As interest in eco-friendly ships increases, methods for status monitoring and forecasting using in-service data from ships are being developed. Models for predicting the energy efficiency of a ship in real time need to effectively process the operational data and be optimized for such an application. This paper presents models that can predict fuel consumption using in-service data collected from a 13,000 TEU class container ship, along with statistical and domain-knowledge methods to select the proper input variables for the models. These methods prevent overfitting and multicollinearity while providing practical applicability. To implement the prediction model, either an artificial neural network (ANN) or multiple linear regression (MLR) were applied, where the ANN-based models showed the best prediction accuracy for both variable selection methods. The goodness of fit of the models based on ANN ranged from 0.9709 to 0.9936. Furthermore, sensitivity analysis of the draught under normal operating conditions indicated an optimal draught of 14.79 m, which was very close to the design draught of the target ship, and provides the optimal fuel consumption efficiency. These models could provide valuable information for ship operators to support decision making to maintain efficient operating conditions.
Improving the robustness of maritime emission inventories is important to ensure we fully understand the point of embarkment for transformation pathways of the sector toward the 1.5 and 2°C targets. A bottom-up assessment of emissions of greenhouse gases and aerosols from the maritime sector is presented, accounting for the emissions from fuel production and processing, resulting in a complete “well-to-wake” geospatial inventory. This high-resolution inventory is developed through the use of the state-of-the-art data-driven MariTEAM model, which combines ship technical specifications, ship location data, and historical weather data. The CO 2 emissions for 2017 amount to 943 million tonnes, which is 11% lower than the fourth International Maritime Organization’s greenhouse gas study for the same year, while larger discrepancies have been found across ship segments. If fuel production is accounted for when developing shipping inventories, total CO 2 emissions reported could increase by 11%. In addition to fuel production, effects of weather and heavy traffic regions were found to significantly impact emissions at global and regional levels. The global annual efficiency for different fuels and ship segments in approximated operational conditions were also investigated, indicating the need for more holistic metrics than current ones when seeking appropriate solutions aiming at reducing emissions.
The incidence of fractures in patients with end-stage kidney disease (ESKD) is high which is associated with high morbidity and mortality. Since fractures are preventable diseases to some extent, epidemiologic studies are needed a lot. The aim of this study is to explore the epidemiology of fractures by modality of kidney replacement therapy (KRT). We performed a retrospective analysis of 52,777 patients dependent on KRT from 2008 to 2017 using the National Health Insurance System of Republic Korea. Fractures were occurred in 8995 (17.04%) of 52,777 patients with ESKD. Hemodialysis and kidney transplant patients had the highest (57.4 per 1000 person-year) and the lowest (25.2 per 1000 person-year) incidence rate, respectively. The two most common fracture sites were the lower limb and upper limb, regardless of KRT modality. The first fractures were about 2.55 ± 2.07 years after KRT initiation, the earliest in Hemodialysis patients. Diabetes mellitus, cerebrovascular disease, chronic lung and liver disease were risk factors of fractures. The use of steroids, anti-osteoporosis medications, and some classes of psychotropics and opioids was associated with an elevated risk. The results of this study inform the understanding of fractures in KRT patients.
<p>The maritime sector is one of the most efficient freight modal options in terms of emissions per tonnage transported per kilometer. However, alongside aviation, it is one of the most challenging transportation sectors to be decarbonized. Among the possible mitigation options are a switch towards less carbon-intensive fuels. However, the adoption of a global strategy towards cleaner fuels is not possible before fully understanding the climate implications throughout their entire life cycle. For such assessment at a global level, reliable and robust emission inventories are necessary. For this purpose, we present a novel bottom-up assessment of emissions of greenhouse gases (GHGs) and aerosols (NOx, SOx, CO, OC, EC and BC) in the maritime sector. Our high-resolution, data-driven emission inventory comprises a baseline of emissions for the year 2017, in which the global fleet has a fuel mix of heavy-fuel oil (HFO) and marine diesel oil (MDO). In addition, we present three scenarios in which the global fleet runs in its entirety with one of the potential fuel substitutes; i) Low-Sulphur diesel, ii) Liquefied-natural gas (LNG), and iii) Ammonia.</p><p>These emission inventories are developed through the use of the state-of-the-art MariTEAM model, which combines ship satellite data (AIS), historical weather data, and individual ship information in its emissions calculations. Additionally, the emissions resulting from the fuel production and processing life cycles are included and presented geospatially, resulting in a full &#8216;well-to-wake&#8217; emission inventory. The spatiotemporal inventories for the alternative scenarios reveal that technology used in the fuel production, the weather, and heavy traffic regions all have a significant environmental impact on the overall emissions, both globally and regionally, highlighting the importance of measuring and modelling this correctly. Results show that a full transition towards LNG could achieve a reduction in terms of global warming potential (GWP100) of 21% and, in the case of ammonia, around 88%. The emission inventories also allow us to estimate the global annual efficiency ratio for each alternative fuel combining upstream and downstream emissions, indicating the need for more comprehensive metrics for designing appropriate policies aiming at net-zero emissions by 2100.</p>
Vessels experience additional resistance by waves during navigation, which becomes a factor that increases energy consumption and exhaust gas emissions. Proper estimation and understanding of this additional resistance is an important task in the marine industry. In this study, we propose a machine-learning model that predicts added resistance in arbitrary wave headings using basic ship parameters. First, extensive model experimental data on added resistance for different ship types and sizes of ships were acquired. To build a proper machine learning model, algorithms such as extreme gradient boosting (XGB), random forest (RF), artificial neural network (ANN), k-nearest neighbor (ANN), gaussian process regression (GPR), and support vector regression (SVR) were considered. Through nested cross-validation, the evaluation and hyperparameter tuning of algorithms were performed together. As a result, SVR was selected among the candidate models due to high accuracy with robustness to the outliers. In the validation with test data of head waves and all wave headings, the R2 scores of the selected model were 0.6738–0.7584 and 0.6744–0.7449, respectively, which was better than estimation methods for added resistance in head waves such as STAWAVE-2 and Cepowski (2020), and similar accuracy to those applicable in arbitrary wave headings. Even estimation of added resistance in irregular waves of sea states, the relative deviation with the semi-empirical methods for arbitrary waves was not large, on average 10%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.