Article
Energy & Fuels
Na Xu, Chuanpeng Xu, Robert B. Finkelman, Mark A. Engle, Qing Li, Mengmeng Peng, Lizhi He, Bin Huang, Yuchen Yang
Summary: The modes of occurrence of elements in coal are crucial for understanding coal formation and predicting impacts from coal utilization. Log-ratio transformations in hierarchical clustering algorithms are effective in inferring these modes of occurrence.
INTERNATIONAL JOURNAL OF COAL GEOLOGY
(2022)
Article
Mathematics, Applied
Salvador Linares-Mustaros, Maria Angels Farreras-Noguer, Nuria Arimany-Serrat, Germa Coenders
Summary: This article discusses a new methodology using Compositional Data (CoDa) to analyze financial statements. Compared to conventional ratio analysis, this method improves the analysis results and avoids statistical problems.
Article
Environmental Sciences
Chong Wang, Lin Zhao, Hongbing Fang, Lingxiao Wang, Zanpin Xing, Defu Zou, Guojie Hu, Xiaodong Wu, Yonghua Zhao, Yu Sheng, Qiangqiang Pang, Erji Du, Guangyue Liu, Hanbo Yun
Summary: This study successfully mapped the surficial soil PSF distribution in two typical permafrost regions in the Qinghai-Tibet Plateau using log-ratio transformation approaches, variable searching methods, and machine learning techniques. Variable selection techniques effectively reduced data redundancy and improved model performance, with isometric log-ratio random forest (ILR-RF) outperforming other models in both regions. The prediction in this study captured the spatial pattern of PSFs more accurately compared to three legacy datasets, showing potential for better understanding the interaction and processes between environmental predictors and soil PSFs in permafrost regions.
Article
Geosciences, Multidisciplinary
Lucia Clarotto, Denis Allard, Alessandra Menafoglio
Summary: This study proposes a novel class of alpha-transformations, named the Isometric alpha-transformation (alpha-IT), for analyzing and predicting georeferenced compositional data. Unlike traditional Isometric Log-Ratio (ILR) transformation, the proposed transformation accepts zero components. Maximum likelihood estimation of the parameter alpha is established. Prediction using kriging on alpha-IT transformed data is validated, and its performance is evaluated using various metrics.
SPATIAL STATISTICS
(2022)
Article
Statistics & Probability
Chuan Tian, Duo Jiang, Austin Hammer, Thomas Sharpton, Yuan Jiang
Summary: Understanding microbiota interactions is crucial for understanding their impact on the host or environment. We introduce a novel method called compositional graphical lasso that explicitly incorporates the unique characteristics of microbiome data and outperforms existing methods in accurately resolving microbial interactions.
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
(2023)
Article
Mathematical & Computational Biology
Haixiang Zhang, Jun Chen, Yang Feng, Chan Wang, Huilin Li, Lei Liu
Summary: The microbiome plays a crucial role in human health and requires special methods for analysis of high-dimensional data. This research proposes a procedure using log-ratio transformation to select significant mediator variables, and the effectiveness of the method is verified through simulations.
STATISTICS IN MEDICINE
(2021)
Article
Soil Science
Pengzhi Zhao, Daniel J. Fallu, Ben R. Pears, Camille Allonsius, Jonas J. Lembrechts, Stijn Van de Vondel, Filip J. R. Meysman, Sara Cucchiaro, Paolo Tarolli, Pu Shi, Johan Six, Antony G. Brown, Bas van Wesemael, Kristof Van Oost
Summary: Oxyhydroxides, soil texture, and soil organic carbon (SOC) fractions are important for organic carbon cycling in soils. Traditional methods to determine these properties are time-consuming and expensive, but visible near infrared (Vis-NIR) and mid-infrared (MIR) spectroscopy offer a promising alternative. This study demonstrates that combining soil infrared spectroscopy with compositional data analysis allows for cost-effective and reliable quantification of these properties, providing a practical opportunity to assess the role of SOC in global carbon cycling.
SOIL & TILLAGE RESEARCH
(2023)
Article
Statistics & Probability
Michael Greenacre, Eric Grunsky, John Bacon-Shone, Ionas Erb, Thomas Quinn
Summary: This article traces the development of John Aitchison's compositional data analysis approach, introduces his logratio approach for working with data with a fixed-sum constraint, and summarizes and reassesses its properties. It argues that subcompositional coherence, the main property on which this approach was built, is not strictly necessary, and quasi-coherence is sufficient for practical purposes. The article also discusses the importance of isometric and related logratio transformations, as well as alternative quasi-coherent transformations.
STATISTICAL SCIENCE
(2023)
Article
Soil Science
Mo Zhang, Wenjiao Shi, Yongxing Ren, Zongming Wang, Yong Ge, Xudong Guo, Dehua Mao, Yuxin Ma
Summary: Soil organic carbon (SOC) plays a vital role in assessing land quality, managing farmland and ecological environment, and understanding carbon cycle. Accurate spatial prediction of multilayer SOC density (SOCD) is important for interpreting changes in SOC stocks and dynamics. Previous mapping techniques have limitations, but the two proposed methods for multilayer mapping based on proportional allocation of soil depth showed better accuracy and interpretability. Among the methods compared, the proportional allocation methods combined with random forest (RF) performed the best. The findings provide valuable insights for SOCD mapping and land management.
SOIL & TILLAGE RESEARCH
(2022)
Article
Computer Science, Artificial Intelligence
Peizhen Peng, Liping Xie, Haikun Wei
Summary: This paper introduces a novel patient-specific method for predicting epileptic seizures, combining Fourier Neural Network (FNN) and Convolutional Neural Network (CNN) for efficient and practical results. By utilizing multi-layer modules and a deep neural network, the prediction of epileptic signals achieves high accuracy and sensitivity.
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS
(2021)
Article
Environmental Sciences
Linke Ouyang, Caiyan Wu, Junxiang Li, Yuhan Liu, Meng Wang, Ji Han, Conghe Song, Qian Yu, Dagmar Haase
Summary: Impervious surface area (ISA) is a crucial indicator of urbanization. Spectral mixture analysis (SMA), commonly used to estimate ISA from remotely sensed data, faces challenges due to endmember spectral variability and plant phenology. This study developed a novel approach, PF-LSMA, which incorporates phenology with Fisher transformation, and demonstrated its effectiveness in accurately extracting ISA.
Article
Statistics & Probability
Wanfeng Liang, Yue Wu, Xiaoyan Ma
Summary: Motivated by the rapid development in high-dimensional compositional data analysis, this paper proposes an Approximate-Plug framework with theoretical justifications for robust precision matrix estimation under the sparsity assumption. The proposed method constructs a robust estimator and utilizes a constrained minimization procedure to obtain the final estimator. Simulation studies and real data application demonstrate the superiority of the proposed method over existing approaches.
STATISTICS & PROBABILITY LETTERS
(2022)
Article
Chemistry, Analytical
Mo H. Modarres, Jonathan E. Elliott, Kristianna B. Weymann, Dennis Pleshakov, Donald L. Bliwise, Miranda M. Lim
Summary: Surface electromyography (EMG) is important in defining sleep stages and certain disease states. A digitized signal processing method using spectral power ratio was developed to evaluate EMG signals. Through further refinement and validation, an accurate automated EMG quantification approach was achieved.
Article
Geochemistry & Geophysics
Yue Liu
Summary: Balance analysis is essential in compositional data analysis. Two approaches, data-driven CoBA and knowledge-driven CoBA, can be used to generate targeted balances for geochemical pattern analysis and anomaly identification. Determining the optimal balance requires further exploration.
GEOCHEMISTRY-EXPLORATION ENVIRONMENT ANALYSIS
(2022)
Article
Computer Science, Information Systems
Yayu Yang, Kun Shang, Chenchao Xiao, Changkun Wang, Hongzhao Tang
Summary: Estimation of soil organic matter content (SOMC) is essential for soil quality evaluation. This study analyzed and evaluated the SOMC-related spectral indices suitable for the ZY1-02D satellite and successfully applied them to SOMC mapping and estimation.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2022)
Article
Plant Sciences
Ane Cecilie Kvernvik, Clara Jule Marie Hoppe, Evelyn Lawrenz, Ondrej Prasil, Michael Greenacre, Jozef Maria Wiktor, Eva Leu
JOURNAL OF PHYCOLOGY
(2018)
Article
Environmental Sciences
Per-Otto Johansen, Trond Einar Isaksen, Einar Bye-Ingebrigtsen, Marte Haave, Thomas G. Dahlgren, Stian Ervik Kvalo, Michael Greenacre, Dominique Durand, Hans Tore Rapp
MARINE POLLUTION BULLETIN
(2018)
Article
Geosciences, Multidisciplinary
Michael Greenacre
MATHEMATICAL GEOSCIENCES
(2019)
Editorial Material
Statistics & Probability
Michael Greenacre
Article
Limnology
Martin Graeve, Michael J. Greenacre
LIMNOLOGY AND OCEANOGRAPHY-METHODS
(2020)
Article
Computer Science, Interdisciplinary Applications
Michael Greenacre, Eric Grunsky, John Bacon-Shone
Summary: The isometric logratio transformation, using ratios of geometric means to contrast two groups of parts in a compositional data set, has theoretical properties but can be affected by small relative values. In practical applications, comparing two groups of parts requires using the logratio of two amalgamations as an interpretable form of balance. This approach highlights which compositional parts drive the data structure and maps well to research-driven objectives.
COMPUTERS & GEOSCIENCES
(2021)
Article
Engineering, Marine
Eva Leu, Thomas A. Brown, Martin Graeve, Jozef Wiktor, Clara J. M. Hoppe, Melissa Chierici, Agneta Fransson, Sander Verbiest, Ane C. Kvernvik, Michael J. Greenacre
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2020)
Correction
Anthropology
Jonathan R. Wood, Michael Greenacre
ARCHAEOLOGICAL AND ANTHROPOLOGICAL SCIENCES
(2021)
Article
Anthropology
Jonathan R. Wood, Michael Greenacre
Summary: Analyzing the chemical compositions of Parthian and Sasanian glazed pottery using statistical methods and expert knowledge can help identify the production practices of Mesopotamian glass and glaze producers. It was found that the silica sources used in later glazes were purer and more standardized. This suggests the possibility of undiscovered glass production centers associated with urbanization in southern Mesopotamia during the Parthian-Sasanian transition.
ARCHAEOLOGICAL AND ANTHROPOLOGICAL SCIENCES
(2021)
Article
Biology
Marina Martinez-Alvaro, Agostina Zubiri-Gaitan, Pilar Hernandez, Michael Greenacre, Alberto Ferrer, Agustin Blasco
Summary: This study provides a comprehensive comparison of microbiome core functionalities between hosts with different genotypes for intramuscular lipid deposition. The differential abundances of microbial genes were found to be influenced by host genetics, shedding light on the impact of host genetic determination on lipid accretion in muscle. The results have implications for the development of strategies targeting obesity.
COMMUNICATIONS BIOLOGY
(2021)
Article
Statistics & Probability
Carles M. Cuadras, Michael Greenacre
Summary: This article presents different concepts of correlation and statistical association in three parts, with the use of historical notes and classic data set. It covers various methods and results related to correlation analysis and multivariate analysis. The fitting of copulas to the data set is also explored.
JOURNAL OF MULTIVARIATE ANALYSIS
(2022)
Article
Statistics & Probability
Germa Coenders, Michael Greenacre
Summary: This article presents three alternative stepwise supervised learning methods to select pairwise logratios that best explain a dependent variable in a generalized linear model. The first method allows unrestricted search, leading to the most accurate predictions. The second method restricts each part to occur only once, making the corresponding logratios intuitively interpretable. The third method uses additive logratios, involving a K-part subcomposition in the selected logratios.
JOURNAL OF APPLIED STATISTICS
(2023)
Article
Biochemistry & Molecular Biology
Felisa Rey, Paulo Cartaxana, Susana Aveiro, Michael Greenacre, Tania Melo, Pedro Domingues, M. Rosario Domingues, Sonia Cruz
Summary: A study on the sea slug Elysia timida revealed that light intensity influences the degradation of stolen chloroplasts (kleptoplasts), with older kleptoplasts being targeted for degradation. The lipidome of E. timida showed differences under different light treatments, indicating a light-driven remodelling of the lipidome.
BIOCHIMICA ET BIOPHYSICA ACTA-MOLECULAR AND CELL BIOLOGY OF LIPIDS
(2023)
Article
Environmental Sciences
Jasmine Nahrgang, Cassandra Granlund, Morgan Lizabeth Bender, Lisbet Sorensen, Michael Greenacre, Marianne Frantzen
Summary: The rise in offshore operations, maritime shipping, and tourism in northern latitudes increases the risk of oil spills to sub-Arctic and Arctic coastal environments. This study investigates the effects of oil exposure on the early life stages of capelin, an important fish species in the Barents Sea. The results suggest that capelin may be more resilient to crude oil exposure than other fish species.
JOURNAL OF TOXICOLOGY AND ENVIRONMENTAL HEALTH-PART A-CURRENT ISSUES
(2023)
Article
Hospitality, Leisure, Sport & Tourism
Tor Korneliussen, Michael Greenacre
JOURNAL OF TRAVEL RESEARCH
(2018)