A5034858546- Atmospheric aerosols and clouds
- Meteorological Phenomena and Simulations
- Atmospheric chemistry and aerosols
- Asphalt Pavement Performance Evaluation
- Infrastructure Maintenance and Monitoring
- Arctic and Antarctic ice dynamics
- Reservoir Engineering and Simulation Methods
- Seismology and Earthquake Studies
- Computational and Text Analysis Methods
- Climate change and permafrost
- Explainable Artificial Intelligence (XAI)
- Advanced Data Processing Techniques
- Ethics and Social Impacts of AI
- Scientific Computing and Data Management
- Aeolian processes and effects
- Solar Radiation and Photovoltaics
- Cryospheric studies and observations
- Risk Perception and Management
- Icing and De-icing Technologies
Albany State University
2019-2024
University at Albany, State University of New York
2019-2024
NSF National Center for Atmospheric Research
2019
University of Wyoming
2019
Vehicle Technologies Office
2018
Abstract Demands to manage the risks of artificial intelligence (AI) are growing. These demands and government standards arising from them both call for trustworthy AI. In response, we adopt a convergent approach review, evaluate, synthesize research on trust trustworthiness AI in environmental sciences propose agenda. Evidential conceptual histories reveal persisting ambiguities measurement shortcomings related inconsistent attention contextual social dependencies dynamics trust....
Abstract Robust quantification of predictive uncertainty is a critical addition needed for machine learning applied to weather and climate problems improve the understanding what driving prediction sensitivity. Ensembles models provide estimates in conceptually simple way but require multiple training prediction, increasing computational cost latency. Parametric deep can estimate with one model by predicting parameters probability distribution does not account epistemic uncertainty....
Abstract A vast amount of ice crystal imagery exists from a variety field campaign initiatives that can be utilized for cloud microphysical research. Here, nine convolutional neural networks are used to classify particles into regimes on over 10 million images the Cloud Particle Imager probe, including liquid and frozen states with evidence riming. transfer learning approach proves Visual Geometry Group (VGG-16) network best classifies respect multiple performance metrics. Classification...
Abstract The Ice Particle and Aggregate Simulator (IPAS) is used to theoretically represent the aggregation process of ice crystals. Aggregates have a variety formations based on initial particle size, shape, falling orientation, all which influence water phase partitioning. dimensional properties density changes are calculated for monomer–monomer (MON–MON), monomer–aggregate (MON–AGG), aggregate–aggregate (AGG–AGG) collection be by ice-microphysical models improvement in parameterizations....
Abstract Aggregation, the process by which two or more ice particles attach to each other, is typically observed in clouds that span a range of temperatures and influenced crystal shape (habit). In this study, resulting characteristics ice–ice two-monomer aggregation investigated, expected improve microphysical parameterizations through precise aggregate turn better predict rate snow development. A systematic way determine aspect ratio was developed, takes into account falling orientations,...
Abstract Bulk ice-microphysical models parameterize the dynamic evolution of ice particles from advection, collection, and sedimentation through a cloud layer to surface. Frozen hydrometeors can grow acquire multitude shapes sizes, which influence distribution mass within systems. Aggregates, defined herein as collection particles, have variety formations based on initial particle size, shape, falling orientation, number that collect. This work focuses using Ice Particle Aggregate Simulator...
Abstract A novel methodology for modeling ice–ice aggregation is presented. This combines a modified hydrodynamic collection algorithm with bulk aggregate characteristic information from an offline simulator that collects ice particles, namely, the Ice Particle and Aggregate Simulator, has been implemented into Adaptive Habit Microphysics scheme in Weather Research Forecasting Model. Aggregates, or snow, are formed via of cloud where initial characteristics resulting geometry determine...
Abstract Artificial intelligence (AI) and machine learning (ML) pose a challenge for achieving science that is both reproducible replicable. The compounded in supervised models depend on manually labeled training data, as they introduce additional decision‐making processes require thorough documentation reporting. We address these limitations by providing an approach to hand labeling data ML integrates quantitative content analysis (QCA)—a method from social research. QCA provides rigorous...