Search

Biomass Waste Derived Porous Carbon (BWDPC) is widely used for its ability to adsorb carbon dioxide (CO 2) in large-scale industrial operations, making it a leading solution for combating air pollution and climate change issues. However, factors such as temperature, pressure, and surface area can influence its performance in adsorbingcarbon dioxide. To maximize CO 2 adsorption, it is vital to determine the relationships among these variables. In this paper, we use several preprocessing techniques and various machine learning algorithms, such as Gradient Boosting Regressor, Convolutional Neural Networks, Multi-Layer Perceptron, and Long Short-Term Memory, to explore the efficacy of these algorithms in predicting CO 2 capture capacities. We augment our datasets by generating new features and in turn our ML models achieve a better performance on the augmented datasets compared to the original dataset. Our models achieved r 2 score of 90.7 % on the training set and 85.73 % on the test set of the augmented datasets. Furthermore, we were able to determine that the ratio of carbon to pressure as well as temperature, and aspects tied to the physical conditions of the adsorbent material emerge as the most influential factors in CO 2 adsorption. A python implementation of all our experiments is publicly available in Github https://github.com/mmaheri/CO2_Capturing.git. • We apply various preprocessing steps and augment the original dataset by generating new features. • We compare the performance of various machine learning algorithms on the original and augmented datasets. • The machine learning algorithms show a better performance on the augmented dataset in terms of r2 score. • Convolutional Neural Network and Gradient Boosting Regression exhibit the best performance. • The ratio of carbon to pressure as well as temperature, and aspects tied to the physical conditions of the adsorbent material emerge as the most influential factors in CO2 adsorption. [ABSTRACT FROM AUTHOR]

Background The clinical implications of vertebrobasilar ectasia (VBE) in patients with cerebral small-artery disease are not well defined. We investigated whether VBE is associated with recurrent stroke, major hemorrhage, and death in a large cohort of patients with recent lacunar stroke. Methods Maximum diameters of the vertebral and basilar arteries were measured by magnetic resonance angiography and computed tomographic angiography in 2621 participants in the Secondary Prevention of Small Subcortical Strokes trial. VBE was defined a priori as basilar artery greater than 4.5 mm and/or vertebral artery greater than 4.0 mm. Patient characteristics and risks of stroke recurrence and mortality during follow-up (median, 3.5 years) were compared between patients with and without VBE. Results VBE affecting 1 or more arteries was present in 200 (7.6%) patients. Patient features independently associated with VBE were increasing age, male sex, white race ethnicity, hypertension, and higher baseline diastolic blood pressure. Baseline systolic blood pressure was inversely associated with VBE. After adjustment for other risk factors, VBE was not predictive of recurrent stroke (hazard ratio [HR], 1.3; 95% confidence interval [CI], .85-1.9) or major hemorrhage (HR, 1.5; CI, .94-2.6), but was of death (HR, 1.7; CI, 1.1-2.7). Conclusions In this large well-characterized cohort of patients with recent lacunar stroke, VBE was predictive of death but not of recurrent stroke or major hemorrhage. In these exploratory analyses, the frequency of VBE was directly related to diastolic blood pressure but inversely related to systolic blood pressure. [ABSTRACT FROM AUTHOR]

This study aims to provide a framework which enables decision-makers and researchers to identify AI technology patterns in renewable energy systems from a massive data set of textual data. However, the study was challenged by the Scopus database limitation that allows users to retrieve only 2000 documents per query. Therefore, we developed a search engine based on the Scopus Application Programming Interface (API) that enables us to download an unlimited number of documents per query based on our desirable settings. We extracted 5661 renewable energy systems-related publications from Scopus database and leveraged Natural Language Processing (NLP) and unsupervised algorithms to identify the most frequent computational science models and dense meta-topics and investigate their evolution throughout the period 2000-2021. Our findings showed 7 meta-topics based on the class-based Term Frequency-Inverse Document Frequency (c-TD-IDF) score and term score decline graph. Emerging advanced algorithms, such as different deep learning architectures, directly impacted growing meta-topics involving problems with uncertainty and dynamic conditions. [Display omitted] • Developed a search engine to retrieve data from Scopus. • Recognized trend of AI algorithms in renewable energy systems. • Used BERTopic model to investigate main topics and their time evolution. • Identified seven meta-topics covering all dimensions of renewable energy systems. • Direct relation between advanced AI models and meta-topics with uncertain condition. [ABSTRACT FROM AUTHOR]

Pavement vehicle interaction (PVI) is one of the significant components in the use phase of pavement life cycle assessment. This component has attribution with excess fuel consumption, resulting in an increase in the global warming potential (GWP). Several research have been conducted to model and quantify the PVI effect based on pavement roughness and deflection. These models estimate excess fuel consumption considering traffic loading, engineering properties of pavement materials and pavement design specifications. However, a big question remains unanswered: how do various climatic parameters including precipitation, temperature, and freezing index influence the PVI and subsequent GWP? Canada is the second largest country in the world and different climate regions can be found in each of its ten provinces and three territories. Therefore, a new, climate-based clustering approach—rather than geometric boundaries is introduced for climate impact analysis from road system. Twenty-two Long-Term Pavement Performance (LTPP) road sections located in the Canadian highways have been selected for this study. These road sections were clustered based on homogenous climate conditions, using a statistical approach. The research finds that a combination of high precipitation, freezing index and medium temperature are associated with an accelerated rate of International Roughness Index (IRI) and consequent GWP because of a high PVI for poor pavement surface. GWP for roughness is found to be very low where high temperature and a low freezing index exist. Very high traffic loading and low subgrade stiffness, when combined, produced the highest GWP emissions because of deflection based PVI. It was also found that the PVI effect in terms of GWP for both roughness and deflection is always dominant for heavy vehicles over light vehicles traffic. • A new, climate-based clustering approach—rather than geometric boundaries is introduced for climate impact analysis. • HDM IV model and PVI Gen II model was used to estimate the GWP value for pavement roughness and deflection, respectively. • A combination of high precipitation, freezing index and medium temperature results accelerated IRI rate and consequent GWP. • Very high traffic loading and low subgrade stiffness altogether produces the highest GWP because of deflection based PVI. [ABSTRACT FROM AUTHOR]