Machine Learning–Enhanced Metaheuristic Optimization for Nonlinear Problems: A Comprehensive Critical Review

Mohammed Loay Moammar; Abdulwahhab F  Shareef; Mohammed F Ibrahim  Alsarraj

Authors

Mohammed Loay Moammar Technical Engineering College for Computer and AI–Mosul, Northern Technical University, Mosul, 41001, Iraq
Abdulwahhab F Shareef Technical Engineering College for Computer and AI–Mosul, Northern Technical University, Mosul, 41001, Iraq.
Mohammed F Ibrahim Alsarraj Technical Engineering College for Computer and AI–Mosul, Northern Technical University, Mosul, 41001, Iraq.

Keywords:

Metaheuristic Optimization, Machine Learning, Hybrid Intelligence, Reinforcement Learning, Adaptive Optimization

Abstract

Nonlinear optimization problems are commonplace in multidisciplinary applications across engineered systems, energy, transportation, healthcare and computational intelligence. Many of these problems remain unsolvable, characterized by nonconvex search landscapes, multimodalities, high dimensionality, and complex constraints. Traditionally, metaheuristic approaches ranging from genetic algorithms to particle swarm optimization to ant colony optimization and differential evolution supply reliable performance but are ultimately ineffective due to slow convergence, premature convergence, or variances of solutions based on problem type. Yet with the latest trajectory of machine learning (ML) technologies, hybrid frameworks provide coupling agents from predictive modeling to adaptive learning to surrogate modeling to reinforcement-based decision support systems that realize enhanced performance by promoting quicker searches. This paper details a comprehensive and critical literature review of ML-coupled metaheuristics for nonlinear optimization. Findings compare recent developments to associated trends, categorize coupling frameworks, review performance increase percentages, acknowledge existing gaps, and recommend future research focus. Ultimately, ML-based metaheuristics promise a new frontier in top-level performance for nonlinear solutions; however, to make them as good as they can be, standardized benchmarking, increased explainability, and better theoretical justification are needed.

References

M. Nassef, M. A. Abdelkareem, H. M. Maghrabie, and A. Baroutaji, “Review of Metaheuristic Optimization Algorithms for Power Systems Problems,” Sustainability, vol. 15, no. 12, p. 9434, June 2023, doi: 10.3390/su15129434.

Akgul, Y. Karaca, M. E. Çimen, A. F. Boz, M. Z. Yildiz, and M. A. Pala, “CHAOS THEORY, ADVANCED METAHEURISTIC ALGORITHMS AND THEIR NEWFANGLED DEEP LEARNING ARCHITECTURE OPTIMIZATION APPLICATIONS: A REVIEW,” Fractals, vol. 32, no. 03, Jan. 2024, doi: 10.1142/s0218348x24300010.

Q. Li, Y. Bai, and W. Gao, “Improved Initialization Method for Metaheuristic Algorithms: A Novel Search Space View,” IEEE Access, vol. 9, pp. 121366–121384, Jan. 2021, doi: 10.1109/access.2021.3073480.

W. H. Bangyal et al., “An Improved Particle Swarm Optimization Algorithm for Data Classification,” Applied Sciences, vol. 13, no. 1, p. 283, Dec. 2022, doi: 10.3390/app13010283.

E. H. Houssein and A. Sayed, “Dynamic Candidate Solution Boosted Beluga Whale Optimization Algorithm for Biomedical Classification,” Mathematics, vol. 11, no. 3, p. 707, Jan. 2023, doi: 10.3390/math11030707.

S. M. Sait, P. Mehta, B. S. Yıldız, and A. R. Yıldız, “Optimal design of structural engineering components using artificial neural network-assisted crayfish algorithm,” Materials Testing, vol. 66, no. 9, pp. 1439–1448, May 2024, doi: 10.1515/mt-2024-0075.

M. S. Turgut, O. E. Turgut, H. M. Sağban, and Ö. T. Özmen, “Whale optimization and sine–cosine optimization algorithms with cellular topology for parameter identification of chaotic systems and Schottky barrier diode models,” Soft Comput, vol. 25, no. 2, pp. 1365–1409, Aug. 2020, doi: 10.1007/s00500-020-05227-6.

J. Ma et al., “Metaheuristic-based support vector regression for landslide displacement prediction: a comparative study,” Landslides, vol. 19, no. 10, pp. 2489–2511, June 2022, doi: 10.1007/s10346-022-01923-6.

S. Szénási and G. Légrádi, “Machine learning aided metaheuristics: A comprehensive review of hybrid local search methods,” Expert Systems with Applications, vol. 258, p. 125192, Aug. 2024, doi: 10.1016/j.eswa.2024.125192.

E.-G. Talbi, “Machine Learning into Metaheuristics,” ACM Comput. Surv., vol. 54, no. 6, pp. 1–32, July 2021, doi: 10.1145/3459664.

S.-S. M. Ajibade, N. B. Binti Ahmad, and A. Zainal, “A Hybrid Chaotic Particle Swarm Optimization with Differential Evolution for feature selection,” Institute Of Electrical Electronics Engineers, July 2020, pp. 1–6. doi: 10.1109/isiea49364.2020.9188198.

Kaya, M. Kaya, Z. H. Kilimci, and M. Uysal, “A Review of Metaheuristic Optimization Techniques in Text Classification,” IJCESEN, vol. 10, no. 2, Apr. 2024, doi: 10.22399/ijcesen.295.

F. Minai and H. Malik, “Metaheuristics Paradigms for Renewable Energy Systems: Advances in Optimization Algorithms,” Springer Singapore, 2020, pp. 35–61. doi: 10.1007/978-981-15-7571-6_2.

N. Urkude, M. S. Hora, and U. Utkarsh, “Enhancing machine learning models with metaheuristic Optimization techniques for accurate prediction of PSC in FRP-reinforced concrete slabs,” Mechanics of Advanced Materials and Structures, vol. 32, no. 15, pp. 3591–3607, Aug. 2024, doi: 10.1080/15376494.2024.2394985.

Z. Fan, Z. Xiao, X. Li, Z. Huang, and C. Zhang, “MSBWO: A Multi-Strategies Improved Beluga Whale Optimization Algorithm for Feature Selection.,” Biomimetics, vol. 9, no. 9, p. 572, Sept. 2024, doi: 10.3390/biomimetics9090572.

Saha, A. Basu, and S. Banerjee, “Enhancing thermal management systems: a machine learning and metaheuristic approach for predicting thermophysical properties of nanofluids,” Eng. Res. Express, vol. 6, no. 4, p. 045537, Nov. 2024, doi: 10.1088/2631-8695/ad8536.

M. F. Alsarraj, “Association Rules and Deep Learning Paradigms for Big Data Processing,” JPR, vol. 24, no. 4, pp. 36–45, Nov. 2024, doi: 10.61704/jpr.v24i4.pp36-45.

O. O. Akinola, A. E. Ezugwu, J. O. Agushaka, R. A. Zitar, and L. Abualigah, “Multiclass feature selection with metaheuristic optimization algorithms: a review,” Neural Comput & Applic, vol. 34, no. 22, pp. 19751–19790, Jan. 2022, doi: 10.1007/s00521-022-07705-4.

S. Mandour, A. Sleem, and A. Gamal, “Mantis Search Algorithm Integrated with Opposition-Based Learning and Simulated Annealing for Feature Selection,” Sustain. Mach. Intell. J., vol. 8, June 2024, doi: 10.61356/smij.2024.8300.

J. Lee, J. Kim, Y.-H. Kim, and Y. Yoon, “Metaheuristic-Based Feature Selection Methods for Diagnosing Sarcopenia with Machine Learning Algorithms.,” Biomimetics, vol. 9, no. 3, p. 179, Mar. 2024, doi: 10.3390/biomimetics9030179.

V. D. P. Adombi, R. Chesnaux, and M.-A. Boucher, “Review: Theory-guided machine learning applied to hydrogeology—state of the art, opportunities and future challenges,” Hydrogeol J, vol. 29, no. 8, pp. 2671–2683, Sept. 2021, doi: 10.1007/s10040-021-02403-2.

H. A. Ganatra, “Machine Learning in Pediatric Healthcare: Current Trends, Challenges, and Future Directions.,” JCM, vol. 14, no. 3, p. 807, Jan. 2025, doi: 10.3390/jcm14030807.

P. Gogoi and J. A. Valan, “Machine learning approaches for predicting and diagnosing chronic kidney disease: current trends, challenges, solutions, and future directions.,” Int Urol Nephrol, vol. 57, no. 4, pp. 1245–1268, Nov. 2024, doi: 10.1007/s11255-024-04281-5.

M. Bahameish, J. Requena Carrión, and T. Stockman, “Strategies for Reliable Stress Recognition: A Machine Learning Approach Using Heart Rate Variability Features.,” Sensors, vol. 24, no. 10, p. 3210, May 2024, doi: 10.3390/s24103210.

Kiakojouri and L. Wang, “A Generalized Convolutional Neural Network Model Trained on Simulated Data for Fault Diagnosis in a Wide Range of Bearing Designs.,” Sensors, vol. 25, no. 8, p. 2378, Apr. 2025, doi: 10.3390/s25082378.