Usable and explainable models for global-scale, cross-lingual proliferation expertise identification and forecasting.

Pacific Northwest National Laboratory’s (PNNL) Generative AI (GenAI) investment aims to harness this transformative technology to drive innovation across the science, energy, and security research domains.

GeoBOSS is a software library that combines the data-handling capabilities of Spark and the user-friendliness of Python to simplify geospatial analytics and the transition between small-scale research and large-scale operational projects.

PNNL deploys advanced drone systems to tackle the nation’s most pressing challenges in energy, environmental remediation, and national security.

PNNL is heavily engaged in the development and use of mass spectrometry technology across its science, energy, and security missions, from fundamental research through mature operational capabilities.

Advancing the understanding and monitoring of nuclear material processing to accelerate development and qualification of new material systems for national security and nuclear energy.

The Mathematics for Artificial Reasoning in Science (MARS) initiative seeks to complement machine learning and deep learning to advance science.

The Molecular Observation Network is a national open science network designed to produce a comprehensive database of molecular and microstructural information on soil, water, microbial communities, and biogenic emissions.

Pacific Northwest National Laboratory supports innovations in data analytics, instrumentation, and experimental techniques for the Northwest (NW) Biopreparedness Research Virtual Environment (BRaVE) Initiative.

The Pacific Northwest Advanced Compound Identification Center (PNACIC) brings together innovations in integrated chemistry and advanced instrumentation to create a platform for comprehensive, unambiguous identification of metabolites.

The Pacific Northwest Center for Cryo-EM electron microscopy is a user facility operated jointly by PNNL and Oregon Health & Science University.

Physics-informed machine learning (PIML) is a modeling approach that harnesses the power of machine learning and big data to improve the understanding of coupled, dynamic systems.

PNNL data scientists and engineers will be presenting at NeurIPS, the Thirty Fourth Conference on Neural Information Processing Systems, and the co-located Women in Machine Learning workshop, WiML.