Jaka Fajar Fatriansyah
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jaka Fajar Fatriansyah has a total of 139 co-authors. Here are the top co-authors by number of shared publications:
- Siti Norasmah Surip
Eco-Technology Program Faculty of Applied Sciences Universiti Teknologi MARA Shah Alam Selangor 40450 Malaysia
8 shared publications - Agrin Febrian Pradana
Department of Metallurgical and Materials Engineering, Faculty of Engineering, Universitas Indonesia, Depok 16424, Indonesia
6 shared publications Andreas Federico
6 shared publications- Andreas Federico
Universitas Indonesia
6 shared publications Agrin Febrian Pradana
5 shared publicationsIping Suhariadi
Bina Nusantara University
5 shared publications
Latest Publications
- Open Access
Simple Stacking Ensemble Machine Learning Approach for Vickers Hardness Prediction of Arc Vacuum Melted High-Entropy Alloys
High-entropy alloys (HEAs) show excellent mechanical properties, but their enormous compositional space makes experimental and computational exploration expensive. This study predicts the Vickers hardness (HV) of HEAs from nominal elemental compositions (at.%) using a composition-based stacking ensemble machine learning approach without the use of handcrafted descriptors. A dataset of 120 vacuum arc-melted (VAM) HEAs containing 15 constituent elements (Re, Ru, Al, Si, Ti, Cr, Fe, Co, Ni, Zr, Nb, Mo, Hf, Ta, and W) was compiled. Four baseline models, k-nearest neighbors (KNN), support vector regression (SVR), extreme gradient boosting (XGB), and artificial neural networks (ANN), were evaluated. SVR achieves the highest baseline performance (R2 = 0.90). Stacking ensembles with the SVR meta-learner improved the weaker base learner performance by 17.20% and 12.50% for KNN-SVR and ANN-SVR respectively, relative to their base models. The best-performing stacking ensemble, XGB-SVR, only results in a minimal improvement of 2.90% compared to SVR. Ru, Re, and Al as the strongest positive contributors to hardness, as well as Fe, Co, and Ni as the strongest negative contributors, are identified with an interpretability test using permutation feature importance (PFI) and Shapley additive explanations (SHAP). Validation on the held-out compositions showed prediction errors below 7%. This study indicates that the composition-only models could form the basis for an effective and interpretable approach for rapid HEAs hardness screening. However, the investigated stacking strategy offers limited benefit compared to the best-performing baseline model.
Open AccessSimple Stacking Ensemble Machine Learning Approach for Vickers Hardness Prediction of Arc Vacuum Melted High-Entropy Alloys
High-entropy alloys (HEAs) show excellent mechanical properties, but their enormous compositional space makes experimental and computational exploration expensive. This study predicts the Vickers hardness (HV) of HEAs from nominal elemental compositions (at.%) using a composition-based stacking ensemble machine learning approach without the use of handcrafted descriptors. A dataset of 120 vacuum arc-melted (VAM) HEAs containing 15 constituent elements (Re, Ru, Al, Si, Ti, Cr, Fe, Co, Ni, Zr, Nb, Mo, Hf, Ta, and W) was compiled. Four baseline models, k-nearest neighbors (KNN), support vector regression (SVR), extreme gradient boosting (XGB), and artificial neural networks (ANN), were evaluated. SVR achieves the highest baseline performance (R2 = 0.90). Stacking ensembles with the SVR meta-learner improved the weaker base learner performance by 17.20% and 12.50% for KNN-SVR and ANN-SVR respectively, relative to their base models. The best-performing stacking ensemble, XGB-SVR, only results in a minimal improvement of 2.90% compared to SVR. Ru, Re, and Al as the strongest positive contributors to hardness, as well as Fe, Co, and Ni as the strongest negative contributors, are identified with an interpretability test using permutation feature importance (PFI) and Shapley additive explanations (SHAP). Validation on the held-out compositions showed prediction errors below 7%. This study indicates that the composition-only models could form the basis for an effective and interpretable approach for rapid HEAs hardness screening. However, the investigated stacking strategy offers limited benefit compared to the best-performing baseline model.
- Open Access
- 22 August 2026
- Published by Elsevier in Next Materials
- Vol. 13
Predicting CO₂ adsorption in Cu- and Zn-metal-organic frameworks using a permutation-invariant deep learning framework
- 22 August 2026
- Published by Elsevier in Next Materials
- Vol. 13
Open AccessPredicting CO₂ adsorption in Cu- and Zn-metal-organic frameworks using a permutation-invariant deep learning framework
- Open Access
- 21 June 2026
- Published by Elsevier in Results in Engineering
- Vol. 31
Ensemble machine learning for metals recovery prediction of lithium battery bioleaching process
- 21 June 2026
- Published by Elsevier in Results in Engineering
- Vol. 31
Open AccessEnsemble machine learning for metals recovery prediction of lithium battery bioleaching process
- Open Access
- 1 January 2026
- Published by Wiley in Advances in Materials Science and Engineering
- Vol. 2026 (1)
Subcritical Thermal Degradation of SA210 Grade A1 Ferritic–Pearlitic Steel: Microstructural Evolution, Hardness Loss, and Strength Reduction
Ferritic–pearlitic boiler tube steel undergoes progressive microstructural degradation during subcritical overheating, impairing mechanical integrity well before severe wall thinning occurs. To quantify this degradation trajectory, we established a stage‐resolved framework linking subcritical thermal exposure, microstructural degradation, Vickers hardness loss, and tensile strength reduction in SA210 Grade A1 boiler tube steel. Isothermal annealing was conducted at 600, 660, and 720°C. Holding times reached up to 100 h at 600°C and 660°C, and up to 30 h at 720°C, producing degradation states ranging from the intact as‐received condition to an advanced carbide‐degraded morphology, classified under the Toft–Marsden six‐stage scheme. Higher temperature severely compressed the degradation timeline. Reaching Stage D required 100 h at 600°C, 30 h at 660°C, and merely 1 h at 720°C. Image analysis revealed a reduction in the pearlite‐derived dark constituent area fraction from 25.44% ± 2.27% in the as‐received condition to 11.63% ± 1.55% at Stage F, tracking the dissolution and spheroidization of continuous pearlite colonies. Ferrite grain coarsening remained minor, with the ASTM grain size number shifting from G = 9.49 ± 0.04 to G = 9.16 ± 0.03. Mechanically, median hardness fell from 167.9 HV to 121.8 HV, corresponding to a 27.4% loss, alongside a 29.55% drop in mean UTS (508.02 ± 9.71 MPa to 357.92 ± 14.61 MPa). A temperature–logarithmic time regression modeled the hardness loss with R 2 = 0.965, indicating that a 60°C thermal increment produced a softening effect equivalent to a tenfold increase in dwelling time. Relative UTS loss scaled proportionally with relative hardness loss, following ΔUTS (%) = 0.989Δ H (%) − 0.194, with R 2 = 0.962. When integrated with metallographic staging and thermal history, hardness testing serves as a robust quantitative proxy for nondestructive strength assessment in degraded boiler tubes.
- 1 January 2026
- Published by Wiley in Advances in Materials Science and Engineering
- Vol. 2026 (1)
Open AccessSubcritical Thermal Degradation of SA210 Grade A1 Ferritic–Pearlitic Steel: Microstructural Evolution, Hardness Loss, and Strength Reduction
Ferritic–pearlitic boiler tube steel undergoes progressive microstructural degradation during subcritical overheating, impairing mechanical integrity well before severe wall thinning occurs. To quantify this degradation trajectory, we established a stage‐resolved framework linking subcritical thermal exposure, microstructural degradation, Vickers hardness loss, and tensile strength reduction in SA210 Grade A1 boiler tube steel. Isothermal annealing was conducted at 600, 660, and 720°C. Holding times reached up to 100 h at 600°C and 660°C, and up to 30 h at 720°C, producing degradation states ranging from the intact as‐received condition to an advanced carbide‐degraded morphology, classified under the Toft–Marsden six‐stage scheme. Higher temperature severely compressed the degradation timeline. Reaching Stage D required 100 h at 600°C, 30 h at 660°C, and merely 1 h at 720°C. Image analysis revealed a reduction in the pearlite‐derived dark constituent area fraction from 25.44% ± 2.27% in the as‐received condition to 11.63% ± 1.55% at Stage F, tracking the dissolution and spheroidization of continuous pearlite colonies. Ferrite grain coarsening remained minor, with the ASTM grain size number shifting from G = 9.49 ± 0.04 to G = 9.16 ± 0.03. Mechanically, median hardness fell from 167.9 HV to 121.8 HV, corresponding to a 27.4% loss, alongside a 29.55% drop in mean UTS (508.02 ± 9.71 MPa to 357.92 ± 14.61 MPa). A temperature–logarithmic time regression modeled the hardness loss with R 2 = 0.965, indicating that a 60°C thermal increment produced a softening effect equivalent to a tenfold increase in dwelling time. Relative UTS loss scaled proportionally with relative hardness loss, following ΔUTS (%) = 0.989Δ H (%) − 0.194, with R 2 = 0.962. When integrated with metallographic staging and thermal history, hardness testing serves as a robust quantitative proxy for nondestructive strength assessment in degraded boiler tubes.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 126376-126392
Deep Learning-Based Generation of Lead-Free Organic–Inorganic Hybrid Halide Perovskite Materials Using Conditional Variational Autoencoders
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 126376-126392
Open AccessDeep Learning-Based Generation of Lead-Free Organic–Inorganic Hybrid Halide Perovskite Materials Using Conditional Variational Autoencoders
- Open Access
- 23 September 2025
- Published by Elsevier in Results in Engineering
- Vol. 28
A machine learning framework for screening phenyl phthalimide derivatives as corrosion inhibitors based on dataset generated by DFT and molecular dynamics simulations
- 23 September 2025
- Published by Elsevier in Results in Engineering
- Vol. 28
Open AccessA machine learning framework for screening phenyl phthalimide derivatives as corrosion inhibitors based on dataset generated by DFT and molecular dynamics simulations
- Open Access
- 10 June 2025
- Published by Elsevier in Chemical Physics Impact
- Vol. 11
TiO2-functionalized mesoporous silica thin films synthesized by spin-coating to enhance methylene blue and methyl orange removal efficiency
- 10 June 2025
- Published by Elsevier in Chemical Physics Impact
- Vol. 11
Open AccessTiO2-functionalized mesoporous silica thin films synthesized by spin-coating to enhance methylene blue and methyl orange removal efficiency
- Open Access
Physical Property Prediction of High-Temperature Nickel and Iron–Nickel Superalloys Using Direct and Inverse Composition Machine Learning Models
Superalloys are a class of materials renowned for their exceptional ability to retain mechanical properties at elevated temperatures. Nickel superalloys, with a nickel content ranging from 38% to 76%, and iron–nickel superalloys (15–60% iron, 25–45% nickel) are extensively employed within the aviation industry due to their resilience in harsh operating environments. These components encounter extreme temperatures during operation, significantly impacting their tensile strength and melting point. Furthermore, high-speed rotation and abrasive conditions necessitate materials with superior hardness. Consequently, material modifications are crucial to ensure that gas turbine components meet their required properties. Machine learning (ML) and deep learning (DL) offer promising solutions for the design of materials with tailored tensile strength, hardness, and melting point properties. This study investigates the efficacy of direct and inverse machine learning models in predicting crucial material properties and composition, respectively. The model with the most favorable prediction accuracy is identified through the systematic variation of key parameters. The findings show that a fully connected feed-forward Artificial Neural Network (ANN) with three hidden layers using ReLU activation functions performs better than the other models. This capability is leveraged to modify the composition of INCONEL-718, successfully achieving significant enhancements in tensile strength (1592 MPa), hardness (152 HRB), and melting point (1665 °C).
Open AccessPhysical Property Prediction of High-Temperature Nickel and Iron–Nickel Superalloys Using Direct and Inverse Composition Machine Learning Models
Superalloys are a class of materials renowned for their exceptional ability to retain mechanical properties at elevated temperatures. Nickel superalloys, with a nickel content ranging from 38% to 76%, and iron–nickel superalloys (15–60% iron, 25–45% nickel) are extensively employed within the aviation industry due to their resilience in harsh operating environments. These components encounter extreme temperatures during operation, significantly impacting their tensile strength and melting point. Furthermore, high-speed rotation and abrasive conditions necessitate materials with superior hardness. Consequently, material modifications are crucial to ensure that gas turbine components meet their required properties. Machine learning (ML) and deep learning (DL) offer promising solutions for the design of materials with tailored tensile strength, hardness, and melting point properties. This study investigates the efficacy of direct and inverse machine learning models in predicting crucial material properties and composition, respectively. The model with the most favorable prediction accuracy is identified through the systematic variation of key parameters. The findings show that a fully connected feed-forward Artificial Neural Network (ANN) with three hidden layers using ReLU activation functions performs better than the other models. This capability is leveraged to modify the composition of INCONEL-718, successfully achieving significant enhancements in tensile strength (1592 MPa), hardness (152 HRB), and melting point (1665 °C).
- Open Access
- 1 January 2025
- Published by Wiley in Journal of Tropical Medicine
- Vol. 2025 (1) , 6631193
Molecular Docking and Molecular Dynamics Study of Propolis Compounds of Sulabiroin‐A, Sulabiroin‐B, and Broussoflavonol F Toward Tuberculosis 3PTY Target Protein
Molecular docking and molecular dynamics simulations were conducted to assess propolis compounds of sulabiroin‐A, sulabiroin‐B, and broussoflavonol F as tuberculosis (TB) inhibitors with rifampicin as the control ligand. TB remains a significant world health concern, requiring the development of new drug candidates to address more drug‐resistant variants. The target protein chosen was 3PTY. The molecular docking simulation showed that sulabiroin‐A, sulabiroin‐B, and broussoflavonol F docking scores are comparable to rifampicin, with the order of docking score from least favorable to more favorable is sulabiroin‐B< sulabiroin‐A< rifampicin< broussoflavonol F (−3.397, −3.449, −5.256, −5.961). Molecular dynamics simulations also demonstrated that sulabiroin‐B exhibited stable interactions with the target protein, comparable to rifampicin, while sulabiroin‐A and broussoflavonol F demonstrated increased fluctuation, suggesting possible instability. Absorption, distribution, metabolism, excretion, and toxicity (ADMET) study verified that all three drugs possess advantageous pharmacokinetic characteristics, with broussoflavonol F exhibiting the most favorable safety and tolerability profile. According to these findings, sulabiroin‐B is recognized as the most promising candidate for TB treatment owing to its enhanced stability in molecular dynamics simulations, although broussoflavonol F and sulabiroin‐A exhibit intermediate promise. Additional experimental validation is advised to verify their therapeutic efficacy.
- 1 January 2025
- Published by Wiley in Journal of Tropical Medicine
- Vol. 2025 (1) , 6631193
Open AccessMolecular Docking and Molecular Dynamics Study of Propolis Compounds of Sulabiroin‐A, Sulabiroin‐B, and Broussoflavonol F Toward Tuberculosis 3PTY Target Protein
Molecular docking and molecular dynamics simulations were conducted to assess propolis compounds of sulabiroin‐A, sulabiroin‐B, and broussoflavonol F as tuberculosis (TB) inhibitors with rifampicin as the control ligand. TB remains a significant world health concern, requiring the development of new drug candidates to address more drug‐resistant variants. The target protein chosen was 3PTY. The molecular docking simulation showed that sulabiroin‐A, sulabiroin‐B, and broussoflavonol F docking scores are comparable to rifampicin, with the order of docking score from least favorable to more favorable is sulabiroin‐B< sulabiroin‐A< rifampicin< broussoflavonol F (−3.397, −3.449, −5.256, −5.961). Molecular dynamics simulations also demonstrated that sulabiroin‐B exhibited stable interactions with the target protein, comparable to rifampicin, while sulabiroin‐A and broussoflavonol F demonstrated increased fluctuation, suggesting possible instability. Absorption, distribution, metabolism, excretion, and toxicity (ADMET) study verified that all three drugs possess advantageous pharmacokinetic characteristics, with broussoflavonol F exhibiting the most favorable safety and tolerability profile. According to these findings, sulabiroin‐B is recognized as the most promising candidate for TB treatment owing to its enhanced stability in molecular dynamics simulations, although broussoflavonol F and sulabiroin‐A exhibit intermediate promise. Additional experimental validation is advised to verify their therapeutic efficacy.
- Open Access
- 30 December 2024
- Published by Universitas Indonesia in Journal of Materials Exploration and Findings
- Vol. 3 (3) , 5
A Comparative Study of Conventional and Statistically Active Corrosion Methods for Corrosion Growth Assessment of a 24-inch Gas Pipeline
Corrosion in oil and gas pipelines can lead to component failures with severe consequences, including environmental damage and operational disruptions. Accurate corrosion growth assessment is critical for pipeline integrity management, providing valuable insights for risk assessment, decision making, and asset management. This paper purpose was to presents a comparative analysis of two methods for corrosion growth assessment of the 24 inch offshore gas pipeline: the conventional method and the statistically active corrosion (SAC) method that can be used by pipeline operators to enhance their corrosion management practices. The study utilized in-line inspection (ILI) data from two consecutive runs in 2020 and 2023, covering the entire 73 km length of the pipeline. The results demonstrate that the SAC method provides a more detailed and localized assessment of the corrosion activity compared to the conventional method, identifying 782 active corrosion joints out of the 5,987 joints in the pipeline. The SAC method also yields higher average and maximum corrosion growth rates and a more detail location of where active corrosion occurs. SAC method proves to be an effective and efficient approach to addressing the challenges of corrosion assessment in pipeline integrity management, enabling operators to prioritize maintenance efforts and enhance overall pipeline safety.
- 30 December 2024
- Published by Universitas Indonesia in Journal of Materials Exploration and Findings
- Vol. 3 (3) , 5
Open AccessA Comparative Study of Conventional and Statistically Active Corrosion Methods for Corrosion Growth Assessment of a 24-inch Gas Pipeline
Corrosion in oil and gas pipelines can lead to component failures with severe consequences, including environmental damage and operational disruptions. Accurate corrosion growth assessment is critical for pipeline integrity management, providing valuable insights for risk assessment, decision making, and asset management. This paper purpose was to presents a comparative analysis of two methods for corrosion growth assessment of the 24 inch offshore gas pipeline: the conventional method and the statistically active corrosion (SAC) method that can be used by pipeline operators to enhance their corrosion management practices. The study utilized in-line inspection (ILI) data from two consecutive runs in 2020 and 2023, covering the entire 73 km length of the pipeline. The results demonstrate that the SAC method provides a more detailed and localized assessment of the corrosion activity compared to the conventional method, identifying 782 active corrosion joints out of the 5,987 joints in the pipeline. The SAC method also yields higher average and maximum corrosion growth rates and a more detail location of where active corrosion occurs. SAC method proves to be an effective and efficient approach to addressing the challenges of corrosion assessment in pipeline integrity management, enabling operators to prioritize maintenance efforts and enhance overall pipeline safety.