Stability-Aware Training of Neural Network Interatomic Potentials with Differentiable Boltzmann Estimators

1 code implementation • 21 Feb 2024 • Sanjeev Raja, Ishan Amin, Fabian Pedregosa, Aditi S. Krishnapriyan

As a general framework applicable across NNIP architectures and systems, StABlE Training is a powerful tool for training stable and accurate NNIPs, particularly in the absence of large reference datasets.

FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators

4 code implementations • 22 Feb 2022 • Jaideep Pathak, Shashank Subramanian, Peter Harrington, Sanjeev Raja, Ashesh Chattopadhyay, Morteza Mardani, Thorsten Kurth, David Hall, Zongyi Li, Kamyar Azizzadenesheli, Pedram Hassanzadeh, Karthik Kashinath, Animashree Anandkumar

FourCastNet accurately forecasts high-resolution, fast-timescale variables such as the surface wind speed, precipitation, and atmospheric water vapor.

Weather Forecasting

Multi-Stage Fault Warning for Large Electric Grids Using Anomaly Detection and Machine Learning

no code implementations • 15 Mar 2019 • Sanjeev Raja, Ernest Fokoué

The time series data are first mapped to highly discriminative features by applying dimensionality reduction based on temporal autocorrelation.

Anomaly Detection BIG-bench Machine Learning +9