Analisis Pola Konvergensi Transpor Kelembapan Udara di Indonesia Bagian Barat Menggunakan K-Means dengan Pembobotan Statistik dan Hierarchical Shape-Based Clustering


Asri Pratiwi(1*), Tukhfatur Rizmah Azis(2), Anwar Fitrianto(3), Erfiani Erfiani(4), L.M. Risman Dwi Jumansyah(5)

(1) IPB University, Indonesia
(2) IPB University, Indonesia
(3) IPB University, Indonesia
(4) IPB University, Indonesia
(5) IPB University, Indonesia
(*) Corresponding Author

Abstract


This study analyzes the convergence patterns of Vertically Integrated Moisture Transport (VIMT) in the western region of Indonesia using the K-Means method with statistical weighting and Hierarchical Shape-Based Clustering based on Dynamic Time Warping (DTW). Daily data on specific humidity, zonal wind speed, and meridional wind speed from 2020–2023 were used to calculate VIMT. Clustering methods were utilized to identify grouping patterns in moisture transport data. The results showed that moisture convergence significantly increased during the rainy season (November–February). Using the K-Means method, five clusters with clearer separations were obtained compared to the four clusters produced by the Hierarchical Clustering method. Performance evaluation using Silhouette and Calinski-Harabasz scores indicated that the K-Means method was superior, with scores of 0.37 and 104.88 compared to 0.13 and 96.34 for the Hierarchical method. This provides an understanding of the moisture transport patterns, serving as a reference for predicting weather and climate patterns, thereby supporting efforts to mitigate the impacts of extreme weather in Western Indonesia.

Keywords


Convergence, DTW, hierarchical clustering, k-means, moisture, VIMT

References


A. I. Károly, R. Fullér, and P. Galambos, “Unsupervised Clustering for Deep Learning: A tutorial survey,” Acta Polytech. Hungarica, vol. 15, no. 8, 2018.

I. Nurandini and A. F. Huda, “Klastering Dokumen dengan Menambahkan Metadata Menggunakan Algoritma COATES,” KUBIK: Jurnal Publikasi Ilmiah Matematika, vol.2, no.2, 2017. Accessed: Nov. 25, 2024. [Online]. Available: https://journal.uinsgd.ac.id/index.php/kubik/article/view/1859

J. Singh and D. Singh, “A comprehensive review of clustering techniques in artificial intelligence for knowledge discovery: Taxonomy, challenges, applications and future prospects,” Adv. Eng. Informatics, vol. 62, p. 102799, Oct. 2024, doi: 10.1016/J.AEI.2024.102799.

D. Dedy and A. Cherid, “Data Mining Pengolahan Data Calon Pekerja Migran Indonesia (PMI) dengan Penerapan Metode Klustering K-Means dan Metode Klasifikasi K-Nearest Neighbor (KNN): Studi Kasus PT. SAM,” Format J. Ilm. Tek. Inform., vol. 9, no. 2, pp. 166–182, Jan. 2021, doi: 10.22441/FORMAT.2020.V9.I2.008.

P. Shetty and S. Singh, “Hierarchical Clustering: A Survey,” Int. J. Appl. Res., vol. 7, no. 4, pp. 178–181, Apr. 2021, doi: 10.22271/ALLRESEARCH.2021.V7.I4C.8484.

B. Khouider, “Moisture and Moist Thermodynamics,” Math. Planet Earth, pp. 23–39, 2019, doi: 10.1007/978-3-030-17775-1_2.

B. M. Smirnov, “Physical Aspects of Climate Change,” Global Energetics of the Atmosphere, pp. 261–291, 2021, doi: 10.1007/978-3-030-90008-3_10.

A. Vázquez-Patiño, L. Campozano, D. Ballari, M. Córdova, and E. Samaniego, “Virtual Control Volume Approach to the Study of Climate Causal Flows: Identification of Humidity and Wind Pathways of Influence on Rainfall in Ecuador,” Atmos. 2020, Vol. 11, Page 848, vol. 11, no. 8, p. 848, Aug. 2020, doi: 10.3390/ATMOS11080848.

N. Hamilton, “Atmospheric condition identification in multivariate data through a metric for total variation,” Atmos. Meas. Tech., vol. 13, no. 2, pp. 1019–1032, Mar. 2020, doi: 10.5194/AMT-13-1019-2020.

M. A. De Oliveira, F. A. Varone, C. W. Fraisse, R. M. Araújo, and G. G. H. Cavalheiro, “Clustering of meteorological data to improve agricultural decisions: a case study with SIMAGRO-RS,” ACM Int. Conf. Proceeding Ser., May 2024, doi: 10.1145/3658271.3658288.

B. N. Ruchjana, H. Khoirunnisa, I. Irianingsih, and B. Suhandi, “Perbandingan Penerapan Metode Agglomerative dengan Metode K-Means pada Data Curah Hujan di Wilayah Bogor,” KUBIK: Jurnal Publikasi Ilmiah Matematika, vol.5 no.2, 2020. Accessed: Nov. 25, 2024. [Online]. Available: https://journal.uinsgd.ac.id/index.php/kubik/article/view/7581

B. Prihasto, D. Darmansyah, D. P. Yuda, F. M. Alwafi, H. N. Ekawati, and Y. P. Sari, “Comparative Analysis of K-Means and K-Medoids Clustering Methods on Weather Data of Denpasar City,” J. Pendidik. Multimed., vol. 5, no. 2, pp. 91–114, Dec. 2023, doi: 10.17509/EDSENCE.V5I2.65925.

R. Bhardwaj and V. Duhoon, “Study and Analysis of Time Series of Weather Data of Classification and Clustering Techniques,” Adv. Intell. Syst. Comput., vol. 1165, pp. 257–270, 2021, doi: 10.1007/978-981-15-5113-0_19.

Y. Barrera et al., “Clustering high dimensional meteorological scenarios: Results and performance index,” Int. J. Approx. Reason., vol. 139, pp. 1–11, Dec. 2021, doi: 10.1016/J.IJAR.2021.08.007.

K. Chansaengkrachang, A. Luadsong, and N. Aschariyaphotha, “Vertically Integrated Moisture Flux Convergence over Southeast Asia and Its Relation to Rainfall over Thailand,” Pertanika J. Sci. Technol, vol. 26, no. 1, pp. 235–246, 2018, Accessed: Oct. 09, 2024. [Online]. Available: https://rbkm.kmutt.ac.th/xmlui//handle/123456789/1665

“GRIB Parameter Database: Param 213.,” European Centre for Medium-Range Weather Forecasts.(n.d.).Accessed:Sep.30,2024.[Online].Available: https://codes.ecmwf.int/grib/param-db/213.

G. Pernigotto, A. Walsh, A. Gasparella, and J. L. M. Hensen, “Clustering of European Climates and Representative Climate Identification for Building Energy Simulation Analyses”, doi: 10.26868/25222708.2019.210938.

D. Sathiaraj, X. Huang, and J. Chen, “Predicting climate types for the Continental United States using unsupervised clustering techniques,” Environmetrics, vol. 30, no. 4, p. e2524, Jun. 2019, doi: 10.1002/ENV.2524.

D. M. Straus, “Clustering Techniques in Climate Analysis,” Oxford Res. Encycl. Clim. Sci., Feb. 2018, doi: 10.1093/ACREFORE/9780190228620.013.711.

T. Kurihana et al., “Identifying Climate Patterns Using Clustering Autoencoder Techniques,” Artif. Intell. Earth Syst., vol. 3, no. 3, Aug. 2024, doi: 10.1175/AIES-D-23-0035.1.

Badan Pusat Statistik , “Statistik Indonesia 2023 (No. 03200.2303),” 2023. Accessed: Sep. 30, 2024.[Online].Available: https://www.bps.go.id/id/publication/2023/02/28/18018f9896f09f03580a614b/statistik-indonesia-2023.html

H. Li, “On-line and dynamic time warping for time series data mining,” Int. J. Mach. Learn. Cybern., vol. 6, no. 1, pp. 145–153, Feb. 2015, doi: 10.1007/S13042-014-0254-0/METRICS.

S. Demir, “Comparison of Normality Tests in Terms of Sample Sizes under Different Skewness and Kurtosis Coefficients,” Int. J. Assess. Tools Educ., vol. 2022, no. 2, pp. 397–409, 2022, doi: 10.21449/ijate.1101295.

H. B. Zhou and J. T. Gao, “Automatic Method for Determining Cluster Number Based on Silhouette Coefficient,” Adv. Mater. Res., vol. 951, pp. 227–230, 2014, doi: 10.4028/WWW.SCIENTIFIC.NET/AMR.951.227.

G. Zhu, X. Li, S. Zhang, X. Xu, and B. Zhang, “An improved method for k-means clustering based on internal validity indexes and inter-cluster variance,” Int. J. Comput. Sci. Eng., vol. 25, no. 3, p. 253, 2022, doi: 10.1504/IJCSE.2022.123112.




DOI: https://doi.org/10.15575/kubik.v9i2.39753

Refbacks

  • There are currently no refbacks.


Copyright (c) 2024 Asri Pratiwi

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.


Journal KUBIK: Jurnal Publikasi Ilmiah Matematika has indexed by:

SINTA DOAJ Dimensions Google Scholar Garuda Moraref DOI Crossref

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.