During emergencies in urban areas it is paramount to assess damage to properties, people and the environment. Remote sensing has become the de-facto standard in observing the Earth and its environment. Remote sensing generally refers to the use of space- or air-borne sensor technologies, to detect and classify objects on the Earth (from its surface, atmosphere, and oceans) by means of emitted or reflected electro-magnetic signals.
Despite the abundance of remote sensing observations temporal gaps in the observations are inevitable due to physical limitations of the sensing platforms because atmospheric opacity can limit the propagation of the electro-magnetic radiation used for acquiring data, or other obstructions. Geo-temporal gaps result, for example, in the case of significant storms or remote locations or complex locations where sensors are not available or not tasked with sufficient frequency to capture the desired data for the necessary length of time.
At the same time easy access to novel information streams such as social media and other non-authoritative sources is redefining situation awareness. These streams are diverse, complex and overwhelming in volume, velocity and in the variety of viewpoints they oer. Negotiating these overwhelming streams is beyond the capacity of human analysts. Current research offers some novel capabilities to utilize these streams in new, groundbreaking ways, leveraging, fusing, and filtering this new generation of air, space, and ground-based sensor- generated data
Social media and other non-authoritative sources can be used to ll the gaps in these spatio-temporal data, and augment the initial satellite observations with tweets, photos or videos about an occurring event. These non-authoritative sources generally include data that was either volunteered by citizens (also known as volunteered geographical information or VGI), or collected for purposes other than disaster assessment, such as traffic cameras or mobile phone locations. Due to the spread of the internet to mobile devices, an unprecedented and massive amount of data has become available, often geolocated and often in real-time.
We describe the development of a CyberGIS approach to facilitate teaching the fusion of the heterogeneous spatio-temporal data sets that include remote sensing observations, point measurements from tweets and other VGIs, a digital elevation model and weather variables. This new tool, developed in Python, is developed to couple together within a GIS framework.
Specifically, we developed a Python plugin for QGIS to input and analyze VGI data. QGIS is a cross-platform open source desktop geographic information systems (GIS) application.
The plugin targets TweetTracker and allows to automatically download and display tweets. This implementation allows to easily visualize and perform spatio-temporal analysis of tweets, and display them over remotely sensed imagery.
Additional interfaces with other data sources can be offered as further projects for students. For example, a student might want to integrate Safecast data and overlay radiation data resulting from an accident similar to Fukushima with remotely sensed observations of atmospheric data.
The proposed research is both evolutionary and transformative by suggesting ways to ex- tend current GIS oerings to include the ability to analyzing massive heterogeneous amounts of data, and by providing ideas to further extend the oerings to include CyberGIS as part of the main curriculum
Guido Cervoneis Director of GeoInformatics & Earth Observation Laboratory in the Department of Geography and Institute for CyberScience at the Pennsylvania State University and Associate Professor at the Department of Geography, Institute for CyberScience, GeoVISTA Center The Pennsylvania State University. He is also affiliated faculty in the Research Application Laboratory (RAL) at the National Center for Atmospheric Research (NCAR).
His fields of expertise are geoinformatics, machine learning and remote sensing. His research focuses on the development and application of computational algorithms for the analysis of spatio-temporal remote sensing, numerical modeling and social media “Big Data” related to man-made, technological and environmental hazards. He operates a satellite receiving station for NOAA POES satellites. His research us funded by ONR, DOT, NASA, Italian Ministry of Research and Education, Draper Labs, Stormcenter Communication.
Guido Cervone is a member of the advisory committee of the United National Environmental Programme, division of Disasters and Early Warning Assessment. In 2013 he received the “Medaglia di Rappresentanza” from the President of the Italian Republic for his work related to the Fukushima crisis. He received the 2013 ISNAAF award. He co-chaired the 2010 SIGSPATIAL Data Mining for Geoinformatics (DMG-10) workshop. He served as the program co-chair for the 2008 and 2009 IEEE International Conference on Data Mining (ICDM) Spatial and Spatio-Temporal Data Mining (SSTDM) workshop.
He authored two edited books, over forty fully refereed articles relative to data mining, remote sensing and environmental hazards. In 2010, he was awarded a US patent for an anomaly detection algorithm. His research on natural hazards was featured on TV news and newspapers, on general interest magazines such as National Geographic, and on international magazines.
As Assistant Director of the Pennsylvania University’s Geoinformatics and Remote Sensing Laboratory, Dr. Mark Coletti is actively performing research in the areas of geoinformatics, machine learning, and evolutionary computation. His principal focus is in big data analytics related to natural hazards, particularly that related to volunteered geographic information, as well as discerning interesting patterns of Medicare use. His research has been funded by the ONR and NSF.
Dr. Coletti is the current Chair of the Penn State Postdoctoral Society, and as such is responsible for organizing career enhancement, personal improvement, and social activities for over 460 postdoctoral scholars. He previously worked at George Mason University where he helped develop an evolutionary computation C++ toolkit; a biologically inspired cognitive model for a DARPA Grand Challenge; a Joint Improvised Explosive Device Defeat Organization related multiagent simulation; an Office of Naval Research Multidisciplinary University Research Initiative Office sponsored massive multiagent simulation of pastoral and farming behavior in eastern Africa; and a geospatial extension, GeoMason, for the multi-agent simulation toolkit MASON.
Earlier in his career he also worked as a senior software engineer in the Washington, DC, area on projects for the National Oceanic and Atmospheric Administration, Federal Highway Administration, U. S. Army's Materiel Command, the U. S. Army Topographic Engineering Center, and the United States Geological Survey. These projects included an expert system to correct human sourced sea surface meteorological data, an expert system for validating materiel purchases, a topographic visualization system, a road surface wear calculator, and a toolkit for spatial data format conversion.
He has published over a dozen papers related to evolutionary computation, machine learning, large-scale multiagent simulations, biologically inspired cognitive architectures, and geographic information systems. He has also written a book on GeoMASON that is open source and freely available to the public.
| Attachment | Size |
|---|---|
 SEA_2015_ColettiPluginPresentation.pdf | 2.95 MB |
If you use a non-flash enabled device, you may download the video here
