GeoPython 2021

On the role of packaging in GIS, or: How to drive computer clusters and GPUs from within desktop GUI applications for non-technical users
2021-04-23, 17:30–18:00, Track 1

There is a growing discrepancy between what FOSS GIS GUI applications are capable of and what the contemporary (geo-) Python stack can do. While the latter is clearly much more powerful, it requires extensive and constantly growing software development skills. This talk looks at ways of how to (re-) connect the two worlds, especially for non-technical users through the means and recent advances in software packaging.

Broad software development skills are becoming a hard requirement for potential (scientific) users of the Free and Open Source Software (FOSS) ecosystem around Geographic Information System (GIS). There is a clear boundary between what can be done with Graphical User Interface (GUI) applications such as QGIS only and contemporary software libraries – if one actually has the required skillset to use the latter. Far more than just rudimentary programming development skills are usually required, however, which are difficult to acquire and distract from the actual scientific work at hand. Installation and deployment on their own of much desired high-performance computing (HPC) software libraries for e.g. general-purpose computing on graphics processing units (GPGPU) or computations on clusters or cloud resources are very often show-stoppers. Recent advances in Python packaging and deployment systems ease the situation and enable a new kind of thinking. Desktop GUI applications can now much more easily be combined with the mentioned type of libraries, which lowers the entry barrier to HPC applications and the handling of large quantities of data drastically. This talk aims at providing an overview over where we are at the moment and what is practically and theoretically possible down the road.