Thursday, December 6, 2018

Locational intelligence through Geoinformatics and AI?

People use computers in their everyday life. From navigation systems to shopping planners and smart houses our life is affected more and more by intelligence systems. But how are such systems working and what will it mean to society?
Artificial intelligence (AI) is the ability of a computer programme or a machine to think logically, solve problems and to learn. In practice however, most applications have picked on problems which computers can do well. Searching data bases and doing calculations are things computers do better than people. On the other hand, "perceiving its environment" in any real sense is way beyond present-day computing. Generally speking, an ideal intelligent machine mimics human cognition. AI involves many different fields like computer science, mathematics, linguistics, psychology, neuroscience, and philosophy.

Researchers from the Department of Geoinformatics - Z_GIS at the University of Salzburg and computer scientists from the University of Klagenfurt critically discussed recent developments of AI for locational intelligence. The main goal of the workshop was to describe and analyze various “intelligent” methods related to natural language processing (NLP) and spatial information. They identified five major topics:

Sentiment analysis
Sentiment analysis is an essential part of Natural Language Processing, which focuses on determining whether the attitude of a piece of text on a particular topic is either positive, negative or neutral. Markus’ work focuses on evaluating the most cutting-edge technologies in sentiment analysis. In particular, he developed a benchmark tool that measures the accuracy, performance and ratio between those qualities and it supports both English and German language.

Topic Modeling
A system was presented that collects news from various sources (blogs, news sites, etc.) categorized based on the specific topic they refer to. Topics are derived by crawling a predefined set of sources various times a day, which results in a corpora for headlines. The process followed extends the traditional bag-of-words search of articles by taking into consideration queries that focus on word order and various regular expression techniques.

Localization based on textual information
Only in some cases text messages can unambiguously be assigned to a location. While there are many methods to retrieve the meaning or the sentiment of a short message like a tweet, localization is still challenging. Recent research demonstrates for extreme events such as floods or Earthquakes that it is possible to construct a spatial footprint of a large body of messages mentioning such events or related keywords.

Pattern Recognition of Places
Traditional search of places (e.g. using Google Maps) is performed using simple sets of keywords. This approach is limited since it cannot identify features of place that go beyond place names, such as activities and purposes. To address this, a novel place search process is proposed based on pattern-based representation. Patterns are derived through a combination of knowledge extraction from narratives and probabilistic machine learning based on real world data. 

Human Trajectories
Most humans generate spatial traces ones they move. Telecom operators always know where customers are but are of course reluctant to give away personal information. However, some providers started to provide generalized and anonymized data which can still provide the base for analyses which aim to understand flows in cities. But many users provide their spatial footprints voluntarily or unknowingly through their activities in social media. This data help scientists to understand movement pattern but trigger research on geo-privacy.

Contact Person: Thomas Blaschke

Monday, November 26, 2018

CopHub.AC - a Horizon 2020 project to support the Copernicus Academy

The Horizon 2020 project CopHub.AC – coordinated by Z_GIS - started in October 2018. The vision of CopHub.AC is to establish within the next two years a long-term Copernicus hub to consolidate and sustain the Copernicus Academy as a knowledge and innovation platform. 

With 13 European partners involved from academia and industry, including associations from the GI / EO sector, the project pursues specific activities on developing a knowledge landscape, new formats of research briefs, outreach and sustainability. It will focus and link ongoing R&D activities on Copernicus-relevant fields on a high scientific level to make the Copernicus Academy sustainable.

Together with the “sister project” CoRdiNet, similarly supporting the Copernicus Relays, the joint Kick-off meeting took place at Research Executive Agency (REA) and NEREUS Secretariat in Brussels on 11th and 12th of October with in total more than 30 participants from all over Europe discussing and planning project-specific and joint activities.

Project Coordination: Stefan Lang, University of Salzburg, Z_GIS
Contact: Stefan Lang, Barbara Riedler

Tuesday, November 20, 2018

Successful PhD defence

Gyula Kothencz, PhD student within the Doctoral College „GIScience“ successfully defended his PhD „Data and information development methodologies for green urban area planning and management“.

In his dissertation, Gyula developed methodologies to map objective and perceived green space characteristics as well as to produce cost-effective urban vegetation height maps from satellite imagery.

The research is comprised of three methodologies. Firstly, Gyula investigated the correlation between green space visitors‘ perceptions and spatial green space indicators. Then, he predicted the influence of perceived green space characteristics on two indicators describing human well-being, which are green space visitors‘ level of satisfaction and quality of life contribution of the green spaces. In this research he investigated also the potential of geo-tagged photographs and running trajectories from park users. The study confirmed correlations between visitors‘ subjective evaluations of green spaces and the examined objective, a.k.a. measurably spatial indicators of the study areas. One applied research article showed already the value for urban planners and decision makers to be able to include subjective human perception of green spaces in planning. The developed methodologies and the results are being practically applied in two similarly sized European cities, Salzburg, Austria and Szeged, Hungary in decision support projects concerned with green urban areas.

We wish Gyula all the best on his future road of life!

‘Perfection’ vs. ‘good enough’ in Information Management - GeOnG 2018

Z_GIS was invited to the GeOnG Forum in Chambéry, France on the 29 October – 31 October 2018 to present a workshop on the humanitarian service Z_GIS is providing to NGOs since 2011. 200 GIS experts and managers from Europe and Africa attended the  biannual event. The GeOnG forum address issues related to data in the humanitarian & development sectors, including topics related to mapping, GIS, data collection & information management. This year, the Forum focused on “‘Perfection’ vs. ‘good enough’ in Information Management – Adjusting to context, scale, phase and funding”. In the context of a machine learning session, Gina Schwendemann presented the workshop: “Extraction of dwellings in refugee camps: how to do it and what it tells you”. Participants learned to object based image analysis (OBIA) in exercises related to the visualization of dwelling density and dwelling change detection in ArcMap. In a live demonstration of dwelling extraction in the refugee camp Minawao, Cameroon, it was demonstrated how the humanitarian office of Z_GIS use them for population estimation in order to supply medical-, food- and shelter logistics in remote places which cannot be found in OpenStreetMap.

Wednesday, November 7, 2018

'Copernicus Master in Digital Earth' - New E+ EMJMD Programme

The 'Copernicus Master in Digital Earth - CDE' initiative, a joint Erasmus+ Key Action 1 project, has been kicked off at the coordinator's site 'Z_GIS' in Salzburg. This joint study programme responds to the current need of highly qualified specialists in the fields Geoinformatics / Geo and Earth Observation / Space. The two year full-time integrated Erasmus Mundus Joint Master Degree (EMJMD) Programme will start in the academic year 2019/2020. A first call for application of admission and E+ scholarships will be published soon.

One starting place for all students aims to establish a strong common denominator and core Geoinformatics competencies for the CDE Master of Science Study Programme. MSc students start their studies at the University of Salzburg, Department of Geoinformatics - Z_GIS for the first two semesters, before continuing towards developing a special flavor at one of the partner universities:
Jointly, these tracks offer outstanding candidates a pathway towards excellence in advanced Geoinformatics addressing the Copernicus and Digital Earth missions and objectives.

The consortium currently consists of thirteen partners, with three core academic partners in Europe who are offering double degrees, and several associated partners, who bring added value to faculty and students: Higher Education Institutions provide research facilities and supervision, Industry partners provide internships and scholarships and UNIGIS International provides outreach to students and scholarships.

Project and Joint Programme Co-ordinator:
Josef Strobl, University of Salzburg, Z_GIS
Programme Office: