Real-Time Monitoring and Detection of Flash Floods in Smart City

Carousel imageCarousel imageCarousel imageCarousel imageCarousel imageCarousel imageCarousel image

Introduction:

Storms and floods cause 70% of the world's natural disasters. These natural disasters affect on average up to 200 million people in a year, with economic losses between US$50 billion to US$100 billion annually. National Weather Services (NWS) reported 28,826 flash floods events in the United States from October 2007 to October 2015, which resulted in 278 live loss. Monitoring these flash flood prone areas proactively in populated areas and providing just-in-time notification to the city officials can help in effectively prioritizing, controlling, and mitigating such disastrous events. Solving flash floods problems helps improve the flow of traffic, reduce traffic congestion, environmental hazards, and formation of stagnant water, and prevent damages of any surrounding properties, premises, and loss of lives. This project is building a portable wireless sensor network-based hardware system to monitor the rising level of water, designing distributed predictive data analytics algorithms with human in the loop, and providing smartphone based real time notifications to city officials. The project proposes to integrate human observations from micro-blogging feeds to forecast the manifestation of the flood events by considering real-time contextual information of the target event. The project will be deployed in several flash flood prone areas in Ellicott City and Baltimore City in partnership with the Howard County and Baltimore County local government officials.

Project Goal:

The NSF CNS EAGER Project # 1640625 seeks to build distributed Data Analytics for Real-Time Monitoring and Detection of Flash Floods in Smart City. In this work, we built many protocols and continued to iterate on various Flash Flood Detection using Physical Sensor as well as Social Sensor(s) as our data points . We then fused these two data sources and tried building and end to end system on one .

Team Members:

Principal Investigator:

  • Dr. Nirmalya Roy

Co-Principal Investigator:

  • Dr. Aryya Gangopadgyay

Graduated Students:

  • Amrita Anam

Current Graduate Students:

  • Bipendra Basnyat
  • Neha Singh

Acknowledgement:

This research is supported by the National Science Foundation under Award Numbers: 1640625.

Community Partners:

  • Howard County
  • National Science Foundation
  • University of Maryland Baltimore County
  • MachineSense (Local Community Startup), Evigia Systems Inc, Progeny Systems Corporation

Research Problem: Monitoring and Detecting the Flash Flood in Ellicott City Area

Solution: The research will pursue the junction of wireless sensor networks-based data analytics and real-time social network data such as tweets.

UMBC - Howard County Government Collaboration

UMBC is collaborating with city partners to measure and compare the key performance improvements over existing municipal systems or protocols in practice and the viability of the proposed system for practical city usage and demonstration as part of the Global City Team Challenge program.

Carousel imageCarousel imageCarousel imageCarousel imageCarousel image

Flash Flood Cyber Physical Design Development and Progressions

Carousel imageCarousel imageCarousel imageCarousel imageCarousel imageCarousel imageCarousel imageCarousel imageCarousel imageCarousel imageCarousel imageCarousel image

Deployment History

Over the past three years we have built and experimented with several IoTs and Flash Flood detection mechanism. Some of our prototypes and our setups along the way are depicted on these images.

Physical & Social Media Data Fusion :

We are currently monitoring Flood Conditions from our 8 Sensors deployed in Ellicott City Main Street Area. We collect ambient site conditions such as Weather, Rainfall amounts and Water Level in the area. We then transmit the data to Twitter and scrape social media engagement from users based on Tweets.

Research Summary and Progress (Major Milestones)

Our research is focused on detecting and monitoring flood related information with the help of mainly two kind of sensors (I) The physical sensor and (II) The social sensor and underling architecture to support them.

Sensor Locations (Ellicott City,MD)

Main Component

(CPU and Solar)

Water Measuring Unit

UMBC FloodBot: Our Community Watch Dog & Public Relation End Point

Our research is focused on detecting and monitoring flood related information with the help of mainly two kind of sensors (I) The physical sensor and (II) The social sensor and underling architecture to support them.

  • The UMBC Flood Bot tweets every 6 hours with the current Weather condition and Water Level Recorded at that moment.
  • UMBC Flood Bot is being integrated with the Vision and Language based Deep learning Models to increase the quality,importance and relevancy of those tweets.


Natural Language Understanding from Social Media Sensing

Tweets Word Cloud Cluster

Application of Transfer Learning in Textual Domain

Transfer Learning for Flood Using ULMFiT

Datasets

  • Physical Sensor (Deployed Systems)
    • We collect real time Water Depth recorded by sensors deployed on site.
    • We collect images captured by our camera(s)
    • We annotate them based on our use case and analysis requirement
  • Social Media Data (Twitter)
    • We post the physical sensor collected data to Tweet
    • We scrape Twitter to analyse user engagement and understand the content using NLP+ Deep Learning Model

Physical & Social Media Manifested by Water Level Peak to Tweet Intensity

Software

Multiple Deep Learning Frameworks

RealTime Weather API

Pre and Post Analysis Twitter Scraping Code and Frameworks


Presentations

  • Graduate Student Neha attended and presented her research at AI for Social Good - AAAI Fall Symposium 2019, Association for the Advancement of Artificial Intelligence, Arlington, Virginia in November, 2019.
  • Graduated Student Amrita presented her work at the workshop on Mining and Learning from Time Series (MiLeTS) in conjunction with 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Anchorage, Alaska, August 2019
  • Graduated Student Amrita presented at the IEEE International Conference on Smart Computing (SmartComp), Washington D.C., June 2019 and in Sicily, Italy, June 2018 .
  • Graduate Student Neha presented at the IEEE International Conference on Smart Computing (SmartComp), Sicily, Italy, June 2018.
  • Graduate Student Bipendra presented at the IEEE International Conference on Smart Computing (SmartComp), Sicily, Italy, June 2018.
  • Dr. Roy presented flash flood project progress at NSF CSR PI meeting in 2017.
  • Dr. Roy, Dr. Gangopadhyay and research team attended the meeting with Howard County officials in May 2016.
  • Dr. Roy, Dr. Gangopadhyay, Bipen, Neha, Sreeni attended the meeting with UMBC Facility in 2016.

Publications

    1. Neha Singh, Nirmalya Roy, and Aryya Gangopadhyay, Localized Flood Detection With Minimal Labeled Social Media Data Using Transfer Learning, AI for Social Good - AAAI Fall Symposium 2019, Association for the Advancement of Artificial Intelligence, Arlington, Virginia, USA, November 7 – 9, 2019.
    2. Neha Singh, Nirmalya Roy and Aryya Gangopadhyay. Analyzing the Emotions of Crowd for Improving the Emergency Response Services, Pervasive and Mobile Computing (PMC) Journal, Volume 58, August 2019, Elsevier 2019
    3. Amrita Anam, Aryya Gangopadhyay and Nirmalya Roy. Event Characterization and Separation using Wavelet Signatures, in proceedings of the 5th workshop on Mining and Learning from Time Series (MiLeTS) in conjunction with 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Anchorage, Alaska, August 2019
    4. Amrita Anam, Aryya Gangopadhyay, Nirmalya Roy. Identifying the Context of Hurricane Posts on Twitter using Wavelet Features, in Proceedings of the 5th IEEE International Conference on Smart Computing (SmartComp), Washington D.C., June 2019
    5. Bipendra Basnyat, Nirmalya Roy and Aryya Gangopadhyay. A Flash Flood Categorization System using Scene-Text Recognition, in Proceedings of the 4th IEEE International Conference on Smart Computing (SmartComp), Sicily, Italy, June 2018
    6. Amrita Anam, Aryya Gangopadhyay and Nirmalya Roy. Evaluating Disaster Time-line from Social Media using Wavelet Analysis, in Proceedings of the 4th IEEE International Conference on Smart Computing (SmartComp), Sicily, Italy, June 2018
    7. Neha Singh, Nirmalya Roy and Aryya Gangopadhyay. Analyzing the Sentiment of Crowd for Improving the Emergency Response Services, in Proceedings of the 4th IEEE International Conference on Smart Computing (SmartComp), Sicily, Italy, June 2018
    8. Bipendra Basnyat, Amrita Anam, Neha Singh, Aryya Gangopadhyay, and Nirmalya Roy. Analyzing Social Media Texts and Images to Assess the Impact of Flash Floods in Cities, in Proceedings of the 2nd IEEE International Workshop on Smart Service Systems (SmartSys), co-located with SmartComp, pp. 1-6, May 2017

Last Updated: 4/16/2020