Hydropower is a superior energy extraction approach, which has been made to work based on renewable energy sources. In the generation of hydropower, Gravitational Vortex Hydropower (GVHP) plays a predominant contributor role because of its free turbulence-relayed energy utilization concept and flexible as well as compact size. Owing to the huge contribution of GVHP in the hydropower sector, multi-objective-based investigations have emerged. However, there is still insufficient literature available for the technology to precede optimum turbine blade design. Two important categories are involved in these multidisciplinary investigations, in which the first phase, a numerical investigation has been done using ANSYS to identify the location of maximum tangential velocity in a conical basin with different notch angles, conical angles, basin shapes, anddiameters. In this second phase, the focal aim is to carry out the numerical investigation on Gravitation Vortex Turbine Blades (GVTB) for the different geometry in order to get the optimum power output with a high structural lifetime through HSI (Hydro–Structural Interaction) computation. The entire conceptual designs of this SGVHP and its hydro-rotors are modeled with the help of CATIA. ANSYS Fluent is a CFD (Computational Fluid Dynamics) numerical tool, which is primarily used in this paper for all the hydrodynamic analyses. Finally, the standard analytical approaches are used for the comparative determinations of thrust production by hydro-rotors, power extraction by hydro-rotors, and propulsive efficiency for the selection process of best hydro-rotors. HSI analyses are additionally carried out and thereby the suitable lightweight material is picked.

We tested selecting data randomly or proportionally in class imbalanced sample. Collecting data into the training and test set according to the initial ratio of QSOs, galaxies and stars were rec-ommended. We experimented using the original imbalanced data or introducing the class balance technologies: SMOTE, SMOTEENN, SMOTETomek, ADASYN, BorderlineSMOTE1, Border-lineSMOTE2, and RandomUndersampling. The SMOTEENN performed the best in the Sample 1. The LightGBM, CatBoost, XGBoost, and RF were compared when adopting the SMOTEENN using the petroMag_u, petroMag_g, petroMag_r, petroMag_i, petroMag_z, J, H, Ks, W1, W2, W3, W4 magnitudes as features. All of the precisions or recalls exceeded 0.94. The RF cost a little more time than the other three algorithms, but resulted in the best evaluating indicators. Utilizing the SMOTEENN +RF technology, the precision, recall and f1-score for QSOs (galaxies, stars) could achieve 0.98 (0.99, 0.98), 0.99 (0.96, 1.00), 0.98 (0.97, 0.99) respectively in Sample 1. Utilizing the SMOTEENN +RF technology, the precision, recall and f1-score for QSOs (galaxies, stars) could achieve 0.94 (0.96, 0.96), 0.98 (0.90, 0.97), 0.96 (0.93, 0.97) using the petroMag_u, petroMag_g, petroMag_r, petroMag_i, petroMag_z, W1, W2, W3, W4 magnitudes as features.