Kshitij Mehta Computer Scientist Contact 865.574.1739 | MEHTAKV@ORNL.GOV All Publications Scalable training of trustworthy and energy-efficient predictive graph foundation models for atomistic materials modeling: a case study with HydraGNN MDLoader: A Hybrid Model-Driven Data Loader for Distributed Graph Neural Network Training Scaling Ensembles of Data-Intensive Quantum Chemical Calculations for Millions of Molecules MDLoader: A Hybrid Model-driven Data Loader for Distributed Deep Neural Networks Training... Deep learning workflow for the inverse design of molecules with specific optoelectronic properties... DDStore: Distributed Data Store for Scalable Training of Graph Neural Networks on Large Atomistic Modeling Datasets Two excited-state datasets for quantum chemical UV-vis spectra of organic molecules Computational Workflow for Accelerated Molecular Design Using Quantum Chemical Simulations and Deep Learning Models Running Ensemble Workflows at Extreme Scale: Lessons Learned and Path Forward Scalable training of graph convolutional neural networks for fast and accurate predictions of HOMO-LUMO gap in molecules A codesign framework for online data analysis and reduction Official Report on the 2021 Computational and Autonomous Workflows Workshop (CAW 2021) A Community Roadmap for Scientific Workflows Research and Development Reusability First: Toward FAIR Workflows DYFLOW: A flexible framework for orchestrating scientific workflows on supercomputers The Exascale Framework for High Fidelity coupled Simulations (EFFIS): Enabling whole device modeling in fusion science Data Federation Challenges in Remote Near-Real-Time Fusion Experiment Data Processing Visualization as a Service for Scientific Data ADIOS 2: The Adaptable Input Output System. A framework for high-performance data management Extending the Publish/Subscribe Abstraction for High-Performance I/O and Data Management at Extreme Scale... Understanding Performance-Quality Trade-offs in Scientific Visualization Workflows with Lossy Compression... A Co-Design Study Of Fusion Whole Device Modeling Using Code Coupling Understanding Performance-Quality Trade-offs in Scientific Visualization Workflows with Lossy Compression A Codesign Framework for Online Data Analysis and Reduction Data Management Challenges of Exascale Scientific Simulations: A Case Study with the Gyrokinetic Toroidal Code and ADIOS... Pagination Current page 1 Page 2 Next page ›â¶Äº Last page Last » Key Links
