Integrating Principal Component Analysis and Clustering for High-Resolution Meteorological Forecasting: A Case Study Using BMKG

  • Helga Charolina Antonia Silubun Physics Education Lecturer, Faculty of Teacher Training and Education, Universitas Musamus
  • Arya Dewa Haryanto Lecturer in Electrical Dept. Engineering Faculty, Universitas Negeri Yogyakarta
  • Rusly Rusly Lecturer in Computer Education, Faculty of Teacher Training and Education, Universitas Musamus
  • Andi Azizah Lecturer in Computer Education, Faculty of Teacher Training and Education, Universitas Musamus

Keywords

PCA, Cluster-K Means, Neural Networks, Weather Forecasting, Hybrid Methods, Data Analysis.

Abstract

Penelitian ini bertujuan untuk mengintegrasikan teknik Analisis Komponen Utama (PCA) dan pengelompokan (clustering) dalam analisis data berdimensi tinggi. Metode PCA digunakan untuk mengurangi dimensi data tanpa kehilangan informasi penting, sedangkan pengelompokan membantu mengelompokkan pola serupa dalam data. Studi ini menerapkan pendekatan ini pada dataset data harian BMKG untuk periode 1 Januari 2024 hingga 19 November 2024, dengan total 325 observasi dari Data Online BMKG di Stasiun Geofisika Sleman DI Yogyakarta, menunjukkan bahwa kombinasi PCA dan pengelompokan meningkatkan efisiensi dan akurasi analisis. Hasil penelitian menunjukkan bahwa teknik hibrida atau integrasi antara PCA, pengelompokan (K-Means), dan jaringan saraf, mampu memberikan solusi efektif untuk analisis data berdimensi tinggi, menghasilkan model prediksi yang akurat dan andal. Penelitian ini dapat menjadi dasar untuk mengembangkan sistem peringatan dini cuaca yang lebih baik dan mendukung pengambilan keputusan yang lebih efektif di berbagai sektor.

References

Abdi, H. and Williams, L.J. (2010) ‘Principal component analysis’, WIREs Computational Statistics, 2(4). Available at: https://doi.org/10.1002/wics.101.

Ba, A. et al. (2023) ‘Power optimization of a photovoltaic system with artificial intelligence algorithms over two seasons in tropical area’, MethodsX, 10. Available at: https://doi.org/10.1016/j.mex.2022.101959.

Balsa, C. et al. (2023) ‘Reconstruction of Meteorological Records by Methods Based on Dimension Reduction of the Predictor Dataset’, Computation, 11(5), p. 98. Available at: https://doi.org/10.3390/computation11050098.

Duarte, B. et al. (2022) ‘Elemental Chemometrics as Tools to Depict Stalked Barnacle (Pollicipes Pollicipes) Harvest Locations and Food Safety’, Molecules, 27(4), p. 1298. Available at: https://doi.org/10.3390/molecules27041298.

Ernst, D. and Dolničar, S. (2017) ‘How to Avoid Random Market Segmentation Solutions’, Journal of Travel Research, 57(1). Available at: https://doi.org/10.1177/0047287516684978.

Geng, D.Y., Zhang, H. and Wu, H. (2020) ‘Short-Term Wind Speed Prediction Based on Principal Component Analysis and LSTM’, Applied Sciences, 10(13), p. 4416. Available at: https://doi.org/10.3390/app10134416.

Gunawan, G. (2024) ‘Disaster Event, Preparedness, and Response in Indonesian Coastal Areas: Data Mining of Official Statistics’, International Journal of Computing and Digital Systems, 15(1), pp. 249–264. Available at: https://doi.org/10.12785/ijcds/160120.

Habibi, M. and Cahyo, P.W. (2019) ‘Clustering User Characteristics Based on the influence of Hashtags on the Instagram Platform’, IJCCS (Indonesian Journal of Computing and Cybernetics Systems), 13(4). Available at: https://doi.org/10.22146/ijccs.50574.

Karamizadeh, S. et al. (2013) ‘An Overview of Principal Component Analysis’, Journal of Signal and Information Processing, 4(3), pp. 173–175. Available at: https://doi.org/10.4236/jsip.2013.43B031.

Kashyap, A. et al. (2020) ‘K- Mean and Euclidian Cluster Analysis for Salt Tolerance Rice Genotypes under Alkaline Soil Condition’, International Journal of Current Microbiology and Applied Sciences, 9(11). Available at: https://doi.org/10.20546/ijcmas.2020.911.043.

Khairati, F. and Putra, H. (2022) ‘Prediksi Kuantitas Penggunaan Obat Pada Layanan Kesehatan Menggunakan Algoritma Backpropagation Neural Network’, Jurnal Sistim Informasi Dan Teknologi, pp. 128–135. Available at: https://doi.org/10.37034/jsisfotek.v4i3.158.

Lèbre, S. et al. (2010) ‘Statistical inference of the time-varying structure of gene-regulation networks’, BMC Systems Biology, 4(1). Available at: https://doi.org/10.1186/1752-0509-4-130.

Lee, S.-H. et al. (2023) ‘Label‐free Atherosclerosis Diagnosis Through a Blood Drop of Apolipoprotein E Knockout Mouse Model Using Surface‐enhanced Raman Spectroscopy Validated by Machine Learning Algorithm’, Bioengineering & Translational Medicine, 8(4). Available at: https://doi.org/10.1002/btm2.10529.

Malinowski, M., Rohrbach, M. and Fritz, M. (2017) ‘Ask Your Neurons: A Deep Learning Approach to Visual Question Answering’, International Journal of Computer Vision, 125(1–3). Available at: https://doi.org/10.1007/s11263-017-1038-2.

Mathivanan, N.M.N., Ghani, N.A.M. and Janor, R.M. (2019) ‘A comparative study on dimensionality reduction between principal component analysis and k-means clustering’, Indonesian Journal of Electrical Engineering and Computer Science, 16(2). Available at: https://doi.org/10.11591/ijeecs.v16.i2.pp752-758.

Matsushima, A. et al. (2017) ‘Principal component analysis for ataxic gait using a triaxial accelerometer’, Journal of NeuroEngineering and Rehabilitation, 14(1). Available at: https://doi.org/10.1186/s12984-017-0249-7.

Muhariya, A., Riadi, I. and Prayudi, Y. (2022) ‘Cyberbullying Analysis on Instagram Using K-Means Clustering’, JUITA : Jurnal Informatika, 10(2). Available at: https://doi.org/10.30595/juita.v10i2.14490.

Pokharel, M., Bhatta, J. and Paudel, N. (2021) ‘Comparative Analysis of K-Means and Enhanced K-Means Algorithms for Clustering’, NUTA Journal, 8(1–2). Available at: https://doi.org/10.3126/nutaj.v8i1-2.44044.

Slijepčević, D. et al. (2018) ‘Automatic Classification of Functional Gait Disorders’, IEEE Journal of Biomedical and Health Informatics, 22(5). Available at: https://doi.org/10.1109/jbhi.2017.2785682.

Soares, D.P. et al. (2016) ‘Principal component analysis in ground reaction forces and center of pressure gait waveforms of people with transfemoral amputation’, Prosthetics &Amp; Orthotics International, 40(6). Available at: https://doi.org/10.1177/0309364615612634.

Surono, S. et al. (2023) ‘Developing an optimized recurrent neural network model for air quality prediction using K-means clustering and PCA dimension reduction’, International Journal of Innovative Research and Scientific Studies, 6(2). Available at: https://doi.org/10.53894/ijirss.v6i2.1427.

Vasileva, Y., Nevedrov, A.V. and Subbotin, S.P. (2020) ‘Development and Performance Evaluation of a Computer Program Based on Neural Network Mathematical Models for Forecasting By- Product Yield’, E3S Web of Conferences, 174. Available at: https://doi.org/10.1051/e3sconf/202017403023.

Venkateswarlu, B. and Raju, G. (2013) ‘Mine Blood Donors Information through Improved K-Means Clustering’, International Journal of Computational Science and Information Technology, 1(3). Available at: https://doi.org/10.5121/ijcsity.2013.1302.

Yoseph, F. et al. (2020) ‘The impact of big data market segmentation using data mining and clustering techniques’, Journal of Intelligent &Amp; Fuzzy Systems, 38(5). Available at: https://doi.org/10.3233/jifs-179698.

Yu, T. et al. (2022) ‘A New Strategy for Microbial Taxonomic Identification Through Micro‐Biosynthetic Gold Nanoparticles and Machine Learning’, Advanced Materials, 34(11). Available at: https://doi.org/10.1002/adma.202109365.

Yuan, R. (2021) ‘An improved K-means clustering algorithm for global earthquake catalogs and earthquake magnitude prediction’, Journal of Seismology, 25(3). Available at: https://doi.org/10.1007/s10950-021-09999-8.

Zhou, B. et al. (2020) ‘A Hybrid Method for Ultrashort-Term Wind Power Prediction Considering Meteorological Features and Seasonal Information’, Mathematical Problems in Engineering, 2020, pp. 1–12. Available at: https://doi.org/10.1155/2020/1795486.

2026-11-05