The Institute of Cartography and Geoinformation (IKG) of ETH Zurich is one of the oldest university institutes in cartography world-wide. The Chair of Cartography conducts research in the field of cartographic visualization with a focus on cartographic production technologies for topographic and thematic maps, atlases, and interactive web maps. The group aims to maintain and expand the leading position of Swiss cartography by further developing existing cartographic knowledge, as well as mining existing analogous and digital geodata and transferring all of them to new media and fields of application.
The project “EMPHASES: Assessing EMergent PHenomenA in complex Social-Ecological Systems with time series of settlement and habitat networks”, funded by the Swiss National Science Foundation (SNSF), aims at extracting, analyzing and utilizing information from historical maps to better understand the evolution of natural and man-made landscapes in order to unravel underlying laws and patterns. This interdisciplinary project will be carried out jointly by IKG, the Institute for Spatial and Landscape Development (IRL) of ETH Zurich, and the Swiss Federal Institute for Forest, Snow and Landscape Research (WSL). The EMPHASES project will officially start on 1 April 2021.
Within EMPHASES, IKG is looking for a highly motivated doctoral candidatewith a background in geoinformatics, computer science, cartography or a related discipline. The successful candidate will develop methods for the extraction of different feature classes (e.g., forests, buildings) from Swiss historical map series while ensuring their correct geometrical and topological representation in space and time. This will be carried out in close collaboration with two doctoral candidates at IRL who will use the vectorized historical geodata to derive and analyze habitat and settlement networks.
The candidate should have expertise in one or more of the following fields: computer vision, machine learning, computational geometry, cartography, and geographic information science (GIS). Ideally, he/she has demonstrated knowledge in geospatial image analysis using libraries for feature extraction (e.g., OpenCV, tensorflow/keras, pytorch) and vectorization (e.g., gdal/ogr, shapely/fiona) with a thorough understanding of the underlying concepts. Proficiency in at least one programming language (e.g., Python, C++) is required. An understanding of common geospatial data storage concepts (e.g., Shapefile, PostgreSQL/PostGIS) is beneficial. The candidate should be fluent in spoken and written English; knowledge in German is advantageous.