Skip to content

A team of Harrisburg University professors and students have set out to develop a smart disaster prediction and prevention system that could help save thousands of lives across the U.S. each year.

Using sets of existing disaster data and an adaptive artificial intelligence model, the team plans to design an alert system capable of predicting natural and human-induced disasters, starting with wildfires and vehicle collisions.

Disaster detection systems are not new, but existing systems are used to detect natural and human-induced disasters after they occur. Think of an earthquake detection system triggered by seismometers that detect seismic wave vibrations as they rip through the earth’s crust.

Using location factors, time frames, accident rates and more, the smart disaster prediction system for smart cities, or technologically modern areas that use technology to collect data and improve operations, will predict, for any locality in the U.S., wildfires and traffic accidents. The system could later be expanded to include other disasters.

HU Information Systems Engineering Management Professor Dr. Amjad Umar, and Information Technology and Management Professor Dr. Iheb Abdellatif, were awarded an HU Presidential Research Grant to develop the system with students. Ph.D. students Praveena Jakkula and Nandkumar Niture are basing their thesis proposals on the work. And undergraduate students, John Vincent and Jonathan Byler, also are assisting with the project.

Abdellatif has supervised the Ph.D. students as work to develop the system took place along three research thrusts:

Thrust one has involved the creation and consolidation of data that will help measure all factors leading to wildfire and traffic collisions throughout the U.S.  During the second thrust, the team identified the major factors contributing to wildfires and traffic accidents in a given locality. This thrust’s contribution is unique because a consensus on significant factors leading to wildfire or traffic accidents did not previously exist.

The third thrust calls for the development of an Artificial Intelligence (AI) model that will predict Wildfire and traffic accidents in any locality in the U.S. The team has already created general forecasting AI models to predict the number of traffic collisions and wildfires in 2022 in Pennsylvania and California. More granular and accurate AI models will be created during the next year.

The technology and processes the project has introduced students to has provided a wealth of hands-on learning experiences. For example, students were able to become familiar with the disruptive technologies used by Smart Cities (artificial Intelligence, Internet of Drones, satellite imagery processing, and more), showing them how satellites work or how autonomous trucks can travel from one point to another without any human intervention.

Undergraduate students have developed teamwork skills by working with graduate students and project partners, including Bluesail Solutions (Industrial partner), California State Polytechnic University, Pomona (First academic partner), and IoT Lab Canada (Second academic partner), all of which share the same interest in designing and implementing a Smart Disaster Prediction System for Smart Cities.

The experiential learning component for students involved with the project has been immeasurable. And using technology and existing resources to help save lives is very rewarding, Umar said.

He noted that between 1960 and 2019, 68 million acres were burned by wildfires across the U.S. And during the 10 years since Hurricane Katrina, the world has seen an annual average of 260 significant natural disasters, with average annual economic losses of $211 billion, insured losses of $63 billion, and 76,000 lives lost. And more than 33,000 people die in traffic accidents in the U.S. each year.

Reducing these tragic figures, even by just a small percentage, makes this effort worthwhile, Umar said. 

“This tool should be able to produce a very simple output that predicts that this type of disaster will occur in this area based on the past information that we have” he said. “Even if we could make a small dent in (fatalities), this would have tremendous value. That is the motivation behind our work.”

ABOUT HARRISBURG UNIVERSITY

Accredited by the Middle States Commission on Higher Education, Harrisburg University is a private nonprofit university offering bachelor and graduate degree programs in science, technology, and math fields to a diverse student body. For more information on the University’s affordable demand-driven undergraduate and graduate programs, call 717.901.5146 or email, Connect@HarrisburgU.edu.