geoweaver_poster_esip_2021_winter.pptx (903.76 kB)
Using Geoweaver to Remember Jupyter Notebook History
posterposted on 2021-01-19, 18:50 authored by Ziheng SunZiheng Sun, Liping Di, Annie BurgessAnnie Burgess, Andrew MagillAndrew Magill, Nicoleta Cristea, Daniel Q. Tong, Xiaogang Ma
Geoweaver is a web system allowing users to easily compose and execute full-stack deep learning workflows via taking advantage of online spatial data facilities, high-performance computation platforms, and open-source deep learning libraries. A new developed feature in Geoweaver allows people to register multiple jupyter servers and one-stop track all the history changes during regular use of jupyter notebooks. The recorded history versions will make it much easier to trace provenance of machine learning experiments. From a long term perspective, Geoweaver will significantly reduce the time cost of machine learning experiments in geosciences, save resources on duplicated experiments, and make machine learning models FAIRable in practice. This poster was presented at the 2021 Earth Science Information Partners (ESIP) Winter Meeting held virtually in January 2021.