Predicting lake bathymetry from the topography of the surrounding terrain using deep learning
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Predicting lake bathymetry from the topography of the surrounding terrain using deep learning. / Martinsen, Kenneth Thorø; Sand-Jensen, Kaj; Selvan, Raghavendra.
In: Limnology and Oceanography: Methods, Vol. 21, No. 10, 2023, p. 625-636.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Predicting lake bathymetry from the topography of the surrounding terrain using deep learning
AU - Martinsen, Kenneth Thorø
AU - Sand-Jensen, Kaj
AU - Selvan, Raghavendra
N1 - Publisher Copyright: © 2023 The Authors. Limnology and Oceanography: Methods published by Wiley Periodicals LLC on behalf of Association for the Sciences of Limnology and Oceanography.
PY - 2023
Y1 - 2023
N2 - Lake morphometric features like surface area, volume, mean, and maximum depth are important predictors of many physical, biological, and ecological processes. Lake bathymetric maps that present the lake basin contours are thus an integral part of limnological investigations. Accurate but cumbersome traditional bathymetric surveys measure the depth using a lead line or echosounder. Recently, airborne bathymetric mapping using imagery or laser scanning has been attempted in shallow freshwater and coastal habitats. However, these methods depend on the ability of light to penetrate the water column, which can be problematic in eutrophic lakes and shallow lakes. To alleviate these issues, we developed and tested a deep learning model (based on the U-net) using data from 153 lakes in Denmark to predict bathymetry using the topography of the surrounding terrain. The deep learning model performed much better (pixel-wise mean absolute error: validation set = 1.75 and test set = 2.15 m) than baseline interpolation approaches (validation set = 3.12 m). In addition, the deep learning model generated more realistic bathymetry maps that did not suffer from interpolation artifacts. We find that the model performance improves slightly with increasing model size (number of trainable parameters) and the extent of the surrounding terrain. In addition, our pretraining procedure improved performance and reduced the time for model convergence. Because the model only relies on digital elevation data which are widely available, it can be fine-tuned and used to predict lake bathymetry in other geographical regions.
AB - Lake morphometric features like surface area, volume, mean, and maximum depth are important predictors of many physical, biological, and ecological processes. Lake bathymetric maps that present the lake basin contours are thus an integral part of limnological investigations. Accurate but cumbersome traditional bathymetric surveys measure the depth using a lead line or echosounder. Recently, airborne bathymetric mapping using imagery or laser scanning has been attempted in shallow freshwater and coastal habitats. However, these methods depend on the ability of light to penetrate the water column, which can be problematic in eutrophic lakes and shallow lakes. To alleviate these issues, we developed and tested a deep learning model (based on the U-net) using data from 153 lakes in Denmark to predict bathymetry using the topography of the surrounding terrain. The deep learning model performed much better (pixel-wise mean absolute error: validation set = 1.75 and test set = 2.15 m) than baseline interpolation approaches (validation set = 3.12 m). In addition, the deep learning model generated more realistic bathymetry maps that did not suffer from interpolation artifacts. We find that the model performance improves slightly with increasing model size (number of trainable parameters) and the extent of the surrounding terrain. In addition, our pretraining procedure improved performance and reduced the time for model convergence. Because the model only relies on digital elevation data which are widely available, it can be fine-tuned and used to predict lake bathymetry in other geographical regions.
U2 - 10.1002/lom3.10573
DO - 10.1002/lom3.10573
M3 - Journal article
AN - SCOPUS:85170380748
VL - 21
SP - 625
EP - 636
JO - Limnology and Oceanography: Methods
JF - Limnology and Oceanography: Methods
SN - 1541-5856
IS - 10
ER -
ID: 367702190