New Algorithm Boosts Fairness in Disaster Aid

Stevens researchers develop a model to optimize truck-drone delivery systems and ensure equitable distribution of emergency supplies.

Mar. 13, 2026 at 2:34am

Got story updates? Submit your updates here. ›

Researchers at Stevens Institute of Technology have developed a new algorithm that aims to minimize the time it takes for the last person to receive disaster aid, ensuring a more equitable distribution of supplies delivered by a collaborative truck-drone system. The algorithm uses AI and machine learning to optimize routes, workload balance, and costs, and was tested in simulations of urban and rural disaster scenarios, including the potential impact of disinformation.

Why it matters

Delivering aid quickly and efficiently to those affected by natural disasters is crucial, but ensuring fairness and equity in the distribution of limited resources can be challenging. This new algorithm provides a data-driven approach to optimize disaster relief logistics and help emergency responders reach even the most isolated and vulnerable populations.

The details

The algorithm developed by the Stevens researchers combines the strengths of trucks, which can transport large volumes of supplies, and drones, which can access hard-to-reach areas. Rather than just minimizing average delivery time, the model aims to shorten the time difference between the earliest and latest deliveries, ensuring a more equitable distribution of aid. The team tested the algorithm in simulations of disaster scenarios in Hoboken, NJ and Hopkins County, KY, and also incorporated the potential impact of disinformation on aid requests.

  • The research was published in the journal Computers & Industrial Engineering in March 2026.
  • The algorithm was developed and tested using data from past disasters, including Hurricane Sandy in 2012 and floods in Hopkins County, KY in 2025.

The players

Jose Ramirez-Marquez

Stevens Associate Professor who studies disaster recovery and resilience and led the research team.

Nafiseh Ghorbani-Renani

Stevens Teaching Assistant Professor who collaborated on the research.

Ramin Talebi Khameneh Ramin

PhD candidate at Stevens who collaborated on the research.

Stevens Institute of Technology

A private research university in Hoboken, New Jersey, where the research was conducted.

Got photos? Submit your photos here. ›

What they’re saying

“This ensures that aid reaches even the most isolated and inaccessible locations. The drone can come back, and then it can be resupplied, and then deliver aid over and over again. This collaborative approach combines the strengths of both vehicles, where trucks handle the bulk transportation of goods while drones extend the reach to remote or difficult-to-access locations.”

— Jose Ramirez-Marquez, Stevens Associate Professor

“We used the so-called evolutionary algorithm, because it evolves from one generation to the next. With each iteration it tells us, 'oh, I found this other solution, and I found this better solution.' At the end, we look at all the good solutions and say, 'you know, this is the best solution we found.'”

— Jose Ramirez-Marquez, Stevens Associate Professor

What’s next

The next step would be to work with a municipality to do a hypothetical test run of the algorithm in real-world settings, according to Ramirez-Marquez.

The takeaway

This new algorithm provides emergency responders with a data-driven tool to optimize disaster relief logistics and ensure more equitable distribution of limited aid resources, even in the face of potential disinformation, helping to reach the most isolated and vulnerable populations affected by natural disasters.