Abstract
Efficient hydrogen (H\(_2\)) storage remains a major challenge for clean energy applications. This study presents an AI-driven methodology to optimize H\(_2\) storage in porous carbon adsorbents. A comprehensive dataset of 917 literature-derived entries was used to develop two machine learning models: Random Forest (RF) and Convolutional Neural Network (CNN). Both models accurately predicted hydrogen uptake based on material properties and experimental conditions. Within the range of the experimental dataset, the CNN demonstrated strong interpolation performance, accurately predicting hydrogen uptake with a high coefficient of determination (\(R^2\) = 0.9353) and a Root Mean Squared Error (RMSE) of 0.0406. The CNN was integrated into a multi-objective optimization framework to maximize hydrogen uptake while minimizing average pore diameter (AVD). Through extrapolative optimization beyond the training data range, the AI-driven technique and optimization method (AiDO) identified theoretical Pareto-optimal solutions extending beyond the experimental dataset, predicting H\(_2\) uptake of up to 16.66 wt% at an AVD of 0.08 nm. While these extrapolated solutions are not directly validated by experiments, constrained optimization scenarios (e.g., realistic pore-size limits) provide physically meaningful design targets. Sensitivity analysis confirmed the robustness of the methodology to different normalization techniques. This approach demonstrates the potential of combining predictive ML with optimization to accelerate the design of high-performance hydrogen adsorbents, reducing experimental costs and supporting sustainable energy systems.
Data availability
All data generated or analysed during this study are included in this published article and its supplementary information files.
Abbreviations
- DT:
-
Decision tree
- PR:
-
Poisson regression
- SVM/SVR:
-
Support vector machine/regression
- RF:
-
Random forest
- LR:
-
Linear regression
- RR:
-
Ridge regression
- ANN:
-
Artificial neural network
- XGBoost/XGBT:
-
Extreme gradient boosting
- CatBoost:
-
Categorical boosting
- LGB:
-
LightGBM
- GBDT:
-
Gradient boosted decision trees
- MGBR:
-
Multiple gradient boosting regressor
- MLP/MLPNN:
-
Multi-layer perceptron
- LSTM:
-
Long short-term memory
- CNN:
-
Convolutional neural network
- BDTR:
-
Bayesian decision tree regressor
- BLR:
-
Bayesian linear regression
- NNR:
-
Nearest neighbor regression
- CFFNN:
-
Cascade feed-forward neural network
- GRNN:
-
Generalized regression neural network
- RNN:
-
Recurrent neural network
- KNN:
-
k-Nearest neighbor
- ET:
-
Extra tree
- BRANN:
-
Bayesian regularized artificial neural network
- AB:
-
AdaBoost
- GB:
-
Gradient boosting
- LSSVM:
-
Least squares support vector machine
- ANFIS:
-
Adaptive neuro-fuzzy inference system
- ELM:
-
Extreme learning machine
- CMIS:
-
Convolutional mixed-integer system
References
Züttel, A. Materials for hydrogen storage. Mater. today 6, 24–33 (2003).
Sakintuna, B., Lamari-Darkrim, F. & Hirscher, M. Metal hydride materials for solid hydrogen storage: A review. Int. J. Hydrogen Energy 32, 1121–1140 (2007).
Firlej, L., Beckner, M., Romanos, J., Pfeifer, P. & Kuchta, B. Different approach to estimation of hydrogen-binding energy in nanospace-engineered activated carbons. J. Phys. Chem. C 118, 955–961 (2014).
Romanos, J. et al. High surface area carbon and process for its production. US Patent 9, 445 (2016).
Romanos, J. et al. Cycling and regeneration of adsorbed natural gas in microporous materials. Energy Fuels 31, 14332–14337 (2017).
Rash, T. A. et al. Microporous carbon monolith synthesis and production for methane storage. Fuel 200, 371–379 (2017).
Kuchta, B. et al. Open carbon frameworks—A search for optimal geometry for hydrogen storage. J. Mol. Model. 19, 4079–4087 (2013).
Romanos, J., Barakat, F. & Dargham, S. A. Nanoporous graphene monolith for hydrogen storage. Mater. Today Proc. 5, 17478–17483 (2018).
Bannenberg, L. et al. Metal (boro-) hydrides for high energy density storage and relevant emerging technologies. Int. J. Hydrogen Energy 45, 33687–33730 (2020).
DOE. Technical targets for onboard hydrogen storage for light-duty vehicles. energy.gov (2017).
Chae, H. K. et al. A route to high surface area, porosity and inclusion of large molecules in crystals. Nature 427, 523 (2004).
Kuchta, B. et al. Hypothetical high-surface-area carbons with exceptional hydrogen storage capacities: Open carbon frameworks. J. Am. Chem. Soc. 134, 15130–15137 (2012).
Romanos, J. et al. Infrared study of boron–carbon chemical bonds in boron-doped activated carbon. Carbon 54, 208–214 (2013).
Romanos, J. et al. Nanospace engineering of KOH activated carbon. Nanotechnology 23, 015401 (2012).
Jordá-Beneyto, M., Suárez-García, F., Lozano-Castelló, D., Cazorla-Amorós, D. & Linares-Solano, A. Hydrogen storage on chemically activated carbons and carbon nanomaterials at high pressures. Carbon 45, 293–303 (2007).
Reyhani, A., Mortazavi, S. Z., Moshfegh, S. M. A. Z., Parvin, P. & Golikand, A. N. Hydrogen storage in decorated multiwalled carbon nanotubes by Ca, Co, Fe, Ni, and Pd nanoparticles under ambient conditions. J. Phys. Chem. C 115, 6994–7001 (2011).
Yang, R. T. Hydrogen storage by alkali-doped carbon nanotubes-revisited. Carbon 38, 623–641 (2000).
Moussa, M. et al. Toward sustainable hydrogen storage and carbon dioxide capture in post-combustion conditions. J. Environ. Chem. Eng. 5, 1628–1637 (2017).
Hu, W. et al. Hierarchically porous carbon derived from neolamarckia cadamba for electrochemical capacitance and hydrogen storage. ACS Sustain. Chem. Eng. 7, 15385–15393 (2019).
Sevilla, M. & Mokaya, R. Energy storage applications of activated carbons: Supercapacitors and hydrogen storage. Energy Environ. Sci. 7, 1250 (2014).
Sevilla, M., Fuertes, A. B. & Mokaya, R. High density hydrogen storage in superactivated carbons from hydrothermally carbonized renewable organic materials. Energy Environ. Sci. 4, 1400–1410 (2011).
Blankenship, L. S., Balahmar, N. & Mokaya, R. Oxygen-rich microporous carbons with exceptional hydrogen storage capacity. Nat. Commun. 8, 1545 (2017).
Pardakhti, M., Moharreri, E., Wanik, D., Suib, S. L. & Srivastava, R. Machine learning using combined structural and chemical descriptors for prediction of methane adsorption performance of metal organic frameworks (mofs). ACS Comb. Sci. 19, 640–645 (2017).
Kim, S.-Y., Kim, S.-I. & Bae, Y.-S. Machine-learning-based prediction of methane adsorption isotherms at varied temperatures for experimental adsorbents. J. Phys. Chem. C 124, 19538–19547 (2020).
Meng, M., Zhong, R. & Wei, Z. Prediction of methane adsorption in shale: Classical models and machine learning based models. Fuel 278, 118358 (2020).
Abdi, J., Hadavimoghaddam, F., Hadipoor, M. & Hemmati-Sarapardeh, A. Modeling of CO2 adsorption capacity by porous metal organic frameworks using advanced decision tree-based models. Sci. Rep. 11, 24468 (2021).
Yuan, X., Suvarna, M., Low, S., Lee, P. D. D. B. & Yong Sik Ok, J. L. W. Applied machine learning for prediction of CO2 adsorption on biomass waste-derived porous carbons. Environ. Sci. Technol. 55, 11925–11936 (2021).
Maheri, M., Bazan, C., Zendehboudi, S. & Usefi, H. Machine learning to assess CO2 adsorption by biomass waste. J. CO2 Util. 76, 102590 (2023).
Alatefi, S., Agwu, O. E., Nait Amar, M. & Alkouh, A. Advancing hydrogen storage: Explainable machine learning models for predicting hydrogen uptake in metal-organic frameworks. Results Eng. 28, 107304 (2025).
Rahnama, A., Zepon, G. & Sridhar, S. Machine learning based prediction of metal hydrides for hydrogen storage, part i: Prediction of hydrogen weight percent. Int. J. Hydrogen Energy 44, 7337–7344 (2019).
Rahnama, A., Zepon, G. & Sridhar, S. Machine learning based prediction of metal hydrides for hydrogen storage, part ii: Prediction of material class. Int. J. Hydrogen Energy 44, 7345–7353 (2019).
Alizadeh, S. M. S., Parhizi, Z., Alibak, A. H., Vaferi, B. & Hosseini, S. Predicting the hydrogen uptake ability of a wide range of zeolites utilizing supervised machine learning methods. Int. J. Hydrogen Energy 47, 21782–21793 (2022).
Salehi, K., Rahmani, M. & Atashrouz, S. Machine learning assisted predictions for hydrogen storage in metal-organic frameworks. Int. J. Hydrogen Energy 48, 33260–33275 (2023).
Meduri, S. & Nandanavanam, J. Prediction of hydrogen uptake of metal organic frameworks using explainable machine learning. Energy AI 12, 100230 (2023).
Kusdhany, M. I. M. & Lyth, S. M. New insights into hydrogen uptake on porous carbon materials via explainable machine learning. Carbon 179, 190–201 (2021).
Davoodi, S. et al. Machine-learning models to predict hydrogen uptake of porous carbon materials from influential variables. Sep. Purif. Technol. 316, 123807 (2023).
Wang, C.-S. & Brinkerhoff, J. Predicting hydrogen adsorption and desorption rates in cylindrical metal hydride beds: Empirical correlations and machine learning. Int. J. Hydrogen Energy 46, 24256–24270 (2021).
Anderson, G., Schweitzer, B., Anderson, R. & Gómez-Gualdrón, D. A. Attainable volumetric targets for adsorption-based hydrogen storage in porous crystals: Molecular simulation and machine learning. J. Phys. Chem. C 123, 120–130 (2019).
Batalović, K., Radaković, J., Kuzmanović, B., Ilić, M. M. & Mamula, B. P. Machine learning-based high-throughput screening of mg-containing alloys for hydrogen storage and energy conversion applications. J. Energy Storage 68, 107720 (2023).
Rossetti, I., Ramis, G., Gallo, A. & Di Michele, A. Hydrogen storage over metal-doped activated carbon. Int. J. Hydrogen Energy 40, 7609–7616 (2015).
Rahimi, M., Abbaspour-Fard, M. H. & Rohani, A. Machine learning approaches to rediscovery and optimization of hydrogen storage on porous bio-derived carbon. J. Clean. Prod. 329, 129714 (2021).
Alatefi, S., Nait Amar, M., Agwu, O. E. & Alkouh, A. Accurate prediction of water activity in ionic liquid-based aqueous ternary solutions using advanced explainable artificial intelligence frameworks. Chem. Eng. Sci. 318, 122218 (2025).
Thanh, H. V. et al. Hydrogen storage on porous carbon adsorbents: rediscovery by nature-derived algorithms in random forest machine learning model. Energies 16, 2348 (2023).
Huang, C.-C., Chen, H.-M., Chen, C.-H. & Huang, J.-C. Effect of surface oxides on hydrogen storage of activated carbon. Sep. Purif. Technol. 70, 291–295 (2010).
Sun, Y. & Webley, P. A. Preparation of activated carbons from corncob with large specific surface area by a variety of chemical activators and their application in gas storage. Chem. Eng. J. 162, 883–892 (2010).
Fierro, V., Zhao, W., Izquierdo, M., Aylon, E. & Celzard, A. Adsorption and compression contributions to hydrogen storage in activated anthracites. Int. J. Hydrogen Energy 35, 9038–9045 (2010).
González-Navarro, M. F., Giraldo, L. & Moreno-Piraján, J. C. Preparation and characterization of activated carbon for hydrogen storage from waste African oil-palm by microwave-induced lioh basic activation. J. Anal. Appl. Pyrol. 107, 82–86 (2014).
Hwang, S.-H., Choi, W. M. & Lim, S. K. Hydrogen storage characteristics of carbon fibers derived from rice straw and paper mulberry. Mater. Lett. 167, 18–21 (2016).
Bader, N. & Ouederni, A. Optimization of biomass-based carbon materials for hydrogen storage. J. Energy Storage 5, 77–84 (2016).
Wang, D., Geng, Z., Zhang, C., Zhou, X. & Liu, X. Effects of thermal activation conditions on the microstructure regulation of corncob-derived activated carbon for hydrogen storage. J. Energy Chem. 23, 601–608 (2014).
Liu, X., Zhang, C., Geng, Z. & Cai, M. High-pressure hydrogen storage and optimizing fabrication of corncob-derived activated carbon. Microporous Mesoporous Mater. 194, 60–65 (2014).
Wang, H., Gao, Q. & Hu, J. High hydrogen storage capacity of porous carbons prepared by using activated carbon. J. Am. Chem. Soc. 131, 7016–7022 (2009).
Wang, J., Senkovska, I., Kaskel, S. & Liu, Q. Chemically activated fungi-based porous carbons for hydrogen storage. Carbon 75, 372–380 (2014).
Üner, O., Geçgel, Ü. & Avcu, T. Comparisons of activated carbons produced from sycamore balls, ripe black locust seed pods, and nerium oleander fruits and also their h2 storage studies. Carbon Lett. 31, 75–92 (2021).
Jin, H., Lee, Y. S. & Hong, I. Hydrogen adsorption characteristics of activated carbon. Catal. Today 120, 399–406 (2007).
Figueroa-Torres, M. Z., Robau-Sánchez, A., De la Torre-Sáenz, L. & Aguilar-Elguézabal, A. Hydrogen adsorption by nanostructured carbons synthesized by chemical activation. Microporous Mesoporous Mater. 98, 89–93 (2007).
Minoda, A., Oshima, S., Iki, H. & Akiba, E. Synthesis of KOH-activated porous carbon materials and study of hydrogen adsorption. J. Alloy. Compd. 580, S301–S304 (2013).
Balathanigaimani, M. et al. Nanostructured biomass based carbon materials from beer lees for hydrogen storage. J. Nanosci. Nanotechnol. 18, 2196–2199 (2018).
Bader, N. & Ouederni, A. Functionalized and metal-doped biomass-derived activated carbons for energy storage application. J. Energy Storage 13, 268–276 (2017).
Cheng, F., Liang, J., Zhao, J., Tao, Z. & Chen, J. Biomass waste-derived microporous carbons with controlled texture and enhanced hydrogen uptake. Chem. Mater. 20, 1889–1895 (2008).
Arshad, S. H. M. et al. Preparation of activated carbon from empty fruit bunch for hydrogen storage. J. Energy Storage 8, 257–261 (2016).
Zhang, C. et al. Microstructure regulation of super activated carbon from biomass source corncob with enhanced hydrogen uptake. Int. J. Hydrogen Energy 38, 9243–9250 (2013).
Ramesh, T., Rajalakshmi, N. & Dhathathreyan, K. S. Synthesis and characterization of activated carbon from jute fibers for hydrogen storage. Renew. Energy Environ. Sustain. 2, 4 (2017).
Xiao, Y. et al. Melaleuca bark based porous carbons for hydrogen storage. Int. J. Hydrogen Energy 39, 11661–11667 (2014).
Choi, Y.-K. & Park, S.-J. Hydrogen storage capacity of highly porous carbons synthesized from biomass-derived aerogels. Carbon Lett. 16, 127–131 (2015).
Lee, S.-Y. & Park, S.-J. Effect of platinum doping of activated carbon on hydrogen storage behaviors of metal-organic frameworks-5. Int. J. Hydrogen Energy 36, 8381–8387 (2011).
Fierro, V. et al. Experimental evidence of an upper limit for hydrogen storage at 77 k on activated carbons. Carbon 48, 1902–1911 (2010).
Jordá-Beneyto, M., Lozano-Castelló, D., Suárez-García, F., Cazorla-Amorós, D. & Linares-Solano, Á. Advanced activated carbon monoliths and activated carbons for hydrogen storage. Microporous Mesoporous Mater. 112, 235–242 (2008).
Kopac, T., Kırca, Y. & Toprak, A. Synthesis and characterization of KOH/boron modified activated carbons from coal and their hydrogen sorption characteristics. Int. J. Hydrogen Energy 42, 23606–23616 (2017).
Pedicini, R. et al. Posidonia oceanica and wood chips activated carbon as interesting materials for hydrogen storage. Int. J. Hydrogen Energy 45, 14038–14047 (2020).
Doğan, M., Sabaz, P., Biıciıl, Z., Kizilduman, B. K. & Turhan, Y. Activated carbon synthesis from tangerine peel and its use in hydrogen storage. J. Energy Inst. 93, 2176–2185 (2020).
Rowlandson, J. L., Edler, K. J., Tian, M. & Ting, V. P. Toward process-resilient lignin-derived activated carbons for hydrogen storage applications. ACS Sustain. Chem. Eng. 8, 2186–2195 (2020).
Rocha, H. R. O. et al. Optimizing a machine learning design of dielectric properties in lead-free piezoelectric ceramics. Mater. Des. 243, 113053 (2024).
Wang, H. et al. Superior hydrogen separation in nanofluidic membranes by synergistic effect of pore tailoring and host–guest interaction. Nano Lett. 25, 9353–9361. https://doi.org/10.1021/acs.nanolett.5c01736 (2025) (PMID: 40434398).
Thommes, M. et al. Physisorption of gases, with special reference to the evaluation of surface area and pore size distribution (iupac technical report). Pure Appl. Chem. 87, 1051–1069 (2015).
Gogotsi, Y. et al. Importance of pore size in high-pressure hydrogen storage by porous carbons. Int. J. Hydrogen Energy 34, 6314–6319. https://doi.org/10.1016/j.ijhydene.2009.05.073 (2009).
Broom, D. et al. Concepts for improving hydrogen storage in nanoporous materials. Int. J. Hydrogen Energy 44, 7768–7779. https://doi.org/10.1016/j.ijhydene.2019.01.224 (2019) (A special issue on hydrogen-based Energy storage.).
Acknowledgements
The authors acknowledge the support of the Research Center Bio-based Economy (KCBBE) at Hanze University of Applied Sciences, The Netherlands, and the Laboratory of Telecommunications (LabTel) at the Federal University of Espírito Santo, Brazil.
Funding
This research was partially supported by Fundação de Amparo à Pesquisa e Inovação do Espírito Santo, Brazil (Grant Nos. 891/2023-P:2023-BDKK7 and 1194/2024-P:2024-26C0T and 2022-BWBR2) and Conselho Nacional de Desenvolvimento Científico e Tecnológico, Brazil (Grant Nos. 311633/2025-0 and 301349/2025-8).
Author information
Authors and Affiliations
Contributions
H.R. designed the study, developed the methodology, wrote the software, and provided resources, while J.R., S.D., and J.S. contributed to the study design and investigations. J.R., S.D., J.S and H.W. validated the results. S.D., R.R., and J.R. conducted the formal analysis. H.R. and S.D. wrote the original draft. All authors reviewed and edited the manuscript and agreed to the published version of the manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Rocha, H.R.O., Romanos, J., Abou Dargham, S. et al. AI-driven optimization of hydrogen storage in porous carbon adsorbents. Sci Rep (2026). https://doi.org/10.1038/s41598-026-45915-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-45915-1
