Publications

You can also find my articles on my Google Scholar profile.

Journal Articles

Analyzing the impact of charge particle rebound on spherical collector efficiency via explainable machine learning

Powder Technology, 2025

Authors: Abhishek Srivastava, Sagar Kandpal, Bahni Ray, Mayank Kumar, Debabrata Dasgupta

A physics-informed and interpretable machine learning framework integrating 3D Lagrangian particle tracking, LightGBM, SHAP, and Partial Dependence Plots (PDP) to analyze charged particle collection efficiency and rebound dynamics in electrostatic precipitators.

Charged Particle Collection Non uniform electric field Machine Learning Explainable AI Shapley Additive Explanations Particle Dynamics

📄 PDF | DOI | 💻 Code | 📑 BibTeX

Influence of Non-Uniform Electric Field Due to Spherical Collector on Particle Dynamics in Quiescent Air

Journal of Electrostatics, 2024

Authors: Abhishek Srivastava, Debabrat Biswal, Bahni Ray, Mayank Kumar, Debabrata Dasgupta

Experimental and numerical investigation of charged particle dynamics in the non-uniform electric field of a spherical collector, providing insights into particle trajectories, energy budgets, and deposition behavior.

Aerosol Filtration Particle Deposition Electrostatics Charged Collector Computational Fluid Dynamics Particle Dynamics

📄 PDF | DOI | 📑 BibTeX

Under Review & Submitted

Conditioning-dependent variational inference for uncertainty quantification in physics-based inverse problems

Probabilistic Engineering Mechanics, 2026

Authors: Abhishek Srivastava, Arijit Hazra, R. Dubaku

Variational-autoencoder-based posterior approximation for Bayesian inverse problems in heat conduction, benchmarked against MCMC reference posteriors, with a Fisher-Information-Matrix analysis explaining when amortized variational posteriors under- or over-estimate uncertainty.

Bayesian Inverse Problems Variational Inference Variational Autoencoders Uncertainty Quantification Fisher Information Matrix MCMC

📄 PDF

Machine learning-based regime identification and size-resolved optimization of charged-particle capture and rebound on spherical collectors

Powder Technology, 2026

Authors: Abhishek Srivastava, Sagar Kandpal, Bahni Ray, Mayank Kumar, Debabrata Dasgupta

A clustering-guided surrogate-assisted optimization framework integrating LightGBM surrogate modeling, K-means clustering, NSGA-II, TOPSIS, and explainable artificial intelligence to optimize charged particle collection while minimizing particle rebound.

Scientific Machine Learning Surrogate Modeling Multi-objective Optimization NSGA-II K-means Clustering Explainable Artificial Intelligence SHAP Electrostatic Precipitators Particle Rebound TOPSIS

📄 PDF | DOI | 💻 Code | 📑 BibTeX

Conference Papers

Dynamic Characteristics of Submicron Particle Deposited on the Charged Spherical Collector

Proceedings of the 9th International and 49th National Conference on Fluid Mechanics and Fluid Power (FMFP 2022), IIT Roorkee, 2022

Authors: Abhishek Srivastava, Bahni Ray, Mayank Kumar, Debabrata Dasgupta, Rochish Thaokar, Y. S. Mayya

Numerical investigation of the dynamic characteristics of oppositely charged submicron particles approaching a charged spherical collector under a non-uniform electric field.

Electrostatic Scrubbing Charged Spherical Collector Particle Dynamics Submicron Particles Aerosol Collection Electrostatic Forces COMSOL Multiphysics CFD