Sangkeun Lee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sangkeun Lee has a total of 73 co-authors. Here are the top co-authors by number of shared publications:
- Supriya Chinthavali
Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
6 shared publications - Dongwon Shin
Oak Ridge National Laboratory
3 shared publications Supriya Chinthavali
Oak Ridge National Laboratory, Oak Ridge, TN, USA
3 shared publicationsAhmed Tbaileh
Pacific Northwest National Laboratory (PNNL)
2 shared publications- Gang Seob Jung
Oak Ridge National Laboratory
2 shared publications Harold Kirkham
Pacific Northwest National Laboratory (PNNL)
2 shared publications
Latest Publications
- Open Access
- 3 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 205439-205456
Integrated Metrics for County-Level Resilience Ranking Using Entropy and TOPSIS
In the face of atypical weather events, power infrastructure failures, and limited resources for resilience investment, energy decision-makers need data-driven metrics to allocate resilience investments and maximize the reduction of power outage impacts. For state-level planning, for instance, ranking the resilience of each county is key to ensuring effective distribution of resources. In such cases, resilience for each spatial unit is multifaceted and is captured by a set of indicators (i.e., metrics) that can be combined into an overall score that reduces the complexity of power outage dynamics to a single decision metric. However, weighting of these indicators is often addressed by simplifying assumptions (i.e., equal weights) or semi-subjective methods that rely on user-defined weights that can introduce biases (e.g., weighted average score). Within the disaster risk reduction and resilience engineering community, a recurring challenge in multicriteria decision-making is the objective weighting of indicators for composite indices. To address this issue, we have leveraged a Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) combined with an entropy-based weighting approach to calculated the integrated scores. This method objectively determines the importance of each metric, better discerns between spatial units (i.e., counties), and offers a more reliable ranking of counties according to their relative resilience attributes. By improving methods for integrating resilience indicators, our approach helps planners and decision-makers prioritize resources more effectively for more efficient resilience investments.
- 3 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 205439-205456
Open AccessIntegrated Metrics for County-Level Resilience Ranking Using Entropy and TOPSIS
In the face of atypical weather events, power infrastructure failures, and limited resources for resilience investment, energy decision-makers need data-driven metrics to allocate resilience investments and maximize the reduction of power outage impacts. For state-level planning, for instance, ranking the resilience of each county is key to ensuring effective distribution of resources. In such cases, resilience for each spatial unit is multifaceted and is captured by a set of indicators (i.e., metrics) that can be combined into an overall score that reduces the complexity of power outage dynamics to a single decision metric. However, weighting of these indicators is often addressed by simplifying assumptions (i.e., equal weights) or semi-subjective methods that rely on user-defined weights that can introduce biases (e.g., weighted average score). Within the disaster risk reduction and resilience engineering community, a recurring challenge in multicriteria decision-making is the objective weighting of indicators for composite indices. To address this issue, we have leveraged a Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) combined with an entropy-based weighting approach to calculated the integrated scores. This method objectively determines the importance of each metric, better discerns between spatial units (i.e., counties), and offers a more reliable ranking of counties according to their relative resilience attributes. By improving methods for integrating resilience indicators, our approach helps planners and decision-makers prioritize resources more effectively for more efficient resilience investments.
- Open Access
- 6 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 139583-139603
A Near-Real-Time Model for Predicting Electricity Disruptions in Texas During Winter Storms
There has been an increase in extreme weather events, posing a threat to power grid systems, potentially influenced by factors such as population growth, changes in ecosystems, land cover, and land use in the service area, as well as the growth of certain vegetation types. This research seeks to develop a predictive model to mitigate potential damages caused by future winter storms. This research utilizes the Light Gradient Boosting Machine (LightGBM), incorporating the number of power outages experienced at the county level, geographic details, weather information, and lagged outage and lagged weather data. The developed models were broadly divided into two groups, with six models in each group - one group without optimization and another with optimization, totaling 12 trained models. For model optimization, Bayesian optimization was employed using Root Mean Squared Error (RMSE) as the objective function. In results, when comparing Group 2 (the optimized group) with Group 1 (the non-optimized group), it was found that optimization did not always lead to a reduction in RMSE and Mean Absolute Error (MAE). However, in terms of Mean Directional Accuracy (MDA), while all results in Group 1 were below the baseline accuracy of 0.33, all results in Group 2 exceeded 0.33, with some cases showing an increase of more than three times the baseline. The results indicated that, in the optimized model group, Population and Pressure were the most influential factors when using current weather data and geographical information. When using lagged data, lagged recorded outages and lagged Pressure emerged as the most significant factors. Among the 12 developed models, the L-1-2-O model showed the lowest RMSE and MAE, as well as the highest accuracy, with values of 390.62 households and 168.13 households, respectively. To normalize the RMSE and MAE values, each metric was divided by the average number of households among the counties in Texas. For the L-1-2-O model, the scaled RMSE was 0.88% and the scaled MAE was 0.38%. In terms of MDA, which indicates the accuracy of the prediction direction, the L-1-O model achieved the highest score of 0.41. Although this study focused on Texas, which suffered the greatest impact from the winter storms in 2021, with additional validation, the methodology used in this research could be applied to other regions.
- 6 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 139583-139603
Open AccessA Near-Real-Time Model for Predicting Electricity Disruptions in Texas During Winter Storms
There has been an increase in extreme weather events, posing a threat to power grid systems, potentially influenced by factors such as population growth, changes in ecosystems, land cover, and land use in the service area, as well as the growth of certain vegetation types. This research seeks to develop a predictive model to mitigate potential damages caused by future winter storms. This research utilizes the Light Gradient Boosting Machine (LightGBM), incorporating the number of power outages experienced at the county level, geographic details, weather information, and lagged outage and lagged weather data. The developed models were broadly divided into two groups, with six models in each group - one group without optimization and another with optimization, totaling 12 trained models. For model optimization, Bayesian optimization was employed using Root Mean Squared Error (RMSE) as the objective function. In results, when comparing Group 2 (the optimized group) with Group 1 (the non-optimized group), it was found that optimization did not always lead to a reduction in RMSE and Mean Absolute Error (MAE). However, in terms of Mean Directional Accuracy (MDA), while all results in Group 1 were below the baseline accuracy of 0.33, all results in Group 2 exceeded 0.33, with some cases showing an increase of more than three times the baseline. The results indicated that, in the optimized model group, Population and Pressure were the most influential factors when using current weather data and geographical information. When using lagged data, lagged recorded outages and lagged Pressure emerged as the most significant factors. Among the 12 developed models, the L-1-2-O model showed the lowest RMSE and MAE, as well as the highest accuracy, with values of 390.62 households and 168.13 households, respectively. To normalize the RMSE and MAE values, each metric was divided by the average number of households among the counties in Texas. For the L-1-2-O model, the scaled RMSE was 0.88% and the scaled MAE was 0.38%. In terms of MDA, which indicates the accuracy of the prediction direction, the L-1-O model achieved the highest score of 0.41. Although this study focused on Texas, which suffered the greatest impact from the winter storms in 2021, with additional validation, the methodology used in this research could be applied to other regions.
- Open Access
- 1 November 2024
- Published by Office of Scientific and Technical Information (OSTI)
H3 Geospatial Mapping Resolution Recommendations
- 1 November 2024
- Published by Office of Scientific and Technical Information (OSTI)
Open AccessH3 Geospatial Mapping Resolution Recommendations
- Open Access
- 20 February 2024
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 3 (3) , 514-527
Active learning of neural network potentials for rare events
Atomistic simulation with machine learning-based potentials (MLPs) is an emerging tool for understanding materials' properties and behaviors and predicting novel materials. Neural network potentials (NNPs) are outstanding in this field as they have shown a comparable accuracy to ab initio electronic structure calculations for reproducing potential energy surfaces while being several orders of magnitude faster. However, such NNPs can perform poorly outside their training domain and often fail catastrophically in predicting rare events in molecular dynamics (MD) simulations. The rare events in atomistic modeling typically include chemical bond breaking/formation, phase transitions, and materials failure, which are critical for new materials design, synthesis, and manufacturing processes. In this study, we develop an automated active learning (AL) capability by combining NNPs and one of the enhanced sampling methods, steered molecular dynamics, for capturing bond-breaking events of alkane chains to derive NNPs for targeted applications. We develop a decision engine based on configurational similarity and uncertainty quantification (UQ), using data augmentation for effective AL loops to distinguish the informative data from enhanced sampled configurations, showing that the generated data set achieves an activation energy error of less than 1 kcal mol−1. Furthermore, we have devised a strategy to alleviate training uncertainty within AL iterations through a carefully constructed data selection process that leverages an ensemble approach. Our study provides essential insight into the relationship between data and the performance of NNP for the rare event of bond breaking under mechanical loading. It highlights strategies for developing NNPs of broader materials and applications through active learning.
- 20 February 2024
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 3 (3) , 514-527
Open AccessActive learning of neural network potentials for rare events
Atomistic simulation with machine learning-based potentials (MLPs) is an emerging tool for understanding materials' properties and behaviors and predicting novel materials. Neural network potentials (NNPs) are outstanding in this field as they have shown a comparable accuracy to ab initio electronic structure calculations for reproducing potential energy surfaces while being several orders of magnitude faster. However, such NNPs can perform poorly outside their training domain and often fail catastrophically in predicting rare events in molecular dynamics (MD) simulations. The rare events in atomistic modeling typically include chemical bond breaking/formation, phase transitions, and materials failure, which are critical for new materials design, synthesis, and manufacturing processes. In this study, we develop an automated active learning (AL) capability by combining NNPs and one of the enhanced sampling methods, steered molecular dynamics, for capturing bond-breaking events of alkane chains to derive NNPs for targeted applications. We develop a decision engine based on configurational similarity and uncertainty quantification (UQ), using data augmentation for effective AL loops to distinguish the informative data from enhanced sampled configurations, showing that the generated data set achieves an activation energy error of less than 1 kcal mol−1. Furthermore, we have devised a strategy to alleviate training uncertainty within AL iterations through a carefully constructed data selection process that leverages an ensemble approach. Our study provides essential insight into the relationship between data and the performance of NNP for the rare event of bond breaking under mechanical loading. It highlights strategies for developing NNPs of broader materials and applications through active learning.
- Open Access
- 25 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 5237-5255
Quantifying the Power System Resilience of the US Power Grid Through Weather and Power Outage Data Mapping
Recent increases in extreme weather events such as severe thunderstorms, floods, and hurricanes are leading to destruction in power system equipment (transmission and distribution poles and lines, substations, power plants, etc.) and are causing widespread prolonged power outages. These outages often cause inconveniences in critical services (health care, transportation, national security, etc.) and significant losses in the economy, leading to human suffering. Therefore, understanding the spatiotemporal correlation of these events with power systems is crucial to planning and for maintaining reliable operation and control under such events. However, developing such correlation requires several datasets, including weather events and power outage datasets, along with coordination from multiple entities (e.g., electric utilities, government agencies, and research organizations). Also, high-resolution data collection is a time-consuming and tedious task because different interest groups are involved in the process. To this end, we propose an automated data framework that maps severe weather events with power outages to quantify power system resilience. This framework uses the publicly available National Weather Service dataset and Oak Ridge National Laboratory’s Environment for Analysis of Geo-Located Energy Information (EAGLE-I) power outage dataset to quantify the power system resilience. The proposed work can quantify power system resilience against extreme weather events at the county/state level for different weather event types (e.g., hurricanes, severe thunderstorms, and floods). The outcome of the proposed work will be useful for identifying vulnerability hot spots, developing weather event-based planning strategies (planning strategies might change with events types), developing asset management strategies, and developing predictive analysis tools.
- 25 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 5237-5255
Open AccessQuantifying the Power System Resilience of the US Power Grid Through Weather and Power Outage Data Mapping
Recent increases in extreme weather events such as severe thunderstorms, floods, and hurricanes are leading to destruction in power system equipment (transmission and distribution poles and lines, substations, power plants, etc.) and are causing widespread prolonged power outages. These outages often cause inconveniences in critical services (health care, transportation, national security, etc.) and significant losses in the economy, leading to human suffering. Therefore, understanding the spatiotemporal correlation of these events with power systems is crucial to planning and for maintaining reliable operation and control under such events. However, developing such correlation requires several datasets, including weather events and power outage datasets, along with coordination from multiple entities (e.g., electric utilities, government agencies, and research organizations). Also, high-resolution data collection is a time-consuming and tedious task because different interest groups are involved in the process. To this end, we propose an automated data framework that maps severe weather events with power outages to quantify power system resilience. This framework uses the publicly available National Weather Service dataset and Oak Ridge National Laboratory’s Environment for Analysis of Geo-Located Energy Information (EAGLE-I) power outage dataset to quantify the power system resilience. The proposed work can quantify power system resilience against extreme weather events at the county/state level for different weather event types (e.g., hurricanes, severe thunderstorms, and floods). The outcome of the proposed work will be useful for identifying vulnerability hot spots, developing weather event-based planning strategies (planning strategies might change with events types), developing asset management strategies, and developing predictive analysis tools.
- Open Access
- 13 August 2023
- Published by American Chemical Society (ACS) in ChemRxiv
Active Learning of Neural Network Potentials for Rare Events
Atomistic simulation with machine learning-based potentials (MLPs) is an emerging tool for understanding materials' properties and behaviors and predicting novel materials. Neural network potentials (NNPs) are outstanding in this field as they have shown a comparable accuracy to ab initio electronic structure calculations for reproducing potential energy surfaces while being several orders of magnitude faster. However, such NNPs can perform poorly outside their training domain and often fail catastrophically in predicting rare events in molecular dynamics (MD) simulations. The rare events in atomistic modeling typically include chemical bond breaking/formation, phase transitions, and materials failure, which are critical for new materials design, synthesis, and manufacturing processes. In this study, we develop an automated active learning (AL) capability by combining NNPs and enhanced sampling methods for capturing rare events to derive NNPs for targeted applications. We develop a decision engine based on configurational similarity and uncertainty quantification (UQ), using data augmentation for effective AL loops to distinguish the informative data from enhanced sampled configurations, showing that the generated data set achieves an activation energy error of less than 1 kcal/mol. Furthermore, we have devised a strategy to alleviate training uncertainty within AL iterations through a carefully constructed data selection process that leverages an ensemble approach. Our study provides essential insight into the relationship between data and the performance of NNP for the rare event of bond breaking under mechanical loading. It highlights strategies for developing NNPs of broader materials and applications through active learning.
- 13 August 2023
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessActive Learning of Neural Network Potentials for Rare Events
Atomistic simulation with machine learning-based potentials (MLPs) is an emerging tool for understanding materials' properties and behaviors and predicting novel materials. Neural network potentials (NNPs) are outstanding in this field as they have shown a comparable accuracy to ab initio electronic structure calculations for reproducing potential energy surfaces while being several orders of magnitude faster. However, such NNPs can perform poorly outside their training domain and often fail catastrophically in predicting rare events in molecular dynamics (MD) simulations. The rare events in atomistic modeling typically include chemical bond breaking/formation, phase transitions, and materials failure, which are critical for new materials design, synthesis, and manufacturing processes. In this study, we develop an automated active learning (AL) capability by combining NNPs and enhanced sampling methods for capturing rare events to derive NNPs for targeted applications. We develop a decision engine based on configurational similarity and uncertainty quantification (UQ), using data augmentation for effective AL loops to distinguish the informative data from enhanced sampled configurations, showing that the generated data set achieves an activation energy error of less than 1 kcal/mol. Furthermore, we have devised a strategy to alleviate training uncertainty within AL iterations through a carefully constructed data selection process that leverages an ensemble approach. Our study provides essential insight into the relationship between data and the performance of NNP for the rare event of bond breaking under mechanical loading. It highlights strategies for developing NNPs of broader materials and applications through active learning.
- Open Access
- 26 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Understanding the Computing and Analysis Needs for Resiliency of Power Systems from Severe Weather Impacts
As the frequency and intensity of severe weather has increased, its effect on the electric grid has manifested in the form of significantly more and larger outages in the United States. This has become especially true for regions that were previously isolated from weather extremes. In this paper, we analyze the weather impacts on the electric power grid across a variety of weather conditions, draw correlations, and provide practical insights into the operational state of these systems. High resolution computational modeling of specific meteorological variables, computational approaches to solving power system models under these conditions, and the types of resiliency needs are highlighted as goal-oriented computing approaches are being built to address grid resiliency needs. An example analysis correlating outages to 1km day-ahead weather from two historical winter storms, calculated on a large cluster using a combination of interpolated and extrapolated inputs from multiple instrumented sites to workflows that produce primary meteorological outputs, is shown as initial proof of concept.
- 26 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessUnderstanding the Computing and Analysis Needs for Resiliency of Power Systems from Severe Weather Impacts
As the frequency and intensity of severe weather has increased, its effect on the electric grid has manifested in the form of significantly more and larger outages in the United States. This has become especially true for regions that were previously isolated from weather extremes. In this paper, we analyze the weather impacts on the electric power grid across a variety of weather conditions, draw correlations, and provide practical insights into the operational state of these systems. High resolution computational modeling of specific meteorological variables, computational approaches to solving power system models under these conditions, and the types of resiliency needs are highlighted as goal-oriented computing approaches are being built to address grid resiliency needs. An example analysis correlating outages to 1km day-ahead weather from two historical winter storms, calculated on a large cluster using a combination of interpolated and extrapolated inputs from multiple instrumented sites to workflows that produce primary meteorological outputs, is shown as initial proof of concept.
- Open Access
Sensor Incipient Fault Impacts on Building Energy Performance: A Case Study on a Multi-Zone Commercial Building
Existing studies show sensor faults/error could double building energy consumption and carbon emissions compared with the baseline. Those studies assume that the sensor error is fixed or constant. However, sensor faults are incipient in real conditions and there were extremely limited studies investigating the incipient sensor fault impacts systematically. This study filled in this research gap by studying time-developing sensor fault impacts to rule-based controls on a 10-zone office building. The control sequences for variable air volume boxes (VAV) with an air handling unit (AHU) system were selected based on ASHRAE Guideline 36-2018: High-Performance Sequences of Operation for HVAC Systems. Large-scale simulations on cloud were conducted (3600 cases) through stochastic approach. Results show (1) The site energy differences could go −3.3% lower or 18.1% higher, compared with baseline. (2) The heating energy differences could go −66.5% lower or 314.4% higher, compared with baseline. (3) The cooling energy differences could go −11.5% lower or 65.0% higher, compared with baseline. (4) The fan energy differences could go 0.15% lower or 6.9% higher, compared with baseline.
Open AccessSensor Incipient Fault Impacts on Building Energy Performance: A Case Study on a Multi-Zone Commercial Building
Existing studies show sensor faults/error could double building energy consumption and carbon emissions compared with the baseline. Those studies assume that the sensor error is fixed or constant. However, sensor faults are incipient in real conditions and there were extremely limited studies investigating the incipient sensor fault impacts systematically. This study filled in this research gap by studying time-developing sensor fault impacts to rule-based controls on a 10-zone office building. The control sequences for variable air volume boxes (VAV) with an air handling unit (AHU) system were selected based on ASHRAE Guideline 36-2018: High-Performance Sequences of Operation for HVAC Systems. Large-scale simulations on cloud were conducted (3600 cases) through stochastic approach. Results show (1) The site energy differences could go −3.3% lower or 18.1% higher, compared with baseline. (2) The heating energy differences could go −66.5% lower or 314.4% higher, compared with baseline. (3) The cooling energy differences could go −11.5% lower or 65.0% higher, compared with baseline. (4) The fan energy differences could go 0.15% lower or 6.9% higher, compared with baseline.
- Open Access
- 1 November 2022
- Published by Office of Scientific and Technical Information (OSTI)
HPC Analytics of Fused Thermal Plants Data to Optimize Operating Envelope
The U.S. Department of Energy's Office of Scientific and Technical Information
- 1 November 2022
- Published by Office of Scientific and Technical Information (OSTI)
Open AccessHPC Analytics of Fused Thermal Plants Data to Optimize Operating Envelope
The U.S. Department of Energy's Office of Scientific and Technical Information
- 1 July 2022
- Published by Office of Scientific and Technical Information (OSTI)
Impacts of New Sensor Types for Selected Advanced Controls
The U.S. Department of Energy's Office of Scientific and Technical Information
- 1 July 2022
- Published by Office of Scientific and Technical Information (OSTI)
Impacts of New Sensor Types for Selected Advanced Controls
The U.S. Department of Energy's Office of Scientific and Technical Information