publications

2026

1. 

   Managing large-scale invasions: Simulation-optimization with Gaussian dispersal Kernels and stochastic seed establishment

   Sevilay Onal, Sabah Bushaj, Jennifer Smith, Gregory R. Houseman, and I. Esra Buyuktahtakin

   Journal of the Operational Research Society, 2026

   Abs

   Biological invaders, such as Sericea lespedeza, cause over 21 billion (about 65 per person in the US) in annual losses for the US, necessitating effective control methods. To our knowledge, this article is the first to integrate random occurrences of an invader that are not attributable to biophysical impacts, within an integrated simulation-optimisation model to control Sericea. Specifically, we introduce a novel dispersal framework that integrates predictable Gaussian seed spread with a random sprout algorithm, explicitly addressing the long-standing question of random pop-ups of new invaders and capturing long-distance establishment events that traditional models miss. The simulation models the species’ biological growth and integrates both predictable dispersal and unpredictable establishment events into a unified framework. Our optimisation model minimises economic damage by determining optimal search and treatment locations under budget constraints. The case study data and parameter calibration are based on large-scale field data collected in Kansas and Oklahoma. We simulate Sericea growth over a 2,500-acre landscape for 25 years, representing a 25-fold increase in spatial coverage and more than double the temporal scope compared to former studies, substantially increasing problem complexity while demonstrating the scalability of our model. Results, averaged over 10 independent replications, show that prioritising searches in low-density areas and treating infestations immediately upon detection yield the greatest benefits. The framework highlights the value of early detection, search speed, and cost-effective control, offering a generalisable tool for invasive species management. Practitioner Summary: In the past, land managers have based decisions about the frequency and allocation of Sericea control efforts on intuition, available time, and expected costs. Our model provides several insights to guide management based on long-term economic analysis. First, annual herbicide treatment should be utilised whenever possible to minimise long-term economic losses. However, if Sericea infestation is low, a biennial control strategy may perform nearly as well as annual treatment. Second, it is better to carefully and completely spray locations where Sericea is located rather than attempting to cover more areas because the benefit of treating additional areas is overshadowed by the long-term costs of plants that survive insufficient herbicide application. Third, part of the control budget should be allocated to searching new areas that did not have Sericea plants in the past. For example, when fields have low to intermediate infestation, the model suggests that 40-60% of the control costs should be allocated to search efforts. When infestation becomes widespread (high frequency), most of the effort should be allocated to control rather than searching for new Sericea patches. Finally, the longevity of Sericea seeds in the seedbank remains uncertain; however, our model suggests that seed germination and dispersal are more important than seedbank longevity. Consequently, managers should minimise opportunities for seed movement by limiting vehicles or grazing animals in pastures from October to January when Sericea plants have mature seed that can be accidentally dispersed by these sources.

2024

1. 

   COVID-19: Agent-based simulation-optimization to vaccine center location vaccine allocation problem

   Xuecheng Yin, Sabah Bushaj, Yue Yuan, and I. Esra Buyuktahtakin

   IISE Transactions, 2024

   Abs

   We then extend the agent-based epidemiological simulation model of COVID-19 (Covasim) by adding new vaccination compartments representing people who take the first vaccine shot and the first two shots. The Covasim involves complex disease transmission contact networks, including households, schools, and workplaces, and demographics, such as age-based disease transmission parameters. We combine the extended Covasim with the vaccination center location-allocation MIP model into one single simulation-optimization framework, which works iteratively forward and backward in time to determine the optimal vaccine allocation under varying disease dynamics. The agent-based simulation captures the inherent uncertainty in disease progression and forecasts the refined number of susceptible individuals and infections for the current time period to be used as an input into the optimization. We calibrate, validate, and test our simulation-optimization vaccine allocation model using the COVID-19 data and vaccine distribution case study in New Jersey. The resulting insights support ongoing mass vaccination efforts to mitigate the impact of the pandemic on public health, while the simulation-optimization algorithmic framework could be generalized for other epidemics.

2. 

   A K-means supported reinforcement learning framework to multi-dimensional knapsack

   Sabah Bushaj, and I. Esra Buyuktahtakin

   Journal of Global Optimization, 2024

2023

1. 

   A simulation-deep reinforcement learning (SiRL) approach for epidemic control optimization

   Sabah Bushaj, Xuecheng Yin, Arjeta Beqiri, Donald Andrews, and I. Esra Buyuktahtakin

   Annals of Operations Research, 2023

   Abs

   In this paper, we address the controversies of epidemic control planning by developing a novel Simulation-Deep Reinforcement Learning (SiRL) model. COVID-19 reminded constituents over the world that government decision-making could change their lives. During the COVID-19 pandemic, governments were concerned with reducing fatalities as the virus spread but at the same time also maintaining a flowing economy. In this paper, we address epidemic decision-making regarding the interventions necessary given of the epidemic based on the purpose of the decision-maker. Further, we intend to compare different vaccination strategies, such as age-based and random vaccination, to shine a light on who should get priority in the vaccination process. To address these issues, we propose a simulation-deep reinforcement learning (DRL) framework. This framework is composed of an agent-based simulation model and a governor DRL agent that can enforce interventions in the agent-based simulation environment. Computational results show that our DRL agent can learn effective strategies and suggest optimal actions given a specific epidemic situation based on a multi-objective reward structure. We compare our DRL agent’s decisions to government interventions at different periods of time during the COVID-19 pandemic. Our results suggest that more could have been done to control the epidemic. In addition, if a random vaccination strategy that allows super-spreaders to get vaccinated early were used, infections would have been reduced by 32% at the expense of 4% more deaths. We also show that a behavioral change of fully quarantining 10% of the risky individuals and using a random vaccination strategy leads to a reduction of the death toll by 14% and 27% compared to the age-based vaccination strategy that was implemented and the New Jersey reported data, respectively. We have also demonstrated the flexibility of our approach to be applied to other locations by validating and applying our model to the COVID-19 case in the state of Kansas.

2022

1. 

   Risk-averse multi-stage stochastic optimization for surveillance and operations planning of a forest insect infestation

   Sabah Bushaj, I. Esra Buyuktahtakin, and Robert G. Haight

   European Journal of Operational Research, 2022

   Abs

   We derive a nested risk measure for a maximization problem and implement it in a scenario-based formulation of a multi-stage stochastic mixed-integer programming problem. We apply the risk-averse formulation to the surveillance and control of a non-native forest insect, the emerald ash borer (EAB), a wood-boring beetle native to Asia and recently discovered in North America. Spreading across the eastern United States and Canada, EAB has killed millions of ash trees and cost homeowners and local governments billions of dollars. We present a mean-Conditional Value-at-Risk (CVaR), multi-stage, stochastic mixed-integer programming model to optimize a manager’s decisions about surveillance and control of EAB. The objective is to maximize the benefits of healthy ash trees in forests and urban environments under a fixed budget. Combining the risk-neutral objective with a risk measure allows for a trade-off between the weighted expected benefits from ash trees and the expected risks associated with experiencing extremely damaging scenarios. We define scenario dominance cuts (sdc) for the maximization problem and under the decision-dependent uncertainty. We then solve the model using the sdc cutting plane algorithm for varying risk parameters. Computational results demonstrate that scenario dominance cuts significantly improve the solution performance relative to that of CPLEX. Our CVaR risk-averse approach also raises the objective value of the least-benefit scenarios compared to the risk-neutral model. Results show a shift in the optimal strategy from applying less expensive insecticide treatment to more costly tree removal as the manager becomes more risk-averse. We also find that risk-averse managers survey more often to reduce the risk of experiencing adverse outcomes.

2. 

   Predicting the COVID19 Trajectory with a Simulation Deep Reinforcement Learning Approach

   Sabah Bushaj, I. Esra Buyuktahtakin, and Arjeta Beqiri

   In IISE Annual Conference and Expo 2022, 2022

2021

1. 

   Optimizing surveillance and management of emerald ash borer in urban environments

   Sabah Bushaj, I. Esra Buyuktahtakin, Denys Yemshanov, and Robert G. Haight

   Natural Resource Modeling, 2021

   Abs

   Emerald ash borer (EAB), a wood-boring insect native to Asia, was discovered near Detroit in 2002 and has spread and killed millions of ash trees throughout the eastern United States and Canada. EAB causes severe damage in urban areas where it kills high-value ash trees that shade streets, homes, and parks and costs homeowners and local governments millions of dollars for treatment, removal, and replacement of infested trees. We present a multistage, stochastic, mixed-integer programming model to help decision-makers maximize the public benefits of preserving healthy ash trees in an urban environment. The model allocates resources to surveillance of the ash population and subsequent treatment and removal of infested trees over time. We explore the multistage dynamics of an EAB outbreak with a dispersal mechanism and apply the optimization model to explore surveillance, treatment, and removal options to manage an EAB outbreak in Winnipeg, a city of Manitoba, Canada. Recommendation to Resource Managers: Our approach demonstrates that timely detection and early response are critical factors for maximizing the number of healthy trees in urban areas affected by the pest outbreak. Treatment of the infested trees is most effective when done at the earliest stage of infestation. Treating asymptomatic trees at the earliest stages of infestation provides higher net benefits than tree removal or no-treatment options. Our analysis suggests the use of branch sampling as a more accurate method than the use of sticky traps to detect infested asymptomatic trees, which enables treating and removing more infested trees at the early stages of infestation. Our results also emphasize the importance of allocating a sufficient budget for tree removal to manage emerald ash borer infestations in urban environments. Tree removal becomes a less useful option in small-budget solutions where the optimal policy is to spend most of the budget on treatments.

2. 

   Multi-Stage Stochastic Optimization and Reinforcement Learning for Forestry Epidemic and COVID-19 Control Planning

   Sabah Bushaj

   New Jersey Institute of Technology, 2021