|TORRES ROCIO NAHIME||Cycle: XXXIII |
Section: Computer Science and Engineering
Tutor: ALIPPI CESARE
Advisor: FRATERNALI PIERO Major Research topic
:Analysis of Geographic Data for Open Data sources enrichment and environmental monitoringAbstract:
Open Source Geographical Information Systems, such as OpenStreetMap (OSM), offers a valuable alternative to proprietary solutions for the development of voluntary environment monitoring systems. However, the quantity and quality of information stored in such systems must be carefully evaluated and the contributions of volunteers must be boosted by means of effective data preparation and engagement methods. To address this issue, an hybrid approach is proposed, in which geographical entities (such as mountain summits, trekking paths, river beds, and other landforms) are automatically discovered by analyzing Open Data sources (such as the NASA SRTM Earth Digital Elevation Model - DEM) and the confidence in the automatically extracted entities is improved by submitting (only) the objects with uncertainty over a threshold to a crowdsourcing step.
Depending on the use case, such the data analysis approaches may exploit heuristic algorithms, which typically depend on multiple manually set parameters and are hard to generalize to different Earth regions. In this research project, I aim to explore the use of Deep Learning methods to train a model capable of identifying geographical entities, which learn hyperparameters from a gold standard data set, and compare learning-based and heuristic methods on large-scale landform recognition tasks; I also aim at developing a web/mobile applications to publish uncertain results within crowdsourcing campaigns for validation and later incorporation of the new objects into open GIS datasets