Exploiting low-cost and commonly shared aerial photographs and LiDAR data for detailed vegetation structure mapping of the Wadden Sea Island of Ameland

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Regular mapping of vegetation structure is important for biodiversity monitoring, and increasingly for tracking compliance with nature policy mandates. As such, the Netherlands uses vegetation structure mapping to monitor the Natura 2000 site on the Dutch Wadden Sea island of Ameland. Three decades of natural gas extraction here has caused soil subsidence, impacting vegetation and habitats on the island. In the Netherlands, vegetation structure mapping is typically done using conventional techniques, primarily field surveys combined with visual interpretation of aerial photographs. This procedure is time-consuming and often too inconsistent and inefficient for large areas. In the current study we exploited commonly shared and low-cost aerial photographs and LiDAR data for detailed vegetation structure mapping. Aerial photographs are not always easy to use in automatic classification procedures, as they often lack calibrated spectral reflectance values. Furthermore, pre-processing of aerial photographs to render them more attractive may skew the image so that it no longer accurately depicts the original scene anymore. Our aim was to determine if automatic or semi-automatic classification techniques could be applied to these readily available Dutch data to support mapping and monitoring of the vegetation structure of larger areas. We compared the effectiveness of two well-known classification methods, namely rule-based (RB) and random forest (RF). The RF algorithm was applied with its default settings, as supplied by eCognition software. Both classification methods performed well, with overall accuracies of 84.1% (RB) and 86.4% (RF). Each method, however, has its advantages and disadvantages, which are discussed. Overall, RF classification was preferred over RB classification, as it was better able to handle the complexity of the rules needed for distinguishing more classes. Provision of in situ training data, such as vegetation relevés, was not really problem in the Dutch context. Nevertheless, exploitation of new digital aerial photographs produced each year in a semi-automatic process remains a challenge. Commercial high resolution satellite imagery (~0.5 m resolution) is therefore still preferred by us. This latter, unfortunately, is more costly than aerial photographs which, while not always ideal, are readily available at no additional costs for involved organisations
LanguageEnglish
Pages502-515
JournalSDRP Journal of Earth Sciences & Environmental Studies
Volume4
Issue number1
DOIs
Publication statusPublished - 27 Jan 2019

Fingerprint

vegetation structure
aerial photograph
cost
vegetation
spectral reflectance
monitoring
satellite imagery
field survey
compliance
Wadden Sea
biodiversity
software
habitat
method

Cite this

@article{f8453374eccd4ba0a46d1c5467158df6,
title = "Exploiting low-cost and commonly shared aerial photographs and LiDAR data for detailed vegetation structure mapping of the Wadden Sea Island of Ameland",
abstract = "Regular mapping of vegetation structure is important for biodiversity monitoring, and increasingly for tracking compliance with nature policy mandates. As such, the Netherlands uses vegetation structure mapping to monitor the Natura 2000 site on the Dutch Wadden Sea island of Ameland. Three decades of natural gas extraction here has caused soil subsidence, impacting vegetation and habitats on the island. In the Netherlands, vegetation structure mapping is typically done using conventional techniques, primarily field surveys combined with visual interpretation of aerial photographs. This procedure is time-consuming and often too inconsistent and inefficient for large areas. In the current study we exploited commonly shared and low-cost aerial photographs and LiDAR data for detailed vegetation structure mapping. Aerial photographs are not always easy to use in automatic classification procedures, as they often lack calibrated spectral reflectance values. Furthermore, pre-processing of aerial photographs to render them more attractive may skew the image so that it no longer accurately depicts the original scene anymore. Our aim was to determine if automatic or semi-automatic classification techniques could be applied to these readily available Dutch data to support mapping and monitoring of the vegetation structure of larger areas. We compared the effectiveness of two well-known classification methods, namely rule-based (RB) and random forest (RF). The RF algorithm was applied with its default settings, as supplied by eCognition software. Both classification methods performed well, with overall accuracies of 84.1{\%} (RB) and 86.4{\%} (RF). Each method, however, has its advantages and disadvantages, which are discussed. Overall, RF classification was preferred over RB classification, as it was better able to handle the complexity of the rules needed for distinguishing more classes. Provision of in situ training data, such as vegetation relev{\'e}s, was not really problem in the Dutch context. Nevertheless, exploitation of new digital aerial photographs produced each year in a semi-automatic process remains a challenge. Commercial high resolution satellite imagery (~0.5 m resolution) is therefore still preferred by us. This latter, unfortunately, is more costly than aerial photographs which, while not always ideal, are readily available at no additional costs for involved organisations",
author = "C.A. M{\"u}cher and H. Kramer and M.R. Najafabadi and L. Kooistra and A.T. Kuiters and P.A. Slim",
year = "2019",
month = "1",
day = "27",
doi = "10.25177/JESES.4.1.2",
language = "English",
volume = "4",
pages = "502--515",
journal = "SDRP Journal of Earth Sciences & Environmental Studies",
issn = "2472-6397",
number = "1",

}

TY - JOUR

T1 - Exploiting low-cost and commonly shared aerial photographs and LiDAR data for detailed vegetation structure mapping of the Wadden Sea Island of Ameland

AU - Mücher, C.A.

AU - Kramer, H.

AU - Najafabadi, M.R.

AU - Kooistra, L.

AU - Kuiters, A.T.

AU - Slim, P.A.

PY - 2019/1/27

Y1 - 2019/1/27

N2 - Regular mapping of vegetation structure is important for biodiversity monitoring, and increasingly for tracking compliance with nature policy mandates. As such, the Netherlands uses vegetation structure mapping to monitor the Natura 2000 site on the Dutch Wadden Sea island of Ameland. Three decades of natural gas extraction here has caused soil subsidence, impacting vegetation and habitats on the island. In the Netherlands, vegetation structure mapping is typically done using conventional techniques, primarily field surveys combined with visual interpretation of aerial photographs. This procedure is time-consuming and often too inconsistent and inefficient for large areas. In the current study we exploited commonly shared and low-cost aerial photographs and LiDAR data for detailed vegetation structure mapping. Aerial photographs are not always easy to use in automatic classification procedures, as they often lack calibrated spectral reflectance values. Furthermore, pre-processing of aerial photographs to render them more attractive may skew the image so that it no longer accurately depicts the original scene anymore. Our aim was to determine if automatic or semi-automatic classification techniques could be applied to these readily available Dutch data to support mapping and monitoring of the vegetation structure of larger areas. We compared the effectiveness of two well-known classification methods, namely rule-based (RB) and random forest (RF). The RF algorithm was applied with its default settings, as supplied by eCognition software. Both classification methods performed well, with overall accuracies of 84.1% (RB) and 86.4% (RF). Each method, however, has its advantages and disadvantages, which are discussed. Overall, RF classification was preferred over RB classification, as it was better able to handle the complexity of the rules needed for distinguishing more classes. Provision of in situ training data, such as vegetation relevés, was not really problem in the Dutch context. Nevertheless, exploitation of new digital aerial photographs produced each year in a semi-automatic process remains a challenge. Commercial high resolution satellite imagery (~0.5 m resolution) is therefore still preferred by us. This latter, unfortunately, is more costly than aerial photographs which, while not always ideal, are readily available at no additional costs for involved organisations

AB - Regular mapping of vegetation structure is important for biodiversity monitoring, and increasingly for tracking compliance with nature policy mandates. As such, the Netherlands uses vegetation structure mapping to monitor the Natura 2000 site on the Dutch Wadden Sea island of Ameland. Three decades of natural gas extraction here has caused soil subsidence, impacting vegetation and habitats on the island. In the Netherlands, vegetation structure mapping is typically done using conventional techniques, primarily field surveys combined with visual interpretation of aerial photographs. This procedure is time-consuming and often too inconsistent and inefficient for large areas. In the current study we exploited commonly shared and low-cost aerial photographs and LiDAR data for detailed vegetation structure mapping. Aerial photographs are not always easy to use in automatic classification procedures, as they often lack calibrated spectral reflectance values. Furthermore, pre-processing of aerial photographs to render them more attractive may skew the image so that it no longer accurately depicts the original scene anymore. Our aim was to determine if automatic or semi-automatic classification techniques could be applied to these readily available Dutch data to support mapping and monitoring of the vegetation structure of larger areas. We compared the effectiveness of two well-known classification methods, namely rule-based (RB) and random forest (RF). The RF algorithm was applied with its default settings, as supplied by eCognition software. Both classification methods performed well, with overall accuracies of 84.1% (RB) and 86.4% (RF). Each method, however, has its advantages and disadvantages, which are discussed. Overall, RF classification was preferred over RB classification, as it was better able to handle the complexity of the rules needed for distinguishing more classes. Provision of in situ training data, such as vegetation relevés, was not really problem in the Dutch context. Nevertheless, exploitation of new digital aerial photographs produced each year in a semi-automatic process remains a challenge. Commercial high resolution satellite imagery (~0.5 m resolution) is therefore still preferred by us. This latter, unfortunately, is more costly than aerial photographs which, while not always ideal, are readily available at no additional costs for involved organisations

U2 - 10.25177/JESES.4.1.2

DO - 10.25177/JESES.4.1.2

M3 - Article

VL - 4

SP - 502

EP - 515

JO - SDRP Journal of Earth Sciences & Environmental Studies

T2 - SDRP Journal of Earth Sciences & Environmental Studies

JF - SDRP Journal of Earth Sciences & Environmental Studies

SN - 2472-6397

IS - 1

ER -