Predict Of Average Humadity in Central Java Clomatology Station Using The SARIMAX Method (Seasonal Autoregressive  Integrated Moving Average With Exogenous Variables) With Average Temperature As The Exogenous Variable

Ailsha Syafa Kinanta; Ihsan Fathoni Amri; Selvi Ana Windia Sari; M. Al Haris; Isnaeni Miftahul Sidqi; Mochamad Fahmi Choirudin

doi:10.30598/parameterv3i02pp93-106

Ailsha Syafa Kinanta Unimus
Ihsan Fathoni Amri Universitas Muhammadiyah Semarang https://orcid.org/0009-0004-7978-8773
Selvi Ana Windia Sari Universitas Muhammadiyah Semarang
M. Al Haris Universitas Muhammadiyah Semarang https://orcid.org/0000-0003-3702-3161
Isnaeni Miftahul Sidqi Universitas Muhammadiyah Semarang
Mochamad Fahmi Choirudin Universitas Muhammadiyah Semarang

DOI: https://doi.org/10.30598/parameterv3i02pp93-106

Keywords: Humidity, Temperature, SARIMAX, Forecasting

Abstract

Average humidity in Indonesia varies depending on location and season. Humidity can also vary throughout the day, with peak humidity usually occurring in the morning and decreasing during the day before increasing again at night. This study aims to predict the average humidity at the Central Java Climatology Station using the SARIMAX (Seasonal Autoregressive Integrated Moving Average with Exogenous Variables) method. The SARIMAX method was chosen because it has the ability to handle time series data that has a seasonal component and involves exogenous variables. Average temperature is used as an exogenous variable because there is a significant correlation between average temperature and average humidity. The average humidity and temperature data were taken from daily records for the period used in the study. The SARIMAX model was then developed with optimized parameters through an iterative process to achieve maximum prediction accuracy. The results showed that the SARIMAX (1, 1, 1)(1, 1, 1)4 model with an AIC value of 323.89 and a MAPE value of 2.863913 was able to provide a fairly accurate prediction of the average humidity at the Central Java Climatology Station, with the lowest prediction error. This model can predict the average humidity for the next 8 days. These findings can help in planning and managing various sectors of activity in the region.

Downloads

Download data is not yet available.

References

DAFTAR PUSTAKA
[1] M. H. Mukron, “Peramalan Curah Hujan di Stasiun Meteorologi Klimatologi Geofisika di Jawa Tengah Menggunakan GSTAR Kalman Filter,” 2021, [Online]. Available: http://repository.unimus.ac.id/4817/%0Ahttp://repository.unimus.ac.id/4817/6/12 BAB II.pdf
[2] Aszani, “Penerapan Probabilistic Neural Network(Pnn) Untuk Prakiraan Cuaca Kota Pekanbaru,” no. 2504, pp. 1–9, 2018.
[3] M. Azizah, A. Subiyanto, S. Triutomo, and D. Wahyuni, “Pengaruh Perubahan Iklim Terhadap Bencana Hidrometeorologi di Kecamatan Cisarua - Kabupaten Bogor,” PENDIPA J. Sci. Educ., vol. 6, no. 2, pp. 541–546, 2022, doi: 10.33369/pendipa.6.2.541-546.
[4] S. Prasetyo, Ulil Hidayat, Yosafat Donni Haryanto, and Nelly Florida Riama, “Karakteristik Suhu Udara di Pulau Jawa Kaitannya Dengan Kelembapan Udara, Curah Hujan, SOI, dan DMI,” J. Geogr. Edukasi dan Lingkung., vol. 5, no. 1, pp. 15–26, 2021, doi: 10.22236/jgel.v5i1.5971.
[5] Y. N. I. Fathulrohman and A. Saepuloh, “Alat Monitoring Suhu Dan Kelembaban Menggunakan Arduino Uno,” Jumantaka, vol. 02, no. 1, p. 1, 2018, [Online]. Available: https://jurnal.stmik-dci.ac.id/index.php/jumantaka/article/view/361
[6] R. M. Abdurrohman, “Prototipe Monitoring Suhu Dan Kelembapan Secara Realtime,” J. ICTEE, vol. 4, no. 2, p. 29, 2023, doi: 10.33365/jictee.v4i2.3158.
[7] Y. Novianto and Y. Nataliani, “Peramalan Curah Hujan dengan Pengelompokan Bulan Menggunakan Metode Double Exponential Smoothing dari Brown,” J. Sist. dan Teknol. Inf., vol. 10, no. 4, p. 347, 2022, doi: 10.26418/justin.v10i4.47167.
[8] G. L. Marcus, H. J. Wattimanela, and Y. A. Lesnussa, “Analisis Regresi Komponen Utama Untuk Mengatasi Masalah Multikolinieritas Dalam Analisis Regresi Linier Berganda,” BAREKENG J. Ilmu Mat. dan Terap., vol. 6, no. 1, pp. 31–40, 2012, doi: 10.30598/barekengvol6iss1pp31-40.
[9] I. Satria, A. Anas Manurung, and M. A. Hanafiah, “Analisis Perkembangan Produksi Tanaman Biofarmaka (Obat) di Indonesia Menggunakan Algoritma Resilient,” vol. 5, no. 1, pp. 122–131, 2023.
[10] H. K. Juliarto, I. Purnamasari, and S. Prangga, “Peramalan Peredaran Uang Kartal Di Indonesia Menggunakan Model Hybrid Sarimax-Neural Network,” J. Gaussian, vol. 12, pp. 465–476, 2024, doi: 10.14710/j.gauss.12.4.465-476.
[11] N. H. Latief, N. Nur’eni, and I. Setiawan, “Peramalan Curah Hujan di Kota Makassar dengan Menggunakan Metode SARIMAX,” Stat. J. Theor. Stat. Its Appl., vol. 22, no. 1, pp. 55–63, 2022, doi: 10.29313/statistika.v22i1.990.
[12] L. Fitriyah, “Pemodelan Penderita Demam Berdarah Dengue (DBD) di Kabupaten Gresik Menggunakan Arima dan Regresi Nonparametrik Kernel,” J. Chem. Inf. Model., vol. 53, no. 9, pp. 1689–1699, 2019.
[13] N. Mutammimah, P. S. Matematika, F. Sains, D. A. N. Teknologi, U. Islam, and N. Sunan, “Prediksi jumlah produksi padi di jawa timur menggunakan metode sarima with exogeneus input (sarimax),” 2022.
[14] N. Permatasari, “Penggunaan Indeks Google Trend Dalam Peramalan Jumlah Pengunjung Taman Rekreasi Selecta Tahun 2020,” Semin. Nas. Off. Stat., vol. 2021, no. 1, pp. 1019–1024, 2021, doi: 10.34123/semnasoffstat.v2021i1.993.
[15] A. A. Indrawati, Pemodelan SARIMAX Variasi Liburan dengan Deret Input Data Iklan (Studi Kasus pada Data Mingguan Banyaknya Pengunjung Taman Rekreasi Yayasan Paggora Kediri). 2017.
[16] Z. Zalila, “Peramalan Jumlah Kunjungan Wisatawan Mancanegara Ke Provinsi Jawa Tengah dengan Metode Seasonal Autoregressive Integrated Moving Average With Exogeneous Input (SARIMAX),” pp. 8–28, 2019, [Online]. Available: http://repository.unimus.ac.id