Lecturer: Dr. Zhenlong Li
Platform: ZOOM Meeting
Class time: 08:00PM-11:00PM, August 22-29, 2021 (EDT/UTC-4)
Language: English
Course description: Geospatial big data plays a major role in the era of big data, as most data today are inherently spatial, collected with ubiquitous location-aware sensors. Efficiently collecting, managing, storing, and analyzing geospatial data streams enables development of new decision-support systems and provides unprecedented opportunities for advancing knowledge discovery and decision making to support domain applications including disaster management, climate change, human mobilities, and public health. In disaster management, traditional data collection methods such as remote sensing and field surveying often fail to offer timely information during or immediately following disaster events. Social sensing enables all citizens to become part of a large sensor network, which is low cost, more comprehensive, and always broadcasting situational awareness information. Meanwhile, data collected with social sensing is inherent “Big Data” as they are often massive, noisy, and comes in continuous streams. For example, during a disaster event, millions of micro-level disaster information (e.g. site specific damage) can be captured in real-time through social media platforms (e.g. Twitter) and voluntarily reported via dedicated crowdsourcing applications (volunteered geographic information, VGI), enabling rapid assessment of evolving disaster situations. Efficient collection, management, analysis, and visualization of social media data is critical for using social sensing to understand the impact of and response to the disaster events in a timely fashion.
This short summer school course will 1) provide students with an overview of the concept of geospatial big data and relevant computing technologies for handling such data, 2) discuss the concept of social sensing and social media data analytics as well as its applications with regards to disaster management, and 3) introduce some basic and practical steps/programming techniques (Python, JavaScript, and web mapping) for geotagged Twitter data analysis from data collection to online visualization (with hands-on exercises).
Course Structure: This course will be delivered online using a mix of approaches, including lectures, readings, discussions, demonstrations, hands-on exercises, and paper writing. Students will need to install Python, Tomcat, Eclipse, and JDK on their computers (preferably Windows) for the hands-on exercises. Installation instructions will be provided.
Upon the completion of the course, students are expected to:
l Understand the concepts, challenges, and opportunities of big data in geospatial domains.
l Grasp the progress and trend in using social sensing and big data computing for disaster management, including applications, challenges, and solutions.
l Obtain basic understanding and technique skills in geotagged social media data analysis.
Course outline:
1. Introduction to social sensing and big data computing for disaster management
2. Geospatial big data and computing techniques
3. Social media (Twitter) data collection and analytics with Python and Hadoop (with hands-on exercises)
4. Web mapping of social media data with JavaScript and Leaflet: introduction and basics (with hands-on exercises)
5. Web mapping of social media data with JavaScript and Leaflet: trajectory mapping (with hands-on exercises)
