Article
Agronomy
Sayanti Guha Majumdar, Anil Rai, Dwijesh Chandra Mishra
Summary: This article discusses the importance of estimating error variance in genomic selection and proposes four methods to implement error variance estimation. The effectiveness of these algorithms is demonstrated through evaluation with simulated and real datasets.
Article
Forestry
Sofia Cortes-Calderon, Francisco Mora, Felipe Arreola-Villa, Patricia Balvanera
Summary: Secondary forests are expected to dominate future tropical landscapes, providing crucial ecosystem services to humanity. A study in a Mexican Pacific coast site showed rapid recovery of multiple forest resources provision, microclimate regulation, and carbon storage within the first two decades of succession. While carbon sequestration slightly increased over time, the supply of forage did not show a clear trend. The interactions among different ecosystem services varied over time, with higher strength in farmlands and old-growth forests. These findings highlight the importance of adaptive forest management practices to recover critical ecosystem services in tropical dry forests.
FOREST ECOLOGY AND MANAGEMENT
(2021)
Article
Mathematical & Computational Biology
Mushan Li, Yanyuan Ma
Summary: Accurate assessment of the mean-variance relation is crucial in biomedical research. To address the unavailability of true mean and true variance in most biomedical data, we propose a semiparametric estimator that accounts for measurement error and model error, and uses a mixture model to handle different mean-variance relations. Simulation studies and data application demonstrate the effectiveness of the proposed method.
STATISTICS IN MEDICINE
(2023)
Article
Engineering, Multidisciplinary
Shashi Bhushan, Anoop Kumar, Abdelaziz Alsubie, Showkat Ahmad Lone
Summary: This study introduces an efficient approach for estimating variance in simple random sampling. The proposed estimators are shown to include existing well-known estimators as special cases. The bias and mean square error of the proposed estimators are determined up to first-order approximation. The effectiveness of the proposed estimators is examined by comparing them with other distinguished estimators. In addition, numerical illustrations and Monte Carlo simulations are conducted to further validate the findings of the study.
AIN SHAMS ENGINEERING JOURNAL
(2023)
Article
Statistics & Probability
Mehdi Dagdoug, Camelia Goga, David Haziza
Summary: This article discusses the methods of estimating finite population parameters in surveys by incorporating auxiliary information to improve estimation precision. It uses random forests to estimate the relationship between survey variables and auxiliary variables and explores a model-calibration procedure for handling multiple survey variables. The results of a simulation study show that the proposed methods perform well in terms of bias, efficiency, and coverage of confidence intervals in various settings.
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
(2023)
Article
Forestry
Musse Tesfaye, Ashenafi Manaye, Berihu Tesfamariam, Zenebe Mekonnen, Shibire Bekele Eshetu, Katharina Loehr, Stefan Sieber
Summary: Dry forests' contribution to climate change adaptation is often overlooked, but in Tigray Region, the overall dry forest income contributes to 16.8% of total household income. Different types of dry forest users are significantly impacted by dry forest income in various ways.
Article
Statistics & Probability
Xingli Yang, Yu Wang, Wennan Yan, Jihong Li
Summary: A model selection method based on the ranks of the frequency of occurrences in a blocked 3x2 cross-validation has been proposed in this study, which shows a considerably larger probability of including the true model and obtaining more accurate variance estimation with lower bias and smaller variance. The theoretical analysis also proves the asymptotic normality property of the proposed variance estimation.
JOURNAL OF APPLIED STATISTICS
(2021)
Article
Computer Science, Artificial Intelligence
Waleed A. Yousef
Summary: This study analyzes the variance of CV-based estimators and proposes a new estimator using the IF method. Results show that the IF method has small RMS error but some bias, with ad-hoc methods performing better. Areas for further research include more simulation studies, mathematical analysis, and exploration of smoothness in relation to reducing bias.
PATTERN RECOGNITION LETTERS
(2021)
Article
Agronomy
Vinicius Londe, Paulo Weslem Portal Gomes, Fernando Roberto Martins
Summary: This study examines the impact of edaphic differences on life zones, vegetation types, beta-diversity, and indicator species in the Caatinga region in northeast Brazil. The results show that soil type plays a secondary role in species distribution compared to climatic variables.
Article
Agronomy
Ulisses A. Bezerra, John Cunha, Fernanda Valente, Rodolfo L. B. Nobrega, Joao M. Andrade, Magna S. B. Moura, Anne Verhoef, Aldrin M. Perez-Marin, Carlos O. Galvao
Summary: Improvement in ET estimates, particularly in Seasonally Dry Tropical Forests (SDTF), has been achieved through the use of remote sensing (RS) products based on multispectral and thermal sensors. The development of a RS-based SEB model called STEEP has addressed the limitations of existing models by considering the specificities of SDTF, such as contrasting phenological phases and soil-water availability. The STEEP model demonstrated enhanced accuracy in ET estimates during the dry season, outperforming traditional SEB models and comparable to global ET products.
AGRICULTURAL AND FOREST METEOROLOGY
(2023)
Article
Environmental Sciences
Ehsan Ali, Muhammad Farooq Azhar, Edris Alam, Zainab Rehman, Sami Ullah, Aqeel Ahmad, Abu Reza Md. Towfiqul Islam, Wajid Zaman, Muhammad Javed, Praveen Mittal
Summary: Deforestation is a major factor in climate change in developing countries, with Pakistan being one of the most affected countries. This study in the Chilas region investigated the current state of deforestation, its causes, and predicted the main drivers using a regression model. The results identified unsustainable fuel wood and timber extraction, urban expansion and rural habitation, and uncontrolled livestock grazing as the primary drivers. To tackle deforestation, the government needs to provide alternative energy sources and economic opportunities to reduce reliance on forests.
FRONTIERS IN ENVIRONMENTAL SCIENCE
(2023)
Article
Statistics & Probability
Assaf Rabinowicz, Saharon Rosset
Summary: This article analyzes the application of K-fold cross-validation in correlated data and introduces a criterion and a correction method, which significantly improves the performance of model evaluation and selection.
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
(2022)
Article
Automation & Control Systems
Jing Wang, Gang Hao
Summary: This study analyzes the impact of system parameters on mean squared error (MSE) in nonlinear systems with uncertain system parameters and proposes an innovative robust estimation algorithm based on analysis results and prior probability statistics. The effectiveness of the proposed algorithm is verified through three examples.
INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL
(2021)
Article
Geosciences, Multidisciplinary
Steinar Love Ellefmo, Thomas Kuhn
Summary: Minerals and metals play a crucial role in society, and there is great potential in mining mineral resources from the deep ocean floor. This study utilized images and expert knowledge to estimate nodules abundance, showcasing the importance of utilizing data effectively for better informed estimates. Future improvements will focus on enhancing the estimation of minimum and maximum values at image locations.
NATURAL RESOURCES RESEARCH
(2021)
Article
Forestry
Bruno K. C. Filgueiras, Carlos A. Peres, Luciana Iannuzzi, Marcelo Tabarelli, Inara R. Leal
Summary: The study found that dung beetle assemblages in Caatinga dry forests in northeastern Brazil did not experience successional replacements along the regeneration gradient, showing high resilience. Additionally, disturbance-associated dung beetle species led to assemblage convergence across the regeneration cline.
FOREST ECOLOGY AND MANAGEMENT
(2021)
Article
Ecology
Narendra Nelli, Diana Francis, Ricardo Fonseca, Olivier Masson, Mamadou Sow, Emmanuel Bosc
Summary: This study investigates the changes in the atmospheric electric field (Ez) during foggy conditions in the hyperarid region of the United Arab Emirates. The results show that as fog persists, Ez becomes more variable due to the absorption and redistribution of charges by the fog, which alters the ion balance and affects electrical conductivity in the atmosphere.
JOURNAL OF ARID ENVIRONMENTS
(2024)
Article
Ecology
Ezra Hadad, Amir Balaban, Jakub Z. Kosicki, Reuven Yosef
Summary: This study investigated whether the prey of striped hyenas has adapted to the change in the natural environment caused by human activities, particularly artificial light at night (ALAN). The results showed that ALAN had no impact on the diet or den distribution of the hyenas in central Israel. The study also found that domestic animals were the most common prey, and there were also some vegetative species in their diet. Overall, the feeding behavior of striped hyenas is influenced by geographical region, habitat, and human activities.
JOURNAL OF ARID ENVIRONMENTS
(2024)
Article
Ecology
Rahim Najafi Tireh Shabankareh, Pardis Ziaee, Mohammad Javad Abedini
Summary: This study evaluated the IMERG satellite-based precipitation product in the Fars province of Iran using daily rain gauges as reference data. The results showed that the product tends to overestimate light rainfall and underestimate heavy rainfall, with the best performance in the 40-80 mm/day range. The accuracy of the product varies by month and is less biased in months with milder temperatures. Additionally, there was a higher correlation in mid-elevated areas, positive bias in low-elevated areas, and negative bias in high-elevated areas. Longer time scales showed considerable improvement in the IMERG estimates.
JOURNAL OF ARID ENVIRONMENTS
(2024)