•Applications of machine learning methods in metal–organic framework research are discussed.•Descriptors and representations of MOFs for machine learning applications.•Prediction of various material ...properties of MOFs with machine learning methods.•Machine learning-assisted design of MOFs and other nanoporous materials.
Machine learning (ML) is the field of computer science where computing systems are trained to perform an analysis of provided data to reveal previously unseen trends and patterns that allow accurate predictions. ML methods have drastically transformed the way scientific research is conducted, making significant contributions in a variety of research fields ranging from natural language processing to drug discovery and materials design. With an abundance of discovered structures and their performance data for various application fields, metal–organic frameworks (MOFs) would undoubtedly benefit from the integration of ML methods for their design and development. In this review, we provide a complete overview of how ML methods can be effectively utilized for MOF research. Various descriptors and representations of MOFs suitable for the ML workflow are first discussed. Then, recent research progresses in which novel ML methods are used to predict various material properties or even design new MOF structures are presented. As many more MOFs are discovered and utilized for various applications, ML will play a much bigger role in their research and development. As such, this review aims to provide readers with basic insights required to comprehend ML-based MOF research, and to help conduct those of their own in the future.
We developed a chemical route to produce graphene nanoribbons (GNR) with width below 10 nanometers, as well as single ribbons with varying widths along their lengths or containing lattice-defined ...graphene junctions for potential molecular electronics. The GNRs were solution-phase-derived, stably suspended in solvents with noncovalent polymer functionalization, and exhibited ultrasmooth edges with possibly well-defined zigzag or armchair-edge structures. Electrical transport experiments showed that, unlike single-walled carbon nanotubes, all of the sub-10-nanometer GNRs produced were semiconductors and afforded graphene field effect transistors with on-off ratios of about 10⁷ at room temperature.
(1) Background: Public sidewalk GIS data are essential for smart city development. We developed an automated street-level sidewalk detection method with image-processing Google Street View data. (2) ...Methods: Street view images were processed to produce graph-based segmentations. Image segment regions were manually labeled and a random forest classifier was established. We used multiple aggregation steps to determine street-level sidewalk presence. (3) Results: In total, 2438 GSV street images and 78,255 segmented image regions were examined. The image-level sidewalk classifier had an 87% accuracy rate. The street-level sidewalk classifier performed with nearly 95% accuracy in most streets in the study area. (4) Conclusions: Highly accurate street-level sidewalk GIS data can be successfully developed using street view images.
Intercritically annealed 10 pct Mn steel has been shown to exhibit an excellent combination of strength and ductility due to the plasticity-enhancing mechanisms of mechanical twinning and ...strain-induced martensite transformation occurring in sequence. This mechanical behavior is only achieved for a multi-phase microstructure obtained after annealing within a specific intercritical temperature range. A model for the selection of the optimal intercritical annealing temperature was developed to achieve a high strength-ductility balance for 10 pct Mn multi-phase steel. The model considers the room temperature stacking fault energy and the thermodynamic stability of the retained austenite.
The transferred microbiota from mother to baby constitutes the initial infant gastrointestinal microbiota and has an important influence on the development and health of infants in human. However, ...the reproductive tract microbiota of avian species and its inheritance have rarely been studied. We aimed to characterize the microbial community in the chicken reproductive tract and determine the origin of the chicken embryo gut microbiota. Microbiota in four different portions of chicken oviduct were determined using 16S rRNA metagenomic approach with the IonTorrent platform. Additionally, we analyzed the mother hen's magnum and cloaca, descendent egg, and embryo gut microbiota. The microbial composition and relative abundance of bacterial genera were stable throughout the entire chicken reproductive tract, without significant differences between the different parts of the oviduct. The chicken reproductive tract showed a relatively high abundance of Lactobacillus species. The number of bacterial species in the chicken reproductive tract significantly increased following sexual maturation. Core genera analysis detected 21 of common genera in the maternal magnum and cloaca, descendent egg shell, egg white, and embryo gut. Some elements of the maternal oviduct microbiota appear to be transferred to the embryo through the egg white and constitute most of the embryo gut bacterial population.
Although interest in the efficacy of efforts to correct false beliefs has peaked in recent years, the extent to which corrective effects endure over time remains understudied. Drawing on insights ...from related literatures in the psychology of belief, persuasion and media effects to inform theoretical expectations, this study uses a longitudinal experiment to observe both contemporaneous and long-term changes in participants’ belief accuracy in response to corrective information within an ongoing, contentious political debate. We measured factors thought to either promote durability (e.g. repeated exposure to corrective information) or cause decay (e.g. political predispositions, media behaviors) in assessing moderators of the magnitude and longevity of corrections. Corrective effects were found to be quite durable, detectable up to 4 weeks after exposure to the initial message, while repeated exposure to corrective information further promoted the longevity of these effects.
The edge platform has evolved to become a part of a distributed computing environment. While typical edges do not have enough processing power to train machine learning models in real time, it is ...common to generate models in the cloud for use on the edge. The pattern of heterogeneous Internet of Things (IoT) data is dependent on individual circumstances. It is not easy to guarantee prediction performance when a monolithic model is used without considering the spatial characteristics of the space generating those data. In this paper, we propose a collaborative framework using a new method to select the best model for the edge from candidate models of cloud based on sample data correlation. This method lets the edge use the most suitable model without any training tasks on the edge side, and it also minimizes privacy issues. We apply the proposed method to predict future fine particulate matter concentration in an individual space. The results suggest that our method can provide better performance than the previous method.
The Soyang Dam, the largest multipurpose dam in Korea, faces water resource management challenges due to global warming. Global warming increases the duration and frequency of days with high ...temperatures and extreme precipitation events. Therefore, it is crucial to accurately predict the inflow rate for water resource management because it helps plan for flood, drought, and power generation in the Seoul metropolitan area. However, the lack of hydrological data for the Soyang River Dam causes a physical-based model to predict the inflow rate inaccurately. This study uses nearly 15 years of meteorological, dam, and weather warning data to overcome the lack of hydrological data and predict the inflow rate over two days. In addition, a sequence-to-sequence (Seq2Seq) mechanism combined with a bidirectional long short-term memory (LSTM) is developed to predict the inflow rate. The proposed model exhibits state-of-the-art prediction accuracy with root mean square error (RMSE) of 44.17 m3/s and 58.59 m3/s, mean absolute error (MAE) of 14.94 m3/s and 17.11 m3/s, and Nash–Sutcliffe efficiency (NSE) of 0.96 and 0.94, for forecasting first and second day, respectively.
Protest has long been associated with left-wing actors and left-wing causes. However, right-wing actors also engage in protest. Are right-wing actors mobilized by the same factors as those actors on ...the left? This article uses cross-national survey data (i.e., US, UK, France, and Canada) gathered in February 2021 to assess the role of misinformation, conspiracy beliefs, and the use of different social media platforms in explaining participation in marches or demonstrations. We find that those who use Twitch or TikTok are twice as likely to participate in marches or demonstrations, compared to non-users, but the uses of these platforms are more highly related to participation in right-wing protests than left-wing protests. Exposure to misinformation on social media and beliefs in conspiracy theories also increase the likelihood of participating in protests. Our research makes several important contributions. First, we separate right-wing protest participation from left-wing protest participation, whereas existing scholarship tends to lump these together. Second, we offer new insights into the effects of conspiracy beliefs and misinformation on participation using cross-national data. Third, we examine the roles of emerging social media platforms such as Twitch and TikTok (as well as legacy platforms such as YouTube and Facebook) to better understand the differential roles that social media platforms play in protest participation.
The exceptional elongation obtained during tensile testing of intercritically annealed 10 pct Mn steel, with a two phase ferrite–austenite microstructure at room temperature, was investigated. The ...austenite phase exhibited deformation-twinning and strain-induced transformation to martensite. These two plasticity-enhancing mechanisms occurred in succession, resulting in a high rate of work hardening and a total elongation of 65 pct for a tensile strength of 1443 MPa. A constitutive model for the tensile behavior of the 10 pct Mn steel was developed using the Kocks–Mecking hardening model.