model (GAM) capable of accounting for non-linear responses. GAM4water can use any type of radiometric data, whether from drones, satellites or other platforms, and can be used with data of different spatial resolutions, geographic extents and with different spatial reference systems. It is a supervised tool that uses pixel information to distinguish between wetted and dry areas within an image set, extract them and produce a rich output that includes a binary raster, polygons of wetted areas, and a classification performance report. We tested it in two case-studies, one using high resolution drone images and another using satellite images. The tests show that GAM4water can produce highly accurate classifications of wetted and non-wetted areas, and has the additional benefit of being easily customizable and not requiring complex implementation procedures.•This paper introduces the first R based method of wetted area extraction within remotely-sensed images.•The method is based on Generalized Additive Models and is applicable to any remotely-sensed data.

KW - wetted areas

KW - dry areas

KW - rivers

KW - lakes

KW - GAM

U2 - 10.1016/j.mex.2024.102955

DO - 10.1016/j.mex.2024.102955

M3 - Article

C2 - 39385941

VL - 13

JO - MethodsX

JF - MethodsX

M1 - 102955

ER -

GAM4water: An R-based method for extracting wetted areas from remote sensed images

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Fingerprint

Cite this