Automatic Detection of Ditches and Natural Streams from Digital Elevation Models Using Deep Learning

SND-ID: 2024-57. Version: 1. DOI: https://doi.org/10.5878/jrex-z325

Download data

channels_shapefiles.zip (6.27 MB)

code.zip (61.34 KB)

DEM.zip (9.32 GB)

models.zip (137.26 MB)

Associated documentation

Download all files

2024-57-1.zip (~9.46 GB)

Citation

Creator/Principal investigator(s)

Mariana dos Santos Toledo Busarello - Swedish University of Agricultural Sciences, Department of Forest Ecology and Management

William Lidberg - Swedish University of Agricultural Sciences, Department of Forest Ecology and Management

Anneli Ågren - Swedish University of Agricultural Sciences, Department of Forest Ecology and Management

Florian Westphal - Jönköping University, Department of Computing

Research principal

Swedish University of Agricultural Sciences

Principal's reference number

SLU.seksko.2024.4.4.IÄ-1

Description

This data contains the digital elevation models and polyline shapefiles with the location of channels from the 12 study areas used in this study. It also has the code to generate the datasets used to train the deep learning models to detect channels, ditches, and streams, and calculate the topographic indices. The code to train the models is also included, along with the models with the highest performance in 0.5 m resolution. The channels were mapped differently based on their type: ditches were manually digitized based on the visual analysis of some topographic indices and orthophotos obtained from the DEM. Streams were mapped by initially detecting all natural channel heads, then tracing the downstream channels, and finally manually editing them based on orthophotos.

Data contains personal data

Yes

Type of personal data

Names of user accounts indicating who performed certain steps of the data processing

Language

English

Method and outcome

Data format / data structure

Numeric

Text

Geospatial

Data collection

Mode of collection: Computer-based observation
Description of the mode of collection:
Professionals from the Swedish Forest Agency manually digitized the ditches within the 12 study areas spread across Sweden based on the hillshade and high-pass median filter obtained from the DEM. Historical photos and current ortophotos (resolution ranging from 0.17-0.5 m), the ditches were manually digitized.
Streams were mapped by initially detecting all natural channel heads, then tracing the downstream channels, and finally manually editing them based on ortophotos.

Geographic coverage

Geographic spread

Geographic location: Sweden

Geographic description: The data covers 12 study areas spread across Sweden, containing information related to channel type for small water channels. More information with the precise locations can be found at the README.html file.

Administrative information

Funding

Funding agency: Marianne and Marcus Wallenberg Foundation
Project name on the application: WASP-HS
Funding information:
This work was partially supported by the Wallenberg AI, Autonomous Systems and Software Program – Humanities and Society (WASP-HS) funded by the Marianne and Marcus Wallenberg Foundation
https://wasp-hs.org/

Topic and keywords

Research area

Geosciences, multidisciplinary (Standard för svensk indelning av forskningsämnen 2011)

Physical geography (Standard för svensk indelning av forskningsämnen 2011)

Soil science (Standard för svensk indelning av forskningsämnen 2011)

Imagery / base maps / earth cover (INSPIRE topic categories)

Geoscientific information (INSPIRE topic categories)

Elevation (INSPIRE topic categories)

Location (INSPIRE topic categories)

Inland waters (INSPIRE topic categories)

Keywords

Rivers/streams, Water channels, Digital elevation model, Hydrography, Ditches, Machine learning, Artificial intelligence, Laser scanning, Lidar, Deep learning, Semantic segmentation

Publications

Sort by name | Sort by year

Paul, S. S., Maher Hasselquist, E., Jarefjäll, A., & Ågren, A. (2023). Virtual landscape-scale restoration of altered channels helps us understand the extent of impacts to guide future ecosystem management. In Ambio (Vol. 52, Issue 1, pp. 182–194). https://doi.org/10.1007/s13280-022-01770-8
URN: urn:nbn:se:uu:diva-494403
DOI: https://doi.org/10.1007/s13280-022-01770-8
SwePub: oai:DiVA.org:uu-494403

Lidberg, W., Paul, S. S., Westphal, F., Richter, K.-F., Lavesson, N., Melniks, R., Ivanovs, J., Ciesielski, M., Leinonen, A., & Ågren, A. M. (2023). Mapping drainage ditches in forested landscapes using deep learning and aerial laser scanning. In Journal of irrigation and drainage engineering (No. 04022051; Vol. 149, Issue 3). https://doi.org/10.1061/jidedh.ireng-9796
DOI: https://doi.org/10.1061/jidedh.ireng-9796
URN: urn:nbn:se:umu:diva-201888
SwePub: oai:DiVA.org:umu-201888

If you have published anything based on these data, please notify us with a reference to your publication(s). If you are responsible for the catalogue entry, you can update the metadata/data description in DORIS.

Published: 2024-03-15