“Our research is a humble effort towards exploiting the fascinating journey of Machine Learning for solving socially relevant engineering problems and exploit it to the best of our society’s need."
The relentless endeavor in Global Optimization and Knowledge Unearthing Lab (GOKUL) is to develop novel methodologies in optimization/machine learning (ML) and apply them while solving various socially relevant and challenging engineering problems. Applications include optimization of wind/bio-energy/H2 energy production under uncertainty, new alloy discovery, monitoring climate change parameters, fast charging protocols in Li+ battery, optimal vaccine production, crop health monitoring etc.
1. Robust design of wind farms: Criticized for inconsistent outputs, wind farms are designed through our novel forecasting, Large Eddy Simulation & ML based wake modeling and data-driven robust optimization techniques, providing realistic bounds on consistent power generation under uncertainty.
2. Deep Neural Networks for novel materials discovery: Unveiling process-structure-property relationship is deeply involved when explored by experimentation/high fidelity simulation. Deep learning based our inverse optimization approach can be winner.
3. India-wide bio supply chain design: Tapping huge biomass generated in India, this waste-to-wealth generation research talks about how to optimize the entire supply chain through techno-economic-environmental & uncertain factor considerations helping the country’s move towards energy self-reliant.
4. ML driven optimal vaccine production: Challenging batch operation, better control profiles for vaccine production can be achieved through our bioreactor semi-batch optimization offering by Bayesian inference.
1. Gumte, K., Pantula, P. D., Soumitri M. S., Mitra, K., Achieving Wealth from Bio-Waste in a Nationwide Supply Chain Setup under Uncertain Environment through Data Driven Robust Optimization Approach, Journal of Cleaner Production 291, 125702 (2021).
2. Mittal, P., Mitra, K., Kulkarni, K., Optimizing the number and locations of turbines in a wind farm addressing energy noise trade-off: A hybrid Approach, Energy Conversion and Management, 132C, 147-160 (2017).
3. Ravi Kiran, I., Soumitri M. S., Mitra, K., Deep Learning Based Dynamic Behaviour Modelling and Prediction of Particulate Matter in Air, Chemical Engineering Journal, 426, 131221 (2021).