Prediksi Indeks Kenyamanan (THI) Menggunakan Metode Long Shortterm Memory (LSTM) di Pelabuhan Tanjung Mas Semarang: Sains | Jurnal Pendidikan Matematika : Judika Education

Authors

Puryani Puryani Universitas Negeri Semarang
Djuniadi Universitas Negeri Semarang
Ngurah Made Darma Putra Universitas Negeri Semarang
Furqon Alfahmi Badan Meteorologi Klimatologi dan Geofisika
Mahardika Jalu Pradana Badan Meteorologi Klimatologi dan Geofisika

DOI:

Abstract

The Temperature Humidity Index (THI) is used to assess thermal comfort levels based on air temperature and relative humidity. The hot and humid conditions at Tanjung Mas Port, Semarang, make THI prediction essential for coastal area planning. This study aims to develop a THI prediction model using the Long Short-Term Memory (LSTM) method with input data of air temperature and relative humidity for the period of September–December 2022. The data were normalized using Min–Max Scaling and evaluated using Pearson correlation, RMSE, and MAPE. The results show that the LSTM model achieved high accuracy with a correlation coefficient of 0.95, RMSE of 0.46, and MAPE of 1.38%, demonstrating its ability to capture daily fluctuation patterns effectively. Therefore, the LSTM method can serve as a reliable predictive tool for monitoring thermal comfort in coastal urban areas.

Keywords: Comfort Index, Relative Humidity, LSTM, Prediction, Air Temperature

Author Biographies

Djuniadi, Universitas Negeri Semarang

Dosen
Ngurah Made Darma Putra, Universitas Negeri Semarang

Dosen
Furqon Alfahmi, Badan Meteorologi Klimatologi dan Geofisika

Badan Meteorologi Klimatologi dan Geofisika
Mahardika Jalu Pradana, Badan Meteorologi Klimatologi dan Geofisika

Badan Meteorologi Klimatologi dan Geofisika

References

Akbar, R., Santoso, R., & Warsito, B. (2023). Prediksi Tingkat Temperatur Kota Semarang Menggunakan Metode Long Short-Term Memory (Lstm). Jurnal Gaussian, 11(4), 572–579. https://doi.org/10.14710/j.gauss.11.4.572-579

Ando, R., & Takefuji, Y. (2021). A Randomized Hyperparameter Tuning of Adaptive Moment Estimation Optimizer of Binary Tree-Structured LSTM. International Journal of Advanced Computer Science and Applications, 12(7), 623–629. https://doi.org/10.14569/IJACSA.2021.0120771

Arwansyah, A., Suryani, S., SY, H., Usman, U., Ahyuna, A., & Alam, S. (2022). Time Series Forecasting Menggunakan Deep Gated Recurrent Units. Digital Transformation Technology, 4(1), 410–416. https://doi.org/10.47709/digitech.v4i1.4141

Akbar, R., Santoso, R., & Warsito, B. (2023). Prediksi Tingkat Temperatur Kota Semarang Menggunakan Metode Long Short-Term Memory (Lstm). Jurnal Gaussian, 11(4), 572–579. https://doi.org/10.14710/j.gauss.11.4.572-579

Chin, W. H., & Kubota, N. (2023). Big data analytics for relative humidity time series forecasting based on the LSTM network and ELM. 9(3), 537–550. https://doi.org/10.26555/ijain.v9i3.905

Kholifatullah, B. A. H., & Prihanto, A. (2023). Penerapan Metode Long Short Term Memory untuk Klasifikasi Pada Hate Speech. Journal of Informatics and Computer Science (JINACS), 04, 292–297. https://doi.org/10.26740/jinacs.v4n03.p292-297

Mahabella, L. S., & Waibo, O. R. G. (2020). Analisis Nilai Indeks Suhu dan Kelembaban Ruang Terbuka Taman Rekreasi Sengkaling. Media Teknik Sipil, 18(2), 75–82. doi:https://doi.org/10.22219/jmts.v18i2.15200

Ruth Saragih, R. M., Rusmayadi, G., Adriani, D. E., & Nugroho, Y. (2024). Analisis Perubahan Urban Heat Island dan Pengaruhnya Terhadap Indeks Kenyamanan Kota Banjarbaru. EnviroScienteae, 20(1), 71–80. https://ppjp.ulm.ac.id/journal/index.php/es/article/view/18850

Selle, N., Yudistira, N., & Dewi, C. (2022). Perbandingan Prediksi Penggunaan Listrik dengan Menggunakan Metode Long Short Term Memory (LSTM) dan Recurrent Neural Network (RNN). Jurnal Teknologi Informasi Dan Ilmu Komputer, 9(1), 155–162. https://doi.org/10.25126/jtiik.2022915585

Hidayatullah, S., & Cherid, A. (2023). Prediksi Temperatur Cuaca di Negara Norwegia Menggunakan Metode LSTM. Jurnal Sistem Informasi dan Sistem Komputer, 8(2), 187-198. https://doi.org/10.51717/simkom.v8i2.192

Tan, N., Suwarlan, S. A., & Aguspriyanti, C. D. (2023). Peningkatan Kenyamanan Termal Sekolah di Iklim Tropis Pesisir Melalui Konsep Bioclimatic Architecture. Journal of Architectural Design and Development (JAD), 4(2), 146-156. https://doi.org/10.37253/jad.v4i2.8566

Waqas, M., & Humphries, U. W. (2024). A critical review of RNN and LSTM Variants in Hydrological Time Series Predictions. MethodsX, 13, 102946. https://doi.org/10.1016/j.mex.2024.102946

Wen, X., & Li, W. (2023). Time Series Prediction Based on LSTM-Attention-LSTM Model. IEEE Access, 11, 48322–48331. https://doi.org/10.1109/ACCESS.2023.3276628

Zaky, F. A., Herbowo, A. C. F., Abrari, F. H., Ally, H., Al-Dzahabi, M. A., Hanif Ahsani Taqwim, M. H. A., Ibriza, N. M., Fil’ardiani, U., Agustin, Y. S., & Daniswara, A. P. (2024a). Analisis Temperature Humidity Index (THI) Secara Time-Series Menggunakan Sistem Monitoring Berbasis Internet Of Things (IoT) di Kelurahan Sumber, Banjarsari, Surakarta. Jurnal Ekosains, Vol. 16(No. 1), Hal. 44-51. www.sumber.eennos.online.

Zaky, F. A., Herbowo, A. C. F., Abrari, F. H., Ally, H., Al-Dzahabi, M. A., Hanif Ahsani Taqwim, M. H. A., Ibriza, N. M., Fil’ardiani, U., Agustin, Y. S., & Daniswara, A. P. (2024b). Analisis Temperature Humidity Index (THI) Secara Time-Series Menggunakan Sistem Monitoring Berbasis Internet of Things (IoT) di Kelurahan Sumber, Banjarsari, Surakarta. Ekosains, 16(1), 44–51. https://doi.org/10.14710/j.gauss.11.4.572-579