Загрузка страницы

Joshua Schrier - Creating Complex Scientific Workflows that Reach into the Real World - IPAM at UCLA

Recorded 02 May 2023. Joshua Schrier of Fordham University presents "Creating Complex Scientific Workflows that Reach into the Real World" at IPAM's workshop for Complex Scientific Workflows at Extreme Computational Scales.
Abstract: A growing field of laboratory automation attempts to give computational workflows "hands" and "eyes" in the laboratory. Achieving this goal requires specifying unambiguous machine-readable experiments plans, capturing comprehensive data and metadata during experiments, and processing the collected data into a form suitable for machine-learning. While one platonic ideal would have a completely autonomous ("closed loop" or "self-driving") experimental workflow, in practice, most experiments involve islands of automation with varying amounts of sample preparation done by human technicians who must also be instructed and given an opportunity to capture data.
In this talk, I will talk about our experience in developing the open-source ESCALATE (Experiment Specification, Capture And Laboratory Automation TEchnology) data management software. The core motivation was to create an abstraction layer for experiment planning algorithms that abstracts away the details of how to tell the humans and machines what to do and capture and interpret those results. We've tested this in the context of distributed, partially-automated syntheses of halide perovskites. To facilitate machine learning, we include packages for automatically adding cheminformatics descriptor featurizations to the data. Interaction can occur either through a web-based GUI or through a REST-API, allowing for both human and computer-based experiment specification and data abstraction. We've tested this on several projects, including a distributed "bakeoff competition" in which third-party participants competed in directing new exploratory synthesis experiments. I will conclude by reflecting on the challenges of developing and maintaining software like this in small academic groups.
Learn more online at: hhttp://www.ipam.ucla.edu/programs/workshops/workshop-iii-complex-scientific-workflows-at-extreme-computational-scales/

Видео Joshua Schrier - Creating Complex Scientific Workflows that Reach into the Real World - IPAM at UCLA канала Institute for Pure & Applied Mathematics (IPAM)
Показать
Комментарии отсутствуют
Введите заголовок:

Введите адрес ссылки:

Введите адрес видео с YouTube:

Зарегистрируйтесь или войдите с
Информация о видео
3 мая 2023 г. 6:27:23
00:48:36
Другие видео канала
Justin Smith - The state of neural network interatomic potentials - IPAM at UCLAJustin Smith - The state of neural network interatomic potentials - IPAM at UCLARichard Hennig & Jason Gibson - AI-driven workflows for the discovery of novel superconductorsRichard Hennig & Jason Gibson - AI-driven workflows for the discovery of novel superconductorsJames Corbett - Flux: a next generation resource manager for HPC and beyond - IPAM at UCLAJames Corbett - Flux: a next generation resource manager for HPC and beyond - IPAM at UCLAJuliane Mueller - Adaptive Computing and multi-fidelity learning - IPAM at UCLAJuliane Mueller - Adaptive Computing and multi-fidelity learning - IPAM at UCLAMichele Ceriotti - Machine learning for atomic-scale modeling - potentials and beyond - IPAM at UCLAMichele Ceriotti - Machine learning for atomic-scale modeling - potentials and beyond - IPAM at UCLAAurora Clark - high-dimension perspective on extracting & encoding information in chemical systemsAurora Clark - high-dimension perspective on extracting & encoding information in chemical systemsRalf Drautz - From electrons to the simulation of materials - IPAM at UCLARalf Drautz - From electrons to the simulation of materials - IPAM at UCLASamuel Blau - High-Throughput DFT and Monte Carlo for Reaction Networks and Machine LearningSamuel Blau - High-Throughput DFT and Monte Carlo for Reaction Networks and Machine LearningAmit Acharya - Slow time-scale behavior of fast microscopic dynamics - IPAM at UCLAAmit Acharya - Slow time-scale behavior of fast microscopic dynamics - IPAM at UCLAFrederic Legoll - Parareal algorithms for molecular dynamics simulations - IPAM at UCLAFrederic Legoll - Parareal algorithms for molecular dynamics simulations - IPAM at UCLABoris Kozinsky - Uncertainty-aware machine learning models of many-body atomic interactionsBoris Kozinsky - Uncertainty-aware machine learning models of many-body atomic interactionsThomas Swinburne - Learning uncertainty-aware models of defect kinetics at scale - IPAM at UCLAThomas Swinburne - Learning uncertainty-aware models of defect kinetics at scale - IPAM at UCLAJames Kermode - Multiscale and data-driven methods for the simulation of material failureJames Kermode - Multiscale and data-driven methods for the simulation of material failureChristoph Ortner - Atomic Cluster Expansion with and Without Atoms - IPAM at UCLAChristoph Ortner - Atomic Cluster Expansion with and Without Atoms - IPAM at UCLARobert Lipton - Fracture as an emergent phenomenon - IPAM at UCLARobert Lipton - Fracture as an emergent phenomenon - IPAM at UCLAMaria Emelianenko - Integrating multiscale materials modeling w/ interpretable automation techniquesMaria Emelianenko - Integrating multiscale materials modeling w/ interpretable automation techniquesYekaterina Epshteyn - Multiscale modeling and analysis of grain growth in polycrystalline materialsYekaterina Epshteyn - Multiscale modeling and analysis of grain growth in polycrystalline materialsFlorin Bobaru - Peridynamic fracture across scales: large scale computations with fast methodsFlorin Bobaru - Peridynamic fracture across scales: large scale computations with fast methodsXiantao Li - A stochastic algorithm for self-consistent calculations in DFT - IPAM at UCLAXiantao Li - A stochastic algorithm for self-consistent calculations in DFT - IPAM at UCLAGabor Csányi - Machine learning potentials: from polynomials to message passing networksGabor Csányi - Machine learning potentials: from polynomials to message passing networks
Яндекс.Метрика