Clustering Evaluation of Upper Air Thermodynamic Patterns Using  K-Means Centroid Optimization with GA, PSO, and GWO Algorithms

Ricky Aurelius Nurtanto Diaz; Ni Luh Gede Pivin  Suwirmayanti; Emy Setyaningsih; Agus Yarcana

doi:10.52436/1.jutif.2026.7.4.6375

Authors

Ricky Aurelius Nurtanto Diaz Department of Computer Systems, Faculty of Informatics and Computer, Institut Teknologi dan Bisnis STIKOM Bali, Indonesia
Ni Luh Gede Pivin Suwirmayanti Department of Computer Systems, Faculty of Informatics and Computer, Institut Teknologi dan Bisnis STIKOM Bali, Indonesia
Emy Setyaningsih Department of Computer Systems Engineering, Faculty of Science and Information Technology, Universitas AKPRIND, Indonesia
Agus Yarcana Stasiun Meteorologi I Gusti Ngurah Rai, Indonesia

DOI:

https://doi.org/10.52436/1.jutif.2026.7.4.6375

Keywords:

Clustering, GA, GWO, K-Means, Optimization, PSO

Abstract

Operationally used early warning systems for significant weather generally rely on conventional weighting-scoring schemes, namely, fixed thresholds set based on empirical experience or expert meteorological consensus. The fundamental limitation of conventional threshold-based methods and supervised classification models lies in their reliance on labeled data, while extreme weather events are naturally rare and imbalanced in historical station observation records. Such approaches are prone to generating false alarms. Therefore, a multilayered unsupervised learning approach is needed to objectively classify upper-air thermodynamic patterns without relying on subjective extreme-event labels. Although widely used, the K-Means algorithm has a fundamental weakness, namely its high sensitivity to the initial centroid determination. This study applies hybrid metaheuristic techniques with K-Means, namely GA-KMeans, PSO-KMeans, and GWO-KMeans, within a consistent evaluation framework, using the same cluster validity index, and applied to the operational meteorological domain. The test results show that the best fitness values are produced by the PSO-KMeans model with a WCSS value of 250.6012, followed by GWO-KMeans with a WCSS value of 304.7890, and finally the GA-KMeans model with a WCSS value of 330.0701. The third model used also consistently produces higher Silhouette Score values compared to the classical K-Means baseline and shows that metaheuristic hybridization is proven to be effective in improving the quality of cluster structures. Specifically within the field of computer science, the results demonstrate that employing appropriate cluster center optimization techniques can improve both clustering quality and resource efficiency when grouping various types of data.

Downloads

Download data is not yet available.

References

K. Hembach-Stunden, T. Vorlaufer, and S. Engel, “False and missed alarms in seasonal forecasts affect individual adaptation choices,” Q Open, vol. 4, no. 1, Dec. 2023, doi: 10.1093/qopen/qoad031.

P. Kushwaha, J. Sukhatme, and R. S. Nanjundiah, “Classification of Middle Tropospheric Systems over the Arabian Sea and Western India,” vol. 149, no. 754, pp. 1572–1592, Mar. 2022, doi: 10.1002/qj.4466.

A. Khattak, P.-W. Chan, F. Chen, H. Peng, and C. Mongina Matara, “Missed Approach, a Safety-Critical Go-Around Procedure in Aviation: Prediction Based on Machine Learning-Ensemble Imbalance Learning,” Advances in Meteorology, vol. 2023, pp. 1–24, Jul. 2023, doi: 10.1155/2023/9119521.

K. Kováčiková, A. Novák, M. Kováčiková, and A. Novak Sedlackova, “A Bibliometric Analysis of the Impact of Extreme Weather on Air Transport Operations,” Atmosphere (Basel)., vol. 16, no. 6, p. 740, Jun. 2025, doi: 10.3390/atmos16060740.

C. L. Loi, C. Wu, and Y. Liang, “Prediction of Tropical Cyclogenesis Based on Machine Learning Methods and Its SHAP Interpretation,” J. Adv. Model. Earth Syst., vol. 16, no. 3, pp. 1–20, Mar. 2024, doi: 10.1029/2023MS003637.

I. Hatıpoğlu and Ö. Tosun, “Predictive Modeling of Flight Delays at an Airport Using Machine Learning Methods,” Applied Sciences, vol. 14, no. 13, p. 5472, Jun. 2024, doi: 10.3390/app14135472.

A. M. Ikotun, M. S. Almutari, and A. E. Ezugwu, “K-Means-Based Nature-Inspired Metaheuristic Algorithms for Automatic Data Clustering Problems: Recent Advances and Future Directions,” Applied Sciences, vol. 11, no. 23, p. 11246, Nov. 2021, doi: 10.3390/app112311246.

A. M. Ikotun, F. Habyarimana, and A. E. Ezugwu, “Cluster validity indices for automatic clustering: A comprehensive review,” Heliyon, vol. 11, no. 2, p. e41953, Jan. 2025, doi: 10.1016/j.heliyon.2025.e41953.

A. M. Ikotun, A. E. Ezugwu, L. Abualigah, B. Abuhaija, and J. Heming, “K-means clustering algorithms: A comprehensive review, variants analysis, and advances in the era of big data,” Inf. Sci. (N. Y)., vol. 622, pp. 178–210, Apr. 2023, doi: 10.1016/j.ins.2022.11.139.

N. L. G. P. Suwirmayanti, E. Setyaningsih, R. A. N. Diaz, and K. Budiarta, “Optimization Of The K-Means Method For Clustering Banking Data Using The Hybrid Model Of Invasive Weed Optimization And K-Means (IWOKM),” ICIC Express Letters, vol. 18, no. 4, pp. 413–422, Apr. 2024, doi: 10.24507/icicel.18.04.413.

T. Handhayani, D. Arisandi, and W. Wasino, “Integrated analysis of meteorological conditions and agricultural yields in Indonesia using causal learning and intelligent clustering for climate change mitigation,” Sci. Rep., vol. 16, no. 1, p. 8657, Feb. 2026, doi: 10.1038/s41598-026-40418-5.

P. Fränti and S. Sieranoja, “How much can k-means be improved by using better initialization and repeats?,” Pattern Recognit., vol. 93, pp. 95–112, Sep. 2019, doi: 10.1016/j.patcog.2019.04.014.

A. A. Khan, M. S. Bashir, A. Batool, M. S. Raza, and M. A. Bashir, “K‐Means Centroids Initialization Based on Differentiation Between Instances Attributes,” International Journal of Intelligent Systems, vol. 2024, no. 1, Jan. 2024, doi: 10.1155/2024/7086878.

Q. Bi, H. Sun, C. Qian, and K. Zhang, “An improved seeds scheme in K‐means clustering algorithm for the UAVs control system application,” IET Communications, vol. 18, no. 7, pp. 437–449, Apr. 2024, doi: 10.1049/cmu2.12746.

N. H. M. M. Shrifan, M. F. Akbar, and N. A. M. Isa, “An adaptive outlier removal aided k-means clustering algorithm,” Journal of King Saud University - Computer and Information Sciences, vol. 34, no. 8, pp. 6365–6376, Sep. 2022, doi: 10.1016/j.jksuci.2021.07.003.

H. Irwandi, O. S. Sitompul, and S. Sutarman, “K-Means Performance Optimization Using Rank Order Centroid (ROC) And Braycurtis Distance,” SinkrOn, vol. 7, no. 2, pp. 472–478, Apr. 2022, doi: 10.33395/sinkron.v7i2.11371.

A. E. Ezugwu, “Nature-inspired metaheuristic techniques for automatic clustering: a survey and performance study,” SN Appl. Sci., vol. 2, no. 2, Feb. 2020, doi: 10.1007/s42452-020-2073-0.

A. E. S. Ezugwu, M. B. Agbaje, N. Aljojo, R. Els, H. Chiroma, and M. A. Elaziz, “A Comparative Performance Study of Hybrid Firefly Algorithms for Automatic Data Clustering,” IEEE Access, vol. 8, pp. 121089–121118, 2020, doi: 10.1109/ACCESS.2020.3006173.

A. M. Ikotun and A. E. Ezugwu, “Boosting k-means clustering with symbiotic organisms search for automatic clustering problems,” PLoS One, vol. 17, no. 8, p. e0272861, Aug. 2022, doi: 10.1371/journal.pone.0272861.

T. M. Shami, A. A. El-Saleh, M. Alswaitti, Q. Al-Tashi, M. A. Summakieh, and S. Mirjalili, “Particle Swarm Optimization: A Comprehensive Survey,” IEEE Access, vol. 10, pp. 10031–10061, 2022, doi: 10.1109/ACCESS.2022.3142859.

S. Sendari, A. B. Putra Utama, N. S. Fanany Putri, P. Widiharso, and R. J. Putra, “K-Means and Fuzzy C-Means Optimization using Genetic Algorithm for Clustering Questions,” International Journal of Advanced Science and Computer Applications, vol. 1, no. 1, pp. 1–9, Dec. 2021, doi: 10.47679/ijasca.v1i1.2.

S. Pourahmad, A. Basirat, A. Rahimi, and M. Doostfatemeh, “Does Determination of Initial Cluster Centroids Improve the Performance of K-Means Clustering Algorithm? Comparison of Three Hybrid Methods by Genetic Algorithm, Minimum Spanning Tree, and Hierarchical Clustering in an Applied Study,” Comput. Math. Methods Med., vol. 2020, pp. 1–11, Aug. 2020, doi: 10.1155/2020/7636857.

H. Yue, H. Zhang, and Y. Dai, “Application of PSO-integrated K-means algorithm in resident digital portrait classification,” PLoS One, vol. 20, no. 8, p. e0329123, Aug. 2025, doi: 10.1371/journal.pone.0329123.

M. Daviran, R. Ghezelbash, and A. Maghsoudi, “GWOKM: A novel hybrid optimization algorithm for geochemical anomaly detection based on Grey wolf optimizer and K-means clustering,” Geochemistry, vol. 84, no. 1, p. 126036, Apr. 2024, doi: 10.1016/j.chemer.2023.126036.

A. Kaur, Y. Kumar, and J. Sidhu, “Exploring meta-heuristics for partitional clustering: methods, metrics, datasets, and challenges,” Artif. Intell. Rev., vol. 57, no. 10, Oct. 2024, doi: 10.1007/s10462-024-10920-1.

T. Dokeroglu, D. Canturk, and T. Kucukyilmaz, “A survey on pioneering metaheuristic algorithms between 2019 and 2024,” Dec. 2024.

M. A. Syakur, B. K. Khotimah, E. M. S. Rochman, and B. D. Satoto, “Integration K-Means Clustering Method and Elbow Method For Identification of The Best Customer Profile Cluster,” IOP Conf. Ser. Mater. Sci. Eng., vol. 336, p. 012017, Apr. 2018, doi: 10.1088/1757-899X/336/1/012017.

P. M. Hasugian, B. Sinaga, J. Manurung, and S. A. Al Hashim, “Best Cluster Optimization with Combination of K-Means Algorithm And Elbow Method Towards Rice Production Status Determination,” International Journal of Artificial Intelligence Research, vol. 5, no. 1, Jun. 2021, doi: 10.29099/ijair.v6i1.232.

M. Shutaywi and N. N. Kachouie, “Silhouette Analysis for Performance Evaluation in Machine Learning with Applications to Clustering,” Entropy, vol. 23, no. 6, p. 759, Jun. 2021, doi: 10.3390/e23060759.