Abdulelah S. Alshehri
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Abdulelah S. Alshehri has a total of 85 co-authors. Here are the top co-authors by number of shared publications:
- Fengqi You
College of Engineering, Cornell University, Ithaca, New York 14853, USA
5 shared publications - Vivek Dua
Department of Chemical Engineering, Centre for Process Systems Engineering , 4919 University College London , Torrington Place , London , WC1E 7JE , UK
3 shared publications - Waqar Muhammad Ashraf
The Sargent Centre for Process Systems Engineering, Department of Chemical Engineering, University College London, Torrington Place, London WC1E 7JE, UK
3 shared publications - Abdulrahman A. Al-Rabiah
Chemical Engineering Department, College of Engineering, King Saud University, P.O. Box 800, Riyadh 11421, Saudi Arabia
2 shared publications Abdulrahman bin Jumah
2 shared publicationsAmir H. Keshavarzzadeh
2 shared publications
Latest Publications
- Open Access
- 3 November 2026
- Published by MDPI AG in Journal of Manufacturing and Materials Processing
- Vol. 10 (11) , 479
Titanium-Based Binary (TiN/316L) and Ternary Nitride (TiAL(x:y)N/316L) Coatings Systems for Proton Exchange Membrane Fuel Cell Metallic Bipolar Plates
The sustainable development of the world requires a cheap and sustainable source of continuous energy supply. Hydrogen fuel cells can be an effective solution, with proton exchange membrane fuel cells as a potential candidate for portable devices and electric vehicles. The bipolar plate is a critical component of proton exchange membrane fuel cells, with a large proportion of cost and weight associated with it. Binary and ternary metal nitride coatings can be applied on 316L for bipolar plate application to achieve better corrosion resistance, protection efficiency, interfacial characteristics, high power density and low-cost manufacturability. In this research work, alloy target-based novel ternary metal nitride coatings, i.e., TiAl(80:20)N, TiAl(70:30)N and TiAl(50:50)N, on 316 L substrate and a binary metal nitride coating, i.e., TiN, on 316L substrate are compared with bare 316L for bipolar plate material. Cathodic arc physical vapor deposition is used for the coating process, and the applied coatings are characterized by XRD, SEM and EDAX. The hydrophobic nature for coating water management ability is evaluated using a water droplet test. Open-circuit potential, potentiodynamic testing and electrochemical impedance spectroscopy are used for electrochemical corrosion characterization of the applied coatings. The maximum open-circuit potential is obtained for TiAl(80:20)N-coated 316L, which is ~27.4% higher than the second-highest TiAl(70:30)N-coated 316L. However, the Tafel extrapolation method indicates that the protection efficiency of TiAl(70:30)N-coated 316L is 15.76% higher compared to TiAl(80:20)N-coated 316L. For the application of bipolar plates, the ternary metal nitride coatings demonstrated superior performance under the tested conditions compared to both the binary metal nitride coating and bare 316L stainless steel.
- 3 November 2026
- Published by MDPI AG in Journal of Manufacturing and Materials Processing
- Vol. 10 (11) , 479
Open AccessTitanium-Based Binary (TiN/316L) and Ternary Nitride (TiAL(x:y)N/316L) Coatings Systems for Proton Exchange Membrane Fuel Cell Metallic Bipolar Plates
The sustainable development of the world requires a cheap and sustainable source of continuous energy supply. Hydrogen fuel cells can be an effective solution, with proton exchange membrane fuel cells as a potential candidate for portable devices and electric vehicles. The bipolar plate is a critical component of proton exchange membrane fuel cells, with a large proportion of cost and weight associated with it. Binary and ternary metal nitride coatings can be applied on 316L for bipolar plate application to achieve better corrosion resistance, protection efficiency, interfacial characteristics, high power density and low-cost manufacturability. In this research work, alloy target-based novel ternary metal nitride coatings, i.e., TiAl(80:20)N, TiAl(70:30)N and TiAl(50:50)N, on 316 L substrate and a binary metal nitride coating, i.e., TiN, on 316L substrate are compared with bare 316L for bipolar plate material. Cathodic arc physical vapor deposition is used for the coating process, and the applied coatings are characterized by XRD, SEM and EDAX. The hydrophobic nature for coating water management ability is evaluated using a water droplet test. Open-circuit potential, potentiodynamic testing and electrochemical impedance spectroscopy are used for electrochemical corrosion characterization of the applied coatings. The maximum open-circuit potential is obtained for TiAl(80:20)N-coated 316L, which is ~27.4% higher than the second-highest TiAl(70:30)N-coated 316L. However, the Tafel extrapolation method indicates that the protection efficiency of TiAl(70:30)N-coated 316L is 15.76% higher compared to TiAl(80:20)N-coated 316L. For the application of bipolar plates, the ternary metal nitride coatings demonstrated superior performance under the tested conditions compared to both the binary metal nitride coating and bare 316L stainless steel.
- Open Access
Deep Reinforcement Learning with Weather Forecasts and Budget Pacing Improves Irrigation Scheduling Under Water Scarcity
Irrigation scheduling under seasonal water-use restrictions is a pressing challenge in water-scarce agricultural regions, where finite volumetric allocations demand careful timing and depth decisions to sustain profitability. Deep reinforcement learning (DRL) offers promise for optimizing such sequential decisions, yet existing observation designs rely on backward-looking weather statistics and omit near-term forecasts that may support the management of limited water across a growing season. This study evaluates whether augmenting the DRL agent’s observation space with seven-day precipitation and reference evapotranspiration forecasts and refactoring existing allocation information into three budget-pacing features can improve irrigation scheduling most effectively under seasonal water scarcity while retaining benefits as restrictions are relaxed. Proximal policy optimization policies were trained within the AquaCrop framework for irrigated maize in southwest Nebraska under 50, 75, 100, 125 mm and unrestricted seasonal water caps. Under the 50 mm cap, the augmented feedforward policy (FB-MLP) achieved 144.76 $/ha, which was 32.2% above the baseline policy and 22.3% above the optimized Soil Moisture Target benchmark against the validation set. Its best-run gains over the baseline across the other four scenarios averaged 2.52%, including a 1.2% improvement under unrestricted irrigation. Under the 75 mm cap, the augmented policy allocated 83.3% of its irrigation to flowering and yield formation. These findings show that the combined observation design improves irrigation scheduling most strongly where water scarcity is binding.
Open AccessDeep Reinforcement Learning with Weather Forecasts and Budget Pacing Improves Irrigation Scheduling Under Water Scarcity
Irrigation scheduling under seasonal water-use restrictions is a pressing challenge in water-scarce agricultural regions, where finite volumetric allocations demand careful timing and depth decisions to sustain profitability. Deep reinforcement learning (DRL) offers promise for optimizing such sequential decisions, yet existing observation designs rely on backward-looking weather statistics and omit near-term forecasts that may support the management of limited water across a growing season. This study evaluates whether augmenting the DRL agent’s observation space with seven-day precipitation and reference evapotranspiration forecasts and refactoring existing allocation information into three budget-pacing features can improve irrigation scheduling most effectively under seasonal water scarcity while retaining benefits as restrictions are relaxed. Proximal policy optimization policies were trained within the AquaCrop framework for irrigated maize in southwest Nebraska under 50, 75, 100, 125 mm and unrestricted seasonal water caps. Under the 50 mm cap, the augmented feedforward policy (FB-MLP) achieved 144.76 $/ha, which was 32.2% above the baseline policy and 22.3% above the optimized Soil Moisture Target benchmark against the validation set. Its best-run gains over the baseline across the other four scenarios averaged 2.52%, including a 1.2% improvement under unrestricted irrigation. Under the 75 mm cap, the augmented policy allocated 83.3% of its irrigation to flowering and yield formation. These findings show that the combined observation design improves irrigation scheduling most strongly where water scarcity is binding.
- Open Access
- 3 June 2026
- Published by Elsevier in Energy Conversion and Management: X
- Vol. 31
Hydrothermal and thermal pretreatments facilitate coal biodegradability for enhanced biogenic methane generation
- 3 June 2026
- Published by Elsevier in Energy Conversion and Management: X
- Vol. 31
Open AccessHydrothermal and thermal pretreatments facilitate coal biodegradability for enhanced biogenic methane generation
- Open Access
- 22 April 2026
- Published by Elsevier in Chemical Engineering Science
- Vol. 332
Engineering coke-resistant with metal promoted Ni/silica–zirconia catalysts for syngas production via dry reforming of methane
- 22 April 2026
- Published by Elsevier in Chemical Engineering Science
- Vol. 332
Open AccessEngineering coke-resistant with metal promoted Ni/silica–zirconia catalysts for syngas production via dry reforming of methane
- Open Access
- 29 March 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (7) , 3320
Fine-Tuning Large Language Models for the Efficient and Concurrent Extraction of Fuel Properties
Large datasets of fuel properties are indispensable for predictive combustion modeling and next-generation fuel design. However, resource-intensive experiments restrict existing databases to 200–500 compounds, capturing an infinitesimal fraction of the C1-20 hydrocarbon space. Furthermore, conventional rule-based and supervised learning extraction methods are constrained by poor scalability, domain-specific nomenclature, and weak contextual inference. To address these limitations, we introduce IgnitionGPT, a large language model fine-tuned on GPT-4.1-mini for the automated, concurrent extraction of three ignition metrics: Research Octane Number, Motor Octane Number, and Cetane Number. The model was trained on a human-annotated JSONL dataset of 304 sources (263 peer-reviewed articles, 41 patents) encompassing 581 diverse compounds. By evaluating IgnitionGPT directly against its zero-shot foundation, we isolate the impact of domain-specific fine-tuning. The model overcomes baseline overgeneralization (47.8% F1) to achieve saturated extraction accuracy on unseen data (i.e., 100% for the best model). Remarkably, it reaches this saturation on an 85% held-out test split using a mere 10% of the data for fine-tuning, demonstrating true robustness across heterogeneous literature. Ultimately, by open-sourcing our data and methods, this fine-tuning framework transitions chemical information retrieval from fragmented, rule-based heuristics to unified, concurrent extraction towards bridging the gap between experimental limitations and data-driven molecular design and modeling.
- 29 March 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (7) , 3320
Open AccessFine-Tuning Large Language Models for the Efficient and Concurrent Extraction of Fuel Properties
Large datasets of fuel properties are indispensable for predictive combustion modeling and next-generation fuel design. However, resource-intensive experiments restrict existing databases to 200–500 compounds, capturing an infinitesimal fraction of the C1-20 hydrocarbon space. Furthermore, conventional rule-based and supervised learning extraction methods are constrained by poor scalability, domain-specific nomenclature, and weak contextual inference. To address these limitations, we introduce IgnitionGPT, a large language model fine-tuned on GPT-4.1-mini for the automated, concurrent extraction of three ignition metrics: Research Octane Number, Motor Octane Number, and Cetane Number. The model was trained on a human-annotated JSONL dataset of 304 sources (263 peer-reviewed articles, 41 patents) encompassing 581 diverse compounds. By evaluating IgnitionGPT directly against its zero-shot foundation, we isolate the impact of domain-specific fine-tuning. The model overcomes baseline overgeneralization (47.8% F1) to achieve saturated extraction accuracy on unseen data (i.e., 100% for the best model). Remarkably, it reaches this saturation on an 85% held-out test split using a mere 10% of the data for fine-tuning, demonstrating true robustness across heterogeneous literature. Ultimately, by open-sourcing our data and methods, this fine-tuning framework transitions chemical information retrieval from fragmented, rule-based heuristics to unified, concurrent extraction towards bridging the gap between experimental limitations and data-driven molecular design and modeling.
- 22 January 2026
- Published by Elsevier in International Journal of Hydrogen Energy
- Vol. 210
Topology-aware hydrogen injection planning in natural gas pipeline networks: A case study for California
- 22 January 2026
- Published by Elsevier in International Journal of Hydrogen Energy
- Vol. 210
Topology-aware hydrogen injection planning in natural gas pipeline networks: A case study for California
- Open Access
- 22 November 2025
- Published by Elsevier in Energy Conversion and Management
- Vol. 348
Domain-informed operation excellence of gas turbine system with machine learning
- 22 November 2025
- Published by Elsevier in Energy Conversion and Management
- Vol. 348
Open AccessDomain-informed operation excellence of gas turbine system with machine learning