Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Presentation @ ISCRAM 2018

46 views

Published on

This presentation was given at the International Conference on Information Systems for Crisis Response and Management (ISCRAM) held in Rochester, NY, USA.

Citation: Horita, F. E. A., Vilela, R. B., Martins, R. G., Bressiani, D. A., Palmas, G., De Albuquerque, J. P. Determining flooded areas using crowd sensing data and weather radar precipitation: a case study in Brazil. 15th International Conference on Information Systems for Crisis Response and Management (ISCRAM), Rochester, NY, USA, 2018. [PDF]

Published in: Education
  • Be the first to comment

  • Be the first to like this

Presentation @ ISCRAM 2018

  1. 1. Determining flooded areas using crowd sensing data and weather radar precipitation: a case study in Brazil Dr. Flávio E. A. Horita | http://www.flaviohorita.com | CMCC/UFABC, Santo André, Brazil 1 10.11.2017 Flávio E. A. Horita1, Ricardo B. Vilela2, Renata G. Martins2, Danielle A. Bressiani2, Gilca Palma2, João Porto de Abuquerque3 1 CMCC, Federal University of ABC (UFABC), Santo André, Brazil 2 Labs, Brazilian Meteorological Agency, São José dos Campos, Brazil 3 CIM, University of Warwick, Coventry, UK flavio.horita@ufabc.edu.br | http://www.flaviohorita.com Determining flooded areas using crowd sensing data and weather radar precipitation: a case study in Brazil ISCRAM 2018 15th International Conference on Information Systems for Crisis Response and Management
  2. 2. Determining flooded areas using crowd sensing data and weather radar precipitation: a case study in Brazil Dr. Flávio E. A. Horita | http://www.flaviohorita.com | CMCC/UFABC, Santo André, Brazil 2 10.11.2017 ▷ Introduction ▷ Research design ▷ Approach ▷ Methods ▷ Preliminary results ▷ Final remarks Agenda
  3. 3. Determining flooded areas using crowd sensing data and weather radar precipitation: a case study in Brazil Dr. Flávio E. A. Horita | http://www.flaviohorita.com | CMCC/UFABC, Santo André, Brazil 3 10.11.2017 Crowdsourcing and VGI for disaster risk management Introduction Source: Elwood (2008); Goodchild & Glennon (2010); Niko et al., (2011); Horita et al. (2013); Haworth & Bruce (2015) Hard sensors Exploratory teams Social Media Collaborative Platforms
  4. 4. Determining flooded areas using crowd sensing data and weather radar precipitation: a case study in Brazil Dr. Flávio E. A. Horita | http://www.flaviohorita.com | CMCC/UFABC, Santo André, Brazil 4 10.11.2017 Categories of crowdsourcing Introduction ▷ Social media: information produced using social media platforms; ▷ Collaborative mapping: information about geographic features collected from mapping platforms; ▷ Crowd sensing: information collected from dedicated applications and platforms; Source: De Albuquerque et al. (2016)
  5. 5. Determining flooded areas using crowd sensing data and weather radar precipitation: a case study in Brazil Dr. Flávio E. A. Horita | http://www.flaviohorita.com | CMCC/UFABC, Santo André, Brazil 5 10.11.2017 Problem statement Hard sensors have been used for filtering (and pre- processing) volunteered information; Provided data are restricted to geographic location of these sensors and thus relevant information may be eliminated.
  6. 6. Determining flooded areas using crowd sensing data and weather radar precipitation: a case study in Brazil Dr. Flávio E. A. Horita | http://www.flaviohorita.com | CMCC/UFABC, Santo André, Brazil 6 10.11.2017 ▷ RAdio Detection And Ranging (RADAR) Problem statement Research Design rainfall eletromagnetic waves reflection
  7. 7. Determining flooded areas using crowd sensing data and weather radar precipitation: a case study in Brazil Dr. Flávio E. A. Horita | http://www.flaviohorita.com | CMCC/UFABC, Santo André, Brazil 7 10.11.2017 Research Question How can weather radar data validate flooded areas identified by crowd sensing data?
  8. 8. Determining flooded areas using crowd sensing data and weather radar precipitation: a case study in Brazil Dr. Flávio E. A. Horita | http://www.flaviohorita.com | CMCC/UFABC, Santo André, Brazil 8 10.11.2017 Approach Crowd sensing data analysis Weather radar systems data analysis Data validation Flooded areas Clusters Rain intensity category • Riverbasin catchments • Rainfall data • Output: 0) no, 1) low, 2) moderate, and 3) high • Kernel-density estimator (KDE); • Bandwidth: 200 meters of distance. • More than 3 elements; • Lag time of 30 minutes.
  9. 9. Determining flooded areas using crowd sensing data and weather radar precipitation: a case study in Brazil Dr. Flávio E. A. Horita | http://www.flaviohorita.com | CMCC/UFABC, Santo André, Brazil 9 10.11.2017 • 12 million inhabitants (9th highest cities in World) • An area of ~1.5 million km² • A population density of ~7,400 inhabitants per km² Case study City of São Paulo
  10. 10. Determining flooded areas using crowd sensing data and weather radar precipitation: a case study in Brazil Dr. Flávio E. A. Horita | http://www.flaviohorita.com | CMCC/UFABC, Santo André, Brazil 10 10.11.2017 • 12 million inhabitants (9th highest cities in World) • An area of ~1.5 million km² • A population density of ~7,400 inhabitants per km²
  11. 11. Determining flooded areas using crowd sensing data and weather radar precipitation: a case study in Brazil Dr. Flávio E. A. Horita | http://www.flaviohorita.com | CMCC/UFABC, Santo André, Brazil 11 10.11.2017 Case study – Geographic distribution Preliminary Results Jan 16th, 2018 Jan 21st, 2018
  12. 12. Determining flooded areas using crowd sensing data and weather radar precipitation: a case study in Brazil Dr. Flávio E. A. Horita | http://www.flaviohorita.com | CMCC/UFABC, Santo André, Brazil 12 10.11.2017 Case study – Crowd sensing data Preliminary Results Jan 16th, 2018 Jan 21st, 2018
  13. 13. Determining flooded areas using crowd sensing data and weather radar precipitation: a case study in Brazil Dr. Flávio E. A. Horita | http://www.flaviohorita.com | CMCC/UFABC, Santo André, Brazil 13 10.11.2017 Case study – Weather Radar Systems Preliminary Results Jan 16th, 2018 Jan 21st, 2018
  14. 14. Determining flooded areas using crowd sensing data and weather radar precipitation: a case study in Brazil Dr. Flávio E. A. Horita | http://www.flaviohorita.com | CMCC/UFABC, Santo André, Brazil 14 10.11.2017 Case study Preliminary Results Nro of generated clusters Jan 21st, 2018 40 clusters Jan 16th, 2018 57 clusters Kernel-density estimator (KDE); Bandwidth: 200 meters of distance. More than 3 elements; Lag time of 30 minutes.
  15. 15. Determining flooded areas using crowd sensing data and weather radar precipitation: a case study in Brazil Dr. Flávio E. A. Horita | http://www.flaviohorita.com | CMCC/UFABC, Santo André, Brazil 15 10.11.2017 Case study Preliminary Results
  16. 16. Determining flooded areas using crowd sensing data and weather radar precipitation: a case study in Brazil Dr. Flávio E. A. Horita | http://www.flaviohorita.com | CMCC/UFABC, Santo André, Brazil 16 10.11.2017 Case study Preliminary Results
  17. 17. Determining flooded areas using crowd sensing data and weather radar precipitation: a case study in Brazil Dr. Flávio E. A. Horita | http://www.flaviohorita.com | CMCC/UFABC, Santo André, Brazil 17 10.11.2017 ▷ Weather radar systems are of great value for validating volunteered information; ▷ Weather radar systems may supplement authoritative data provided by rainfall gauges and hydrological stations for pre-processing volunteered information; Final Remarks
  18. 18. Determining flooded areas using crowd sensing data and weather radar precipitation: a case study in Brazil Dr. Flávio E. A. Horita | http://www.flaviohorita.com | CMCC/UFABC, Santo André, Brazil 18 10.11.2017 ▷ Employment of further methods for spatial data analysis like DBSCAN and Moran’s I; ▷ Consideration of community and flood vulnerability variables in the data analysis; ▷ Conduction of more case studies ▷ Different context settings; e.g., heavy weather and KDE’s threshold on 120m. ▷ Other collaborative platforms (e.g., Twitter and Instagram). Future directions Final Remarks
  19. 19. Determining flooded areas using crowd sensing data and weather radar precipitation: a case study in Brazil Dr. Flávio E. A. Horita | http://www.flaviohorita.com | CMCC/UFABC, Santo André, Brazil 19 10.11.2017 • ELWOOD, S. Volunteered geographic information: future research directions motivated by critical, participatory, and feminist GIS. GeoJournal, v. 72, n. 3-4, p. 173–183, 2008. • HORITA, F. E. A.; DEGROSSI, L. C.; ASSIS, L. F. G.; ZIPF, A.; ALBUQUERQUE, J. P. The use of volunteered geographic information (VGI) and crowdsourcing in disaster management: a systematic literature review. In: Proceedings of the 19th Americas Conference on Information Systems (AMCIS). [S.l.: s.n.], 2013. p. 1–10. • GOODCHILD, M. F.; GLENNON, J. A. Crowdsourcing geographic information for disaster response: a research frontier. International Journal of Digital Earth, v. 3, n. 3, p. 231–241, 2010. • HAWORTH, B.; BRUCE, E. A review of volunteered geographic information for disaster management. Geography Compass, v. 9, n. 5, p. 237–250, 2015. • NIKO, D. L.; HWANG, H.; LEE, Y.; KIM, C. Integrating User-generated Content and Spatial Data into Web GIS for Disaster History. Computers, Networks, Systems, and Industrial Engineering 2011, v. 365, p. 245–255, 2011. • DE ALBUQUERQUE, J. P.; HERFORT, B.; ECKLE, M.; ZIPF, A. (2016). Crowdsourcing geographic information for disaster management and improving urban resilience: an overview of recent developments and lessons learned. In C. Capineri, M. Haklay, H. Huang, V. Antoniou, J. Kettunen, F. Ostermann, & R. Purves (Eds.), European handbook on crowdsourced geographic information (pp. 309–321). References
  20. 20. Determining flooded areas using crowd sensing data and weather radar precipitation: a case study in Brazil Dr. Flávio E. A. Horita | http://www.flaviohorita.com | CMCC/UFABC, Santo André, Brazil 20 10.11.2017 • http://obeyproximity.com/2017/06/22/report-13-million- proximity-sensors-now-deployed-globally/ • http://www.tiemporojas.com/la-provincia-adhiere-al-sistema- nacional-de-radares-meteorologicos/ • http://chuvaonline.iag.usp.br/ • http://www.starnet.iag.usp.br/chuvaonline/sobre_chuva.php • https://en.wikipedia.org/wiki/Radar Images References
  21. 21. Determining flooded areas using crowd sensing data and weather radar precipitation: a case study in Brazil Dr. Flávio E. A. Horita | http://www.flaviohorita.com | CMCC/UFABC, Santo André, Brazil 21 10.11.2017 Determining flooded areas using crowd sensing data and weather radar precipitation: a case study in Brazil Dr. Flávio E. A. Horita Center for Mathematics, Computation and Cognition (CMCC) Federal University of ABC (UFABC), Santo André/SP, Brazil e-mail: flavio.horita@ufabc.edu.br website: http://flavio.horita.com

×