View Profile

Pavan Mohan Neelamraju

Wolfson School of Mechanical, Electrical and Manufacturing Engineering · Loughborough University

https://researchid.co/npavanmohan3
@lboro.ac.uk
110Google Scholar Citations
4Google Scholar h-index
2Google Scholar i10-index

Research Interests

His interest sits at the compelling intersection of Applied Machine Learning, Inverse Problems, Physics-Consistent Learning and Signal Processing.

Biography

I am an applied machine learning researcher working on inverse, constrained, and physics-consistent learning for wave-driven and complex engineered systems. My research focuses on integrating physical structure, signal representations, and domain constraints into machine learning models to improve robustness, interpretability, and data efficiency. I am currently pursuing a PhD in Electronic, Electrical and Systems Engineering at Loughborough University (UK). My doctoral work explores learning-enabled modeling and control of reconfigurable wave-based systems for next-generation communication and sensing, while my broader research agenda addresses inverse learning and physically grounded machine intelligence across multiple application domains. My interests span applied ML, signal processing, inverse problems, and wave-based systems, with applications including communications, sensing, seismic modeling, and imaging. I am particularly interested in research that bridges theory, systems,

Education

Doctor of Philosophy: Loughborough University Master of Science: Indian Institute of Technology Madras Bachelor of Technology: SRM University

Recent Google Scholar Publications

  1. A deep learning prediction model for on-site earthquake early warning system in India
    Journal of Seismology 30 (3), 38 , 2026, 2026
  2. An ML-Assisted Recommender for Multi-Shape Patch Antenna Design
    2026 IEEE International Workshop on Antenna Technology (iWAT), 1-4 , 2026, 2026
  3. A System and Method for Simulating and Analysing Surface Bioluminescence
    IN Patent 583,906 , 2026, 2026
  4. Ground Motion Modelling with Bidirectional Liquid Neural Network (Bliqnet)
    Geodata and AI, 100080 , 2026, 2026 | Citations: 2.0
  5. Enhanced Seismic Ground Motion Modeling With Conditional Variational Autoencoder
    Earthquake Engineering and Resilience 4 (2), 178-201 , 2025, 2025

Links