Article
Environmental Sciences
Ruhollah Taghizadeh-Mehrjardi, Hassan Fathizad, Mohammad Ali Hakimzadeh Ardakani, Hamid Sodaiezadeh, Ruth Kerry, Brandon Heung, Thomas Scholten
Summary: This study aimed to predict the spatial distribution of absorbable heavy metals in arid regions of Iran from 1986 to 2016 using a random forest model, with successful predictions for Fe, Mn, Ni, Pb, and Zn. Results showed significant increases in heavy metal distribution over time, providing valuable insights for developing appropriate management strategies.
Article
Environmental Sciences
Shoaib Ali, Dong Liu, Qiang Fu, Muhammad Jehanzeb Masud Cheema, Quoc Bao Pham, Md Mafuzur Rahaman, Thanh Duc Dang, Duong Tran Anh
Summary: This study developed a machine-learning-based model to downscale GRACE data from coarse resolution to higher resolution, creating spatial maps of water storage over the Indus basin irrigation system. The random forest model outperformed the artificial neural network model and showed strong correlation with training dataset from 2003 to 2016. The downscaled groundwater storage data indicated a loss in water storage at a rate of -0.68 km(3)/year from 2003 to 2016, with validation results showing good correlation with observational wells data at seasonal and annual scales.
Article
Biodiversity Conservation
M. A. Gonzalez-Rodriguez, U. Dieguez-Aranda
Summary: This study proposed a method for delimiting the uncertainty of climate-sensitive extrapolations of forest productivity, using Support Vector Regression to predict forest productivity in Galicia. The analysis revealed that extrapolations for unseen climatic conditions were extremely regularised, leading to narrow validity areas for the model.
ECOLOGICAL INDICATORS
(2021)
Article
Engineering, Geological
Chao Shi, Yu Wang
Summary: Rapid land reclamation is an attractive method for expanding congested coastal megacities. However, such projects often face delays and budget overruns due to unforeseen ground conditions. This study combines a unified framework with machine learning, finite element method, and Monte Carlo simulation to accurately analyze the spatio-temporal consolidation of reclaimed lands, taking into account the subsurface stratigraphy and spatial variability of soil parameters. The proposed method is applied to a real reclamation project in Hong Kong, demonstrating its ability to accurately characterize subsurface geological cross-sections and soil permeability with quantified uncertainty.
Article
Geosciences, Multidisciplinary
Zipeng Zhang, Jianli Ding, Chuanmei Zhu, Jinjie Wang, Xiang Li, Xiangyu Ge, Lijing Han, Xiangyue Chen, Jingzhe Wang
Summary: This study proposed a modeling framework for combining spatiotemporal prediction models to investigate the characteristics and climate drivers of soil organic carbon (SOC) variability in China from the 1980s to 2010s. The results showed that SOC prediction accuracy was higher in the top 0-20 cm of soil compared to the first meter of soil, and the predicted spatial patterns were consistent with previous studies. Climate factors had scale- and location-specific effects on SOC, and coupled climatic factors accounted for the majority of SOC variability.
Article
Environmental Sciences
Elisa Vega-Martinez, Juan Ramon Molina, Vidal Barron, Francisco Rodriguez ySilva, Maria del Carmen del Campillo, Antonio Rafael Sanchez-Rodriguez
Summary: In recent years, controlled burns have become more frequent in Europe as a means of managing forest ecosystems. This study evaluated the main alterations in soil properties caused by a high intensity-controlled burn in Los Boquerones area in Spain. The results showed that the burn significantly affected soil pH, nutrient availability, and soil microorganisms.
SCIENCE OF THE TOTAL ENVIRONMENT
(2023)
Article
Environmental Studies
Mohammed B. B. Altoom, Elhadi Adam, Khalid Adem Ali
Summary: This study used multitemporal Landsat observation data to investigate the spatio-temporal dynamics of rainfed agriculture in North Darfur State from 1984-2019. The results showed that there was high spatial variability in rainfed agriculture during this period, which may exacerbate regional land degradation and disputes among farmers over scarce wadi lands.
Article
Environmental Sciences
Adeniyi Adeyemi, Abel Ramoelo, Moses Azong Cho, Jacobus Strydom
Summary: This study assessed the impact of rapid urban growth on natural lands and the expansion of impervious surface area in 1995, 2005, and 2015. The findings showed that most areas in Pretoria experienced ISA expansion, and the results from Landsat TIRS bands calculations were also accurate.
GEOCARTO INTERNATIONAL
(2022)
Article
Environmental Sciences
J. A. Mukarugwiro, S. W. Newete, E. Adam, F. Nsanganwimana, K. Abutaleb, M. J. Byrne
Summary: This study used remote sensing technology to investigate the spread of water hyacinth in Rwandan water bodies, revealing fluctuations in invasion rates from 1989 to 2017 with a decline observed from 2002 to 2017, possibly due to manual control efforts by the government since 2002.
INTERNATIONAL JOURNAL OF ENVIRONMENTAL SCIENCE AND TECHNOLOGY
(2021)
Article
Biodiversity Conservation
Yunfei Cao, Li Hua, Qi Tang, Lin Liu, Chongfa Cai
Summary: Soil water erosion has caused significant damage to agriculture and ecosystems globally. This study calculated the average monthly-scale soil erosion modulus from 2001 to 2019 in Northeast China using the revised universal soil loss equation (RUSLE) to evaluate soil erosion risk. The results showed a yearly average soil erosion modulus of 8.53 t center dot ha(- 1)center dot year(- 1) and a monthly average of 0.78 t center dot ha(-1)center dot month(-1). The months of April-July and October were identified as critical periods for erosion, with high erosion concentrated in southern Liaoning province and western Inner Mongolia. The topographic factor LS, rainfall erosivity (R), and cover management (C) were identified as important drivers of soil erosion.
ECOLOGICAL INDICATORS
(2023)
Review
Engineering, Environmental
V. F. Sehaber, W. H. Bonat, P. J. Diggle, P. J. Ribeiro
Summary: The study focuses on a Gaussian conditional geostatistical spatio-temporal model (CGSTM) that fits data observed at non-fixed locations over discrete times. The model has attractive features such as dynamic linear modeling, forecasting maps, and interaction between space and time. Simulation and application to real datasets verified the robustness and unbiasedness of the model, also demonstrating its capability in providing future rainfall forecasting maps.
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
(2021)
Article
Computer Science, Interdisciplinary Applications
Yuna Kim, Abolfazl Safikhani, Emre Tepe
Summary: Understanding the dynamics of urban growth is crucial in urban planning, and accurate prediction of urban growth is important for regional policy makers. Machine learning methods, especially the random forest algorithm, show better performance in predicting urban growth at regional levels.
COMPUTERS ENVIRONMENT AND URBAN SYSTEMS
(2022)
Article
Environmental Sciences
Joy Rajbanshi, Sharmistha Das
Summary: Desertification in India has spread from the west to the south, causing severe degradation in states like Rajasthan and Ladakh. The random forest model identifies drought resistance and erosion protection as the most important drivers of this phenomenon. Without immediate action, irreversible losses may occur on 33.76% of the country's land.
LAND DEGRADATION & DEVELOPMENT
(2021)
Article
Environmental Sciences
Jordan Brizi Neris, Diango M. Montalvan Olivares, Caroline Santos Santana, PraiseGod Chidozie Emenike, Fermin G. Velasco, Sergio Fred Ribeiro Andrade, Caio Marcio Paranhos
Summary: Risk assessment is important for managing polluted areas, with the HERisk code allowing for spatiotemporal assessments of ecological, radiological, and human health risks. Analysis of potentially toxic elements in soils and surface waters from a mining area in Brazil showed nonhomogeneous distribution of metals due to human activities.
SCIENCE OF THE TOTAL ENVIRONMENT
(2021)
Article
Environmental Sciences
Bifeng Hu, Modian Xie, Hongyi Li, Rebin He, Yue Zhou, Yefeng Jiang, Wenjun Ji, Jie Peng, Fang Xia, Zongzheng Liang, Wanming Deng, Junjie Wang, Zhou Shi
Summary: The study investigates the spatio-temporal variation of soil nutrients and soil organic matter (SOM) in farmland over Jiangxi Province in Southern China. Based on a dataset of soil samples collected between 2005 and 2012, the study examines the changes in SOM, available nitrogen (N), phosphorus (P), potassium (K), pH, and cation exchange capacity. The results indicate significant temporal trends in the concentrations of SOM, available P, available N, and available K, with climate and soil management practices playing a dominant role in determining soil fertility.
JOURNAL OF SOILS AND SEDIMENTS
(2023)
Article
Soil Science
Cynthia C. E. van Leeuwen, Vera L. Mulder, Niels H. Batjes, Gerard B. M. Heuvelink
Summary: There is a growing demand for high-quality soil data, with this study quantifying uncertainties in wet chemistry soil data using a linear mixed-effects model. Experimental measurement design and replicate measurements were found to be crucial for accurate uncertainty quantification in soil data.
EUROPEAN JOURNAL OF SOIL SCIENCE
(2022)
Article
Soil Science
Luc Steinbuch, Dick J. Brus, Gerard B. M. Heuvelink
Summary: This study aimed to evaluate if extending a Bayesian Generalized Linear Model (BGLM) to a Bayesian Generalized Linear Geostatistical Model (BGLGM) is worth it for mapping binary soil properties. The results showed that BGLGM performs considerably better than BGLM in terms of statistical validation metrics when a large observation sample and few relevant covariates are available, although it is more demanding in terms of calibration and application.
EUROPEAN JOURNAL OF SOIL SCIENCE
(2022)
Article
Geography
Mihaly Kocsis, Gabor Szatmari, Piroska Kassai, Gabor Kovacs, Janos Toth, Tamas Kramer, Peter Torma, Krisztian Homorodi, Piroska Pomogyi, Peter Szeglet, Kalman Csermak, Andras Mako
Summary: Lake Balaton has experienced rapid eutrophication, leading to deteriorating water quality. Despite successful improvements, algal blooms have reemerged in recent years. This study used a reanalysis method to explore the nutrient content of lake sediment. The results suggest that analyzing soluble phosphorus is crucial for water quality management planning.
Article
Environmental Sciences
Eszter Tanacs, Marta Belenyesi, Robert Lehoczki, Robert Pataki, Otto Petrik, Tibor Standovar, Laszlo Pasztor, Annamaria Laborczi, Gabor Szatmari, Zsolt Molnar, Akos Bede-Fazekas, Imelda Somodi, Daniel Kristof, Aniko Kovacs-Hostyanszki, Katalin Torok, Livia Kisne Fodor, Zita Zsembery, Zoltan Friedl, Gergely Maucha
Summary: High-resolution ecosystem maps can improve policy implementation efficiency, but challenges related to data and methods make such maps scarce for nationwide analyses. The new Ecosystem Map of Hungary offers solutions to typical challenges of national-scale ecosystem mapping, providing a detailed map with a hierarchical typology.
GEOCARTO INTERNATIONAL
(2022)
Article
Environmental Sciences
Gabor Szatmari, Mihaly Kocsis, Andras Mako, Laszlo Pasztor, Zsofia Bakacsi
Summary: Eutrophication, water quality, and environmental status of lakes are global issues affected by both external and internal loadings. Applying multivariate geostatistics in water ecosystems can provide coherent and accurate spatial models, taking into account the interdependence among variables and generating predictions at different scales.
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
Soil Science
Bertin Takoutsing, Gerard B. M. Heuvelink, Jetse J. Stoorvogel, Keith D. Shepherd, Ermias Aynekulu
Summary: Digital soil mapping (DSM) approaches provide soil information by utilizing the relationship between soil properties and environmental variables. This study incorporates measurement error variances in the geostatistical models of soil properties, weights measurements according to their accuracy, and assesses the effects of measurement errors on DSM outputs. The results show that considering measurement errors in the models allows for more accurate quantification of prediction uncertainty. This approach is important for improving soil property estimation and uncertainty quantification in DSM.
EUROPEAN JOURNAL OF SOIL SCIENCE
(2022)
Article
Environmental Sciences
Csongor Gedeon, Matyas Arvai, Gabor Szatmari, Eric C. Brevik, Tunde Takats, Zsofia A. Kovacs, Janos Meszaros
Summary: This study introduces an imagery-based method to semi-automatically identify and count animal burrows by combining remotely recorded RGB images and RF classification. By collecting and processing field images, accurate estimation of population abundance and delineation of occupancy areas can be achieved.
Article
Environmental Sciences
Maria Eliza Turek, Laura Poggio, Niels H. Batjes, Robson Andre Armindo, Quirijn de Jong van Lier, Luis de Sousa, Gerard B. M. Heuvelink
Summary: The development of point-based global maps of soil water retention improves the availability and quality of soil data, compared to traditional map-based approaches. By combining measured and predicted data with environmental variables, this study demonstrates the superior performance of the point-based mapping approach.
INTERNATIONAL SOIL AND WATER CONSERVATION RESEARCH
(2023)
Article
Soil Science
M. E. Angelini, G. B. M. Heuvelink, P. Lagacherie
Summary: This study aimed to help urban planners preserve soils of the highest quality by mapping a soil potential multifunctionality index. However, the prediction accuracy was poor and further improvements are needed.
EUROPEAN JOURNAL OF SOIL SCIENCE
(2023)
Article
Soil Science
Stephan van der Westhuizen, Gerard B. M. Heuvelink, David P. Hofmeyr
Summary: In digital soil mapping, traditional univariate methods neglect the dependence structure between soil properties, while multivariate machine learning models can capture complex non-linear relationships and maintain the dependence structure. This study compares the performance of a multivariate random forest model with two separate univariate random forest models, and finds that the multivariate model outperforms in maintaining the dependence structure and producing more realistic results.
Article
Ecology
Alexandre M. J. -C. Wadoux, Gerard B. M. Heuvelink
Summary: Global, continental and regional maps of natural resources are important for assessing ecosystem response to human disturbance and global warming. However, these maps suffer from multiple error sources, and it is important to report the associated uncertainties for users to evaluate their reliability.
METHODS IN ECOLOGY AND EVOLUTION
(2023)
Article
Environmental Sciences
Nandor Csikos, Brigitta Szabo, Tamas Hermann, Annamaria Laborczi, Judit Matus, Laszlo Pasztor, Gabor Szatmari, Katalin Takacs, Gergely Toth
Summary: A methodology is presented for the quantitative assessment of soil biomass productivity at a national scale. The traditional land evaluation approach was followed, using satellite images, measured yield and net primary productivity data, as well as digital soil and climate maps. The study provides measured soil health and quality indicators for designing sustainable land management practices, and the results can be implemented in cadastral systems and agricultural development programs.
Article
Plant Sciences
Georgina Veronika Visztra, Kata Frei, Alida Anna Habenczyus, Anna Sooky, Zoltan Batori, Annamaria Laborczi, Nandor Csikos, Gabor Szatmari, Peter Szilassi
Summary: Invasive tree species pose a significant threat to native flora by modifying the environment and inhibiting the growth of native species. Preventing the spread of invasive plants is the most effective control method, requiring identification of the environmental factors that promote their occurrence. This study compared the efficiency and reliability of point-based and polygon-based databases in investigating the occurrence of three invasive tree species and their relationships with soil, hydrological, and climatic factors.
Article
Environmental Studies
Laszlo Pasztor, Katalin Takacs, Janos Meszaros, Gabor Szatmari, Matyas Arvai, Tibor Toth, Gyoengyi Barna, Sandor Koos, Zsofia Adrienn Kovacs, Peter Laszlo, Kitti Balog
Summary: This study indirectly estimated soil parameters of salt meadows within National Parks using spectral indices and UAV survey data. A vegetation map and soil property distribution map were created, providing a model-based estimation of soil conditions for different habitat types without disturbing protected areas. This research is important for the management and conservation of salt meadows within protected areas.