Evaluation of Boulder Characteristics for Improved Boulder Detection Based on Machine Learning Techniques
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Evaluation of Boulder Characteristics for Improved Boulder Detection Based on Machine Learning Techniques. / Hansen, Signe Schilling; Ernstsen, Verner Brandbyge; Andersen, Mikkel Skovgaard; Al-Hamdani, Zyad; Baran, Ramona; Niederwieser, Manfred; Steinbacher, Frank; Kroon, Aart.
In: Geosciences, Vol. 12, No. 11, 421, 2022.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Evaluation of Boulder Characteristics for Improved Boulder Detection Based on Machine Learning Techniques
AU - Hansen, Signe Schilling
AU - Ernstsen, Verner Brandbyge
AU - Andersen, Mikkel Skovgaard
AU - Al-Hamdani, Zyad
AU - Baran, Ramona
AU - Niederwieser, Manfred
AU - Steinbacher, Frank
AU - Kroon, Aart
PY - 2022
Y1 - 2022
N2 - Detailed maps of the seabed and knowledge of its habitats are critical for a wide range of tasks, such as sustainable development, and environmental protection. Boulders on the seabed form an important environment for ecosystems, but the detection of them is challenging. In this study, we aim to improve the understanding of boulder predictors and to determine connections between predictors and boulder environments on different spatial scales. The Relief-F filter feature selection algorithm was used on four 30 m x 30 m areas in Rodsand lagoon, containing one boulder each, to determine the most relevant predictors. The predictors could be divided into four groups detecting different boulder characteristics: colour contrast, height, boulder boundaries, and spherical geometry. Twelve different types of boulder environments were evaluated. Bare, spherical boulders on sandy seabeds can be predicted from all four predictor groups. It is not possible to detect non-spherical boulders on seabed covered by vegetation. The best predictors for boulder detection depend on the shape and size of the boulder and the surrounding sediment and vegetation. The predictors were evaluated on a larger 400 x 2500 m area. When up-scaling the boulder detection area, larger seabed structures may affect the results. Therefore, knowledge about these structures can be used to remove errors and uncertainties from machine learning input data.
AB - Detailed maps of the seabed and knowledge of its habitats are critical for a wide range of tasks, such as sustainable development, and environmental protection. Boulders on the seabed form an important environment for ecosystems, but the detection of them is challenging. In this study, we aim to improve the understanding of boulder predictors and to determine connections between predictors and boulder environments on different spatial scales. The Relief-F filter feature selection algorithm was used on four 30 m x 30 m areas in Rodsand lagoon, containing one boulder each, to determine the most relevant predictors. The predictors could be divided into four groups detecting different boulder characteristics: colour contrast, height, boulder boundaries, and spherical geometry. Twelve different types of boulder environments were evaluated. Bare, spherical boulders on sandy seabeds can be predicted from all four predictor groups. It is not possible to detect non-spherical boulders on seabed covered by vegetation. The best predictors for boulder detection depend on the shape and size of the boulder and the surrounding sediment and vegetation. The predictors were evaluated on a larger 400 x 2500 m area. When up-scaling the boulder detection area, larger seabed structures may affect the results. Therefore, knowledge about these structures can be used to remove errors and uncertainties from machine learning input data.
KW - boulder characteristics
KW - boulder detection
KW - boulder predictors
KW - habitat mapping
KW - machine learning
KW - seabed environments
U2 - 10.3390/geosciences12110421
DO - 10.3390/geosciences12110421
M3 - Journal article
VL - 12
JO - Geosciences
JF - Geosciences
SN - 2076-3263
IS - 11
M1 - 421
ER -
ID: 329745977