Yanbu Industrial College

About: Yanbu Industrial College is a based out in . It is known for research contribution in the topics: Photovoltaic system & AC power. The organization has 114 authors who have published 311 publications receiving 2776 citations.

Redox Flow Battery for Energy Storage

Abstract: The redox flow battery has undergone widespread research since the early 1970s. Several different redox couples have been investigated and reported in the literature. Only three systems as such have seen some commercial development, namely the all-vanadium (by VRB-ESS), the bromine–polysulfide (RGN-ESS) and the zinc–bromine (Powercell) systems. The vanadium–bromine system may be an attractive replacement for the all-vanadium system due to its higher energy density with possible applications as energy storage systems for electric vehicles. Other redox flow battery systems have faced problems due to slow electrochemical kinetics of redox couples, membrane fouling, cross-contamination, high costs (mainly due to the membrane as well as inefficient cell stack design), poor sealing, shunt current losses and low energy capacity (due to the use of aqueous electrolytes). One of the main factors limiting further development of the redox flow battery so far is the high costs associated with the ion-exchange membrane. Focussed research in this as well as areas such as reactor characterization and electrode design is necessary to ensure the widespread commercialization of the technology. In this paper, various redox flow systems are discussed historically and technically and the latest developments are compared.

Spatial prediction of landslide susceptibility in western Serbia using hybrid support vector regression (SVR) with GWO, BAT and COA algorithms

Abstract: In this study, we developed multiple hybrid machine-learning models to address parameter optimization limitations and enhance the spatial prediction of landslide susceptibility models. We created a geographic information system database, and our analysis results were used to prepare a landslide inventory map containing 359 landslide events identified from Google Earth, aerial photographs, and other validated sources. A support vector regression (SVR) machine-learning model was used to divide the landslide inventory into training (70%) and testing (30%) datasets. The landslide susceptibility map was produced using 14 causative factors. We applied the established gray wolf optimization (GWO) algorithm, bat algorithm (BA), and cuckoo optimization algorithm (COA) to fine-tune the parameters of the SVR model to improve its predictive accuracy. The resultant hybrid models, SVR-GWO, SVR-BA, and SVR-COA, were validated in terms of the area under curve (AUC) and root mean square error (RMSE). The AUC values for the SVR-GWO (0.733), SVR-BA (0.724), and SVR-COA (0.738) models indicate their good prediction rates for landslide susceptibility modeling. SVR-COA had the greatest accuracy, with an RMSE of 0.21687, and SVR-BA had the least accuracy, with an RMSE of 0.23046. The three optimized hybrid models outperformed the SVR model (AUC = 0.704, RMSE = 0.26689), confirming the ability of metaheuristic algorithms to improve model performance.