Big Data Framework will focus on monitoring natural disasters

Big data refers to a large volume of structured and unstructured data. These voluminous data sets compiled from different sources are analyzed by business enterprises for better decision making. Big Data has opened new doors for disaster management. Various different methods are used for assessment prediction of earthquakes, hurricanes and floods.   

 

Researchers at Texas A&M University have devised a framework that can be employed for recovery assessment of communities post natural disasters. Big data derived tools analyze data from previous natural disasters to ascertain recovery time frames.

 

Natural disasters like floods and hurricanes displace humans from their homes. Areas affected by natural disasters take a long time to come back to their previous state. Long term disaster response unravels in multiple stages. Information related to available resources, assets, affected communities, and partners is analyzed for developing disaster management strategies.  

 

Disaster resilience is defined as communities, organisations, and individuals abilities to recover and return back to pre disaster state. Resilience plays an intrinsic role in calculating the number of years that are required to return back to pre- disaster state. Resilience is determined by the assessment of surveys. Surveys provide insightful information but take a long time to arrive at conclusions. 

 

(Must Check: 4 ways with which IoT helps in disaster management)

 

Big Data Framework

 

In collaboration with the Safegraph research team collected  data during Hurricane Harvey.  Collected cell phone data recorded people’s location to keep a track of their locations after Hurricane Harvey. Hospitals, gas stations, departmental stores were marked as “points of interest” to record changes in visitors traffic. 

 

Further big data was mined to compare differences in points of interest pre and post hurricane harvey. Combined resilience was calculated on the basis of comparison levels. Percentage change in “points of interest played a significant factor in concluding combined resilience. 

 

Areas with low resilience encountered more problems in terms of flooding. Areas in the close vicinity of affected areas were also at the risk of flooding. Floods geographical stretches beyond the affected areas. Big data shed light on important aspects and helped researchers to develop a report and mitigation strategies for areas with low resilience. 

 

According to ScienceDaily , Ali Mostafavi researcher who led the team said  "Although we focused on Hurricane Harvey for this study, our framework is applicable for any other natural disaster as well. "But as a next step, we'd like to create an intelligent dashboard that would display the rate of recovery and impacts in different areas in near real time.