A robust fuzzy framework for designing a sustainable blood supply chain network under disruption
DOI:
https://doi.org/10.15282/Keywords:
Fuzzy optimization, Blood supply chain, Demand forecasting, Long Short-Term Memory, Non-dominated Sorting Genetic Algorithm II, Disruption managementAbstract
Blood supply chain network is impacted by multiple uncertainties including demand, short shelf life of blood products, and disruption of normal operations. This paper proposes an integrated data-driven framework that includes Long Short-Term Memory (LSTM) demand forecasting, fuzzy scenario modeling, and robust multi-objective optimization to support the design of a sustainable blood supply chain network. Historical demand data is first predicted with an LSTM model under three conditions: optimistic, base and pessimistic. The forecasts are expressed as asymmetric triangular fuzzy numbers and then defuzzified before being input to the optimization model. The model is structured to minimize three objectives concurrently: total cost, blood shortage and environmental impacts. The optimization solutions are obtained by the Non-dominated Sorting Genetic Algorithm II (NSGA-II) and the results are verified by CPLEX. The LSTM model showed good forecast performance with Root Mean Squared Error (RMSE) values between 1.28 and 3.65 and Mean Absolute Percentage Error (MAPE) values between 4.12% and 8.90%. Among the three scenarios, the base scenario generated the least prediction errors. The deviations of NSGA-II from the exact CPLEX solutions were 1.97% for total cost and 4.76% for environmental impact, while the blood shortage deviation was 0%. The results indicate that NSGA-II can provide solutions close to the exact optimization results with substantially less computational effort. Sensitivity analysis on demand growth, budgets for temporary facilities and disruption severity also showed the framework can adapt to changes in operating conditions. Overall, the proposed framework provides a practical decision-support approach for planning sustainable and more disruption-resilient blood supply chain networks.
Downloads
References
[1] M. Habibi Kouchaksaraei, M. M. Paydar, and E. Asadi Gangraj, “Designing a bi-objective multi-echelon robust blood supply chain in a disaster,” Applied Mathematical Modeling, vol. 55, pp. 583–599, 2018, doi: 10.1016/j.apm.2017.11.004.
[2] S.-M. Hosseini Motlagh, M. R. Ghatreh Samani, and S. Homaei, “Blood supply chain management: Robust optimization, disruption risk, and blood group compatibility (A real-life case),” Journal of Ambient Intelligence and Humanized Computing, vol. 11, no. 3, pp. 1085–1104, 2020, doi: 10.1007/s12652-019-01315-0.
[3] S. K. Fariman et al., “A robust optimization model for multi-objective blood supply chain network considering scenario analysis under uncertainty: A multi-objective approach,” Scientific Reports, vol. 14, Art. no. 9452, 2024, doi: 10.1038/s41598-024-57521-0.
[4] M. Motamedi, J. Dawson, N. Li, D. G. Down, and N. M. Heddle, “Demand forecasting for platelet usage: From univariate time series to multivariable models,” PLOS ONE, vol. 19, no. 4, Art. no. e0297391, 2024, doi: 10.1371/journal.pone.0297391.
[5] S. Zebari et al., “LSTMXGBoost: An ensemble model for blood demand distribution forecasting—A case study in Zakho City, Kurdistan Region, Iraq,” SN Computer Science, vol. 6, Art. no. 143, 2025, doi: 10.1007/s43069-024-00413-w.
[6] N. Li et al., “Blood demand forecasting and supply management: An analytical assessment of key studies utilizing novel computational techniques,” Transfusion Medicine Reviews, vol. 37, no. 4, Art. no. 150768, 2023, doi: 10.1016/j.tmrv.2023.150768.
[7] M. Asadpour, T. L. Olsen, and O. Boyer, “An updated review on blood supply chain quantitative models: A disaster perspective,” Transportation Research Part E: Logistics and Transportation Review, vol. 158, Art. no. 102583, 2022, doi: 10.1016/j.tre.2021.102583.
[8] M. Meneses, D. Santos, and A. Barbosa-Póvoa, “Modeling the blood supply chain,” European Journal of Operational Research, vol. 307, no. 2, pp. 499–518, 2023, doi: 10.1016/j.ejor.2022.06.005.
[9] S. Edalat Sarvestani, N. Hatam, M. Seif, L. Kasraian, F. S. M. Lari, and M. Bayati, “Forecasting blood demand for different blood groups in Shiraz using ARIMA, ANN and hybrid approaches,” Scientific Reports, vol. 12, Art. no. 22031, 2022, doi: 10.1038/s41598-022-26461-y.
[10] E. M. Miri Moghaddam, S. Khosravi Bizhaem, Z. Moezzifar, and F. Salmani, “Long-term prediction of Iranian blood product supply using LSTM: A 5-year forecast,” BMC Medical Informatics and Decision Making, vol. 24, Art. no. 213, 2024, doi: 10.1186/s12911-024-02614-z.
[11] M. S. Pishvaee, J. Razmi, S. A. Torabi, M. A. Zahedi, and S. M. A. Hosseini, “Robust possibilistic programming for socially responsible supply chain network design: A new approach,” Fuzzy Sets and Systems, vol. 206, pp. 1–20, 2012, doi: 10.1016/j.fss.2012.04.010.
[12] A. M. Esfandabadi et al., “Developing a multi-objective model for a multi-level supply chain of blood products under uncertainty and the global pandemic: A hybrid robust optimization approach,” Discover Applied Sciences, vol. 6, Art. no. 410, 2024, doi: 10.1007/s42452-024-05942-x.
[13] P. B. Niakan, M. Keramatpour, B. Afshar-Nadjafi, and A. R. Komijan, “An integrated supply chain model for predicting demand and supply and optimizing blood distribution,” Logistics, vol. 8, no. 4, Art. no. 134, 2024, doi: 10.3390/logistics8040134.
[14] L. Qing, Y. Yin, D. Wang, Y. Yu, and T. C. E. Cheng, “A two-stage adaptive robust model for designing a reliable blood supply chain network with disruption considerations in disaster situations,” Naval Research Logistics, vol. 72, no. 1, pp. 45–71, 2025, doi: 10.1002/nav.22214.
[15] Y. Wang et al., “Forecasting demands of blood components based on prediction models,” Transfusion Clinique et Biologique, vol. 31, no. 3, pp. 141–148, 2024, doi: 10.1016/j.tracli.2024.04.003.
[16] E. Babaee Tirkolaee, H. Golpîra, A. Javanmardan, and R. Maihami, “A socio-economic optimization model for blood supply chain network design during the COVID-19 pandemic: An interactive possibilistic programming approach for a real case study,” Socio-Economic Planning Sciences, vol. 85, Art. no. 101439, 2023, doi: 10.1016/j.seps.2022.101439.
[17] S. Khalilpourazari and H. Hashemi Doulabi, “A flexible robust model for blood supply chain network design problem,” Annals of Operations Research, vol. 328, pp. 701–726, 2023, doi: 10.1007/s10479-022-04882-2.
[18] Q. X. Li, “Defuzzification methods for fuzzy inventory model,” Advanced Materials Research, vols. 479–481, pp. 399–402, 2012, doi: 10.4028/www.scientific.net/AMR.479-481.399.
[19] M. C. N. R. Carvalho, “Fuzzy weighted average: The linear programming approach via Charnes and Cooper’s rule,” Fuzzy Sets and Systems, vol. 117, no. 1, pp. 157–160, 2001, doi: 10.1016/S0165-0114(98)00333-9.
[20] A. Saltelli et al., Global Sensitivity Analysis: The Primer. Chichester, U.K.: John Wiley & Sons, 2008, doi: 10.1002/9780470725184.
[21] S. A. Seyfi-Shishavan, Y. Donyatalab, E. Farrokhizadeh, and S. I. Satoglu, “A fuzzy optimization model for designing an efficient blood supply chain network under uncertainty and disruption,” Annals of Operations Research, vol. 331, no. 1, pp. 447–501, 2023, doi: 10.1007/s10479-021-04123-y.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 The Author(s)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
