IGM simulates the ice dynamics, surface mass balance, and its coupling through mass conservation to predict the evolution of glaciers, icefields, or ice sheets. The specificity of IGM is that it models the ice flow by a Neural Network, which is trained from ice flow physics. Doing so permits to speed-up and facilitate considerably the implementation of the forward model and the inverse model required to assimilate data. As a result, IGM permits user-friendly, highly-efficient, and mechanically state-of-the-art glacier simulations with data assimilation / inversion capability. IGM is a modular open-source Python package, which runs across both CPU and GPU and deals with two-dimensional gridded input and output data.
IGM's documentation can be found on the dedicated wiki.
The easiest and quickest way is to get to know IGM is to run notebooks in , which offers free access to GPU, or to install IGM on your machine, and start with examples.
Feel free to drop me an email for any questions, bug reports, or ideas of model extension: guillaume.jouvet at unil.ch