Articles | Volume 24, issue 5
https://doi.org/10.5194/hess-24-2505-2020
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/hess-24-2505-2020
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
14 May 2020
Research article |
| 14 May 2020
| 14 May 2020
Systematic comparison of five machine-learning models in classification and interpolation of soil particle size fractions using different transformed data
Mo Zhang
Key Laboratory of Land Surface Pattern and Simulation, State Key
Laboratory of Resources and Environmental Information System, Institute of
Geographic Sciences and Natural Resources Research, Chinese Academy of
Sciences, Beijing 100101, China
School of Earth Sciences and Resources, China University of
Geosciences, Beijing 100083, China
Wenjiao Shi
CORRESPONDING AUTHOR
Key Laboratory of Land Surface Pattern and Simulation, State Key
Laboratory of Resources and Environmental Information System, Institute of
Geographic Sciences and Natural Resources Research, Chinese Academy of
Sciences, Beijing 100101, China
College of Resources and Environment, University of Chinese Academy of Sciences, Beijing 100049, China
Ziwei Xu
State Key Laboratory of Earth Surface Processes and Resource Ecology, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China
Related authors
Mo Zhang and Wenjiao Shi
Hydrol. Earth Syst. Sci. Discuss., https://doi.org/10.5194/hess-2021-86, https://doi.org/10.5194/hess-2021-86, 2021
Revised manuscript not accepted
Short summary
Short summary
We paid more attention to explain the performance of linear model, machine-learning model and their hybrid patterns on both Euclidean space and Aitchison space using appropriate statistical methods. Different accuracy performance of soil particle-size fraction interpolation were revealed in terms of different compositional balances of isometric log ratio transformation. This study provides a reference for the mapping of soil PSFs combined with transformed data at the regional scale.
Mo Zhang and Wenjiao Shi
Hydrol. Earth Syst. Sci. Discuss., https://doi.org/10.5194/hess-2020-384, https://doi.org/10.5194/hess-2020-384, 2020
Manuscript not accepted for further review
Short summary
Short summary
We used generalized linear model (GLM), random forest (RF), and their hybrid patterns (regression kriging, RK) to map soil particle-size fractions (PSF) using isometric log-ratio (ILR) transformed data. RF and GLM did well in accuracy and bias, respectively. RK can modify bias and accuracy for most models. Different ILR transformed data based on sequential binary partitions was also discussed further. This study can reference soil PSF spatial simulation and how to choose the ILR balances.
Mo Zhang and Wenjiao Shi
Hydrol. Earth Syst. Sci. Discuss., https://doi.org/10.5194/hess-2018-584, https://doi.org/10.5194/hess-2018-584, 2019
Revised manuscript not accepted
Short summary
Short summary
We systematically analyzed both direct (or indirect) soil texture classification and soil particle size fractions (psf) interpolation using five machine learning methods combined with untransformed and log ratio transformed data. The results showed that random forest had notable consequences for soil psf interpolation and soil texture classification (indirect performed better). Our systematic comparison helps to elucidate the processing and selection of compositional data in spatial simulation.
Yaoming Ma, Zhipeng Xie, Yingying Chen, Shaoming Liu, Tao Che, Ziwei Xu, Lunyu Shang, Xiaobo He, Xianhong Meng, Weiqiang Ma, Baiqing Xu, Huabiao Zhao, Junbo Wang, Guangjian Wu, and Xin Li
Earth Syst. Sci. Data Discuss., https://doi.org/10.5194/essd-2024-9, https://doi.org/10.5194/essd-2024-9, 2024
Revised manuscript under review for ESSD
Short summary
Short summary
Current models and the satellites struggle to accurately represent the land-atmosphere (L-A) interactions over the Tibetan Plateau. We present the most extensive compilation of in-situ observations to date, comprising 17 years of data on L-A interactions across 12 sites. This quality-assured benchmark dataset provides independent validation to improve models and remote sensing for the region and it enables new investigations of fine-scale L-A processes and their mechanistic drivers
Yibo Sun, Bilige Sude, Xingwen Lin, Bing Geng, Bo Liu, Shengnan Ji, Junping Jing, Zhiping Zhu, Ziwei Xu, Shaomin Liu, and Zhanjun Quan
Atmos. Meas. Tech., 16, 5659–5679, https://doi.org/10.5194/amt-16-5659-2023, https://doi.org/10.5194/amt-16-5659-2023, 2023
Short summary
Short summary
Unoccupied aerial vehicles (UAVs) provide a versatile platform for eddy covariance (EC) flux measurements at regional scales with low cost, transport, and infrastructural requirements. This study evaluates the measurement performance in the wind field and turbulent flux of a UAV-based EC system based on the data from a set of calibration flights and standard operational flights and concludes that the system can measure the georeferenced wind vector and turbulent flux with sufficient precision.
Shaomin Liu, Ziwei Xu, Tao Che, Xin Li, Tongren Xu, Zhiguo Ren, Yang Zhang, Junlei Tan, Lisheng Song, Ji Zhou, Zhongli Zhu, Xiaofan Yang, Rui Liu, and Yanfei Ma
Earth Syst. Sci. Data, 15, 4959–4981, https://doi.org/10.5194/essd-15-4959-2023, https://doi.org/10.5194/essd-15-4959-2023, 2023
Short summary
Short summary
We present a suite of observational datasets from artificial and natural oases–desert systems that consist of long-term turbulent flux and auxiliary data, including hydrometeorological, vegetation, and soil parameters, from 2012 to 2021. We confirm that the 10-year, long-term dataset presented in this study is of high quality with few missing data, and we believe that the data will support ecological security and sustainable development in oasis–desert areas.
Xinlei He, Yanping Li, Shaomin Liu, Tongren Xu, Fei Chen, Zhenhua Li, Zhe Zhang, Rui Liu, Lisheng Song, Ziwei Xu, Zhixing Peng, and Chen Zheng
Hydrol. Earth Syst. Sci., 27, 1583–1606, https://doi.org/10.5194/hess-27-1583-2023, https://doi.org/10.5194/hess-27-1583-2023, 2023
Short summary
Short summary
This study highlights the role of integrating vegetation and multi-source soil moisture observations in regional climate models via a hybrid data assimilation and machine learning method. In particular, we show that this approach can improve land surface fluxes, near-surface atmospheric conditions, and land–atmosphere interactions by implementing detailed land characterization information in basins with complex underlying surfaces.
Mo Zhang and Wenjiao Shi
Hydrol. Earth Syst. Sci. Discuss., https://doi.org/10.5194/hess-2021-86, https://doi.org/10.5194/hess-2021-86, 2021
Revised manuscript not accepted
Short summary
Short summary
We paid more attention to explain the performance of linear model, machine-learning model and their hybrid patterns on both Euclidean space and Aitchison space using appropriate statistical methods. Different accuracy performance of soil particle-size fraction interpolation were revealed in terms of different compositional balances of isometric log ratio transformation. This study provides a reference for the mapping of soil PSFs combined with transformed data at the regional scale.
Mo Zhang and Wenjiao Shi
Hydrol. Earth Syst. Sci. Discuss., https://doi.org/10.5194/hess-2020-384, https://doi.org/10.5194/hess-2020-384, 2020
Manuscript not accepted for further review
Short summary
Short summary
We used generalized linear model (GLM), random forest (RF), and their hybrid patterns (regression kriging, RK) to map soil particle-size fractions (PSF) using isometric log-ratio (ILR) transformed data. RF and GLM did well in accuracy and bias, respectively. RK can modify bias and accuracy for most models. Different ILR transformed data based on sequential binary partitions was also discussed further. This study can reference soil PSF spatial simulation and how to choose the ILR balances.
Tao Che, Xin Li, Shaomin Liu, Hongyi Li, Ziwei Xu, Junlei Tan, Yang Zhang, Zhiguo Ren, Lin Xiao, Jie Deng, Rui Jin, Mingguo Ma, Jian Wang, and Xiaofan Yang
Earth Syst. Sci. Data, 11, 1483–1499, https://doi.org/10.5194/essd-11-1483-2019, https://doi.org/10.5194/essd-11-1483-2019, 2019
Short summary
Short summary
The paper presents a suite of datasets consisting of long-term hydrometeorological, snow cover and frozen ground data for investigating watershed science and functions from an integrated, distributed and multiscale observation network in the upper reaches of the Heihe River Basin in China. These data are expected to serve as a testing platform to provide accurate forcing data and validate and evaluate remote-sensing products and hydrological models in cold regions for a broader community.
Mo Zhang and Wenjiao Shi
Hydrol. Earth Syst. Sci. Discuss., https://doi.org/10.5194/hess-2018-584, https://doi.org/10.5194/hess-2018-584, 2019
Revised manuscript not accepted
Short summary
Short summary
We systematically analyzed both direct (or indirect) soil texture classification and soil particle size fractions (psf) interpolation using five machine learning methods combined with untransformed and log ratio transformed data. The results showed that random forest had notable consequences for soil psf interpolation and soil texture classification (indirect performed better). Our systematic comparison helps to elucidate the processing and selection of compositional data in spatial simulation.
Feinan Xu, Weizhen Wang, Jiemin Wang, Ziwei Xu, Yuan Qi, and Yueru Wu
Hydrol. Earth Syst. Sci., 21, 4037–4051, https://doi.org/10.5194/hess-21-4037-2017, https://doi.org/10.5194/hess-21-4037-2017, 2017
T. R. Xu, S. M. Liu, Z. W. Xu, S. Liang, and L. Xu
Hydrol. Earth Syst. Sci. Discuss., https://doi.org/10.5194/hessd-10-3927-2013, https://doi.org/10.5194/hessd-10-3927-2013, 2013
Preprint withdrawn
Related subject area
Subject: Catchment hydrology | Techniques and Approaches: Remote Sensing and GIS
Sediment transport in South Asian rivers high enough to impact satellite gravimetry
On the timescale of drought indices for monitoring streamflow drought considering catchment hydrological regimes
Pairing remote sensing and clustering in landscape hydrology for large-scale change identification: an application to the subarctic watershed of the George River (Nunavik, Canada)
Uncertainty assessment of satellite remote-sensing-based evapotranspiration estimates: a systematic review of methods and gaps
Monitoring the extreme flood events in the Yangtze River basin based on GRACE and GRACE-FO satellite data
Predicting soil moisture conditions across a heterogeneous boreal catchment using terrain indices
A combined use of in situ and satellite-derived observations to characterize surface hydrology and its variability in the Congo River basin
Monitoring surface water dynamics in the Prairie Pothole Region of North Dakota using dual-polarised Sentinel-1 synthetic aperture radar (SAR) time series
Watershed zonation through hillslope clustering for tractably quantifying above- and below-ground watershed heterogeneity and functions
Climatic and anthropogenic drivers of a drying Himalayan river
On the selection of precipitation products for the regionalisation of hydrological model parameters
Discharge of groundwater flow to Potter Cove on King George Island, Antarctic Peninsula
The value of ASCAT soil moisture and MODIS snow cover data for calibrating a conceptual hydrologic model
Using hydrological and climatic catchment clusters to explore drivers of catchment behavior
Using MODIS estimates of fractional snow cover area to improve streamflow forecasts in interior Alaska
Informing a hydrological model of the Ogooué with multi-mission remote sensing data
Spatial characterization of long-term hydrological change in the Arkavathy watershed adjacent to Bangalore, India
Spatial pattern evaluation of a calibrated national hydrological model – a remote-sensing-based diagnostic approach
A method to employ the spatial organization of catchments into semi-distributed rainfall–runoff models
Multi-source hydrological soil moisture state estimation using data fusion optimisation
Temporal and spatial evaluation of satellite-based rainfall estimates across the complex topographical and climatic gradients of Chile
Daily Landsat-scale evapotranspiration estimation over a forested landscape in North Carolina, USA, using multi-satellite data fusion
Using object-based geomorphometry for hydro-geomorphological analysis in a Mediterranean research catchment
Comparing the Normalized Difference Infrared Index (NDII) with root zone storage in a lumped conceptual model
Case-based knowledge formalization and reasoning method for digital terrain analysis – application to extracting drainage networks
Improved large-scale hydrological modelling through the assimilation of streamflow and downscaled satellite soil moisture observations
Vegetative impacts upon bedload transport capacity and channel stability for differing alluvial planforms in the Yellow River source zone
Evaluation of global fine-resolution precipitation products and their uncertainty quantification in ensemble discharge simulations
Multidecadal change in streamflow associated with anthropogenic disturbances in the tropical Andes
Integration of 2-D hydraulic model and high-resolution lidar-derived DEM for floodplain flow modeling
Relating seasonal dynamics of enhanced vegetation index to the recycling of water in two endorheic river basins in north-west China
Urbanization dramatically altered the water balances of a paddy field-dominated basin in southern China
GRACE storage-runoff hystereses reveal the dynamics of regional watersheds
Impacts of high inter-annual variability of rainfall on a century of extreme hydrologic regime of northwest Australia
Identification of catchment functional units by time series of thermal remote sensing images
Flow regime change in an endorheic basin in southern Ethiopia
Evaluating digital terrain indices for soil wetness mapping – a Swedish case study
The suitability of remotely sensed soil moisture for improving operational flood forecasting
Modelling stream flow and quantifying blue water using a modified STREAM model for a heterogeneous, highly utilized and data-scarce river basin in Africa
Operational reservoir inflow forecasting with radar altimetry: the Zambezi case study
Three perceptions of the evapotranspiration landscape: comparing spatial patterns from a distributed hydrological model, remotely sensed surface temperatures, and sub-basin water balances
Assessment of waterlogging in agricultural megaprojects in the closed drainage basins of the Western Desert of Egypt
Estimating water discharge from large radar altimetry datasets
Estimation of antecedent wetness conditions for flood modelling in northern Morocco
MODIS snow cover mapping accuracy in a small mountain catchment – comparison between open and forest sites
The AACES field experiments: SMOS calibration and validation across the Murrumbidgee River catchment
A soil moisture and temperature network for SMOS validation in Western Denmark
Classification and flow prediction in a data-scarce watershed of the equatorial Nile region
On the use of AMSU-based products for the description of soil water content at basin scale
Estimating flooded area and mean water level using active and passive microwaves: the example of Paraná River Delta floodplain
Alexandra Klemme, Thorsten Warneke, Heinrich Bovensmann, Matthias Weigelt, Jürgen Müller, Tim Rixen, Justus Notholt, and Claus Lämmerzahl
Hydrol. Earth Syst. Sci., 28, 1527–1538, https://doi.org/10.5194/hess-28-1527-2024, https://doi.org/10.5194/hess-28-1527-2024, 2024
Short summary
Short summary
Satellite data help estimate groundwater depletion, but earlier assessments missed mass loss from river sediment. In the Ganges–Brahmaputra–Meghna (GBM) river system, sediment accounts for 4 % of the depletion. Correcting for sediment in the GBM mountains reduces estimated depletion by 14 %. It's important to note that the Himalayas' uplift may offset some sediment-induced mass loss. This understanding is vital for accurate water storage trend assessments and sustainable groundwater management.
Oscar M. Baez-Villanueva, Mauricio Zambrano-Bigiarini, Diego G. Miralles, Hylke E. Beck, Jonatan F. Siegmund, Camila Alvarez-Garreton, Koen Verbist, René Garreaud, Juan Pablo Boisier, and Mauricio Galleguillos
Hydrol. Earth Syst. Sci., 28, 1415–1439, https://doi.org/10.5194/hess-28-1415-2024, https://doi.org/10.5194/hess-28-1415-2024, 2024
Short summary
Short summary
Various drought indices exist, but there is no consensus on which index to use to assess streamflow droughts. This study addresses meteorological, soil moisture, and snow indices along with their temporal scales to assess streamflow drought across hydrologically diverse catchments. Using data from 100 Chilean catchments, findings suggest that there is not a single drought index that can be used for all catchments and that snow-influenced areas require drought indices with larger temporal scales.
Eliot Sicaud, Daniel Fortier, Jean-Pierre Dedieu, and Jan Franssen
Hydrol. Earth Syst. Sci., 28, 65–86, https://doi.org/10.5194/hess-28-65-2024, https://doi.org/10.5194/hess-28-65-2024, 2024
Short summary
Short summary
For vast northern watersheds, hydrological data are often sparse and incomplete. Our study used remote sensing and clustering to produce classifications of the George River watershed (GRW). Results show two types of subwatersheds with different hydrological behaviors. The GRW experienced a homogenization of subwatershed types likely due to an increase in vegetation productivity, which could explain the measured decline of 1 % (~0.16 km3 y−1) in the George River’s discharge since the mid-1970s.
Bich Ngoc Tran, Johannes van der Kwast, Solomon Seyoum, Remko Uijlenhoet, Graham Jewitt, and Marloes Mul
Hydrol. Earth Syst. Sci., 27, 4505–4528, https://doi.org/10.5194/hess-27-4505-2023, https://doi.org/10.5194/hess-27-4505-2023, 2023
Short summary
Short summary
Satellite data are increasingly used to estimate evapotranspiration (ET) or the amount of water moving from plants, soils, and water bodies into the atmosphere over large areas. Uncertainties from various sources affect the accuracy of these calculations. This study reviews the methods to assess the uncertainties of such ET estimations. It provides specific recommendations for a comprehensive assessment that assists in the potential uses of these data for research, monitoring, and management.
Jingkai Xie, Yue-Ping Xu, Hongjie Yu, Yan Huang, and Yuxue Guo
Hydrol. Earth Syst. Sci., 26, 5933–5954, https://doi.org/10.5194/hess-26-5933-2022, https://doi.org/10.5194/hess-26-5933-2022, 2022
Short summary
Short summary
Monitoring extreme flood events has long been a hot topic for hydrologists and decision makers around the world. In this study, we propose a new index incorporating satellite observations combined with meteorological data to monitor extreme flood events at sub-monthly timescales for the Yangtze River basin (YRB), China. The conclusions drawn from this study provide important implications for flood hazard prevention and water resource management over this region.
Johannes Larson, William Lidberg, Anneli M. Ågren, and Hjalmar Laudon
Hydrol. Earth Syst. Sci., 26, 4837–4851, https://doi.org/10.5194/hess-26-4837-2022, https://doi.org/10.5194/hess-26-4837-2022, 2022
Short summary
Short summary
Terrain indices constitute a good candidate for modelling the spatial variation of soil moisture conditions in many landscapes. In this study, we evaluate nine terrain indices on varying DEM resolution and user-defined thresholds with validation using an extensive field soil moisture class inventory. We demonstrate the importance of field validation for selecting the appropriate DEM resolution and user-defined thresholds and that failing to do so can result in ambiguous and incorrect results.
Benjamin Kitambo, Fabrice Papa, Adrien Paris, Raphael M. Tshimanga, Stephane Calmant, Ayan Santos Fleischmann, Frederic Frappart, Melanie Becker, Mohammad J. Tourian, Catherine Prigent, and Johary Andriambeloson
Hydrol. Earth Syst. Sci., 26, 1857–1882, https://doi.org/10.5194/hess-26-1857-2022, https://doi.org/10.5194/hess-26-1857-2022, 2022
Short summary
Short summary
This study presents a better characterization of surface hydrology variability in the Congo River basin, the second largest river system in the world. We jointly use a large record of in situ and satellite-derived observations to monitor the spatial distribution and different timings of the Congo River basin's annual flood dynamic, including its peculiar bimodal pattern.
Stefan Schlaffer, Marco Chini, Wouter Dorigo, and Simon Plank
Hydrol. Earth Syst. Sci., 26, 841–860, https://doi.org/10.5194/hess-26-841-2022, https://doi.org/10.5194/hess-26-841-2022, 2022
Short summary
Short summary
Prairie wetlands are important for biodiversity and water availability. Knowledge about their variability and spatial distribution is of great use in conservation and water resources management. In this study, we propose a novel approach for the classification of small water bodies from satellite radar images and apply it to our study area over 6 years. The retrieved dynamics show the different responses of small and large wetlands to dry and wet periods.
Haruko M. Wainwright, Sebastian Uhlemann, Maya Franklin, Nicola Falco, Nicholas J. Bouskill, Michelle E. Newcomer, Baptiste Dafflon, Erica R. Siirila-Woodburn, Burke J. Minsley, Kenneth H. Williams, and Susan S. Hubbard
Hydrol. Earth Syst. Sci., 26, 429–444, https://doi.org/10.5194/hess-26-429-2022, https://doi.org/10.5194/hess-26-429-2022, 2022
Short summary
Short summary
This paper has developed a tractable approach for characterizing watershed heterogeneity and its relationship with key functions such as ecosystem sensitivity to droughts and nitrogen export. We have applied clustering methods to classify hillslopes into
watershed zonesthat have distinct distributions of bedrock-to-canopy properties as well as key functions. This is a powerful approach for guiding watershed experiments and sampling as well as informing hydrological and biogeochemical models.
Gopal Penny, Zubair A. Dar, and Marc F. Müller
Hydrol. Earth Syst. Sci., 26, 375–395, https://doi.org/10.5194/hess-26-375-2022, https://doi.org/10.5194/hess-26-375-2022, 2022
Short summary
Short summary
We develop an empirical approach to attribute declining streamflow in the Upper Jhelum watershed, a key subwatershed of the transboundary Indus basin. We find that a loss of streamflow since the year 2000 resulted primarily due to interactions among vegetation and groundwater in response to climate rather than local changes in land use, revealing the climate sensitivity of this Himalayan watershed.
Oscar M. Baez-Villanueva, Mauricio Zambrano-Bigiarini, Pablo A. Mendoza, Ian McNamara, Hylke E. Beck, Joschka Thurner, Alexandra Nauditt, Lars Ribbe, and Nguyen Xuan Thinh
Hydrol. Earth Syst. Sci., 25, 5805–5837, https://doi.org/10.5194/hess-25-5805-2021, https://doi.org/10.5194/hess-25-5805-2021, 2021
Short summary
Short summary
Most rivers worldwide are ungauged, which hinders the sustainable management of water resources. Regionalisation methods use information from gauged rivers to estimate streamflow over ungauged ones. Through hydrological modelling, we assessed how the selection of precipitation products affects the performance of three regionalisation methods. We found that a precipitation product that provides the best results in hydrological modelling does not necessarily perform the best for regionalisation.
Ulrike Falk and Adrián Silva-Busso
Hydrol. Earth Syst. Sci., 25, 3227–3244, https://doi.org/10.5194/hess-25-3227-2021, https://doi.org/10.5194/hess-25-3227-2021, 2021
Short summary
Short summary
This paper focuses on the groundwater flow aspects of a small hydrological catchment at the northern tip of the Antarctic Peninsula. This region has experienced drastic climatological changes in the recent past. The basin is representative for the rugged coastline of the peninsula. It is discussed as a case study for possible future evolution of similar basins further south. Results include a quantitative analysis of glacial and groundwater contribution to total discharge into coastal waters.
Rui Tong, Juraj Parajka, Andreas Salentinig, Isabella Pfeil, Jürgen Komma, Borbála Széles, Martin Kubáň, Peter Valent, Mariette Vreugdenhil, Wolfgang Wagner, and Günter Blöschl
Hydrol. Earth Syst. Sci., 25, 1389–1410, https://doi.org/10.5194/hess-25-1389-2021, https://doi.org/10.5194/hess-25-1389-2021, 2021
Short summary
Short summary
We used a new and experimental version of the Advanced Scatterometer (ASCAT) soil water index data set and Moderate Resolution Imaging Spectroradiometer (MODIS) C6 snow cover products for multiple objective calibrations of the TUWmodel in 213 catchments of Austria. Combined calibration to runoff, satellite soil moisture, and snow cover improves runoff (40 % catchments), soil moisture (80 % catchments), and snow (~ 100 % catchments) simulation compared to traditional calibration to runoff only.
Florian U. Jehn, Konrad Bestian, Lutz Breuer, Philipp Kraft, and Tobias Houska
Hydrol. Earth Syst. Sci., 24, 1081–1100, https://doi.org/10.5194/hess-24-1081-2020, https://doi.org/10.5194/hess-24-1081-2020, 2020
Short summary
Short summary
We grouped 643 rivers from the United States into 10 behavioral groups based on their hydrological behavior (e.g., how much water they transport overall). Those groups are aligned with the ecoregions in the United States. Depending on the groups’ location and other characteristics, either snow, aridity or seasonality is most important for the behavior of the rivers in a group. We also find that very similar river behavior can be found in rivers far apart and with different characteristics.
Katrina E. Bennett, Jessica E. Cherry, Ben Balk, and Scott Lindsey
Hydrol. Earth Syst. Sci., 23, 2439–2459, https://doi.org/10.5194/hess-23-2439-2019, https://doi.org/10.5194/hess-23-2439-2019, 2019
Short summary
Short summary
Remotely sensed snow observations may improve operational streamflow forecasting in remote regions, such as Alaska. In this study, we insert remotely sensed observations of snow extent into the operational framework employed by the US National Weather Service’s Alaska Pacific River Forecast Center. Our work indicates that the snow observations can improve snow estimates and streamflow forecasting. This work provides direction for forecasters to implement remote sensing in their operations.
Cecile M. M. Kittel, Karina Nielsen, Christian Tøttrup, and Peter Bauer-Gottwein
Hydrol. Earth Syst. Sci., 22, 1453–1472, https://doi.org/10.5194/hess-22-1453-2018, https://doi.org/10.5194/hess-22-1453-2018, 2018
Short summary
Short summary
In this study, we integrate free, global Earth observations in a user-friendly and flexible model to reliably characterize an otherwise unmonitored river basin. The proposed model is the best baseline characterization of the Ogooué basin in light of available observations. Furthermore, the study shows the potential of using new, publicly available Earth observations and a suitable model structure to obtain new information in poorly monitored or remote areas and to support user requirements.
Gopal Penny, Veena Srinivasan, Iryna Dronova, Sharachchandra Lele, and Sally Thompson
Hydrol. Earth Syst. Sci., 22, 595–610, https://doi.org/10.5194/hess-22-595-2018, https://doi.org/10.5194/hess-22-595-2018, 2018
Short summary
Short summary
Water resources in the Arkavathy watershed in southern India are changing due to human modification of the landscape, including changing agricultural practices and urbanization. We analyze surface water resources in man-made lakes in satellite imagery over a period of 4 decades and find drying in the northern part of the watershed (characterized by heavy agriculture) and wetting downstream of urban areas. Drying in the watershed is associated with groundwater-irrigated agriculture.
Gorka Mendiguren, Julian Koch, and Simon Stisen
Hydrol. Earth Syst. Sci., 21, 5987–6005, https://doi.org/10.5194/hess-21-5987-2017, https://doi.org/10.5194/hess-21-5987-2017, 2017
Short summary
Short summary
The present study is focused on the spatial pattern evaluation of two models and describes the similarities and dissimilarities. It also discusses the factors that generate these patterns and proposes similar new approaches to minimize the differences. The study points towards a new approach in which the spatial component of the hydrological model is also calibrated and taken into account.
Henning Oppel and Andreas Schumann
Hydrol. Earth Syst. Sci., 21, 4259–4282, https://doi.org/10.5194/hess-21-4259-2017, https://doi.org/10.5194/hess-21-4259-2017, 2017
Short summary
Short summary
How can we evaluate the heterogeneity of natural watersheds and how can we assess its spatial organization? How can we make use of this information for hydrological models and is it beneficial to our models? We propose a method display and assess the interaction of catchment characteristics with the flow path which we defined as the ordering scheme within a basin. A newly implemented algorithm brings this information to the set-up of a model and our results show an increase in model performance.
Lu Zhuo and Dawei Han
Hydrol. Earth Syst. Sci., 21, 3267–3285, https://doi.org/10.5194/hess-21-3267-2017, https://doi.org/10.5194/hess-21-3267-2017, 2017
Short summary
Short summary
Reliable estimation of hydrological soil moisture state is of critical importance in operational hydrology to improve the flood prediction and hydrological cycle description. This paper attempts for the first time to build a soil moisture product directly applicable to hydrology using multiple data sources retrieved from remote sensing and land surface modelling. The result shows a significant improvement of the soil moisture state accuracy; the method can be easily applied in other catchments.
Mauricio Zambrano-Bigiarini, Alexandra Nauditt, Christian Birkel, Koen Verbist, and Lars Ribbe
Hydrol. Earth Syst. Sci., 21, 1295–1320, https://doi.org/10.5194/hess-21-1295-2017, https://doi.org/10.5194/hess-21-1295-2017, 2017
Short summary
Short summary
This work exhaustively evaluates – for the first time – the suitability of seven state-of-the-art satellite-based rainfall estimates (SREs) over the complex topography and diverse climatic gradients of Chile.
Several indices of performance are used for different timescales and elevation zones. Our analysis reveals what SREs are in closer agreement to ground-based observations and what indices allow for understanding mismatches in shape, magnitude, variability and intensity of precipitation.
Yun Yang, Martha C. Anderson, Feng Gao, Christopher R. Hain, Kathryn A. Semmens, William P. Kustas, Asko Noormets, Randolph H. Wynne, Valerie A. Thomas, and Ge Sun
Hydrol. Earth Syst. Sci., 21, 1017–1037, https://doi.org/10.5194/hess-21-1017-2017, https://doi.org/10.5194/hess-21-1017-2017, 2017
Short summary
Short summary
This work explores the utility of a thermal remote sensing based MODIS/Landsat ET data fusion procedure over a mixed forested/agricultural landscape in North Carolina, USA. The daily ET retrieved at 30 m resolution agreed well with measured fluxes in a clear-cut and a mature pine stand. An accounting of consumptive water use by land cover classes is presented, as well as relative partitioning of ET between evaporation (E) and transpiration (T) components.
Domenico Guida, Albina Cuomo, and Vincenzo Palmieri
Hydrol. Earth Syst. Sci., 20, 3493–3509, https://doi.org/10.5194/hess-20-3493-2016, https://doi.org/10.5194/hess-20-3493-2016, 2016
Short summary
Short summary
The authors apply an object-based geomorphometric procedure to define the runoff contribution areas. The results enabled us to identify the contribution area related to the different runoff components activated during the storm events through an advanced hydro-chemical analysis. This kind of approach could be useful applied to similar, rainfall-dominated, forested and no-karst Mediterranean catchments.
Nutchanart Sriwongsitanon, Hongkai Gao, Hubert H. G. Savenije, Ekkarin Maekan, Sirikanya Saengsawang, and Sansarith Thianpopirug
Hydrol. Earth Syst. Sci., 20, 3361–3377, https://doi.org/10.5194/hess-20-3361-2016, https://doi.org/10.5194/hess-20-3361-2016, 2016
Short summary
Short summary
We demonstrated that the readily available NDII remote sensing product is a very useful proxy for moisture storage in the root zone of vegetation. We compared the temporal variation of the NDII with the root zone storage in a hydrological model of eight catchments in the Upper Ping River in Thailand, yielding very good results. Having a reliable NDII product that can help us to estimate the actual moisture storage in catchments is a major contribution to prediction in ungauged basins.
Cheng-Zhi Qin, Xue-Wei Wu, Jing-Chao Jiang, and A-Xing Zhu
Hydrol. Earth Syst. Sci., 20, 3379–3392, https://doi.org/10.5194/hess-20-3379-2016, https://doi.org/10.5194/hess-20-3379-2016, 2016
Short summary
Short summary
Application of digital terrain analysis (DTA), which is typically a modeling process involving workflow building, relies heavily on DTA domain knowledge. However, the DTA knowledge has not been formalized well to be available for inference in automatic tools. We propose a case-based methodology to solve this problem. This methodology can also be applied to other domains of geographical modeling with a similar situation.
Patricia López López, Niko Wanders, Jaap Schellekens, Luigi J. Renzullo, Edwin H. Sutanudjaja, and Marc F. P. Bierkens
Hydrol. Earth Syst. Sci., 20, 3059–3076, https://doi.org/10.5194/hess-20-3059-2016, https://doi.org/10.5194/hess-20-3059-2016, 2016
Short summary
Short summary
We perform a joint assimilation experiment of high-resolution satellite soil moisture and discharge observations in the Murrumbidgee River basin with a large-scale hydrological model. Additionally, we study the impact of high- and low-resolution meteorological forcing on the model performance. We show that the assimilation of high-resolution satellite soil moisture and discharge observations has a significant impact on discharge simulations and can bring them closer to locally calibrated models.
Zhi Wei Li, Guo An Yu, Gary Brierley, and Zhao Yin Wang
Hydrol. Earth Syst. Sci., 20, 3013–3025, https://doi.org/10.5194/hess-20-3013-2016, https://doi.org/10.5194/hess-20-3013-2016, 2016
Short summary
Short summary
Influence of vegetation upon bedload transport and channel morphodynamics is examined along a channel stability gradient ranging from meandering to anabranching to anabranching–braided to fully braided planform conditions along trunk and tributary reaches of the Yellow River source zone in western China. This innovative work reveals complex interactions between channel planform, bedload transport capacity, sediment supply in the flood season, and the hydraulic role of vegetation.
W. Qi, C. Zhang, G. Fu, C. Sweetapple, and H. Zhou
Hydrol. Earth Syst. Sci., 20, 903–920, https://doi.org/10.5194/hess-20-903-2016, https://doi.org/10.5194/hess-20-903-2016, 2016
Short summary
Short summary
Six precipitation products, including TRMM3B42, TRMM3B42RT, GLDAS/Noah, APHRODITE, PERSIANN, and GSMAP-MVK+, are investigated in the usually neglected area of NE China, and a framework is developed to quantify the contributions of uncertainties from precipitation products, hydrological models, and their interactions to uncertainty in simulated discharges. It is found that interactions between hydrological models and precipitation products contribute significantly to uncertainty in discharge.
A. Molina, V. Vanacker, E. Brisson, D. Mora, and V. Balthazar
Hydrol. Earth Syst. Sci., 19, 4201–4213, https://doi.org/10.5194/hess-19-4201-2015, https://doi.org/10.5194/hess-19-4201-2015, 2015
Short summary
Short summary
Andean catchments play a key role in the provision of freshwater resources. The development of megacities in the inter-Andean valleys raises severe concerns about growing water scarcity. This study is one of the first long-term (1970s-now) analyses of the role of land cover and climate change on provision and regulation of streamflow in the tropical Andes. Forest conversion had the largest impact on streamflow, leading to a 10 % net decrease in streamflow over the last 40 years.
D. Shen, J. Wang, X. Cheng, Y. Rui, and S. Ye
Hydrol. Earth Syst. Sci., 19, 3605–3616, https://doi.org/10.5194/hess-19-3605-2015, https://doi.org/10.5194/hess-19-3605-2015, 2015
M. A. Matin and C. P.-A. Bourque
Hydrol. Earth Syst. Sci., 19, 3387–3403, https://doi.org/10.5194/hess-19-3387-2015, https://doi.org/10.5194/hess-19-3387-2015, 2015
Short summary
Short summary
This paper describes a methodology in analysing the interdependencies between components of the hydrological cycle and vegetation characteristics at different elevation zones of two endorheic river basins in an arid-mountainous region of NW China. The analysis shows that oasis vegetation has an important function in sustaining the water cycle in the river basins and oasis vegetation is dependent on surface and shallow subsurface water flow from mountain sources.
L. Hao, G. Sun, Y. Liu, J. Wan, M. Qin, H. Qian, C. Liu, J. Zheng, R. John, P. Fan, and J. Chen
Hydrol. Earth Syst. Sci., 19, 3319–3331, https://doi.org/10.5194/hess-19-3319-2015, https://doi.org/10.5194/hess-19-3319-2015, 2015
Short summary
Short summary
The role of land cover in affecting hydrologic and environmental changes in the humid region in southern China is not well studied. We found that high flows and low flows increased and evapotranspiration decreased due to urbanization in the Qinhuai River basin. Urbanization masked climate warming effects in a rice-paddy-dominated watershed in altering long-term hydrology. Flooding risks and heat island effects are expected to rise due to urbanization.
E. A. Sproles, S. G. Leibowitz, J. T. Reager, P. J. Wigington Jr, J. S. Famiglietti, and S. D. Patil
Hydrol. Earth Syst. Sci., 19, 3253–3272, https://doi.org/10.5194/hess-19-3253-2015, https://doi.org/10.5194/hess-19-3253-2015, 2015
Short summary
Short summary
The paper demonstrates how data from the Gravity Recovery and Climate Experiment (GRACE) can be used to describe the relationship between water stored at the regional scale and stream flow. Additionally, we employ GRACE as a regional-scale indicator to successfully predict stream flow later in the water year. Our work focuses on the Columbia River Basin (North America), but is widely applicable across the globe, and could prove to be particularly useful in regions with limited hydrological data.
A. Rouillard, G. Skrzypek, S. Dogramaci, C. Turney, and P. F. Grierson
Hydrol. Earth Syst. Sci., 19, 2057–2078, https://doi.org/10.5194/hess-19-2057-2015, https://doi.org/10.5194/hess-19-2057-2015, 2015
Short summary
Short summary
We reconstructed a 100-year monthly history of flooding and drought of a large wetland in arid northwest Australia, using hydroclimatic data calibrated against 25 years of satellite images. Severe and intense regional rainfall, as well as the sequence of events, determined surface water expression on the floodplain. While inter-annual variability was high, changes to the flood regime over the last 20 years suggest the wetland may become more persistent in response to the observed rainfall trend.
B. Müller, M. Bernhardt, and K. Schulz
Hydrol. Earth Syst. Sci., 18, 5345–5359, https://doi.org/10.5194/hess-18-5345-2014, https://doi.org/10.5194/hess-18-5345-2014, 2014
Short summary
Short summary
We present a method to define hydrological landscape units by a time series of thermal infrared satellite data. Land surface temperature is calculated for 28 images in 12 years for a catchment in Luxembourg. Pattern measures show spatio-temporal persistency; principle component analysis extracts relevant patterns. Functional units represent similar behaving entities based on a representative set of images. Resulting classification and patterns are discussed regarding potential applications.
F. F. Worku, M. Werner, N. Wright, P. van der Zaag, and S. S. Demissie
Hydrol. Earth Syst. Sci., 18, 3837–3853, https://doi.org/10.5194/hess-18-3837-2014, https://doi.org/10.5194/hess-18-3837-2014, 2014
A. M. Ågren, W. Lidberg, M. Strömgren, J. Ogilvie, and P. A. Arp
Hydrol. Earth Syst. Sci., 18, 3623–3634, https://doi.org/10.5194/hess-18-3623-2014, https://doi.org/10.5194/hess-18-3623-2014, 2014
N. Wanders, D. Karssenberg, A. de Roo, S. M. de Jong, and M. F. P. Bierkens
Hydrol. Earth Syst. Sci., 18, 2343–2357, https://doi.org/10.5194/hess-18-2343-2014, https://doi.org/10.5194/hess-18-2343-2014, 2014
J. K. Kiptala, M. L. Mul, Y. A. Mohamed, and P. van der Zaag
Hydrol. Earth Syst. Sci., 18, 2287–2303, https://doi.org/10.5194/hess-18-2287-2014, https://doi.org/10.5194/hess-18-2287-2014, 2014
C. I. Michailovsky and P. Bauer-Gottwein
Hydrol. Earth Syst. Sci., 18, 997–1007, https://doi.org/10.5194/hess-18-997-2014, https://doi.org/10.5194/hess-18-997-2014, 2014
T. Conradt, F. Wechsung, and A. Bronstert
Hydrol. Earth Syst. Sci., 17, 2947–2966, https://doi.org/10.5194/hess-17-2947-2013, https://doi.org/10.5194/hess-17-2947-2013, 2013
M. El Bastawesy, R. Ramadan Ali, A. Faid, and M. El Osta
Hydrol. Earth Syst. Sci., 17, 1493–1501, https://doi.org/10.5194/hess-17-1493-2013, https://doi.org/10.5194/hess-17-1493-2013, 2013
A. C. V. Getirana and C. Peters-Lidard
Hydrol. Earth Syst. Sci., 17, 923–933, https://doi.org/10.5194/hess-17-923-2013, https://doi.org/10.5194/hess-17-923-2013, 2013
Y. Tramblay, R. Bouaicha, L. Brocca, W. Dorigo, C. Bouvier, S. Camici, and E. Servat
Hydrol. Earth Syst. Sci., 16, 4375–4386, https://doi.org/10.5194/hess-16-4375-2012, https://doi.org/10.5194/hess-16-4375-2012, 2012
J. Parajka, L. Holko, Z. Kostka, and G. Blöschl
Hydrol. Earth Syst. Sci., 16, 2365–2377, https://doi.org/10.5194/hess-16-2365-2012, https://doi.org/10.5194/hess-16-2365-2012, 2012
S. Peischl, J. P. Walker, C. Rüdiger, N. Ye, Y. H. Kerr, E. Kim, R. Bandara, and M. Allahmoradi
Hydrol. Earth Syst. Sci., 16, 1697–1708, https://doi.org/10.5194/hess-16-1697-2012, https://doi.org/10.5194/hess-16-1697-2012, 2012
S. Bircher, N. Skou, K. H. Jensen, J. P. Walker, and L. Rasmussen
Hydrol. Earth Syst. Sci., 16, 1445–1463, https://doi.org/10.5194/hess-16-1445-2012, https://doi.org/10.5194/hess-16-1445-2012, 2012
J.-M. Kileshye Onema, A. E. Taigbenu, and J. Ndiritu
Hydrol. Earth Syst. Sci., 16, 1435–1443, https://doi.org/10.5194/hess-16-1435-2012, https://doi.org/10.5194/hess-16-1435-2012, 2012
S. Manfreda, T. Lacava, B. Onorati, N. Pergola, M. Di Leo, M. R. Margiotta, and V. Tramutoli
Hydrol. Earth Syst. Sci., 15, 2839–2852, https://doi.org/10.5194/hess-15-2839-2011, https://doi.org/10.5194/hess-15-2839-2011, 2011
M. Salvia, F. Grings, P. Ferrazzoli, V. Barraza, V. Douna, P. Perna, C. Bruscantini, and H. Karszenbaum
Hydrol. Earth Syst. Sci., 15, 2679–2692, https://doi.org/10.5194/hess-15-2679-2011, https://doi.org/10.5194/hess-15-2679-2011, 2011
Cited articles
Abdi, D., Cade-Menun, B. J., Ziadi, N., and Parent, L. E.: Compositional
statistical analysis of soil 31P-NMR forms, Geoderma, 257, 40–47, https://doi.org/10.1016/j.geoderma.2015.03.019, 2015.
Adhikari, K. and Hartemink, A. E.: Linking soils to ecosystem services – A
global review, Geoderma, 262, 101–111,
https://doi.org/10.1016/j.geoderma.2015.08.009, 2016.
Aitchison, J.: The statistical-analysis of compositional data, Chapman and
Hall, 139–177, 1982.
Aitchison, J.: On criteria for measures of compositional difference,
Math. Geol., 24, 365–379,
https://doi.org/10.1007/bf00891269, 1992.
Bagheri Bodaghabadi, M., Antonio Martinez-Casasnovas, J., Salehi, M. H.,
Mohammadi, J., Esfandiarpoor Borujeni, I., Toomanian, N., and Gandomkar, A.: Digital soil mapping using artificial neural networks and terrain-related
attributes, Pedosphere, 25, 580–591, 2015.
Bationo, A., Kihara, J., Vanlauwe, B., Waswa, B., and Kimetu, J.: Soil
organic carbon dynamics, functions and management in west african
agro-ecosystems, Agr. Syst., 94, 13–25,
https://doi.org/10.1016/j.agsy.2005.08.011, 2007.
Bedall, F. K. and Zimmermann, H.: Algorithm as 143: The mediancentre,
J. Roy. Stat. Soc. C-Appl., 28,
325–328, https://doi.org/10.2307/2347218, 1979.
Behrens, T. and Scholten, T.: Chapter 25 A comparison of data-mining
techniques in predictive soil mapping, in: Developments in soil science,
edited by: Lagacherie, P., McBratney, A. B., and Voltz, M., Elsevier,
353–617, https://doi.org/10.1016/S0166-2481(06)31025-2, 2006.
Bergmeir, C. and Benitez, J. M.: Neural networks in R using the stuttgart
neural network simulator: RSNNS, J. Stat. Softw., 46, 1–26,
https://doi.org/10.18637/jss.v046.i07, 2012.
Breiman, L.: Bagging predictors, Mach. Learn., 24, 123–140,
https://doi.org/10.1023/a:1018054314350, 1996.
Breiman, L.: Random forests, Mach. Learn., 45, 5–32,
https://doi.org/10.1023/a:1010933404324, 2001.
Brus, D. J., Kempen, B., and Heuvelink, G. B. M.: Sampling for validation of
digital soil maps, Eur. J. Soil Sci., 62, 394–407,
https://doi.org/10.1111/j.1365-2389.2011.01364.x, 2011.
Burges, C. J. C.: A tutorial on support vector machines for pattern
recognition, Data Min. Knowl. Disc., 2, 121–167,
https://doi.org/10.1023/a:1009715923555, 1998.
Burrough, P. A., van Gaans, P. F. M., and Hootsmans, R.: Continuous
classification in soil survey: Spatial correlation, confusion and
boundaries, Geoderma, 77, 115–135,
https://doi.org/10.1016/S0016-7061(97)00018-9, 1997.
Butler, J. C.: Effects of closure on the moments of a distribution, J.
Int. Ass. Math. Geol., 11, 75–84,
https://doi.org/10.1007/bf01043247, 1979.
Camera, C., Zomeni, Z., Noller, J. S., Zissimos, A. M., Christoforou, I. C.,
and Bruggeman, A.: A high resolution map of soil types and physical
properties for Cyprus: A digital soil mapping optimization, Geoderma, 285,
35–49, https://doi.org/10.1016/j.geoderma.2016.09.019, 2017.
Chen, T. and Guestrin, C.: Xgboost: A scalable tree boosting system,
Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge
Discovery and Data Mining, San Francisco, California, USA,
https://doi.org/10.1145/2939672.2939785, 2016.
Chen, T., He, T., Benesty, M., Khotilovich, V., Tang, Y., Cho, H., Chen, K.,
Mitchell, R., Cano, I., Zhou, T., Li, M., Xie, J., Lin, M., Geng, Y., and
Li, Y.: Xgboost: Extreme gradient boosting, R package version 0.71.2,
available at: https://CRAN.R-project.org/package=xgboost (last access: 14 March 2020), 2018.
Conrad, O., Bechtel, B., Bock, M., Dietrich, H., Fischer, E., Gerlitz, L., Wehberg, J., Wichmann, V., and Böhner, J.: System for Automated Geoscientific Analyses (SAGA) v. 2.1.4, Geosci. Model Dev., 8, 1991–2007, https://doi.org/10.5194/gmd-8-1991-2015, 2015.
Cortes, C. and Vapnik, V.: Support-vector networks, Mach. Learn., 20,
273–297, https://doi.org/10.1023/a:1022627411411, 1995.
Cover, T. M. and Hart, P. E.: Nearest neighbor pattern classification, IEEE
T. Inform. Theory, 13, 21–27,
https://doi.org/10.1109/tit.1967.1053964, 1967.
Crouvi, O., Pelletier, J. D., and Rasmussen, C.: Predicting the thickness
and aeolian fraction of soils in upland watersheds of the Mojave Desert,
Geoderma, 195, 94–110,
https://doi.org/10.1016/j.geoderma.2012.11.015, 2013.
Davis, J. and Goadrich, M.: The relationship between precision-recall and
ROC curves, Proceedings of the 23rd international conference on Machine
learning, Pittsburgh, Pennsylvania, USA, 2006.
Egozcue, J. J., Pawlowsky-Glahn, V., Mateu-Figueras, G., and Barcelo-Vidal,
C.: Isometric logratio transformations for compositional data analysis,
Math. Geol., 35, 279–300,
https://doi.org/10.1023/a:1023818214614, 2003.
Egozcue, J. J. and Pawlowsky-Glahn, V.: Groups of parts and their balances
in compositional data analysis, Math. Geol., 37, 795–828,
https://doi.org/10.1007/s11004-005-7381-9, 2005.
Elith, J., Leathwick, J. R., and Hastie, T.: A working guide to boosted
regression trees, J. Anim. Ecol., 77, 802–813,
https://doi.org/10.1111/j.1365-2656.2008.01390.x, 2008.
Filzmoser, P., and Hron, K.: Correlation analysis for compositional data,
Math. Geosci., 41, 905–919,
https://doi.org/10.1007/s11004-008-9196-y, 2009.
Filzmoser, P., Hron, K., and Reimann, C.: Univariate statistical analysis of
environmental (compositional) data: Problems and possibilities, Sci.
Total Environ., 407, 6100–6108,
https://doi.org/10.1016/j.scitotenv.2009.08.008, 2009.
Fiserova, E. and Hron, K.: On the interpretation of orthonormal coordinates
for compositional data, Math. Geosci., 43, 455–468,
https://doi.org/10.1007/s11004-011-9333-x, 2011.
Follain, S., Minasny, B., McBratney, A. B., and Walter, C.: Simulation of
soil thickness evolution in a complex agricultural landscape at fine spatial
and temporal scales, Geoderma, 133, 71–86,
https://doi.org/10.1016/j.geoderma.2006.03.038, 2006.
Fu, G., Xu, F., Zhang, B., and Yi, L.: Stable variable selection of
class-imbalanced data with precision-recall criterion, Chemometr.
Intell. Lab., 171, 241–250,
https://doi.org/10.1016/j.chemolab.2017.10.015, 2017.
Gobin, A., Campling, P., and Feyen, J.: Soil-landscape modelling to quantify
spatial variability of soil texture, Phys. Chem. Earth Pt.
B, 26, 41–45,
https://doi.org/10.1016/s1464-1909(01)85012-7, 2001.
Gochis, D. J., Vivoni, E. R., and Watts, C. J.: The impact of soil depth on
land surface energy and water fluxes in the North American Monsoon region,
J. Arid Environ., 74, 564–571,
https://doi.org/10.1016/j.jaridenv.2009.11.002, 2010.
Hengl, T., Heuvelink, G. B. M., Kempen, B., Leenaars, J. G. B., Walsh, M.
G., Shepherd, K. D., Sila, A., MacMillan, R. A., de Jesus, J. M., Tamene,
L., and Tondoh, J. E.: Mapping soil properties of Africa at 250 m
resolution: Random forests significantly improve current predictions, Plos
One, 10, e0125814, https://doi.org/10.1371/journal.pone.0125814, 2015.
Hengl, T., de Jesus, J. M., Heuvelink, G. B. M., Gonzalez, M. R., Kilibarda,
M., Blagotic, A., Shangguan, W., Wright, M. N., Geng, X.,
Bauer-Marschallinger, B., Guevara, M. A., Vargas, R., MacMillan, R. A.,
Batjes, N. H., Leenaars, J. G. B., Ribeiro, E., Wheeler, I., Mantel, S., and
Kempen, B.: Soilgrids250m: Global gridded soil information based on machine
learning, Plos One, 12, e0169748,
https://doi.org/10.1371/journal.pone.0169748, 2017.
Hengl, T., Nussbaum, M., Wright, M. N., Heuvelink, G. B. M., and Graeler,
B.: Random forest as a generic framework for predictive modeling of spatial
and spatio-temporal variables, Peerj, 6, e5518,
https://doi.org/10.7717/peerj.5518, 2018.
Heung, B., Ho, H. C., Zhang, J., Knudby, A., Bulmer, C. E., and Schmidt, M.
G.: An overview and comparison of machine-learning techniques for
classification purposes in digital soil mapping, Geoderma, 265, 62–77,
https://doi.org/10.1016/j.geoderma.2015.11.014, 2016.
Hijazi, R., and Jernigan, R.: Modelling compositional data using Dirichlet
regression models, Journal of Applied Probability and Statistics, 4, 77–91,
2009.
Huang, G. and Jiang, Y.: Soil texture of soil sampling points in Yingke Irrigation District, available at: http://data.tpdc.ac.cn/zh-hans/data/2e9cbc1a-5972-4e29-945d-99a1902cadb7/, last access: 11 May 2020.
Huang, J., Subasinghe, R., and Triantafilis, J.: Mapping particle-size
fractions as a composition using additive log-ratio transformation and
ancillary data, Soil Sci. Soc. Am. J., 78, 1967–1976,
https://doi.org/10.2136/sssaj2014.05.0215, 2014.
Huete, A., Didan, K., Miura, T., Rodriguez, E. P., Gao, X., and Ferreira, L.
G.: Overview of the radiometric and biophysical performance of the MODIS
vegetation indices, Remote Sens. Environ., 83, 195–213,
https://doi.org/10.1016/s0034-4257(02)00096-2, 2002.
Huete, A. R.: A soil-adjusted vegetation index (SAVI), Remote Sens.
Environ., 25, 295–309,
https://doi.org/10.1016/0034-4257(88)90106-x, 1988.
Jafari, A., Khademi, H., Finke, P. A., Van de Wauw, J., and Ayoubi, S.:
Spatial prediction of soil great groups by boosted regression trees using a
limited point dataset in an arid region, southeastern Iran, Geoderma, 232,
148–163, https://doi.org/10.1016/j.geoderma.2014.04.029, 2014.
Kuhn, M.: Caret: Classification and regression training, R package version
6.0-80, available at: https://CRAN.R-project.org/package=caret (last access: 14 March 2020), 2018.
Landis, J. R. and Koch, G. G.: Measurement of observer agreement for
categorical data, Biometrics, 33, 159–174,
https://doi.org/10.2307/2529310, 1977.
Liaw, A., and Wiener, M.: Classification and regression by randomforest, R
News, 2, 18–22, available at: https://CRAN.R-project.org/doc/Rnews/ (last access: 29 April 2020), 2002.
Liess, M., Glaser, B., and Huwe, B.: Uncertainty in the spatial prediction
of soil texture comparison of regression tree and random forest models,
Geoderma, 170, 70–79,
https://doi.org/10.1016/j.geoderma.2011.10.010, 2012.
Lloyd, C. D., Pawlowsky-Glahn, V., and Jose Egozcue, J.: Compositional data
analysis in population studies, Ann. Assoc. Am.
Geogr., 102, 1251–1266,
https://doi.org/10.1080/00045608.2011.652855, 2012.
Ma, M.: HiWATER: Dataset of soil parameters in the midstream of the Heihe River Basin (2012), available at: http://data.tpdc.ac.cn/zh-hans/data/371ce545-e8d0-4e96-81e1-e862dbfc3b50/, last access: 11 May 2020.
Martin-Fernandez, J. A., Olea-Meneses, R. A., and Pawlowsky-Glahn, V.:
Criteria to compare estimation methods of regionalized compositions,
Math. Geol., 33, 889–909,
https://doi.org/10.1023/a:1012293922142, 2001.
McNamara, J. P., Chandler, D., Seyfried, M., and Achet, S.: Soil moisture
states, lateral flow, and streamflow generation in a semi-arid,
snowmelt-driven catchment, Hydrol. Process., 19, 4023–4038,
https://doi.org/10.1002/hyp.5869, 2005.
Menafoglio, A., Guadagnini, A., and Secchi, P.: A kriging approach based on
Aitchison geometry for the characterization of particle-size curves in
heterogeneous aquifers, Stoch. Environ. Res. Risk Assess., 28, 1835–1851,
https://doi.org/10.1007/s00477-014-0849-8, 2014.
Menafoglio, A., Secchi, P., and Guadagnini, A.: A class-kriging predictor
for functional compositions with application to particle-size curves in
heterogeneous aquifers, Math. Geosci., 48, 463–485,
https://doi.org/10.1007/s11004-015-9625-7, 2016a.
Menafoglio, A., Guadagnini, A., and Secchi, P.: Stochastic simulation of
soil particle-size curves in heterogeneous aquifer systems through a Bayes
space approach, Water Resour. Res., 52, 5708–5726,
https://doi.org/10.1002/2015wr018369, 2016b.
Metternicht, G. I. and Zinck, J. A.: Remote sensing of soil salinity:
Potentials and constraints, Remote Sens. Environ., 85, 1–20,
https://doi.org/10.1016/s0034-4257(02)00188-8, 2003.
Meyer, D., Dimitriadou, E., Hornik, K., Andreas, W., and Friedrich, L.:
e1071: Misc functions of the department of statistics, probability theory
group (formerly: E1071), TU Wien, R package version 1.6-8, available at:
https://CRAN.R-project.org/package=e1071 (last
access: 14 March 2020), 2017.
Mishra, S., and Datta-Gupta, A.: Exploratory data analysis, in:
Applied Statistical Modeling and Data Analytics, chap. 2, edited by: Mishra, S. and
Datta-Gupta, A., Elsevier, 15–29,
https://doi.org/10.1016/B978-0-12-803279-4.00002-X, 2018.
Molayemat, H., Torab, F. M., Pawlowsky-Glahn, V., Morshedy, A. H., and Jose
Egozcue, J.: The impact of the compositional nature of data on coal reserve
evaluation, a case study in Parvadeh IV coal deposit, Central Iran,
Int. J. Coal Geol., 188, 94–111,
https://doi.org/10.1016/j.coal.2018.02.003, 2018.
Pahlavan-Rad, M. R. and Akbarimoghaddam, A.: Spatial variability of soil
texture fractions and pH in a flood plain (case study from eastern Iran),
Catena, 160, 275–281,
https://doi.org/10.1016/j.catena.2017.10.002, 2018.
Poggio, L. and Gimona, A.: 3D mapping of soil texture in Scotland, Geoderma
Regional, 9, 5–16,
https://doi.org/10.1016/j.geodrs.2016.11.003, 2017.
Reimann, C. and Filzmoser, P.: Normal and lognormal data distribution in
geochemistry: Death of a myth. Consequences for the statistical treatment of
geochemical and environmental data, Environ. Geol., 39, 1001–1014,
https://doi.org/10.1007/s002549900081, 2000.
Saito, T. and Rehmsmeier, M.: Precrec: Fast and accurate precision-recall
and ROC curve calculations in R, Bioinformatics, 33, 145–147,
https://doi.org/10.1093/bioinformatics/btw570, 2017.
Salazar, E., Giraldo, R., and Porcu, E.: Spatial prediction for
infinite-dimensional compositional data, Stoch. Environ. Res.
Risk A., 29, 1737–1749,
https://doi.org/10.1007/s00477-014-1010-4, 2015.
Schliep, K. and Hechenbichler, K.: kknn: Weighted K-nearest neighbors, R
package version 1.3.1, available at:
https://CRAN.R-project.org/package=kknn (last access: 14 March 2020), 2016.
Segal, M. and Xiao, Y. Y.: Multivariate random forests, Wiley
Interdisciplinary Reviews-Data Mining and Knowledge Discovery, 1, 80–87,
https://doi.org/10.1002/widm.12, 2011.
Si, J.: Data set of soil moisture in the lower reaches of Heihe River (2012), available at: http://data.tpdc.ac.cn/zh-hans/data/438fc689-ad9e-4370-8961-5b2de53d8b87/, last access: 12 May 2020.
Small, C. G.: A survey of multidimensional medians, Int.
Stat. Rev., 58, 263–277,
https://doi.org/10.2307/1403809, 1990.
Song, X., Brus, D. J., Liu, F., Li, D., Zhao, Y., Yang, J., and Zhang, G.:
Mapping soil organic carbon content by geographically weighted regression: A
case study in the Heihe River Basin, China, Geoderma, 261, 11–22,
https://doi.org/10.1016/j.geoderma.2015.06.024, 2016.
Streiner, D. L.: Maintaining standards: Differences between the standard
deviation and standard error, and when to use each, Can. J.
Psychiat., 41, 498–502,
https://doi.org/10.1177/070674379604100805, 1996.
Subasi, A.: Eeg signal classification using wavelet feature extraction and a
mixture of expert model, Expert Syst. Appl., 32, 1084–1093,
https://doi.org/10.1016/j.eswa.2006.02.005, 2007.
Taalab, K., Corstanje, R., Zawadzka, J., Mayr, T., Whelan, M. J., Hannam, J.
A., and Creamer, R.: On the application of bayesian networks in digital soil
mapping, Geoderma, 259, 134–148,
https://doi.org/10.1016/j.geoderma.2015.05.014, 2015.
Taghizadeh-Mehrjardi, R., Nabiollahi, K., Minasny, B., and Triantafilis, J.:
Comparing data mining classifiers to predict spatial distribution of
USDA-family soil groups in Baneh region, Iran, Geoderma, 253, 67–77,
https://doi.org/10.1016/j.geoderma.2015.04.008, 2015.
Thompson, J. A., Roecker, S., Grunwald, S., and Owens, P. R.:
Digital soil mapping: Interactions with and applications for hydropedology,
chap. 21, in: Hydropedology, edited by: Lin, H., Academic Press, Boston, 665–709,
https://doi.org/10.1016/B978-0-12-386941-8.00021-6, 2012.
Tolosana-Delgado, R., Mueller, U., and van den Boogaart, K. G.:
Geostatistics for compositional data: An overview, Math. Geosci.,
51, 485–526, https://doi.org/10.1007/s11004-018-9769-3, 2019.
van den Boogaart, K. G. and Tolosana-Delgado, R.: Compositions: A unified R
package to analyze compositional data, Comput. Geosci., 34,
320–338, https://doi.org/10.1016/j.cageo.2006.11.017, 2008.
Vapnik, V.: The support vector method of function estimation, Nonlinear
modeling: Advanced black-box techniques, edited by: Suykens, J. A. K. and
Vandewalle, J., 55–85,
https://doi.org/10.1007/978-1-4615-5703-6_3, 1998.
Wang, Z. and Shi, W.: Mapping soil particle-size fractions: A comparison of
compositional kriging and log-ratio kriging, J. Hydrol., 546,
526–541, https://doi.org/10.1016/j.jhydrol.2017.01.029, 2017.
Wang, Z. and Shi, W.: Robust variogram estimation combined with isometric
log-ratio transformation for improved accuracy of soil particle-size
fraction mapping, Geoderma, 324, 56–66,
https://doi.org/10.1016/j.geoderma.2018.03.007, 2018.
Wu, B., Yan, N., Xiong, J., Bastiaanssen, W. G. M., Zhu, W., and Stein, A.:
Validation of ETWatch using field measurements at diverse landscapes: A case
study in Hai Basin of China, J. Hydrol., 436, 67–80,
https://doi.org/10.1016/j.jhydrol.2012.02.043, 2012.
Wu, W., Li, A., He, X., Ma, R., Liu, H., and Lv, J.: A comparison of support
vector machines, artificial neural network and classification tree for
identifying soil texture classes in southwest China, Comput.
Electron. Agr., 144, 86-93,
https://doi.org/10.1016/j.compag.2017.11.037, 2018.
Xu, T., He, X., Bateni, S. M., Auligne, T., Liu, S., Xu, Z., Zhou, J., and
Mao, K.: Mapping regional turbulent heat fluxes via variational assimilation
of land surface temperature data from polar orbiting satellites, Remote
Sens. Environ., 221, 444–461,
https://doi.org/10.1016/j.rse.2018.11.023, 2019.
Yang, R., Zhang, G., Liu, F., Lu, Y., Yang, F., Yang, F., Yang, M., Zhao,
Y., and Li, D.: Comparison of boosted regression tree and random forest
models for mapping topsoil organic carbon concentration in an alpine
ecosystem, Ecol. Indic., 60, 870–878,
https://doi.org/10.1016/j.ecolind.2015.08.036, 2016.
Yi, C., Li, D., Zhang, G., Zhao, Y., Yang, J., Liu, F., and Song, X.:
Criteria for partition of soil thickness and case studies, Acta Pedologica
Sinica, 52, 220–227, https://doi.org/10.11766/trxb201402180069,
2015.
Yoo, K., Amundson, R., Heimsath, A. M., and Dietrich, W. E.: Spatial
patterns of soil organic carbon on hillslopes: Integrating geomorphic
processes and the biological C cycle, Geoderma, 130, 47–65,
https://doi.org/10.1016/j.geoderma.2005.01.008, 2006.
Yue, T. and Zhao, N.: Digital soil mapping dataset of soil texture (soil particle-size fractions) in the Tianlaochi basin (2012–2014), available at: http://data.tpdc.ac.cn/zh-hans/data/737e4d01-c5f8-4940-98d2-3bda306784ad/, last access: 11 May 2020a.
Yue, T. and Zhao, N.: Digital soil mapping dataset of soil texture (soil particle-size fractions) in the upstream of the Heihe river basin (2012–2016), available at: http://data.tpdc.ac.cn/zh-hans/data/7f91d36d-8bbd-40d5-8eaf-7c035e742f40/, last access: 11 May 2020b.
Yue, T., Zhang, L., Zhao, N., Zhao, M., Chen, C., Du, Z., Song, D., Fan, Z.,
Shi, W., Wang, S., Yan, C., Li, Q., Sun, X., Yang, H., Wilson, J., and Xu,
B.: A review of recent developments in HASM, Environ. Earth Sci.,
74, 6541–6549, https://doi.org/10.1007/s12665-015-4489-1, 2015.
Yue, T., Liu, Y., Zhao, M., Du, Z., and Zhao, N.: A fundamental theorem of
Earth's surface modelling, Environ. Earth Sci., 75, 751,
https://doi.org/10.1007/s12665-016-5310-5, 2016.
Zeraatpisheh, M., Ayoubi, S., Jafari, A., and Finke, P.: Comparing the
efficiency of digital and conventional soil mapping to predict soil types in
a semi-arid region in Iran, Geomorphology, 285, 186–204,
https://doi.org/10.1016/j.geomorph.2017.02.015, 2017.
Zhang, G.: Soil texture of representative samples in the Heihe River Basin, available at: http://data.tpdc.ac.cn/zh-hans/data/b5835154-1e3c-41a4-ba6c-a6ec5c968949/, last access: 11 May 2020.
Zhang, G. and Song, X.: Digital soil mapping dataset of hydrological parameters in the Heihe River Basin (2012), available at: http://data.tpdc.ac.cn/zh-hans/data/e977f5e8-972b-42a5-bffe-cd0195f3b42b/, last access: 11 May 2020a.
Zhang, G. and Song, X.: Digital soil mapping dataset of soil depth in the Heihe River Basin (2012–2014), available at: http://data.tpdc.ac.cn/zh-hans/data/fc84083e-8c66-4a42-b729-4f19334d0d67/, last access: 11 May 2020b.
Zhang, S., Shen, C., Chen, X., Ye, H., Huang, Y., and Lai, S.: Spatial
interpolation of soil texture using compositional kriging and regression
kriging with consideration of the characteristics of compositional data and
environment variables, J. Integr. Agr., 12, 1673–1683,
https://doi.org/10.1016/s2095-3119(13)60395-0, 2013.
Zhang, X., Liu, H., Zhang, X., Yu, S., Dou, X., Xie, Y., and Wang, N.:
Allocate soil individuals to soil classes with topsoil spectral
characteristics and decision trees, Geoderma, 320, 12–22,
https://doi.org/10.1016/j.geoderma.2018.01.023, 2018.
Zhao, C. and Ma, W.: Soil physical properties-soil bulk density and mechanical composition dataset of Tianlaochi Watershed in Qilian Mountains, available at: http://data.tpdc.ac.cn/zh-hans/data/b8bfbb8b-97e4-4622-acbd-06b5ac466403/, last access: 12 May 2020.
Short summary
We systematically compared 45 models for direct and indirect soil texture classification and soil particle size fraction interpolation based on 5 machine-learning models and 3 log-ratio transformation methods. Random forest showed powerful performance in both classification of imbalanced data and regression assessment. Extreme gradient boosting is more meaningful and computationally efficient when dealing with large data sets. The indirect classification and log-ratio methods are recommended.
We systematically compared 45 models for direct and indirect soil texture classification and...
