Leakage-aware machine learning with physics-based features for propeller performance prediction and conformal uncertainty quantification
Open Access
- 25 October 2026
- journal article
- Published by Elsevier in Results in Engineering
- Vol. 32
Abstract
No abstract availableFunding Information
- College of Petroleum Engineering and Geosciences, King Fahd University of Petroleum and Minerals
This publication has 24 references indexed in Scilit:
- Physics-guided residual learning for predicting aerodynamic characteristics of 3D wing under diverse operating conditionsAerospace Science and Technology, 2026
- A detailed geometry-free approach for propeller performance prediction using machine learning modelsAerospace Science and Technology, 2026
- Multi-dimensional analysis of the hybrid profiled propeller of a pentacopter UAV: Aerodynamic, aero-acoustic, and structural parametric estimations utilizing synergistic engineering approachesResults in Engineering, 2025
- Experimental study on efficient propulsion system for multicopter UAV design applicationsResults in Engineering, 2023
- Leakage and the reproducibility crisis in machine-learning-based sciencePatterns, 2023
- Comparison studies on aerodynamic performances of a rotating propeller for small-size UAVsAerospace Science and Technology, 2023
- Aerodynamic optimization of a VTOL drone using wingletsResults in Engineering, 2023
- Surrogate models for predicting noise emission and aerodynamic performance of propellersAerospace Science and Technology, 2022
- Tabular data: Deep learning is not all you needInformation Fusion, 2022
- Data-driven modeling for unsteady aerodynamics and aeroelasticityProgress in Aerospace Sciences, 2021