scholarly journals High-resolution paleovalley classification from airborne electromagnetic imaging and deep neural network training using digital elevation model data

2019 ◽  
Vol 23 (6) ◽  
pp. 2561-2580 ◽  
Author(s):  
Zhenjiao Jiang ◽  
Dirk Mallants ◽  
Luk Peeters ◽  
Lei Gao ◽  
Camilla Soerensen ◽  
...  
Keyword(s):  
Neural Network ◽  
High Resolution ◽  
Digital Elevation Model ◽  
South Australia ◽  
Training Dataset ◽  
Valley Bottom ◽  
Archie’S Law ◽  
Digital Elevation ◽  
Airborne Electromagnetic ◽  
Elevation Model

Abstract. Paleovalleys are buried ancient river valleys that often form productive aquifers, especially in the semiarid and arid areas of Australia. Delineating their extent and hydrostratigraphy is however a challenging task in groundwater system characterization. This study developed a methodology based on the deep learning super-resolution convolutional neural network (SRCNN) approach, to convert electrical conductivity (EC) estimates from an airborne electromagnetic (AEM) survey in South Australia to a high-resolution binary paleovalley map. The SRCNN was trained and tested with a synthetic training dataset, where valleys were generated from readily available digital elevation model (DEM) data from the AEM survey area. Electrical conductivities typical of valley sediments were generated by Archie's law, and subsequently blurred by down-sampling and bicubic interpolation to represent noise from the AEM survey, inversion and interpolation. After a model training step, the SRCNN successfully removed such noise, and reclassified the low-resolution, converted unimodal but skewed EC values into a high-resolution paleovalley index following a bimodal distribution. The latter allows us to distinguish valley from non-valley pixels. Furthermore, a realistic spatial connectivity structure of the paleovalley was predicted when compared with borehole lithology logs and a valley bottom flatness indicator. Overall the methodology permitted us to better constrain the three-dimensional paleovalley geometry from AEM images that are becoming more widely available for groundwater prospecting.

scholarly journals High-resolution palaeovalley classification from airborne electromagnetic imaging and deep neural network training using digital elevation model data

2019 ◽  
Author(s):  
Zhenjiao Jiang ◽  
Dirk Mallants ◽  
Luk Peeters ◽  
Lei Gao ◽  
Gregoire Mariethoz
Keyword(s):  
Neural Network ◽  
High Resolution ◽  
Digital Elevation Model ◽  
South Australia ◽  
Training Dataset ◽  
Valley Bottom ◽  
Archie’S Law ◽  
Digital Elevation ◽  
Airborne Electromagnetic ◽  
Elevation Model

Abstract. Palaeovalleys are buried ancient river valleys that often form productive aquifers, especially in the semi-arid and arid areas of Australia. Delineating their extent and hydrostratigraphy is however a challenging task in groundwater system characterization. This study developed a methodology based on the deep learning super-resolution convolutional neural network (SRCNN) approach, to convert electrical conductivity (EC) estimates from an airborne electromagnetic (AEM) survey in South Australia to a high-resolution binary palaeovalley map. The SRCNN was trained and tested with a synthetic training dataset, where valleys were generated from readily available digital elevation model (DEM) data from the AEM survey area. Electrical conductivities typical of valley sediments were generated by Archie’s Law, and subsequently blurred by down-sampling and bicubic interpolation to represent noise from the AEM survey, inversion and interpolation. After a model training step, the SRCNN successfully removed such noise, and reclassified the low-resolution, unimodal but skewed EC values into a high-resolution palaeovalley index following a bimodal distribution. The latter allows distinguishing valley from non-valley pixels. Furthermore, a realistic spatial connectivity structure of the palaeovalley was predicted when compared with borehole lithology logs and valley bottom flatness indicator. Overall the methodology permitted to better constrain the three-dimensional palaeovalley geometry from AEM images that are becoming more widely available for groundwater prospecting.

scholarly journals Assessing Optimal Digital Elevation Model Selection for Active River Area Delineation Across Broad Regions

2021 ◽  
Author(s):  
Shizhou Ma ◽  
Karen Beazley ◽  
Patrick Nussey ◽  
Chris Greene
Keyword(s):  
High Resolution ◽  
Digital Elevation Model ◽  
Smoothing Algorithm ◽  
Processing Efficiency ◽  
Spatial Approach ◽  
Digital Elevation ◽  
Elevation Data ◽  
Computer Based ◽  
Lidar Dem ◽  
Elevation Model

Abstract The Active River Area (ARA) is a spatial approach for identifying the extent of functional riparian area. Given known limitations in terms of input elevation data quality and methodology, ARA studies to date have not achieved effective computer-based ARA-component delineation, limiting the efficacy of the ARA framework in terms of informing riparian conservation and management. To achieve framework refinement and determine the optimal input elevation data for future ARA studies, this study tested a novel Digital Elevation Model (DEM) smoothing algorithm and assessed ARA outputs derived from a range of DEMs for accuracy and efficiency. It was found that the tested DEM smoothing algorithm allows the ARA framework to take advantage of high-resolution LiDAR DEM and considerably improves the accuracy of high-resolution LiDAR DEM derived ARA results; smoothed LiDAR DEM in 5-meter spatial resolution best balanced ARA accuracy and data processing efficiency and is ultimately recommended for future ARA delineations across large regions.

scholarly journals A 20-year record (1998–2017) of permafrost, active layer, and meteorological conditions at a High Arctic permafrost research site (Bayelva, Spitsbergen): an opportunity to validate remote sensing data and land surface, snow, and permafrost models

2017 ◽  
Author(s):  
Julia Boike ◽  
Inge Juszak ◽  
Stephan Lange ◽  
Sarah Chadburn ◽  
Eleanor Burke ◽  
...  
Keyword(s):  
Energy Balance ◽  
High Resolution ◽  
Observational Data ◽  
Digital Elevation Model ◽  
Positive Feedback ◽  
The Arctic ◽  
Data Sets ◽  
Data Set ◽  
Digital Elevation ◽  
Elevation Model

Abstract. Most permafrost is located in the Arctic, where frozen organic carbon makes it an important component of the global climate system. Despite the fact that the Arctic climate changes more rapidly than the rest of the globe, observational data density in the region is low. Permafrost thaw and carbon release to the atmosphere are a positive feedback mechanism that can exacerbate climate warming. This positive feedback functions via changing land-atmosphere energy and mass exchanges. There is thus a great need to understand links between the energy balance, which can vary rapidly over hourly to annual time scales, and permafrost, which changes slowly over long time periods. This understanding thus mandates long-term observational data sets. Such a data set is available from the Bayelva Site at Ny-Ålesund, Svalbard, where meteorology, energy balance components and subsurface observations have been made for the last 20 years. Additional data include a high resolution digital elevation model and a panchromatic image. This paper presents the data set produced so far, explains instrumentation, calibration, processing and data quality control, as well as the sources for various resulting data sets. The resulting data set is unique in the Arctic and serves a baseline for future studies. Since the data provide observations of temporally variable parameters that mitigate energy fluxes between permafrost and atmosphere, such as snow depth and soil moisture content, they are suitable for use in integrating, calibrating and testing permafrost as a component in Earth System Models. The data set also includes a high resolution digital elevation model that can be used together with the snow physical information for snow pack modeling. The presented data are available in the supplementary material for this paper and through the PANGAEA website ( https://doi.pangaea.de/10.1594/PANGAEA.880120).

scholarly journals HydroSHEDS v2.0 – Refined global river network and catchment delineations from TanDEM-X elevation data

2021 ◽  
Author(s):  
Bernhard Lehner ◽  
Achim Roth ◽  
Martin Huber ◽  
Mira Anand ◽  
Günther Grill ◽  
...  
Keyword(s):  
High Resolution ◽  
Digital Elevation Model ◽  
Multiple Scales ◽  
Environmental Conservation ◽  
The Arctic ◽  
River Networks ◽  
Northern Latitude ◽  
Digital Elevation ◽  
Elevation Data ◽  
Elevation Model

<p>Since its introduction in 2008, the HydroSHEDS database (www.hydrosheds.org) has transformed large-scale hydro-ecological research and applications worldwide by offering standardized spatial units for hydrological assessments. At its core, HydroSHEDS provides digital hydrographic information that can be applied in Geographic Information Software (GIS) or hydrological models to delineate river networks and catchment boundaries at multiple scales, from local to global. Its various data layers form the basis for applications in a wide range of disciplines including environmental, conservation, socioeconomic, human health, and sustainability studies.</p><p>Version 1 of HydroSHEDS was derived from the digital elevation model of the Shuttle Radar Topography Mission (SRTM) at a pixel resolution of 3 arc-seconds (~90 meters at the equator). It was created using customized processing and optimization algorithms and a high degree of manual quality control. Results are available at varying resolutions, ranging from 3 arc-seconds (~90 m) to 5 minutes (~10 km), and in nested sub-basin structures, making the data uniquely suitable for applications at multiple scales. A suite of related data collections and value-added information, foremost the HydroATLAS compilation of over 50 hydro-environmental attributes for every river reach and sub-basin, continuously enhance the versatility of the HydroSHEDS family of products. Yet version 1 of HydroSHEDS shows some important limitations. In particular, coverage above 60° northern latitude (i.e., largely the Arctic) is missing for the 3 arc-second product and is of low quality for coarser products because no SRTM elevation data are available for this region. Also, some areas are affected by inherent data gaps or other errors that could not be fully resolved at the time of creating version 1 of HydroSHEDS.</p><p>Today, the TanDEM-X dataset (TerraSAR-X add-on for Digital Elevation Measurement), created in partnership between the German Aerospace Agency (DLR) and Airbus, offers a new digital elevation model covering the entire global land surface including northern latitudes. In a collaborative project, this dataset is used to extract HydroSHEDS v2.0, following the same basic specifications as version 1. DLR is processing the original 12 m resolution TanDEM-X data to create a hydrologically pre-conditioned version at 3 arc-second resolution. In this step, corrections with high-resolution vegetation and settlement maps are applied to reduce distortions caused by vegetation cover and in built-up areas. Following this preprocessing, refined hydrological optimization and correction algorithms are used to derive the drainage pathways, including improved ‘stream-burning’ techniques that incorporate recent data products such as high-resolution terrestrial open water masks and improved tracing of drainage pathways as center lines in global lake and river maps. The resulting HydroSHEDS v2.0 database will provide river networks and catchment boundaries at full global coverage. Release of the data under a free license is scheduled for 2022, with regions above 60° northern latitude being completed first in 2021.</p>

Sign in / Sign up

Export Citation Format

Share Document