Mega AI seeks to develop massive-scale, self-supervised, multimodal foundation models of scientific knowledge capable of general-purpose inferences to enable reasoning with existing knowledge and discovery of new knowledge.
PNNL's Ocean Dynamics Modeling group studies coastal processes such as marine-hydrokinetic energy, coastal circulations, storm surge and extreme waves, tsunamis, sediment transport and nutrient-macroalgal dynamics.
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.
PREPARES demonstrates linkages between climate or weather conditions and human domain systems by combining quantitative geophysical data with qualitative data.
The user-friendly Project Schedule Visualizer software developed at PNNL helps users readily identify and understand the impacts of updates to the schedule, budget, and risks associated with large, complex projects that cross departments.
PNNL combines AI and cloud computing with damage assessment tools to predict the path of wildfires and quickly evaluate the impact of natural disasters, giving first responders an upper hand.
The RD2C laboratory-directed research initiative seeks to develop resilient, adaptive, and intelligent sensing and control algorithms through the observational understanding and characterization of CPSs under adverse conditions.
PNNL has developed performance assessment guidance for remediation of volatile contaminants in the vadose zone, inorganic contaminant remediation in the vadose zone, and pump-and-treat of groundwater contaminant plumes.
PNNL's River Corridor Hydrobiogeochemistry Scientific Focus Area works to transform understanding of spatial and temporal dynamics in river corridor hydrobiogeochemical functions from molecular reaction to watershed and basin scales.
Powered by few-shot learning, the Sharkzor AI-driven, scalable web application makes it possible to quickly characterize and sort electron microscopy images used to analyze radioactive materials.
The Suite Of Comprehensive Rapid Analysis Tools for Environmental Sites online tools provide rapid data analytics and visualization of environmental data supporting remedy decisions, optimization, and exit strategies.
STOMP is a suite of numerical simulators for solving problems involving coupled flow and transport processes in the subsurface. The suite of STOMP simulators is distinguished by application areas and solved mathematical equations.
The TRAC web tool displays the environmental remediation status—and metrics about progress toward closure—for cleanup sites overseen by the DOE Office of Environmental Management.
PNNL has developed a tool suite of interactive analytics that can be rapidly integrated into analyst workflows to empirically analyze and gain qualitative understanding of AI model performance jointly across dimensions.