Article
Computer Science, Interdisciplinary Applications
D. R. Newman, D. D. Saurette, J. M. H. Cockburn, Lucian Dragut, J. B. Lindsay
Summary: Topographic data are becoming increasingly important for environmental models, especially with the availability of high-resolution and wide coverage datasets. The scale at which topographic parameters are represented spatially varies, and this research compared different scaling strategies for predictive soil model performance. The results showed that multiscale feature sets performed better than unscaled data, and there was not a substantial difference between heterogeneous and homogeneous feature sets in terms of accuracy and uncertainty. However, one scaling strategy consistently outperformed others in terms of accuracy and ranked among the least uncertain and error-prone methods.
ENVIRONMENTAL MODELLING & SOFTWARE
(2023)
Article
Multidisciplinary Sciences
Maximilian Noelscher, Michael Mutz, Stefan Broda
Summary: The presented dataset EU-MOHP v013.1.1 provides multiscale information on the hydrologic position (MOHP) of a geographic point within its respective river network and catchment as gridded maps. It serves as a valuable static environmental descriptor or predictor variable for hydrogeological and hydrological modeling tasks. The dataset can be transferred to other regions or input datasets due to its generation using free open source software.
Editorial Material
Multidisciplinary Sciences
Chen Li, Feifei Qian
Summary: A four-legged robot has achieved a faster running speed on sand than humans can jog on solid ground. This rapid robot demonstrates the importance of combining data-driven learning with accurate and simple models, as it shows low energy consumption and few failures.
Article
Geosciences, Multidisciplinary
Aaron E. Maxwell, Charles M. Shobe
Summary: This review focuses on the use of land-surface parameters derived from digital land surface models (DLSMs) in mapping and modeling tasks. It discusses the challenges in selecting and optimizing the feature space, highlights best practices and future research needs, and explores recent developments that may simplify feature space engineering in predictive modeling tasks.
EARTH-SCIENCE REVIEWS
(2022)
Article
Environmental Sciences
Nigel Van Nieuwenhuizen, John B. Lindsay, Ben DeVries
Summary: Fine-resolution LiDAR DEMs can accurately represent surface features such as road and railway embankments. A novel algorithm was proposed to identify embankments in LiDAR DEMs, achieving moderate to high accuracy. The technique showed good performance on test DEMs from southwest Ontario, Canada, with acceptable processing times for practical applications.
Article
Geography, Physical
Lars O. Hansen, Verner B. Ernstsen, Lars B. Clemmensen, Zyad Al-Hamdani, Aart Kroon
Summary: This study presents a method to quantify washover fan volumes and estimate sediment exchanges using high resolution digital terrain models and geomorphometric analysis. The results show that this approach provides estimates of washover deposit volumes with an accuracy between 1% and 28% compared to control volumes.
EARTH SURFACE PROCESSES AND LANDFORMS
(2021)
Article
Geosciences, Multidisciplinary
Gerard B. M. Heuvelink, Richard Webster
Summary: Pedologists traditionally mapped soil by drawing boundaries, but the introduction of geostatistics and ordinary kriging in the 1980s revolutionized soil mapping. Machine learning techniques have also been adopted, but they lack transparency and spatial correlation considerations. Spatial statisticians and pedometricians have important roles in incorporating uncertainty and communicating it to end users.
SPATIAL STATISTICS
(2022)
Article
Geosciences, Multidisciplinary
Khadijeh Taghipour, Mehdi Heydari, Yahya Kooch, Hassan Fathizad, Brandon Heung, Ruhollah Taghizadeh-Mehrjardi
Summary: Soil quality, one of the most important characteristics of soil, is crucial for sustainable soil management and evaluating soil degradation. This study aims to assess the impacts of deforestation on soil quality in Iran using a digital soil mapping approach. The results show that the soil quality in the protected forested area is significantly higher than the degraded/deforested area. Machine learning techniques, particularly the Random Forest model, outperform geostatistical approaches in mapping soil quality. This study provides a framework for assessing the impacts of deforestation on soil patterns, which can inform land use planning and forest resource management strategies.
Article
Environmental Sciences
Sam Anderson, Valentina Radic
Summary: Heatwaves not only have wide-ranging impacts on various aspects, including human health and agriculture, but also control streamflow through the melting of snow and glacier ice. This study uses a deep learning hydrological model to simulate the streamflow response to heatwaves in southwestern Canada and finds that glaciers can buffer the impacts of heatwaves on streamflow.
WATER RESOURCES RESEARCH
(2023)
Article
Geosciences, Multidisciplinary
Junko Iwahashi, Dai Yamazaki
Summary: This article presents a method for terrain classification using high-resolution digital elevation models, addressing the limitations of previous studies in accurately classifying small landforms. The dataset improves upon previous global terrain classification data and can be used in various applications related to topography.
PROGRESS IN EARTH AND PLANETARY SCIENCE
(2022)
Review
Engineering, Environmental
Prince Chapman Agyeman, Samuel Kudjo Ahado, Lubos Boruvka, James Kobina Mensah Biney, Vincent Yaw Oppong Sarkodie, Ndiye M. Kebonye, John Kingsley
Summary: This paper reviews articles from 2001 to the first quarter of 2019 on spatial prediction of potentially toxic elements in soil, indicating diverse sources of soil pollution and the preference for geostatistical models over machine learning algorithms.
ENVIRONMENTAL GEOCHEMISTRY AND HEALTH
(2021)
Article
Soil Science
Fa Wang, Jun Zhang, Jinjiao Lian, Zhiyong Fu, Zidong Luo, Yunpeng Nie, Hongsong Chen
Summary: This study investigated the spatial variability of epikarst thickness in Huanjiang, Guangxi, China. The results showed that epikarst thickness was thicker in depression areas compared to hill slopes, and soil properties were found to be a better predictor for epikarst thickness than terrain-vegetation variables.
Article
Green & Sustainable Science & Technology
Shaniel Chotkan, Raymond van der Meij, Wouter Jan Klerk, Phil J. Vardon, Juan Pablo Aguilar-Lopez
Summary: This study aims to identify factors affecting susceptibility to drought-induced cracking in levees and uses them to build a machine learning model. Key relationships between crack size and moisture content were observed, showing low moisture content as an important driver in cracking. Various factors including precipitation, evapotranspiration, soil type, and soil stiffness were proposed to affect cracking susceptibility, with cumulative precipitation deficit being most associated with crack occurrence. Model tree algorithms were used to predict cracking likelihood, with factors like peat thickness, soil stiffness and levee orientation deemed important for determining crack-proneness.
Article
Environmental Sciences
Rodrigo Cesar Vasconcelos dos Santos, Mauricio Fornalski Soares, Luis Carlos Timm, Tirzah Moreira Siqueira, Carlos Rogerio Mello, Samuel Beskow, Douglas Rodrigo Kaiser
Summary: This study utilized sequential Gaussian simulation to simulate the spatial variability of saturated soil hydraulic conductivity (K-sat) in a subtropical watershed in Southern Brazil. The results showed that lower K-sat uncertainty estimates were found in densely sampled areas, while higher uncertainty estimates were obtained in soils located at steeper areas of the watershed and alongside the main watercourse.
ENVIRONMENTAL EARTH SCIENCES
(2021)
Article
Water Resources
Sandra M. Hauswirth, Marc F. P. Bierkens, Vincent Beijk, Niko Wanders
Summary: The study demonstrates that incorporating machine learning in hydrology can support national water management by providing necessary information efficiently, with advanced Random Forest and LSTM methods showing the best performance in simulating hydrological variables at a national scale.
ADVANCES IN WATER RESOURCES
(2021)
Article
Agriculture, Multidisciplinary
Gerard Francois Hermanus van Ginkel Bekker, Matthew Addison, Pia Addison, Adriaan van Niekerk
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2019)
Article
Environmental Sciences
Tsitsi Bangira, Silvia Maria Alfieri, Massimo Menenti, Adriaan van Niekerk
Article
Agriculture, Multidisciplinary
Barry Watkins, Adriaan Van Niekerk
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2019)
Article
Agriculture, Multidisciplinary
Mmamokoma Grace Maponya, Adriaan van Niekerk, Zama Eric Mashimbye
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2020)
Article
Agriculture, Multidisciplinary
S. J. Muller, P. Sithole, A. Singels, A. Van Niekerk
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2020)
Article
Remote Sensing
Paul Macintyre, Adriaan van Niekerk, Ladislav Mucina
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2020)
Article
Plant Sciences
Ladislav Mucina, Mervyn C. Lotter, Michael C. Rutherford, Adriaan van Niekerk, Paul D. Macintyre, James L. Tsakalos, Jonathan Timberlake, Janine B. Adams, Taryn Riddin, Lauren K. Mccarthy
Summary: This study mapped and classified the forests of Southern Africa and neighboring countries according to the global system of biomes, introducing a new four-tier hierarchical biome system. The system includes zonobiome, global biome, continental biome, and regional biome categories, improving the precision of forest mapping. The research reveals unique three zonal forest types in Southern Africa and introduces novel concepts like Zonobiome I and Tropical Dry Forests, expanding knowledge of the biome structure in African biotic communities.
NEW ZEALAND JOURNAL OF BOTANY
(2022)
Article
Environmental Sciences
Peter L. Guth, Adriaan Van Niekerk, Carlos H. Grohmann, Jan-Peter Muller, Laurence Hawker, Igor V. Florinsky, Dean Gesch, Hannes I. Reuter, Virginia Herrera-Cruz, Serge Riazanoff, Carlos Lopez-Vazquez, Claudia C. Carabajal, Clement Albinet, Peter Strobl
Summary: Digital elevation models (DEMs) provide fundamental depictions of the Earth’s shape and are influenced by various spheres including the hydrosphere, cryosphere, biosphere, and anthroposphere. The treatment of DEM surfaces depends on their intended use and sensor characteristics. Different types of DEMs have varying vertical datums and data spacings, highlighting the importance of understanding and reflecting on their characteristics for users.
Article
Environmental Sciences
Christiaan J. Harmse, Hannes Gerber, Adriaan van Niekerk
Summary: This study utilized livestock tracking, in situ observations, and remote sensing data analysis to investigate vegetation conditions and sheep movement patterns in a semi-arid environment. The results indicated that sheep exhibit selective grazing behavior under low stocking rates, leading to localized overgrazing. Additionally, high-resolution remote sensing data can provide a landscape-scale overview of livestock movement patterns.
Article
Environmental Sciences
Caley Higgs, Adriaan van Niekerk
Summary: This study evaluated different sampling strategies for training a machine learning classifier to differentiate between Acacia, Eucalyptus, and Pinus trees in South Africa. The results showed that using an even sample with the maximum size resulted in the highest overall accuracy.
Article
Remote Sensing
Adriaan Jacobus Prins, Adriaan Van Niekerk
Summary: LiDAR data is increasingly available and plays a crucial role in precision agriculture. By combining LiDAR, Sentinel-2, and aerial imagery data with machine learning algorithms, different crop types can be effectively differentiated, providing a foundation for operational crop type mapping.
GEO-SPATIAL INFORMATION SCIENCE
(2021)
Article
Geography
Adriaan Jacobus Prins, Adriaan Van Niekerk
INTERNATIONAL JOURNAL OF APPLIED GEOSPATIAL RESEARCH
(2020)
Article
Geography
A. Van Niekerk, Z. Munch
SOUTH AFRICAN GEOGRAPHICAL JOURNAL
(2020)
Article
Geography
Andre Breytenbach, Adriaan Van Niekerk
SOUTH AFRICAN GEOGRAPHICAL JOURNAL
(2020)
Article
Water Resources
Zama Eric Mashimbye, Willem Petrus De Clercq, Adriaan Van Niekerk