Welcome to REMI! This site will host a diverse collection of scripting notebooks (Jupyter, Matlab LiveScripts, etc.) for collecting, pre-processing, analyzing, and visualizing materials data. Notebooks are curated using tags aligned to Materials Science and Data Science topics. If you know of notebooks that would be great additions to REMI, please click here. We are also working to integrate a communication platform for holding discussions.
Above you will find links for learning resources, methods to contribute to REMI, upcoming workshops in pertinent fields, and open positions in academia and national labs.
Many scientists would like to apply machine learning to their research, but they don’t know how to start. Typically, we start learning something new by picking up a learning resource (e.g. a textbook or intro paper) and working through some examples. If the examples are particularly useful, we build off of them to solve our own challenges.
REMI emerged from the realization that both experts and novices wanted examples of using machine learning for science. Meanwhile, lots of experts are developing digital notebooks (e.g. Jupyter) to demonstrate step-by-step data collection, pre-processing, analysis and visualization. However, before REMI there were no indexed repositories of notebooks with such examples and no community to maintain, build or learn from these resources. We hope that REMI can fill this gap, enabling scientists to more easily pick up machine learning while also helping to build a community for sharing knowledge, discussing, debating, establish collaborations, and benchmarking methods.