Earth scientists spend numerous hours coding and exploring new technologies leading to ML-based scientific discovery. However, many efforts involving ML workflows developed in universities and research institutes are incomplete or not reproducible. Geoweaver (Sun et al., 2020) is an open-source workflow management tool that saves the history of ML model runs together with the source code and the output logs in a local database (two portable files under home directory) that can be shared with others. Geoweaver is a user-friendly tool that has been designed with the scientist's needs in mind. The workflow automation, provenance recording, history exportation, are completely under the hood, allowing scientists to focus on problem solving and information extraction without worrying about potential loss of their experiment history or source code. Using Geoweaver is a long term investment and will make every scientist' work fresh, preserved and understandable even years after the original experiments.
GStatSim is a Python package specifically designed for geostatistical interpolation and simulation. It is inspired by open source geostatistical resources such as GeostatsPy and SciKit-GStat. The functions are intended to address the challenges of working with datasets with large crossover errors, non-linear trends, variability in measurement density, and non-stationarity. These tools are part of our ongoing effort to develop and adapt open-access geostatistical functions.
