Principal investigators: Jingui Xie (TUM), Xiaolan Xie (IMT); other contact person: Nan Yang (TUM), Thierry Garaix (IMT)

Short summary and central question 

Capacity planning and resource management is a fundamental global challenge in the face of global crises such as the Covid-19 pandemic. One needs to understand the variabilities in time-varying demand for resources to hedge against the random demand fluctuations and take advantage of the risk-pooling effect. Covid-19 predictive and machine learning models used in capacity planning typically predict the mean values of the demands in both the temporal and spatial dimensions. However, they seldom provide reliable predictions or estimations of demand variabilities and, therefore, are insufficient for proper capacity planning. Some works focus on forecasting the evolution of the epidemic based on limited historical data and the resource needs over the days and weeks to come. However, the diversity of decisions, system dynamics over time, and demand uncertainties make decisions challenging even with good forecasts. 

During the crisis, regional or national resource pooling and allocation must be planned. Healthcare providers should identify their maximal capacity and decide how much capacity to share with others. National strategic reserve resources should also be planned, and emergency resources should be obtained from every organization. Once the capacity of the healthcare providers has been identified, and the sharing resources are allocated, the dynamic management of the resources must be put in place according to the epidemiological development. 

It is a question of managing the allocated capacity as well as possible according to the progression of the crisis and the limited available data and information. The number of confirmed cases, the number of hospitalizations (e.g., intensive care patients), the number of deaths, etc., are the primary demand data, which in fact may be underestimated during the crisis. There is also a time lag between the data collection and the actual crisis development, making demand prediction even more difficult. On the other hand, the number of places open for infected patients in intensive care and hospitalizations is the major supply data. These resources are counted with material, equipment, consumables, and personal support. The organization of staff working time must therefore be integrated into these decisions. Resources such as mobile resuscitation units from the military would be managed at this level.

 Using data analytics, machine learning predictive models, and data-driven optimization methods, it appears that playing on the management of resources according to the evolution of needs linked to the epidemic would make it possible to utilize better the limited resource and hedge against the temporal and spatial prediction uncertainties.

Overview of the state-of-the-art 

Resource management in crises is an emerging topic and has become even more critical given the recent Covid-19 pandemic and wars, as well as other ongoing and future crisis: climatic change, social inequality, and other planet-wide crises (Marco et al. 2020; Zhu and Xie, 2020; Azizi et al. 2021; Chumachenko and Chumachenko, 2022). Efficient and timely hospital resource management can mitigate the negative impact of a pandemic on public health (El-Rifai et al., 2016; Khichar et al. 2020). However, it is very challenging because of the dynamic random epidemic evolution, unpredictable and time-varying demands and limited resources. Researchers have developed advanced methods to deal with these difficulties. For instance, Pehlivan et al. (2014) study hierarchical service networks’ dynamic 4 capacity planning and location. With time-varying uncertain demand, Liu and Xie (2018) study human resource planning for emergency care. The recent Covid-19 pandemic has boosted this stream of research based on data analytics. Among those, Hong et al. (2022) study the demand variability scaling and capacity planning in the Covid-19 pandemic. Xie et al. (2022) use advanced analytics to manage hospital resources when facing bed shortages. However, most existing literature applies the traditional “data prediction and estimation, then optimization” framework. This project aims to develop a novel data-driven decision-making tool that directly transfers the data into optimal, robust and easy-to-implement decisions in future unknown crises. 


Pehlivan, C., Augusto, V., & Xie, X. (2014). Dynamic capacity planning and location of hierarchical service networks under service level constraints. IEEE Transactions on Automation Science and Engineering, 11(3), 863-880. El-Rifai, O., Garaix, T., & Xie, X. (2016). Proactive on-call scheduling during a seasonal epidemic. Operations Research for Health Care, 8, 53-61. Liu, R., & Xie, X. (2018). Physician staffing for emergency departments with time-varying demand. INFORMS Journal on Computing, 30(3), 588-607. Di Marco, M., Baker, M. L., Daszak, P., De Barro, P., Eskew, E. A., Godde, C. M., … & Ferrier, S. (2020). Opinion: Sustainable development must account for pandemic risk. Proceedings of the National Academy of Sciences, 117(8), 3888-3892. Zhu, Y., Xie, J., Huang, F., & Cao, L. (2020). Association between short-term exposure to air pollution and COVID-19 infection: Evidence from China. Science of the total environment, 727, 138704. Khichar, S., Midha, N., Bohra, G. K., Kumar, D., Gopalakrishanan, M., Kumar, B., … & Garg, M. K. (2020). Healthcare resource management and pandemic preparedness for COVID-19: a single centre experience from Jodhpur, India. International Journal of Health Policy and Management, 9(11), 493. Azizi, M. R., Atlasi, R., Ziapour, A., Abbas, J., & Naemi, R. (2021). Innovative human resource management strategies during the COVID-19 pandemic: A systematic narrative review approach. Heliyon, 7(6), e07233. Chumachenko, D., & Chumachenko, T. (2022). Ukraine war: The humanitarian crisis in Kharkiv. BMJ, 376. Hong, L. J., Liu, G., Luo, J., & Xie, J. (2022). Variability Scaling and Capacity Planning in Covid-19 Pandemic. Fundamental Research. Xie, J., Loke, G. G., Sim, M., & Lam, S. W. (2022). The Analytics of Bed Shortages: Coherent Metric, Prediction, and Optimization. Operations Research.

Objectives of the project 

This project aims to develop data-driven decision-making tools for dynamic hospital resource management under a significant, long-lasting, widespread crisis such as a pandemic.

Expected impact on academia, industry and society 

The project will impact academia by developing data-driven decision-making tools to support dynamic resource management under uncertainties and time varying demand, which has proved to be very challenging. This project aims to develop a novel data-driven decisionmaking tool that directly converts the data into optimal and easy-to-implement decisions in future unknown crises, while most existing literature applies the traditional two-step “data prediction or estimation, then optimization” framework. Timely and effective resource planning and management can help society combat the crisis and minimize the negative impact on public health and the economy.