A new method for creating maps of artificially drained areas in large river basins based on aerial photographs and geodata

Tetzlaff, BjÃ¶rn; Kuhr, Petra; Wendland, Frank

doi:10.1002/ird.426

Cited by 22 publications

(16 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous studies also identified uncertainties. Tetzlaff, Kuhr, and Wendland () noted the difficulty of acquiring aerial images at the right time associated with rainfall events and vegetation growth for a large area. Sugg's () GIS analysis based on soil drainage class and land cover in the Midwest United States overestimated total SD in Minnesota by 3,643 km 2 compared to the 1992 National Resource Inventory (NRI) including inflated estimates of SD for the RRB region.…”

Section: Resultsmentioning

confidence: 99%

Identifying Subsurface Drainage using Satellite Big Data and Machine Learning via Google Earth Engine

Cho

Jacobs

Jia

et al. 2019

Water Resources Research

View full text Add to dashboard Cite

Human‐induced landscape changes affect hydrologic responses (e.g., floods) that can be detected from a suite of satellite and model data sets. Tapping these vast data sets using machine learning algorithms can produce critically important and accurate insights. In the Red River of the North Basin in the United States, agricultural subsurface drainage (SD; so‐called tile drainage) systems have greatly increased since the late 1990s. Over this period, river flow in the Red River has markedly increased and 6 of 13 major floods during the past century have occurred in the past two decades. The impact of SD systems on river flow is elusive because there are surprisingly few SD records in the United States. In this study, Random Forest machine learning (RFML) classification method running on Google Earth Engine's cloud computing platform was able to capture SD within a field (30 m) and its expansion over time for a large watershed (>100,000 km2). The resulting RFML classifier drew from operational multiple satellites and model data sets (total 14 variables with 36 layers including vegetation, land cover, soil properties, and climate variables). The classifier identified soil properties and land surface temperature to be the strongest predictors of SD. The maps agreed well with SD permit records (overall accuracies of 76.9–87.0%) and corresponded with subwatershed‐level statistics (r = 0.77–0.96). It is expected that the maps produced with this data‐intensive machine learning approach will help water resource managers to assess the hydrological impact from SD expansion and improve flood predictions in SD‐dominated regions.

show abstract

Section: Resultsmentioning

confidence: 99%

Identifying Subsurface Drainage using Satellite Big Data and Machine Learning via Google Earth Engine

Cho

Jacobs

Jia

et al. 2019

Water Resources Research

View full text Add to dashboard Cite

show abstract

“…Consistent information about tile drains is missing and only exists on the regional scale (Tetzlaff et al, 2009). At the national scale, however, there are no maps on tile drains.…”

Section: Discussion Of Model Uncertaintymentioning

confidence: 99%

Large-scale regionalization of water table depth in peatlands optimized for greenhouse gas emission upscaling

Bechtold¹,

Tiemeyer²,

Laggner³

et al. 2014

Hydrol. Earth Syst. Sci.

View full text Add to dashboard Cite

Abstract. Fluxes of the three main greenhouse gases (GHG) CO 2 , CH 4 and N 2 O from peat and other soils with high organic carbon contents are strongly controlled by water table depth. Information about the spatial distribution of water level is thus a crucial input parameter when upscaling GHG emissions to large scales. Here, we investigate the potential of statistical modeling for the regionalization of water levels in organic soils when data covers only a small fraction of the peatlands of the final map. Our study area is Germany. Phreatic water level data from 53 peatlands in Germany were compiled in a new data set comprising 1094 dip wells and 7155 years of data. For each dip well, numerous possible predictor variables were determined using nationally available data sources, which included information about land cover, ditch network, protected areas, topography, peatland characteristics and climatic boundary conditions. We applied boosted regression trees to identify dependencies between predictor variables and dip-well-specific long-term annual mean water level (WL) as well as a transformed form (WL t ). The latter was obtained by assuming a hypothetical GHG transfer function and is linearly related to GHG emissions. Our results demonstrate that model calibration on WL t is superior. It increases the explained variance of the water level in the sensitive range for GHG emissions and avoids model bias in subsequent GHG upscaling. The final model explained 45 % of WL t variance and was built on nine predictor variables that are based on information about land cover, peatland characteristics, drainage network, topography and climatic boundary conditions. Their individual effects on WL t and the observed parameter interactions provide insight into natural and anthropogenic boundary conditions that control water levels in organic soils. Our study also demonstrates that a large fraction of the observed WL t variance cannot be explained by nationally available predictor variables and that predictors with stronger WL t indication, relying, for example, on detailed water management maps and remote sensing products, are needed to substantially improve model predictive performance.

show abstract

“…www.nature.com/scientificdata www.nature.com/scientificdata/ Generally, the usefulness of scientific data mainly depends upon the level of accuracy and the quality of validation data. Most of the previous studies identified tile drained croplands at a smaller scale (field, catchment, or watershed scale) than the present study and employed GIS-based, remote-sensing-based or data-intensive methods like machine learning approaches 25,29,32 to achieve an overall accuracy of 79% to 86%. The availability and the spatial extent of validation data is the major constraint to these studies.…”

Section: Technical Validationmentioning

confidence: 97%

Mapping of 30-meter resolution tile-drained croplands using a geospatial modeling approach

et al. 2020

View full text Add to dashboard Cite

Tile drainage is one of the dominant agricultural management practices in the United States and has greatly expanded since the late 1990s. It has proven effects on land surface water balance and quantity and quality of streamflow at the local scale. The effect of tile drainage on crop production, hydrology, and the environment on a regional scale is elusive due to lack of high-resolution, spatially-explicit tile drainage area information for the Contiguous United States (CONUS). We developed a 30-m resolution tile drainage map of the most-likely tile-drained area of the CONUS (AgTile-US) from county-level tile drainage census using a geospatial model that uses soil drainage information and topographic slope as inputs. Validation of AgTile-US with 16000 ground truth points indicated 86.03% accuracy at the CONUS-scale. Over the heavily tile-drained midwestern regions of the U.S., the accuracy ranges from 82.7% to 93.6%. These data can be used to study and model the hydrologic and water quality responses of tile drainage and to enhance streamflow forecasting in tile drainage dominant regions.

show abstract

A new method for creating maps of artificially drained areas in large river basins based on aerial photographs and geodata

Cited by 22 publications

References 4 publications

Identifying Subsurface Drainage using Satellite Big Data and Machine Learning via Google Earth Engine

Identifying Subsurface Drainage using Satellite Big Data and Machine Learning via Google Earth Engine

Large-scale regionalization of water table depth in peatlands optimized for greenhouse gas emission upscaling

Mapping of 30-meter resolution tile-drained croplands using a geospatial modeling approach

Contact Info

Product

Resources

About