Micah J. Casteel
Research Subjects
Micah J. Casteel has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Temitayo Olayemi Olowu
Energy and Environment Science and Technology Directorate, Idaho National Laboratory, Idaho Falls, ID, USA
7 shared publications - Jeremy Lee Hartvigsen
Idaho National Laboratory (INL), Idaho Falls, ID (United States)
4 shared publications - Nicholas Kane
Energy and Environment Science and Technology, Idaho National Laboratory
3 shared publications - Tyler L. Westover
Idaho National Laboratory, Idaho Falls, ID 83415, USA
3 shared publications Elvan Sahin
2 shared publications- Jan W. Lambrechtsen2 shared publications
Latest Publications
- Open Access
- 17 October 2026
- Published by Elsevier in Applied Energy
- Vol. 427
Continuous health monitoring of solid oxide electrolyzers using pulse-width modulation current interrupt analysis
- 17 October 2026
- Published by Elsevier in Applied Energy
- Vol. 427
Open AccessContinuous health monitoring of solid oxide electrolyzers using pulse-width modulation current interrupt analysis
- Open Access
- 17 September 2026
- Published by Elsevier in Energy and AI
- Vol. 26
Digital twin-enabled reinforcement learning for adaptive and degradation-aware control of high-temperature electrolysis
- 17 September 2026
- Published by Elsevier in Energy and AI
- Vol. 26
Open AccessDigital twin-enabled reinforcement learning for adaptive and degradation-aware control of high-temperature electrolysis
- 2 June 2026
- Published by Elsevier in Applied Energy
- Vol. 420
Coordinated control of HTSE and microgrid for improved capacity factor and grid support
- 2 June 2026
- Published by Elsevier in Applied Energy
- Vol. 420
Coordinated control of HTSE and microgrid for improved capacity factor and grid support
- Open Access
- 20 March 2026
- Published by Elsevier in SSRN Electronic Journal
Data-Driven Forecasting of Solid Oxide Electrolysis Cell Degradation Using Deep Transfer Learning
Solid oxide electrolysis cells (SOECs) offer high efficiency for hydrogen production but can suffer from progressive performance degradation that limits durability and commercial deployment. Reliable forecasting of long-term degradation is therefore critical for condition monitoring, lifetime management, rapid material/cell development, and operational decision-making. However, existing physics-based models require extensive parameterization, while most data-driven approaches focus on short-term performance prediction and struggle to generalize across cells, particularly when degradation data are limited. In this work, a data-driven prognostics framework was developed to forecast SOEC degradation trajectories using a hybrid convolutional neural network-long short-term memory (CNN-LSTM) architecture augmented with an attention mechanism and deep transfer learning. The model was trained on degradation data from 8 source cells and evaluated on 12 independent cells tested under varying operating conditions and designed to capture both local temporal patterns and long-range dependencies in bounded degradation signals. Transfer learning was employed to adapt the pretrained model to previously unseen cells using only a small fraction of early-life data. Cross-validation on the source dataset demonstrated high predictive accuracy and strong agreement between predicted and measured degradation trajectories. When applied to independent target cells, the transfer learning strategy reduced RMSE from 0.0588 to 0.0130 on unseen cells when only 10% of early-life data was available. These results demonstrate that deep transfer learning enables accurate early-life, long-horizon degradation forecasting for SOECs, offering a practical pathway toward data-efficient durability prediction and improved operational management of electrolysis systems.
- 20 March 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessData-Driven Forecasting of Solid Oxide Electrolysis Cell Degradation Using Deep Transfer Learning
Solid oxide electrolysis cells (SOECs) offer high efficiency for hydrogen production but can suffer from progressive performance degradation that limits durability and commercial deployment. Reliable forecasting of long-term degradation is therefore critical for condition monitoring, lifetime management, rapid material/cell development, and operational decision-making. However, existing physics-based models require extensive parameterization, while most data-driven approaches focus on short-term performance prediction and struggle to generalize across cells, particularly when degradation data are limited. In this work, a data-driven prognostics framework was developed to forecast SOEC degradation trajectories using a hybrid convolutional neural network-long short-term memory (CNN-LSTM) architecture augmented with an attention mechanism and deep transfer learning. The model was trained on degradation data from 8 source cells and evaluated on 12 independent cells tested under varying operating conditions and designed to capture both local temporal patterns and long-range dependencies in bounded degradation signals. Transfer learning was employed to adapt the pretrained model to previously unseen cells using only a small fraction of early-life data. Cross-validation on the source dataset demonstrated high predictive accuracy and strong agreement between predicted and measured degradation trajectories. When applied to independent target cells, the transfer learning strategy reduced RMSE from 0.0588 to 0.0130 on unseen cells when only 10% of early-life data was available. These results demonstrate that deep transfer learning enables accurate early-life, long-horizon degradation forecasting for SOECs, offering a practical pathway toward data-efficient durability prediction and improved operational management of electrolysis systems.
- Open Access
- 24 January 2026
- Published by Elsevier in Journal of Power Sources
- Vol. 669
The structure, composition, and performance impact of a YSZ-GDC interdiffusion layer in solid oxide electrolysis cells
- 24 January 2026
- Published by Elsevier in Journal of Power Sources
- Vol. 669
Open AccessThe structure, composition, and performance impact of a YSZ-GDC interdiffusion layer in solid oxide electrolysis cells
- Open Access
- 15 July 2025
- Published by Elsevier in International Journal of Hydrogen Energy
- Vol. 157
Ultra-high efficiency hydrogen production using a large-scale solid oxide electrolysis cell system
- 15 July 2025
- Published by Elsevier in International Journal of Hydrogen Energy
- Vol. 157
Open AccessUltra-high efficiency hydrogen production using a large-scale solid oxide electrolysis cell system
- Open Access
- 21 June 2025
- Published by Elsevier in International Journal of Hydrogen Energy
- Vol. 148, 149961
Solid oxide electrolysis cell and stack testing best practices
- 21 June 2025
- Published by Elsevier in International Journal of Hydrogen Energy
- Vol. 148, 149961
Open AccessSolid oxide electrolysis cell and stack testing best practices
- Open Access
- 16 June 2025
- Published by Elsevier in e-Prime - Advances in Electrical Engineering, Electronics and Energy
- Vol. 13
Physics-informed and machine learning-based design optimization of Solid Oxide Fuel Cells
- 16 June 2025
- Published by Elsevier in e-Prime - Advances in Electrical Engineering, Electronics and Energy
- Vol. 13
Open AccessPhysics-informed and machine learning-based design optimization of Solid Oxide Fuel Cells