Comparison of LSTM and Random Forest for Hydrogen Production Prediction in Alkaline Water Electrolysis

Ulil Amri Ulil; Ardi Pujiyanta; Sunardi Sunardi

doi:10.30871/jaic.v10i4.13254

Authors

Ulil Amri Ulil Universitas Ahmad Dahlan
Ardi Pujiyanta Universitas Ahmad Dahlan
Sunardi Sunardi Universitas Ahmad Dahlan

DOI:

https://doi.org/10.30871/jaic.v10i4.13254

Keywords:

Alkaline water Electrolysis, Random Forest, Long Short- Term Memory, Hydrogen Production Prediction, Machine Learning

Abstract

Hydrogen has emerged as a promising clean energy carrier capable of supporting the transition toward sustainable energy systems. In alkaline water electrolysis systems, accurate prediction of hydrogen production is essential for improving system monitoring, operational efficiency, and future control strategies. This study aims to compare the performance of Random Forest (RF) and Long Short-Term Memory (LSTM) algorithms in predicting hydrogen production based on operational parameters of an alkaline water electrolysis system. The dataset used in this study consists of more than 100,000 operational data samples collected from laboratory-scale electrolysis experiments, including voltage, current, temperature, and hydrogen gas pressure measurements. Hydrogen production was calculated using the ideal gas law and used as the target variable for model development. Prior to model training, the dataset underwent preprocessing, including data cleaning, normalization, and train-test splitting. The predictive performance of both models was evaluated using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and coefficient of determination (R²). Experimental results show that the Random Forest model achieved superior performance with an MAE of 0.0085, RMSE of 0.0106, and R² of 0.9905, while the LSTM model obtained an MAE of 0.0302, RMSE of 0.0361, and R² of 0.7907. The findings indicate that Random Forest is more effective than LSTM in modeling the relationship between operational parameters and hydrogen production in the investigated alkaline water electrolysis system. This study demonstrates the potential of machine learning approaches for accurate hydrogen production prediction and provides insights into the suitability of different predictive models for electrolysis-based hydrogen generation systems.

Downloads

Download data is not yet available.

References

[1] H. Tüysüz, “Alkaline Water Electrolysis for Green Hydrogen Production,” Acc. Chem. Res., Feb. 2024, doi: 10.1021/acs.accounts.3c00709.

[2] S. Dash et al., “Advances in green hydrogen production through alkaline water electrolysis: A comprehensive review,” Int. J. Hydrogen Energy, vol. 83, pp. 614–629, Sep. 2024, doi: 10.1016/j.ijhydene.2024.08.157.

[3] L. P. Campo Schneider et al., “Advancements in hydrogen production using alkaline electrolysis systems: A short review on experimental and simulation studies,” Curr. Opin. Electrochem., vol. 47, p. 101552, Oct. 2024, doi: 10.1016/j.coelec.2024.101552.

[4] Z. Ibnu Faqih, E. Kurniawan, and U. Kurniawan Usman, “SYNERGY Jurnal Ilmiah Multidisiplin Penerapan Iot Sebagai Monitoring Jarak Jauh Untuk Mengetahui Proses Elektrolisis Air Mineral,” vol. 1, no. 2, pp. 70–74, 2023, [Online]. Available: https://e-journal.naureendigition.com/index.php/sjim

[5] A. M. Maghfuri and M. Kuku, “Optimized hydrogen production through machine learning: comparative analysis of electrolyzer technologies using hybrid renewable energy,” Appl. Therm. Eng., vol. 276, Oct. 2025, doi: 10.1016/j.applthermaleng.2025.126923.

[6] R. Zhang, A. Xie, L. Cheng, Z. Bai, Y. Tang, and P. Wan, “Hydrogen production by traditional and novel alkaline water electrolysis on nickel or iron based electrocatalysts,” Chemical Communications, vol. 59, no. 53, pp. 8205–8221, 2023, doi: 10.1039/D3CC00996C.

[7] M. Muthiah, M. Elnashar, W. Afzal, and H. Tan, “Safety assessment of hydrogen production using alkaline water electrolysis,” Int. J. Hydrogen Energy, vol. 84, pp. 803–821, Sep. 2024, doi: 10.1016/j.ijhydene.2024.08.237.

[8] Y. Zuo et al., “High-performance alkaline water electrolyzers based on Ru-perturbed Cu nanoplatelets cathode,” Nat. Commun., vol. 14, no. 1, p. 4680, Aug. 2023, doi: 10.1038/s41467-023-40319-5.

[9] Q. He, M. Zhao, S. Li, X. Li, and Z. Wang, “Machine Learning Prediction of Photovoltaic Hydrogen Production Capacity Using Long Short-Term Memory Model,” Energies (Basel)., vol. 18, no. 3, p. 543, Jan. 2025, doi: 10.3390/en18030543.

[10] W. Xu, J. Tu, N. Xu, and Z. Liu, “Predicting daily heating energy consumption in residential buildings through integration of random forest model and meta-heuristic algorithms,” Energy, vol. 301, p. 131726, Aug. 2024, doi: 10.1016/j.energy.2024.131726.

[11] H. Yadav and A. Thakkar, “NOA-LSTM: An efficient LSTM cell architecture for time series forecasting,” Expert Syst. Appl., vol. 238, p. 122333, Mar. 2024, doi: 10.1016/j.eswa.2023.122333.

[12] N. Hamed Al Hajri, R. Naji Al Harthi, G. K. Pasam, and R. Natarajan, “IoT and Machine Learning based Green Energy Generation using Hybrid Renewable Energy Sources of Solar, Wind and Hydrogen Fuel Cells,” E3S Web of Conferences, vol. 472, p. 01008, Jan. 2024, doi: 10.1051/e3sconf/202447201008.

[13] G. S. Cassol et al., “Ultra-fast green hydrogen production from municipal wastewater by an integrated forward osmosis-alkaline water electrolysis system,” Nat. Commun., vol. 15, no. 1, p. 2617, Mar. 2024, doi: 10.1038/s41467-024-46964-8.

[14] W. Luo et al., “Research on the method to improve the efficiency of ScCO2 fracturing and the mechanism of proppant transport and drag-reducing,” Energy, vol. 319, p. 135012, Mar. 2025, doi: 10.1016/j.energy.2025.135012.

[15] S. Ali Akbar, M. Azis Sidiq, A. Yudhana, and R. Rian Hidayat, “Integrasi Sensor Pintar dengan Sistem IoT untuk Memantau Kadar Gas Nitrogen pada Reaktor Biogas,” Jurnal Pekommas, vol. 10, no. 1, Jun. 2025, doi: 10.56873/jpkm.v9i1.5918.

[16] T. Sutikno, H. S. Purnama, A. Pamungkas, A. Fadlil, I. M. Alsofyani, and M. H. Jopri, “Internet of things-based photovoltaics parameter monitoring system using NodeMCU ESP8266,” International Journal of Electrical and Computer Engineering, vol. 11, no. 6, pp. 5578–5587, Dec. 2021, doi: 10.11591/ijece.v11i6.pp5578-5587.

[17] “Internet of Things and Cloud-Based Monitoring of an Electrolysis and Fuel Cell System,” J. Sci. Ind. Res. (India)., vol. 84, no. 7, Jul. 2025, doi: 10.56042/jsir.v84i7.14515.

[18] S. Hari mukti, A. Pujiyanta, and A. Fadlil, “Klasifikasi Berat Itik Pedaging Berbasis Convolutional Neural Network dan Internet of Things,” Jurnal Riset Rekayasa Elektro, vol. 7, no. 2, pp. 223–236, Dec. 2025, doi: 10.30595/jrre.v7i2.27847.

[19] J. Yoon, D.-Y. Cheong, and G. Baek, “Predicting current and hydrogen productions from microbial electrolysis cells using random forest model,” Appl. Energy, vol. 371, p. 123641, Oct. 2024, doi: 10.1016/j.apenergy.2024.123641.