Article
Biodiversity Conservation
Michael Oliewo Aluma, Lilian Pukk, Margo Hurt, Katrin Kaldre
Summary: Invasive non-indigenous crayfish species pose a significant threat to native crayfish populations in European freshwater ecosystems. The presence of signal crayfish, marbled crayfish, and spiny-cheek crayfish in Estonia has increased the risk of extinction for the native noble crayfish. This study provides an overview of the status, distribution, and impacts of these invasive species on native crayfish populations, as well as the effectiveness of trapping in controlling their abundance.
Article
Automation & Control Systems
Lorenzo Nespoli, Vasco Medici
Summary: This paper presents a computationally efficient algorithm for fitting multivariate boosted trees and proves that multivariate trees outperform univariate trees when there is prediction correlation. The algorithm also allows for arbitrary regularization of predictions to enforce properties like smoothness, consistency, and functional relations. Applications and numerical results related to forecasting and control are presented.
JOURNAL OF MACHINE LEARNING RESEARCH
(2022)
Article
Automation & Control Systems
Yichen Zhou, Giles Hooker
Summary: This paper examines a novel gradient boosting framework for regression, which regularizes gradient boosted trees through subsampling and a modified shrinkage algorithm. The resulting algorithm, Boulevard, is shown to converge as the number of trees grows, and a central limit theorem is demonstrated for its limit, providing a characterization of uncertainty for predictions. Simulation study and real world examples support both the predictive accuracy of the model and its limiting behavior.
JOURNAL OF MACHINE LEARNING RESEARCH
(2022)
Article
Computer Science, Artificial Intelligence
Paulino Jose Garcia-Nieto, Esperanza Garcia-Gonzalo, Jose Ramon Alonso Fernandez, Cristina Diaz Muniz
Summary: The article introduces a nonparametric machine learning algorithm that combines the GBRT model and L-SHADE algorithm to better predict and control algal atypical proliferation in water systems, successfully estimating Chlorophyll-a and Total Phosphorus concentrations.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Environmental Sciences
Wan Nur Shaziayani, Ahmad Zia Ul-Saufie, Hasfazilah Ahmat, Dhiya Al-Jumeily
Summary: Air pollution is a significant global environmental issue, with sources in Malaysia including mobile and stationary sources, and PM10 being the most noticeable pollutant. By comparing QR and OLS in the BRT model for predicting PM10 concentrations in different areas, it was found that QR performs slightly better than OLS.
AIR QUALITY ATMOSPHERE AND HEALTH
(2021)
Article
Agriculture, Multidisciplinary
Er Sheng Gong, Bin Li, Binxu Li, Natalia S. Podio, Hongyu Chen, Tong Li, Xiyun Sun, Ningxuan Gao, Wenlong Wu, Tianran Yang, Guang Xin, Jinlong Tian, Xu Si, Changjiang Liu, Jiyue Zhang, Rui Hai Liu
Summary: The study found that different blackberry varieties' extracts contain abundant phenolic compounds, with ferulic acid, ellagic acid, and other compounds being major in bound fractions. The bound fractions of different blackberry varieties' extracts are high in phenolics and exhibit great antioxidant activity. Analysis revealed that different antioxidant compounds have different contributions to the antioxidant activity of free and bound fractions.
JOURNAL OF THE SCIENCE OF FOOD AND AGRICULTURE
(2022)
Article
Economics
Ioannis Nasios, Konstantinos Vogklis
Summary: In this study, a blending methodology for machine learning models from the gradient boosted trees and neural networks families was described to address the problem of point and probabilistic forecasting. Key points include transforming the task into regression on sales for a single day, information-rich feature engineering, creating a diverse set of state-of-the-art machine learning models, and carefully constructing validation sets for model tuning.
INTERNATIONAL JOURNAL OF FORECASTING
(2022)
Article
Demography
Jack Baker, David Swanson, Jeff Tayman
Summary: Small-area population forecasting faces challenges such as small population sizes, shifting population dynamics, data availability, and the evolution of census geographies. Machine learning techniques, specifically boosted regression trees, have shown to have greater accuracy and produce fewer extreme outliers in population forecasts compared to traditional methods.
POPULATION RESEARCH AND POLICY REVIEW
(2023)
Article
Forestry
Ho-Tung Lin, Tzeng Yih Lam, Ping-Hsun Peng, Chih-Ming Chiu
Summary: This study successfully integrated Boosted Regression Trees (BRT) into the Parameter Prediction Method (PPM) and applied it to thinning experiments of Taiwania cryptomerioides, selecting influential predictors on the parameters of probability density functions. The research found that diameter distribution was influenced by years since thinning and residual diameter distribution immediately after thinning, indicating that intensive thinning from below results in a more positively skewed post-harvest diameter distribution and larger minimum diameter.
FOREST ECOLOGY AND MANAGEMENT
(2021)
Article
Biodiversity Conservation
Junjun Zhi, Zequn Zhou, Xinyue Cao
Summary: The results showed that in alpine meadows, modified soil-adjusted vegetation index 2, elevation, slope, topographic wetness index, relative slope position, and mean annual precipitation are the most important environmental variables controlling mattic horizon thickness. The BRT algorithm-based variable selection approach can reliably identify the determinants of MHT and map the spatial distributions of MHT.
ECOLOGICAL INDICATORS
(2021)
Article
Green & Sustainable Science & Technology
Zafar Said, Prabhakar Sharma, Arun Kumar Tiwari, Van Vang Le, Zuohua Huang, Van Ga Bui, Anh Tuan Hoang
Summary: This work examined the thermal performance of a small-scale solar organic Rankine cycle system and successfully predicted the energy efficiency of the solar collector and the energy-exergy efficiency of the ORC system using machine learning algorithms. The experimental results showed significant improvements in thermal and exergy efficiency under specific flow rates and concentrations. The GPR-based models performed exceptionally well, outperforming the BRT-based model in terms of prediction accuracy.
JOURNAL OF CLEANER PRODUCTION
(2022)
Article
Environmental Sciences
Daria Paniotova-Maczka, Piotr Jabkowski, Piotr Matczak, Patrycja Przewoz, Krzysztof Maczka, Marcin Mielewczyk, Adam Inglot
Summary: This study shows that sociological, psychological, and physical factors play an important role in forming residents' opinions on tree removal on private land. The study used survey data and satellite images to analyze the likelihood of residents preferring the municipality or landowners to decide on tree removal. It emphasizes the importance of considering social factors when involving residents in tree management decisions.
ENVIRONMENTAL SCIENCE & POLICY
(2023)
Article
Computer Science, Interdisciplinary Applications
Thibaut Vaulet, Maya Al-Memar, Hanine Fourie, Shabnam Bobdiwala, Srdjan Saso, Maria Pipi, Catriona Stalder, Phillip Bennett, Dirk Timmerman, Tom Bourne, Bart De Moor
Summary: This study developed a clinical model using machine learning algorithms and an interpretability strategy for predicting first trimester viability. The results showed that gradient boosted algorithms performed similarly to traditional logistic regression models in terms of discrimination and calibration, and were more robust in handling missing values and feature selection.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2022)
Article
Green & Sustainable Science & Technology
Peng Cui, Chunyu Dai, Jun Zhang, Tingting Li
Summary: The distribution of PM2.5 is influenced by urban morphology parameters. This study investigated the correlation between PM2.5 distribution and urban morphology parameters in a cold-climate city in China. Field measurements were conducted to record PM2.5 concentration and microclimate parameters. The study used GIS to extract and screen urban morphology parameter data and applied the GBRT model to predict PM2.5 concentration. The results showed that building density and average building height were the most significant factors affecting PM2.5 concentration.
Article
Green & Sustainable Science & Technology
Zafar Said, Prabhakar Sharma, L. Syam Sundar, Van Giao Nguyen, Viet Dung Tran, Van Vang Le
Summary: The thermal performance of a flat plate solar collector operating under thermosyphon conditions using MWCNT + Fe3O4/Water hybrid nanofluids was investigated. Field testing showed that using hybrid nanofluids can significantly improve the thermal efficiency and heat transfer coefficient of the collector under certain Reynold's numbers and nanoparticle concentrations.
SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS
(2022)
Article
Marine & Freshwater Biology
Octavian Pacioglu, Jochen P. Zubrod, Ralf Schulz, J. Iwan Jones, Lucian Parvulescu
Article
Geology
Octavian Pacioglu, Nicoleta Ianovici, Marioara N. Filimon, Adrian Sinitean, Gabriel Iacob, Henrietta Barabas, Alexandru Pahomi, Andrei Acs, Hanelore Muntean, Lucian Parvulescu
INTERNATIONAL JOURNAL OF SPELEOLOGY
(2019)
Article
Biodiversity Conservation
Octavian Pacioglu, Kathrin Theissinger, Andreea Alexa, Corina Samoila, Ovidiu-Ioan Sirbu, Anne Schrimpf, Jochen P. Zubrod, Ralf Schulz, Malina Pirvu, Sandra-Florina Lele, John I. Jones, Lucian Parvulescu
BIOLOGICAL INVASIONS
(2020)
Article
Behavioral Sciences
Mihaela C. Ion, Adela E. Puha, Tudor Suciu, Lucian Parvulescu
Article
Zoology
Octavian Pacioglu, Nicoleta Ianovici, Marioara N. Filimon, Adrian Sinitean, Gabriel Iacob, Henrietta Barabas, Andrei Acs, Hanelore Muntean, Gabriel Plavan, Ralf Schulz, Jochen P. Zubrod, Lucian Parvulescu, Tefan-Adrian Strungaru
Article
Multidisciplinary Sciences
Lucian Parvulescu, Elena-Iulia Iorgu, Claudia Zaharia, Mihaela C. Ion, Alina Satmari, Ana-Maria Krapal, Oana-Paula Popa, Kristian Miok, Iorgu Petrescu, Luis-Ovidiu Popa
SCIENTIFIC REPORTS
(2020)
Article
Biology
Olena Maiakovska, Ranja Andriantsoa, Sina Toenges, Carine Legrand, Julian Gutekunst, Katharina Hanna, Lucian Parvulescu, Roman Novitsky, Andras Weiperth, Arnold Sciberras, Alan Deidun, Fabio Ercoli, Antonin Kouba, Frank Lyko
Summary: This study used whole-genome sequencing to investigate the genetic structure and population dynamics of marbled crayfish, revealing systematic genetic differences between geographically separated populations and illustrating the emerging differentiation of the marbled crayfish genome. Additionally, mark-recapture population size estimation combined with genetic data was used to model the growth patterns of marbled crayfish populations, uncovering the evolutionary dynamics in the marbled crayfish genome and highlighting the rapid population growth as a crucial factor for ecological monitoring.
COMMUNICATIONS BIOLOGY
(2021)
Article
Ecology
Lucian Parvulescu, Dan Ioan Stoia, Kristian Miok, Mihaela Constanta Ion, Adela Estera Puha, Melania Sterie, Mihajel Veres, Ioan Marcu, Mirela Danina Muntean, Oana Maria Aburel
Summary: The intrusion success of the invasive crayfish species in competition against the native species is attributed to its more effective anatomical features, leading to bolder behavior. In contrast, the native species relies on intimidation display despite having larger chelae and better muscular tissue performance.
FRONTIERS IN ECOLOGY AND EVOLUTION
(2021)
Article
Environmental Sciences
Andrei Dornik, Mihaela Constanta Ion, Marinela Adriana Chetan, Lucian Parvulescu
Summary: This study aimed to explore the value of soil properties in the spatial distribution of four European indigenous crayfish species, finding that different species have different preferences for soil characteristics.
Editorial Material
Ecology
Giulio Formenti, Kathrin Theissinger, Carlos Fernandes, Iliana Bista, Aureliano Bombarely, Christoph Bleidorn, Claudio Ciofi, Angelica Crottini, Jose A. Godoy, Jacob Hoglund, Joanna Malukiewicz, Alice Mouton, Rebekah A. Oomen, Sadye Paez, Per J. Palsboll, Christophe Pampoulie, Maria J. Ruiz-Lopez, Hannes Svardal, Constantina Theofanopoulou, Jan de Vries, Ann-Marie Waldvogel, Guojie Zhang, Camila J. Mazzoni, Erich D. Jarvis, Miklos Balint
Summary: Progress in genome sequencing has enabled the generation of large-scale reference genomes, representing global biodiversity. These genomes provide unique insights into genomic diversity and architecture, allowing comprehensive analyses in population and functional genomics, and are expected to revolutionize conservation genomics.
TRENDS IN ECOLOGY & EVOLUTION
(2022)
Review
Genetics & Heredity
Kathrin Theissinger, Carlos Fernandes, Giulio Formenti, Iliana Bista, Paul R. Berg, Christoph Bleidorn, Aureliano Bombarely, Angelica Crottini, Guido R. Gallo, Jose A. Godoy, Sissel Jentoft, Joanna Malukiewicz, Alice Mouton, Rebekah A. Oomen, Sadye Paez, Per J. Palsboll, Christophe Pampoulie, Maria J. Ruiz-Lopez, Simona Secomandi, Hannes Svardal, Constantina Theofanopoulou, Jan de Vries, Ann-Marie Waldvogel, Guojie Zhang, Erich D. Jarvis, Miklos Balint, Claudio Ciofi, Robert M. Waterhouse, Camila J. Mazzoni, Jacob Hoglund
Summary: The availability of public genomic resources can greatly assist biodiversity assessment, conservation, and restoration efforts. Reference genomes play a key role in facilitating biodiversity research and conservation. Integrating the use of reference genomes as a best practice in conservation genomics is essential.
TRENDS IN GENETICS
(2023)
Review
Mycology
Hossein Masigol, Pieter Van West, Seyedeh Roksana Taheri, Juan-Miguel Fregeneda-Grandes, Lucian Parvulescu, Debbie McLaggan, Tim Tobias Bliss, Reza Mostowfizadeh-Ghalamfarsa, Mohammad Javad Pourmoghaddam, Hans-Peter Grossart
Summary: This study reviewed 1073 papers and 2803 ITS sequences of Saprolegniales to investigate their taxonomy, diversity, and potential roles in freshwater ecosystems. The results showed that our knowledge on the diversity and ecology of Saprolegniales is limited, and both classic taxonomy and molecular techniques have been insufficient for their identification and distribution. Furthermore, the involvement of Saprolegniales in carbon turnover and food web dynamics is not well understood. The study proposes new research avenues and suggests increasing the practicality of classic taxonomy and utilizing molecular toolboxes to overcome the challenges in studying Saprolegniales.
FUNGAL BIOLOGY REVIEWS
(2023)
Article
Biodiversity Conservation
Alina Satmari, Kristian Miok, Mihaela C. Ion, Claudia Zaharia, Anne Schrimpf, Lucian Parvulescu
Summary: This study investigates the relationship between invasive crayfish species and native crayfish populations, identifying environmental factors that influence the invasion. The research provides insights for the conservation of native crayfish species and highlights the importance of preventing the spread of dangerous invasive species and pathogen strains.
Article
Marine & Freshwater Biology
Caterina Francesconi, Malina Pirvu, Anne Schrimpf, Ralf Schulz, Lucian Parvulescu, Kathrin Theissinger
Summary: The study compared the reproductive strategies of the invasive spiny-cheek crayfish and a sympatric indigenous crayfish, finding multiple paternity in both species. However, multiple paternity does not seem to play a dominant role in the successful colonization of the invasive crayfish in the Danube.
FRESHWATER CRAYFISH
(2021)
Article
Marine & Freshwater Biology
Elena Ungureanu, Michaela Mojzisova, Michiel Tangerman, Mihaela C. Ion, Lucian Parvulescu, Adam Petrusek
FRESHWATER CRAYFISH
(2020)