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
Environmental Sciences
Xianglin Zhang, Jie Xue, Songchao Chen, Nan Wang, Tieli Xie, Yi Xiao, Xueyao Chen, Zhou Shi, Yuanfang Huang, Zhiqing Zhuo
Summary: This study used Quantile Regression Forest to map the spatial distribution of soil organic carbon in cropland in the Northeast China Plain. The results showed that SOC increased overall from the southern area to the northern area, and decreased with depth. Climate, position, and organism were identified as the dominant controlling factors. Additionally, higher uncertainty was observed in certain areas.
Article
Geosciences, Multidisciplinary
Sanaz Zare, Ali Abtahi, Seyed Rashid Fallah Shamsi, Philippe Lagacherie
Summary: This study fills the gap in comparing and developing methods for integrating new sources of soil data for DSM by mapping electrical conductivities using real measurements and EM38MK2 measurements. The results show the utility of EM38MK2 data as surrogate input data for mapping soil salinity, with regression co-kriging identified as the best integration method. The impact of EM38MK2 data on performance gains increases as the sizes of real soil salinity measurements decrease, indicating a promising way to tackle constraints of DSM in areas where soil sensing as alternative data is accessible.
Article
Soil Science
Nagarjuna N. Reddy, Bhabani S. Das
Summary: Water and nutrient holding capacities in soils are primarily controlled by secondary soil parameters. Pedotransfer functions are commonly used to derive these parameters in soil databases. This study used PTFs and laboratory-measured data to map these parameters in the Indian soil legacy database, and found that terrain attributes have a stronger influence on their distribution than climatic parameters. The study also highlighted the importance of monsoon rain and temperature in driving water relationships in Indian soils.
Article
Soil Science
Yixuan Zhou, Zhuodong Zhang, Jingwen Rao, Bo Chen
Summary: This study explored the spatial pattern of soil magnetic susceptibility in an agro-pastoral transitional zone of north China and revealed influencing factors, such as parent material, topography, and vegetation. The results showed substantial spatial variation of magnetic susceptibility in the area, with water erosion and wind being significant factors affecting the distribution.
SOIL & TILLAGE RESEARCH
(2022)
Article
Geosciences, Multidisciplinary
Manuel E. Camacho, Rafael Mata, Manuel Barrantes-Viquez, Alfredo Alvarado
Summary: This study confirmed the occurrence of Oxisols in Costa Rica and classified eight pedons into diverse taxonomic groups based on geological materials, geomorphology, and climatic conditions. The diversity observed in the studied areas enhanced knowledge in soil genesis and forming factors of advanced weathering stage soils in Central America.
Article
Soil Science
Jonas Schmidinger, Gerard B. M. Heuvelink
Summary: In digital soil mapping, probabilistic predictions are commonly used but their validation is often overlooked. By adopting metrics from the broader probabilistic literature, the reliability and sharpness of these predictions can be evaluated. In a case study, the probabilistic predictions of five different models were compared, with QRF and QRPP RF performing the best and NM performing the worst.
Article
Environmental Sciences
Santanu Mallik, Tridip Bhowmik, Umesh Mishra, Niladri Paul
Summary: This study successfully predicted soil organic carbon using remote sensing and terrain derivatives, with the advanced geostatistical method outperforming other techniques. The results can aid policymakers in adopting sustainable land use management.
GEOCARTO INTERNATIONAL
(2022)
Article
Soil Science
Rafael G. Siqueira, Cassio M. Moquedace, Marcio R. Francelino, Carlos E. G. R. Schaefer, Elpidio I. Fernandes-Filho
Summary: Soil texture is a crucial soil property in Antarctica, as it influences various ecological processes and is affected by climate changes and human disturbances. This study aimed to predict the distribution of sand, silt, and clay in the main ice-free areas of Maritime Antarctica and Northern Antarctic Peninsula. Machine learning models, particularly Random Forest, were used to analyze legacy soil texture data and generate soil texture maps. The accuracy of clay prediction was the highest, especially in the topsoil. The final maps showed good spatial consistency, reflecting factors such as geomorphology, parent material, and pedogenetic development. These findings contribute to decision-making regarding Antarctic soils and provide valuable data for global environmental models.
Article
Soil Science
A. J. Gibson, G. R. Hancock, D. Bretreger, T. Cox, J. Hughes, V Kunkel
Summary: This study examined the impact of DEM resolution on the relationship between topography and SOC, finding that SOC could be predicted using topography in a catchment-wide dataset but not in a finer-scale dataset. Elevation was identified as the main driver at the catchment scale, while topographic variables linked to soil redistribution were more important at finer scales. This suggests that SOC estimation methods using coarse resolution DEM data may have limitations in capturing the effect of topography, which could impact SOC management and modeling.
Article
Environmental Sciences
Shuai Wang, Mingyi Zhou, Qianlai Zhuang, Liping Guo
Summary: The study used remote sensing data to predict the soil organic carbon (SOC) density in coastal wetland ecosystems in Northeast China. The full variable model outperformed the other two models, with the addition of remote sensing-related variables significantly improving the predictive performance. SAVI, NDVI, and DVI were identified as the main environmental factors influencing the spatial variation of topsoil SOC density in flat terrain coastal wetlands.
Article
Soil Science
Mercedes Roman Dobarco, Alex McBratney, Budiman Minasny, Brendan Malone
Summary: Soil entities are typically defined based on soil properties and can be characterized by groupings of homogeneous soil-forming factors to create unique soil entities with similar properties. This study successfully developed a methodology for mapping pedogenon classes during the European settlement in New South Wales, providing important information for local and regional management.
Article
Chemistry, Analytical
Changda Zhu, Yuchen Wei, Fubin Zhu, Wenhao Lu, Zihan Fang, Zhaofu Li, Jianjun Pan
Summary: This study utilized the regression kriging model to predict soil organic carbon (SOC) content in a hilly farming area with continuous undulating terrain. The results show that among the ensemble models, Cubist performed best in terms of prediction accuracy and stability. The regression kriging model, which combines the advantages of machine learning and kriging methods, effectively improved the prediction accuracy. This study is of great significance for soil survey and digital mapping in complex terrain areas.
Article
Environmental Studies
Ramalingam Kumaraperumal, Sellaperumal Pazhanivelan, Vellingiri Geethalakshmi, Moorthi Nivas Raj, Dhanaraju Muthumanickam, Ragunath Kaliaperumal, Vishnu Shankar, Athira Manikandan Nair, Manoj Kumar Yadav, Thamizh Vendan Tarun Kshatriya
Summary: This study compared six machine learning algorithms for predicting soil information in Indian landscapes. The results showed that tree-based ensemble random forest and rule-based tree models efficiently predicted soil properties, while the efficiency of other models can be improved. The comprehensive comparison of algorithms can support model selection and mapping, aiding farmers and policymakers in decision-making to enhance agricultural productivity and food security.
Article
Biodiversity Conservation
Qilin Zan, Xiaoming Lai, Qing Zhu, Liuyang Li, Kaihua Liao
Summary: In this study, the global pattern of soil nitrogen stable isotope (delta N-15) was mapped based on environmental variables using the random forest regression algorithm. The results showed that the control factors of soil delta N-15 varied among different climate zones, providing insights into the potential environmental regulations on terrestrial nitrogen cycle.
ECOLOGICAL INDICATORS
(2023)
Article
Horticulture
Thomas M. Kon, Melanie A. Schupp, Hans E. Winzeler, James R. Schupp
Article
Horticulture
Thomas M. Kon, Melanie A. Schupp, Hans E. Winzeler, James R. Schupp
Article
Statistics & Probability
Yunfan Li, Jyotishka Datta, Bruce A. Craig, Anindya Bhadra
Summary: Seemingly unrelated regression is a flexible framework for regressing multiple correlated responses on multiple predictors. The use of horseshoe priors on both the mean vector and the inverse covariance matrix addresses the challenges of inferring both parameters simultaneously in a Bayesian framework.
JOURNAL OF MULTIVARIATE ANALYSIS
(2021)
Article
Mathematical & Computational Biology
Ritwik Bhaduri, Ritoban Kundu, Soumik Purkayastha, Michael Kleinsasser, Lauren J. Beesley, Bhramar Mukherjee, Jyotishka Datta
Summary: The study suggests that considering false negative rates of diagnostic tests for severe acute respiratory coronavirus 2 and selection bias due to prioritized testing, and extending the widely used SEIR model can improve the accuracy of COVID-19 transmission dynamics modeling. Analyzing data from the first two waves of the pandemic in India, the study provides estimates of undetected infections and deaths, and demonstrates the impact of misclassification and selection on future infection prediction and R0 estimation.
STATISTICS IN MEDICINE
(2022)
Article
Environmental Studies
Hans Edwin Winzeler, Phillip R. Owens, Quentin D. Read, Zamir Libohova, Amanda Ashworth, Tom Sauer
Summary: This study assessed the effectiveness of Topographic Wetness Index (TWI) in representing soil moisture across different timescales and calculation methods. The results showed that TWI performance was influenced by seasonal variation of soil moisture and greatly improved when using DEM filtration and resampling.
Article
Computer Science, Information Systems
Alfieri Ek, Grant Drawve, Samantha Robinson, Jyotishka Datta
Summary: Law enforcement agencies are increasingly using spatial analysis to identify patterns of outcomes. However, there has been little progress in the statistical modeling of mental health events in Little Rock, Arkansas. In this article, insights into the spatial nature of mental health data from 2015 to 2018 in Little Rock, Arkansas are provided. Different models are used and their relative predictive performances are presented. The findings have the potential to assist law enforcement agencies and the city in resource allocation.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2023)
Article
Environmental Studies
Hans Edwin Winzeler, Phillip R. Owens, Tulsi Kharel, Amanda Ashworth, Zamir Libohova
Summary: The objective of this research was to develop and test a technique for identifying and classifying agricultural terraces using computer vision applied to terrain derivatives calculated from digital elevation models. A total of 38 terrain-derivative grid combinations were tested, and the best subsets achieved a 98% classification accuracy. Further study will investigate the relationship between terrace borrow and deposition areas, and their impact on yield and salinity issues.
Article
Microbiology
Emily H. Branstad-Spates, Lina Castano-Duque, Gretchen A. Mosher, Charles R. Hurburgh Jr, Phillip Owens, Edwin Winzeler, Kanniah Rajasekaran, Erin L. Bowers
Summary: A predictive model was developed using historical data from Iowa to forecast aflatoxin contamination in corn. The model showed high accuracy but low sensitivity in detecting high contamination events. Satellite-acquired vegetative index and soil-saturated hydraulic conductivity were identified as important factors for predicting corn contamination.
FRONTIERS IN MICROBIOLOGY
(2023)
Article
Biodiversity Conservation
John G. Jelesko, Kyla Thompson, Noah Magerkorth, Elizabeth Verteramo, Hannah Becker, Joy G. Flowers, Jonathan Sachs, Jyotishka Datta, Jordan Metzgar
Summary: Urushiol, produced by poison ivy, causes millions of cases of delayed contact allergenic dermatitis in North America annually. Avoiding poison ivy plant material is recommended to prevent symptoms. However, the variable leaf shape of poison ivy makes accurate identification difficult.
PLANTS PEOPLE PLANET
(2023)
Proceedings Paper
Agricultural Engineering
I. S. Minas, G. L. Reighard, B. Black, J. A. Cline, D. J. Chavez, E. Coneva, G. A. Lang, M. Parker, T. L. Robinson, J. Schupp, P. Francescato, J. Lordan, T. Beckman, W. W. Shane, J. R. Pieper, D. G. Sterle, C. Bakker, B. Clark, D. Ouellette, A. Swain, H. E. Winzeler
Summary: Eight vigor-limiting, standard, and vigorous Prunus rootstocks budded with 'Cresthaven' peach were planted at 10 locations in North America in spring 2017. During the first three years of establishment, significant differences among rootstocks and sites were found for survival, root suckers, tree growth, yield, fruit size, and yield efficiency.
XII INTERNATIONAL SYMPOSIUM ON INTEGRATING CANOPY, ROOTSTOCK AND ENVIRONMENTAL PHYSIOLOGY IN ORCHARD SYSTEMS
(2022)
Article
Criminology & Penology
Grant Drawve, Casey T. Harris, Shaun A. Thomas, Jyotishka Datta, Jack Cothren
Summary: This study focuses on criminal incidents reported to the National Incident Based Reporting System in Arkansas in 2016, aiming to showcase the benefits of collecting address-identified NIBRS data for Arkansas and other states. By comparing statewide NIBRS data with address-level data for a specific city, the study illustrates spatial variation in crime occurrence at different levels of analysis.
CRIME & DELINQUENCY
(2021)
Article
Statistics & Probability
Anindya Bhadra, Jyotishka Datta, Nicholas G. Polson, Brandon T. Willard
Summary: This paper introduces an alternative method for feature subset selection called the horseshoe regularization penalty, which shows superior theoretical and computational performance compared to existing methods. The distinguishing feature is the probabilistic representation of the penalty, enabling efficient optimization algorithms and uncertainty quantification.
SANKHYA-SERIES B-APPLIED AND INTERDISCIPLINARY STATISTICS
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Souradip Chakraborty, Ekansh Verma, Saswata Sahoo, Jyotishka Datta
20TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS (ICDMW 2020)
(2020)
Meeting Abstract
Horticulture
James Schupp, Melanie A. Schupp, H. Edwin Winzeler
Article
Statistics & Probability
Anindya Bhadra, Jyotishka Datta, Nicholas G. Poison, Brandon T. Willard
SANKHYA-SERIES A-MATHEMATICAL STATISTICS AND PROBABILITY
(2020)
Article
Geosciences, Multidisciplinary
Haihua Wang, Huaiyang Ke, Hongping Wu, Siyuan Ma, Muhammad Mohsin Altaf, Xiaoping Diao
Summary: Carbon storage in mangroves is crucial for mitigating climate change, but our understanding of this aspect is limited. This study investigated the seasonal changes in the carbon metabolic profile of microbial communities in mangrove soils on Hainan Island, China, and found that season plays a critical role in shaping the carbon functional diversity of microbial communities.
Article
Geosciences, Multidisciplinary
Donghui Zhao, Congcong Shen, Zhi-Ming Zhang, Jichen Wang, Li-Mei Zhang, Baodong Chen, Guo-Xin Sun, Yuan Ge
Summary: By studying soil samples from different slope directions along an elevational gradient in a mountain ecosystem, we found that soil bacterial diversity and microbial functions exhibit distinct elevational patterns, which are consistent across slope directions. The bacterial diversity shows a hump-shaped pattern, while microbial functions exhibit a linear increasing trend. Additionally, the beta diversity pattern of soil bacteria is significantly influenced by elevational distance decay relationships. Soil bacterial diversity patterns are determined by transitions in community assembly processes, whereas microbial functions are mainly influenced by bacterial community composition.
Article
Geosciences, Multidisciplinary
Guanfang Sun, Yan Zhu, Wei Mao, Yonghong Li, Jinzhong Yang, Zhaoliang Gao
Summary: This study developed a water and salt balance model to predict long-term water and salt dynamics in seasonally frozen arid agricultural regions. The model was validated in a region in China and showed that increasing autumn irrigation water can decrease soil salinity during the irrigation period, but has limited impact on long-term average soil salinity.
Article
Geosciences, Multidisciplinary
Alfredo Mayoral, Ana Ejarque, Arnau Garcia-Molsosa, Mercourios Georgiadis, Giannis Apostolou, Vincent Gaertner, Constantina Kallintzi, Eurydice Kefalidou, Hector Orengo
Summary: This paper presents an integrated Geoarchaeological approach to studying the landscape change and socio-environmental interaction around ancient Abdera. The study uses a combination of remote sensing, geomorphological mapping, sedimentary coring, and radiocarbon dating to reconstruct the palaeogeographic evolution of the area. The results challenge previous narratives about the rise and decline of Abdera and provide new insights into the role of historical and environmental factors. It also introduces evidence of submerged Neolithic landscapes and the impact of anthropogenic forcing on the sedimentary systems.
Article
Geosciences, Multidisciplinary
Jiale Chen, Michael Dannenmann, Qiang Yu, Yalong Shi, Matthew D. Wallenstein, Xinguo Han, Honghui Wu, Klaus Butterbach-Bahl
Summary: This study investigated the effects of temperature and moisture on soil nitrogen turnover through field experiments and laboratory incubation experiments. The results showed that soil temperature had a greater explanatory power than moisture in gross ammonification and nitrification rates. Climate warming may have a greater impact on gross nitrogen turnover compared to changes in rainfall.
Article
Geosciences, Multidisciplinary
Zhen Han, Xiuchao Yang, Xiaoai Yin, Qian Fang, Longshan Zhao
Summary: This study investigated the effects of exposed root distribution patterns on rainfall-runoff processes. The results showed that the distribution patterns of exposed root had a significant impact on rainfall-runoff processes. A vertical slope arrangement was conducive to rainfall infiltration, a parallel slope arrangement resulted in more surface runoff, and a transverse slope arrangement could reduce water loss.
Article
Geosciences, Multidisciplinary
Bo Zhao
Summary: Seismic earthflows, as special seismic landslides, have not received much attention in previous studies. This study analyzed the characteristics and movement of earthflows induced by recent earthquakes. The results showed that earthflows occur in high-rainfall areas and are sensitive to rainfall. Compared to other seismic landslides, seismic earthflows occur on gentler hills and have higher mobility.
Article
Geosciences, Multidisciplinary
Tingxi Liu, Xueqin Wang, Mingyang Li, Dongfang Li, Limin Duan, Xin Tong, Guanli Wang
Summary: Soil respiration plays a crucial role in the global carbon cycle in arid and semi-arid regions, and is regulated by hydrothermal factors. This study examined the seasonal and diurnal dynamics of soil respiration in two typical ecosystems in northern China, and investigated their responses to precipitation, temperature, and drought. The results showed that soil respiration varied seasonally and diurnally, and its response to environmental factors depended on the ecosystem type and soil moisture status. Incorporating multiple factors into carbon cycle models can improve the simulation and prediction of carbon emissions in arid and semi-arid regions.
Article
Geosciences, Multidisciplinary
Yaochen Xu, Ninghua Chen, Deguo Zhang, Bowen Gao, Xuhua Weng, Hongcheng Qiu
Summary: This study provides systematic investigation on how yardangs exert control over dune morphology, and reveals the intricate wind dynamics and mechanisms involved. Computational fluid dynamics modeling and remote sensing data further support the observations and shed light on the influences of yardangs on wind deposition and dune formation.
Article
Geosciences, Multidisciplinary
Yuri Lopes Zinn, Welton Pereira da Rocha Jr
Summary: This study assessed the evolution of Journal Impact Factors (JIF) and related data in the field of Soil Science over a 26-year period, and compared it with the field of Agronomy. The results showed a significant growth in JIFs and output in Soil Science, with commercial scientific publishers' journals experiencing higher growth rates than non-profit journals. The study also highlighted the importance of considering not only JIF, but also the bibliometric footprint, in determining the relevance and leadership of journals in the discipline.
Article
Geosciences, Multidisciplinary
Shanshan Liao, Xiaodong Nie, Aoqi Zeng, Wenfei Liao, Yi Liu, Zhongwu Li
Summary: Lake drawdown areas, where sediment is exposed due to water level fluctuations, have a significant impact on the carbon cycle. This study examined microbial necromass carbon (MNC) content and its contribution to soil organic carbon (SOC) in different habitats within the drawdown area of Dongting Lake. The results showed that MNC content varied among habitats and was primarily influenced by carbon and nitrogen availability, plant biomass, clay content, and soil moisture. External factors, such as plant and soil properties, played a more crucial role in the long-term accumulation of MNC. These findings enhance our understanding of MNC stability in drawdown areas.
Article
Geosciences, Multidisciplinary
Vanessa Alves Mantovani, Marcela de Castro Nunes Santos Terra, Andre Ferreira Rodrigues, Carlos Alberto Silva, Li Guo, Jose Marcio de Mello, Carlos Rogerio de Mello
Summary: There is a lack of research on the potential of tropical soils in the Brazilian Atlantic Forest biome to store carbon. This study aimed to determine the soil carbon stocks at different depths, describe their temporal variability, and identify the main drivers that influence their variations. The results showed significant spatial and seasonal variability in soil carbon stocks, with a high accumulation in December and a low accumulation in August. The study also found that litterfall, throughfall, tree sizes, and soil moisture were important factors affecting the distribution of soil carbon.
Article
Geosciences, Multidisciplinary
Anais Zimmer, Timothy Beach, Sheryl Luzzadder-Beach, Antoine Rabatel, Rolando Cruz Encarnacion, Joshua Lopez Robles, Edison Jara Tarazona, Arnaud J. A. M. Temme
Summary: Climate warming has accelerated glacial retreat and soil formation in mountainous regions. The accumulation of soil organic carbon and nitrogen is influenced by environmental factors, with maximum temperature and initial site conditions playing important roles in soil development.
Article
Geosciences, Multidisciplinary
Ren-Min Yang, Lai-Ming Huang, Feng Liu
Summary: This study investigated the soil organic carbon (SOC) stocks in seasonally frozen ground (SFG) in the Tibet Autonomous Region, China, in 2020 and 2021, and explored the effects of various factors on SOC using partial least squares structural equation modeling (PLS-SEM). The results showed that C inputs exerted the greatest control on SOC, and the influence of these factors decreased with increasing soil depth. Additionally, timely spatial SOC estimates were found to be important for assessing carbon stocks in the context of environmental changes.
Article
Geosciences, Multidisciplinary
Shue Wei, Kuandi Zhang, Chenglong Liu, Youdong Cen, Junqiang Xia
Summary: This study analyzed the effects of different vegetation components on erosion through simulated rainfall experiments and found that litter had the best effect in reducing erosion, followed by roots. The study also revealed that the reduction in runoff and sediment by the treatments decreased with increasing rainfall intensity.