Modeling Earth Skin Temperature and Cloud Amount: A Hybrid Fourier Series – Neural Network for Kalimantan Environmental Patterns

Andrea Tri Rian  Dani; Nur Chamidah; I Nyoman  Budiantara; Dursun Aydin; Ahmad Hakiim  Jamaluddin; Naufal Ramadhan Al Akhwal  Siregar

doi:10.59395/ijadis.v7i2.1549

Authors

Andrea Tri Rian Dani Doctoral Study Program MIPA, Faculty of Science and Technology, Universitas Airlangga, Indonesia https://orcid.org/0000-0003-1949-3215
Nur Chamidah Department of Mathematics, Faculty of Science and Technology, Universitas Airlangga, Indonesia https://orcid.org/0000-0003-1592-4671
I Nyoman Budiantara Department of Statistics, Faculty of Science and Data Analytics, Sepuluh Nopember Institute of Technology, Indonesia https://orcid.org/0000-0001-6572-4083
Dursun Aydin Department of Statistics, Faculty of Science, Mugla Sitki Kocman University, Turkey
Ahmad Hakiim Jamaluddin Department of Mathematics & Statistics, Universiti Putra Malaysia, Malaysia https://orcid.org/0000-0002-1715-6912
Naufal Ramadhan Al Akhwal Siregar Master of Mathematics Study Program, Faculty of Science and Technology, Airlangga University, Indonesia https://orcid.org/0009-0009-1688-5548

DOI:

https://doi.org/10.59395/ijadis.v7i2.1549

Keywords:

Climate Action, Cloud Amount, Earth Skin Temperature, Fourier Series, Hybrid Model

Abstract

This study focuses on the development and application of a Hybrid Fs-DLFFNN model to analyze Earth Skin Temperature and Cloud Amount in Balikpapan and Samarinda. For comparison purposes, Fourier Series (Fs) and Double Layer Feed Forward Neural Network (DLFFNN) models are also considered. Model performance is evaluated using MSE, RMSE, and MAPE on both training and testing data. The results indicate that the Hybrid Fs-DLFFNN model consistently achieves lower error values on the training data, reflecting its ability to capture both periodic and nonlinear patterns within a unified framework. However, testing results show that model performance varies across variables and locations, highlighting the importance of generalization. Forecasting for the next 18 periods provides indicative patterns of temporal variation in both cities. These projections are presented as exploratory insights rather than definitive conclusions. Overall, the Hybrid Fs-DLFFNN model offers a flexible and integrative approach for modeling complex environmental data. This study contributes to the advancement of hybrid modeling frameworks for environmental time series and provides a foundation for further methodological development and climate-related analysis, in line with the objectives of SDG 13 (Climate Action).

462 137

Downloads

Download data is not yet available.

References

[1] M. Akhtaruzzaman, S. Boubaker, P. Gamage, and V. Obeng, Environmental innovation and climate risk awareness: The moderating role of SDG13, Res Int Bus Finance, vol. 75, Mar. 2025, doi: 10.1016/j.ribaf.2024.102713. DOI: https://doi.org/10.1016/j.ribaf.2024.102713

[2] K. E. Trenberth and D. J. Shea, Relationships between precipitation and surface temperature, Geophys Res Lett, vol. 32, no. 14, pp. 14, Jul. 2005, doi: 10.1029/2005GL022760. DOI: https://doi.org/10.1029/2005GL022760

[3] J. A. Sobrino, Y. Julien, and S. Garca-Monteiro, Surface temperature of the planet earth from satellite data, Remote Sens (Basel), vol. 12, no. 2, Jan. 2020, doi: 10.3390/rs12020218. DOI: https://doi.org/10.3390/rs12020218

[4] H. Iftikhar, M. Khan, J. ywioek, M. Khan, and J. Linkolk Lpez-Gonzales, Modeling and forecasting carbon dioxide emission in Pakistan using a hybrid combination of regression and time series models, Heliyon, vol. 10, no. 13, Jul. 2024, doi: 10.1016/j.heliyon.2024.e33148. DOI: https://doi.org/10.1016/j.heliyon.2024.e33148

[5] A. Radovan, V. unde, D. Kuak, and . Ban, Solar irradiance forecast based on cloud movement prediction, Energies (Basel), vol. 14, no. 13, Jul. 2021, doi: 10.3390/en14133775. DOI: https://doi.org/10.3390/en14133775

[6] S. Sam and M. zger, A multi-method and multi-duration trend analysis of temperature and precipitation in Istanbul, Turkey, by using meteorological records, MERRA-2 reanalysis, and IMERG estimations, HydroResearch, vol. 8, pp. 209222, Jan. 2025, doi: 10.1016/j.hydres.2024.11.005. DOI: https://doi.org/10.1016/j.hydres.2024.11.005

[7] M. T. Nakkazi, J. I. Sempewo, M. D. Tumutungire, and J. Byakatonda, Performance evaluation of CFSR, MERRA-2 and TRMM3B42 data sets in simulating river discharge of data-scarce tropical catchments: a case study of Manafwa, Uganda, Journal of Water and Climate Change, vol. 13, no. 2, pp. 522541, Feb. 2022, doi: 10.2166/wcc.2021.174. DOI: https://doi.org/10.2166/wcc.2021.174

[8] A. T. R. Dani, N. Chamidah, I. N. Budiantara, B. Lestari, R. Kusuma, and D. Aydin, Semiparametric Time Series Regression Using Exponential Complex Fourier Series for Temperature Prediction in the Tropical Rainforest of Samarinda, Innovaciencia, vol. 13, no. 1, Dec. 2025, doi: 10.15649/2346075x.5364. DOI: https://doi.org/10.15649/2346075X.5364

[9] W. W. S. Wei, Time Series Analysis: Univariate and Multivariate Methods, 2nd ed. New York: Pearson Education, Inc, 2006.

[10] T. W. Kim and M. Jehanzaib, Drought risk analysis, forecasting and assessment under climate change, Jul. 01, 2020, MDPI AG. doi: 10.3390/W12071862. DOI: https://doi.org/10.3390/w12071862

[11] B. Billah, M. L. King, R. D. Snyder, and A. B. Koehler, Exponential smoothing model selection for forecasting, Int J Forecast, vol. 22, no. 2, pp. 239247, Apr. 2006, doi: 10.1016/j.ijforecast.2005.08.002. DOI: https://doi.org/10.1016/j.ijforecast.2005.08.002

[12] J. Yu, S. B. Kim, J. Bai, and S. W. Han, Comparative study on exponentially weighted moving average approaches for the self-starting forecasting, Applied Sciences (Switzerland), vol. 10, no. 20, pp. 118, Oct. 2020, doi: 10.3390/app10207351. DOI: https://doi.org/10.3390/app10207351

[13] D. Zhao, R. Zhang, H. Zhang, and S. He, Prediction of global omicron pandemic using ARIMA, MLR, and Prophet models, Sci Rep, vol. 12, no. 1, pp. 113, 2022, doi: 10.1038/s41598-022-23154-4. DOI: https://doi.org/10.1038/s41598-022-23154-4

[14] Suhartono, E. Setyowati, N. A. Salehah, M. H. Lee, S. P. Rahayu, and B. S. S. Ulama, A hybrid singular spectrum analysis and neural networks for forecasting inflow and outflow currency of bank Indonesia, in Communications in Computer and Information Science, Springer Verlag, 2019, pp. 318. doi: 10.1007/978-981-13-3441-2_1. DOI: https://doi.org/10.1007/978-981-13-3441-2_1

[15] M. Bilodeau, Fourier smoother and additive models, The Canadian Journal of Statistics, vol. 20, no. 3, pp. 257269, 1992. DOI: https://doi.org/10.2307/3315313

[16] D. Aydin, A Comparative Study of Neural Networks and Non-Parametric Regression Models for Trend and Seasonal Time Series, Trends Appl Sci Res, vol. 4, no. 3, pp. 126137, Mar. 2009, doi: 10.3923/tasr.2009.126.137. DOI: https://doi.org/10.3923/tasr.2009.126.137

[17] N. Chamidah, S. D. Febriana, R. A. Ariyanto, and R. Sahawaly, Fourier series estimator for predicting international market price of white sugar, in AIP Conference Proceedings, American Institute of Physics Inc., Feb. 2021. doi: 10.1063/5.0042287. DOI: https://doi.org/10.1063/5.0042287

[18] N. Afifah, I. N. Budiantara, and I. N. Latra, Mixed Estimator of Kernel and Fourier Series in Semiparametric Regression, in Journal of Physics: Conference Series, Institute of Physics Publishing, Jun. 2017. doi: 10.1088/1742-6596/855/1/012002. DOI: https://doi.org/10.1088/1742-6596/855/1/012002

[19] I. E. Livieris, E. Pintelas, S. Stavroyiannis, and P. Pintelas, Ensemble Deep learning models for forecasting cryptocurrency time-series, Algorithms, vol. 13, no. 5, May 2020, doi: 10.3390/A13050121. DOI: https://doi.org/10.3390/a13050121

[20] A. T. R. Dani and F. B. Putra, Time Series Modeling with Intervention Analysis to Evaluate of COVID-19 Impact on the Stock Markets in Indonesia and Global, Euler: Jurnal Ilmiah Matematika, Sains dan Teknologi, vol. 13, no. 1, pp. 113126, Apr. 2025, doi: 10.37905/euler.v13i1.31081. DOI: https://doi.org/10.37905/euler.v13i1.31081

[21] R. Recylia, T. Saifudin, and N. Chamidah, Forecasting the Number of Search and Rescue Operations for Ship Accidents in Indonesia using Fourier Series Analysis, BAREKENG: Journal of Mathematics and Its Applications, vol. 19, no. 2, pp. 10231036, Jun. 2025, doi: 10.30598/barekengvol19iss2pp1023-1036. DOI: https://doi.org/10.30598/barekengvol19iss2pp1023-1036

[22] A. K. Rahma, Q. Z. Abidin, J. K. Prasetyo, B. Larasati, D. Amelia, and N. Chamidah, Prediction of Crude Oil Prices in Indonesia using Fourier Series Estimator and ARIMA Method, BAREKENG: Jurnal Ilmu Matematika dan Terapan, vol. 18, no. 3, pp. 16731682, Jul. 2024, doi: 10.30598/barekengvol18iss3pp1673-1682. DOI: https://doi.org/10.30598/barekengvol18iss3pp1673-1682

[23] I. D. Mienye, T. G. Swart, and G. Obaido, Recurrent Neural Networks: A Comprehensive Review of Architectures, Variants, and Applications, Information, vol. 15, no. 9, p. 517, Aug. 2024, doi: 10.3390/info15090517. DOI: https://doi.org/10.3390/info15090517

[24] Suhartono, D. E. Ashari, D. D. Prastyo, H. Kuswanto, and M. H. Lee, Deep neural network for forecasting inflow and outflow in Indonesia, Sains Malays, vol. 48, no. 8, pp. 17871798, 2019, doi: 10.17576/jsm-2019-4808-26. DOI: https://doi.org/10.17576/jsm-2019-4808-26

[25] G. P. Zhang and M. Qi, Neural network forecasting for seasonal and trend time series, in European Journal of Operational Research, Jan. 2005, pp. 501514. doi: 10.1016/j.ejor.2003.08.037. DOI: https://doi.org/10.1016/j.ejor.2003.08.037