Publications and responsibilities
Discovering Thermoelectric Materials Using Machine Learning: Insights and Challenges
This work involves the use of combined forces of data-driven machine learning models and high fidelity density functional theory for the identification of new potential thermoelectric materials. The traditional method of thermoelectric material discovery from an almost limitless search space of chem...
Numerical investigation of modeling frameworks and geometric approximations on NREL 5 MW wind turbine
The key to the better design of an industrial scale wind turbine is to understand the influence of blade geometry and its dynamics on the complicated flow-structures. An industrial-scale wind turbine can be numerically represented using various approaches (from simpler 2D steady flow to complex 3D w...
Geilo Winter School in eScience on Artificial Intelligence
Lecture notes on "Bias-Variance trade-off in Artificial Intelligence and Support Vector Machine" with tutorials and examples.
Hybrid analytics for drone landing and take-off in urban areas.
Machine learning based investigation of influence of weather on transport mobility.
Current work involves data-driven analysis of travel mobility. For this purpose, traffic counts of cars and bikes at various traffic routes along With the associated weather have been collected in Oslo, Norway. Amongst the 6 machine learning algorithms compared (linear regression, random forest, dec...
A step towards reduced order modelling of flow characterized by wakes using Proper Orthogonal Decomposition
High fidelity simulations of flow can be quite demanding, involving up to O(106) to O(109) degrees of freedom, and several hours or days of computational time, even on powerful parllel architectures. These techniques become prohibitive when expected to deal quickly and efficiently with repetitive so...
Quasi-Static & Dynamic Numerical Modeling of Full Scale NREL 5MW Wind Turbine
Simulations of the National Renewable Energy Laboratory (NREL) 5MW wind turbine under quasi-static Multiple Reference Frame (MRF) and dynamic Sliding Mesh Interface (SMI) methodologies are presented. Two reference zone approach is considered, inertial and moving reference frame. The former contains ...
A full-scale 3D Vs 2.5D Vs 2D analysis of flow pattern and forces for an industrial-scale 5MW NREL reference wind-turbine
NREL 5MW reference turbine, which is a popular, realistic and standardized industrial scale offshore turbine model, is used in this work for understanding the associated flow-complexities and for testing models. For such full-scale wind-turbine, the wish list is towards a accurate real-time predicti...