Cyber Data & ResilienceSafeguards and validation of data integrity with data used to train machine learning models.
Data resilience represents the safeguards and validation of integrity with data that is utilized in the training of machine learning models. The Cyber & Data Resilience Pillar envisions several grand challenge areas. Each is important for various reasons offering a range of capabilities: the first is the trustworthiness of training data, currently called data resilience. The second area deals with adversarial machine learning (AML) and the malicious use of artificial intelligence (MUAI). A third potential area deals with understanding the gap between human and artificial intelligence.
The DARPA GARD (Guaranteed AI Robustness of Data) program begins to address the poisoning aspect of this problem, but training data can have other problems that have yet to be discovered such as missing data, improper data ordering or labeling. The ability to detect when data has been poisoned, or is otherwise inaccurate, is fundamental to trustworthy AI/ML. The data resilience initiative would work by first validating data obtained in the cyber-physical system (CPS) environment. Rather than the traditional validating through source authentication, this effort involves three pillars of information theory (temporal, contextual and descriptive) and collecting information from both physical systems and cybersecurity in order to create an accurate operational profile with acceptable deviations for the six meta states of processing (initialization, normal processing, busy processing, stressed processing, system failure, no processing). These states, and the deviations of the time, context and descriptive data points, provide the necessary baseline values that can be compared at any point in the processing lifecycle. When comparisons reveal significant discrepancies, the ability to reconstitute to the last known good state is enacted.
A series of studies involves several institutions in various roles as we work through the iterations in a water, electric, or nuclear CPS environment. The University of Wyoming dedicates their portion of the effort to developing meaningful metrics. Boise State University has students with knowledge of CPS security. Prof. Sin Ming Loo has the background in physical systems and cybersecurity to oversee the development of solutions that capture the data of interest. Indiana University (both IU and IUPUI) and Purdue University have access to a test environment (the virtual city) and students with both cyber and control systems knowledge that provides the researchers with capable students physically located, if necessary, to collect the data under our guidance. Data evaluation will be a combined effort by the team.
The above work describes creating trustworthy data for use in AI/ML. The actual deployment and testing of the AI/ML software would be led by INL with Purdue (lead) with IUPUI, and Boise State also participating in various aspects. Evaluations for efficacy will be performed by the University of Wyoming as part of their AI metrics efforts.
Adversarial Machine Learning (AML) and Malicious Use of Artificial Intelligence (MUAI)
Adversarial machine learning (AML) and the Malicious Use of Artificial Intelligence (MUAI) represent a rapidly growing challenge area that goes straight to the heart of our mission (protection of our nuclear arsenal). We have already witnessed manipulation of ML algorithms in other areas such as the Tay example in social media, where the chatbot learned new undesirable lessons (racism, etc.). Furthermore we have witnessed the work that bots can do to manipulate AI algorithms through flooding AML can go beyond the manipulation of training data to include algorithm manipulation. We have observed cases where AI misidentified characteristics about the target through erroneous assumptions. We propose several efforts in this space ranging from discovery vulnerabilities and unintended outcomes to countering through manipulation of AI.
Current work at INL in this space can serve as a departure point to many of the proposed studies. A newly approved LDRD on red teaming AI serves as the starting point along with the Microsoft/Harvard report on “Failure Modes in Machine Learning,” however, these studies represent a launching point of a much broader problem that requires a comprehensive, holistic approach that is interdisciplinary in nature. For example, disruption of the learning process (consider how the human mind works when distracted or interrupted) may impact the classification process, allowing us to fingerprint the adversary algorithms and possibly manipulate weights.
Another possible idea in countering the MUAI would involve countering and manipulating bot behaviors. Bot behaviors have been used to manipulate human emotions by slowly increasing inflammatory responses. One study might involve developing a bot to engage the malicious bot through “fingerprinting” and suggesting alternative behaviors forcing the malicious bot to potentially change its objective. This work has been discussed as an international joint effort with the University of Warwick, where a strong CPS program exists with a strong AI/ML program that has deep ties to UK defense research groups (DSTL and GCHQ).
Countering MUAI and AML are high priority focus areas since our adversaries are putting significant investments into AML/MUAI programs to gain knowledge and exploit our nuclear defenses. Automated responses with our own resilient AI/ML solutions offers an opportunity to assume the dominant position in this upcoming battle.
Exploring the Human Intelligence-Artificial Intelligence Gap
Human intelligence (HI) is the inspiration and model for artificial intelligence (AI). Consider the security council definition of AI, “a technology that performs tasks that mimic HI.” This definition opens up numerous possibilities to research into AI based in part on understanding the cognitive models that explain HI. Cognitive neuroscience is a relatively young discipline where new discoveries that explain the human thought process are still being made, which suggests that the HI-AI gap will present inspiration for many areas of research ranging from understanding algorithm biases to applying human cognitive disorders to AI. The partnering of cognitive neuroscience and cybersecurity has precedence in decision science. There are many potential areas for studies that may allow for active defense of adversarial behaviors. Studies in this space range from understanding ethics and values of different groups of people that can influence AI applications through recreating effects of human brain injuries in AI technology (such as causing trees to temporarily prune branches, disrupting NN processing). The overall goal is the identification of the HI-AI gaps and how those gaps inform potential vulnerabilities.
The resultant output, likely a framework or matrix, would provide a research roadmap for long-term future research in AI/ML.
Ideally this is a multilab/university/government collaborative effort. In addition to expertise at INL in cybersecurity and human factors, PNNL and Sandia both offer complementary skill sets. The Army Research Laboratory also has a long history of work in decision science.
Collaborations & Projects:
Defense Nuclear Nonproliferation (DNN) Program
The development of new advanced reactors (Gen IV) increases the importance of new methods to understand diversion and misuse scenarios, and determine mitigation pathways. INL is developing a complete digital twin framework for safeguards by design. This provides the opportunity for comprehensive understanding of nuclear fuel cycle facility operations to significantly strengthen nuclear safeguards and nonproliferation regime.
National Reactor Innovation Center (NRIC) Program
The National Reactor Innovation Center (NRIC) leads new advanced demonstration projects using a model-based systems engineering approach. SysML and LML models are developed and traced to traditional requirements artifacts to realize this vision. Activity models are integrated with Discrete Event and Monte Carlo simulation to check for correctness, integrate cost and schedule, and monitor expected performance. NRIC is working to develop integrations between MBSE, engineering, operations, and traditional CAD software to enable a full digital thread in design.
Transformational Challenge Reactor (TCR) Program
INL is assisting in the development of the requirements and definition of design-agnostic digital platform that will support the TCR core manufacturing and overall program goals. The digital platform consists of design data, modeling data, in-situ data, ex-situ data, and integral test data as well as established links between these five categories.
High Performance Computing (HPC)
Nuclear Science User Facility (NSUF) High Performance Computing (HPC) resources offered through Idaho National Laboratory provide scientific computing capabilities to support efforts in advanced modeling and simulation. These resources support a wide range of research activities, including performance of materials in harsh environments (such as the effects of irradiation and high temperatures), performance of existing light water and advanced nuclear reactors, and multiscale multiphysics analysis of nuclear fuel performance.
INL HPC computing resources are available to industry, universities, national laboratories, and federal agencies to support research and development. Access is generally granted for research related to the DOE Office of Nuclear Energy and INL’s mission focusing on nuclear energy development, workforce development, and education.
Sawtooth: an HPE SGI 8600-based system with 99,792 cores, 403 TB of memory and a LINPACK rating of 5.6 Petaflop/s. Sawtooth’s network is a nine-dimensional enhanced hypercube utilizing EDR and HDR InfiniBand. Individual compute nodes contain dual Xeon Platinum 8268 processors with 24 cores each. The majority of compute nodes contain 196 GB of memory while twenty-seven contain 384 GB of memory coupled with four NVIDIA V100 GPUs with 32 GB of on-GPU memory each. Sawtooth came online in late 2019 and ranked #37 on the November 2019 TOP500 list.
Lemhi: a Dell 6420-based system with 20,160 cores, 94 TB of memory and a LINPACK rating of 1.0 Petaflop/s. Lemhi’s network is an OmniPath fat tree. Individual compute nodes contain dual Xeon Gold 6148 processors with 20 cores each and 192 GB of memory. Lemhi came online in Fall 2018 and ranked #427 on the November 2018 TOP500 list.
Falcon: a SGI ICE-X distributed memory system with 34,992 cores, 121 TB of memory and a LINPACK rating of 1.1 Petaflop/s. Falcon’s network is a seven-dimensional enhanced hypercube utilizing FDR InfiniBand. Individual compute nodes contain dual Xeon E5-2695 v4 processors with 18 cores each and 128 GB of memory. Falcon came online in Fall 2014 and ranked #97 on the November 2014 TOP500 list.
Applied Visualization Laboratory (AVL)
The Applied Visualization Laboratory contains several 3D immersive environments for scientists and engineers to walk into their data, examine it, and provide deep analysis in pursuit of their research. As mixed, virtual, and augmented reality technology evolves, the opportunities for portable, in-depth analysis of complex data sets increases. Augmented reality solutions are envisioned to allow researchers to have CAVE-like experiences anywhere. Web-based 3-D geographic information systems, mobile applications (for both phone and tablet) and serious games (games built for training or educational purposes) allow users to conduct research at their desks or in the field, enabling discovery outside the lab. Virtual reality exploration systems offer the ability to create visualizations of large data sets that can be projected and run in real-time simulations. Using six-degrees-of-freedom input devices – which allow a body to move forward and backward, up and down, left to right – and stereoscopic output, they offer the benefits of more realistic interaction.
The Center for Advanced Energy Studies (CAES) opened its first Cave Automatic Virtual Environment (CAVE) in 2010. With the new CAVE installed in 2017, CAES’s Applied Visualization Laboratory is even better equipped to provide researchers from universities, industry and government agencies with a user facility where they can visualize and address scientific and technical challenges.
|Digital Thread||Ahmad Al Rashdan, Jeren Browning, Christopher Ritter, “Data Integration Aggregated Model and Ontology for Nuclear Deployment (DIAMOND): Preliminary Model and Ontology”, September 11, 2019.|
|Digital Thread||Christopher Ritter, Jeren Browning, Lee Nelson, Tammie Borders, John Bumgardner, Mitchell Kerman, “Digital Engineering Ecosystem for Future Nuclear Power Plants: Innovation of Ontologies, Tools, and Data Exchange”, October 29, 2019.|
|Digital Thread||Christopher Ritter, Jeren Browning, “Towards a Digital Twin to Detect Nuclear Proliferation Activities”, September 8, 2020.|
|Digital Twin||Christopher Ritter, Jeren Browning, Lee Nelson, Tammie Borders, John Bumgardner, Mitchell Kerman, “Digital Engineering Ecosystem for Future Nuclear Power Plants: Innovation of Ontologies, Tools, and Data Exchange”, October 29, 2019.|
|Operational Artificial Intelligence||Agarwal, V., N. Lybeck, B. Pham, R. Rusaw, and R. Bickford, 2015, “Asset fault signatures for prognostic and health management in the nuclear industry,” IEEE Reliability Digest, February 2015.|
|Operational Artificial Intelligence||Agarwal, V., N. Lybeck, B. Pham, R. Rusaw, and R. Bickford, 2015, “Prognostic and health management of active assets in nuclear power plants,” International Journal of Prognostics and Health Management, Special Issue on Nuclear Energy PHM, 6:1–17.|
|Operational Artificial Intelligence||Al Rashdan, A., J. Smith, S. St. Germain, C. Ritter, V. Agarwal, R. Boring, T. Ulrich, and J. Hansen, 2018, “Development of a technology roadmap for online monitoring of nuclear power plants,” INL/EXT-18-52206, Idaho Falls, ID, USA.|
|Operational Artificial Intelligence||Al Rashdan, A., and T. Mortenson, 2018, “Automation technologies impact on the work process of nuclear power plants,” INL/EXT-18-51457, Idaho Falls, ID, USA.|
|Operational Artificial Intelligence||Al Rashdan, A. and D. Roberson, 2019, “A frequency domain control perspective on xenon resistance for load following of thermal nuclear reactors,” IEEE Transactions on Nuclear Science., Vol. 66, No. 9, pp. 2034–2041.|
|Operational Artificial Intelligence||Al Rashdan, A., C. Krome, S. St. Germain, J. Corporan, K. Ruppert, and J. Rosenlof, 2019, “Method and application of data integration at a nuclear power plant,” INL/EXT-19-54294, Idaho Falls, ID, USA.|
|Operational Artificial Intelligence||Al Rashdan, A., M. Griffel, R. Boza, and D. P. Guillen, 2019, “Subtle process anomalies detection using machine learning methods,” INL/EXT-19-55629, Idaho Falls, ID, USA.|
|Operational Artificial Intelligence||Alamamiotis, M., and V. Agarwal, 2014, “Fuzzy integration of support vector regression models for anticipatory control of complex energy systems,” International Journal of Monitoring and Surveillance Technologies Research, 2(2):26–40.|
|Operational Artificial Intelligence||Farber, J., D. Cole, A. Al Rashdan, and V. Yadav, 2019. “Using kernel density estimation to detect loss-of-coolant accidents in a pressurized water reactor,” Nuclear Technology, special issue on Big Data for Nuclear Power Plants, 205(8):1043–1052.|
|Operational Artificial Intelligence||Garcia, H., S. Aumeier, and A. Al Rashdan, 2019, “Integrated state awareness through secure embedded intelligence in nuclear systems: Opportunities and implications,” Nuclear Science and Engineering, accepted for publication. DOI:10.1080/00295639.2019.1698237.|
|Operational Artificial Intelligence||Garcia, H., S. Aumeier, A. Al Rashdan, and B. Rolston, 2020, “Secure embedded intelligence in nuclear systems: Framework and methods,” Annals of Nuclear Energy, accepted for publication. DOI:10.1016/j.anucene.2019.107261.|
|Operational Artificial Intelligence||Gentillon, C., C. L. Atwood, A. L. Mack, and Z. Ma, 2020, “Evaluation of weakly informed priors for FLEX data,” INL/EXT-20-58327, Idaho Falls, ID, USA.|
|Operational Artificial Intelligence||Guillen, D., N. Anderson, C. Krome, R. Boza, M. Griffel, J. Zouabe, and A. Al-Rashdan, 2019, “The application of physics-informed machine-learning to predict drywell cooling fan failure,” In: Proceedings of the Big Data for Nuclear Power Plants Workshop 2019.|
|Operational Artificial Intelligence||Manjunatha, K, A. L. Mack, V. Agarwal, D. Adams, and D. Koester, 2020, “Diagnosis of corrosion processes in nuclear power plants secondary piping structures,” ASME Pressure Vessels and Piping Conference, July – August (held virtually).|
|Operational Artificial Intelligence||Mandelli, D., C. Wang, S. Staples, C. S. Ritter, A. L. Mack, S. W. St. Germain, A. Alfonsi, C. Rabiti, and R. Kunz, 2018, “Cost risk analysis framework (CRAFT): An integrated risk analysis tool and its application in an industry use case,” INL/EXT-18-51442, Idaho Falls, ID, USA.|
|Cyber & Data Resilience Pillar||"Data Fidelity: Security's Soft Underbelly" (RCIS 2017),"Data Fidelity in the Post-Truth Era" (ICCWS 2018)|
|Decision Sciences & Visualization||Toba, A.L., Griffel, L.M., & Hartley, D.S., (2020). Devs Based Modeling and Simulation of Agricultural Machinery Movement. In Press, Computers and Electronics in Agriculture.|
|Decision Sciences & Visualization||Hartley, D.S., Thompson, D. N.; Griffel, L. M., Nguyen, Q. A and Roni, M.S. 2020. The effect of biomass properties and system configuration on the operating effectiveness of biomass to biofuel systems. ACS Sustainable Chemistry & Engineering. In Press. DOI: 10.1021/acssuschemeng.9b06551|
|Decision Sciences & Visualization||Wang, Y, Wang, J, Schuler, J, Hartley, D., Volk, T and Eisenbies, M. 2020. Optimization of harvest and logistics for multiple lignocellulosic biomass feedstocks in the northeastern United States. Energy (197)117260. DOI: 10.1016/j.energy.2020.117260.|
|Decision Sciences & Visualization||Wahlen, B. D., Wendt, L. M., Murphy, A., Thompson, V. S., Hartley, D. S., Dempster, T. and Gerken, H. 2020. Preservation of Microalgae, Lignocellulosic Biomass Blends by Ensiling to Enable Consistent Year-Round Feedstock Supply for Thermochemical Conversion to Biofuels. Frontiers in Bioengineering and Biotechnology.(8)316. DOI:10.3389/fbioe.2020.00316|
|Decision Sciences & Visualization||Meyer, P. A., Snowden-Swan, L. J., Jones, S. B., Rappe, K. G. and Hartley, D. S. 2020. The effect of feedstock composition on fast pyrolysis and upgrading to transportation fuels: Techno-economic analysis and greenhouse gas life cycle analysis. Fuel (259)116218. DOI:10.1016/j.fuel.2019.116218|
|Decision Sciences & Visualization||Griffel, L. M., Vazhnik, V., Hartley, D. S., Hansen, J. K., and Roni, M. 2020. Agricultural field shape descriptors as predictors of field efficiency for perennial grass harvesting: An empirical proof. Computers and Electronics in Agriculture (168)105088. DOI: 10.1016/j.compag.2019.105088|
|Decision Sciences & Visualization||Abou Ali, H., Delparte, D., & Griffel, L. M. (2020). From Pixel to Yield: Forecasting Potato Productivity in Lebanon and Idaho. The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 42, 1-7. DOI: 10.5194/isprs-archives-XLII-3-W11-1-2020.|
|Decision Sciences & Visualization||Hansen, J. K., Roni, M. S., Nair, S. K., Hartley, D. S., Griffel, L. M., Vazhnik, V., & Mamun, S. 2019. Setting a baseline for Integrated Landscape Design: Cost and risk assessment in herbaceous feedstock supply chains. Biomass and Bioenergy, 130. doi:10.1016/j.biombioe.2019.105388|
|Decision Sciences & Visualization||Jin, H., Reed, D. W., Thompson, V. S., Fujita, Y., Jiao, Y., Crain-Zamora, M., Fisher, J., Scalzone, K., Griffel, L. M., Hartley, D. and Sutherland, J. W. (2019). Sustainable bioleaching of rare earth elements from industrial waste materials using agricultural wastes. ACS Sustainable Chemistry & Engineering, 7(18), pp.15311-15319. DOI: 10.1021/acssuschemeng.9b02584.|
|Decision Sciences & Visualization||Roni, M.S., Thompson, D.N. and Hartley, D.S., 2019. Distributed biomass supply chain cost optimization to evaluate multiple feedstocks for a biorefinery. Applied Energy, 254, p.113660.|
|Decision Sciences & Visualization||Langholtz, M., Davis, M., Hartley, D., Brandt, C., Hilliard, M., Eaton, L. 2019. Cost and profit impacts of modifying stover harvest operations to improve feedstock quality. Biofuels, Bioproducts & Biorefining.|
|Decision Sciences & Visualization||Narani, A., Konda, N.V.S.N.M, Chen, C.-S., Tachea, F., Coffman, P., Gardner, J., Li, C., Ray, A.E., Hartley, D.S., Simmons, B., Pray, T.R., Tanjore, D. 2019. Simultaneous application of predictive model and least cost formulation can substantially benefit biorefineries outside Corn Belt in United States: A case study in Florida. Bioresource Technology. 271:218-227.|
|Decision Sciences & Visualization||Emerson, R.M., Hernandez, S., Williams, C.L., Lacey, J.A., Hartley, D.S. 2018. Improving bioenergy feedstock quality of high moisture short rotation woody crops using air classification. Biomass and Bioenergy. 117:56-62|
|Decision Sciences & Visualization||Wendt, L.M., Smith, W.A., Hartley, D.S., Wendt, D.S., Ross, J.A., Sexton, D.M., Lukas, J.C, Nguyen, Q.A., Murphy, A.J., Kenney, K.L. 2018. Techno-economic assessment of a chopped feedstock logistics supply chain for corn stover. Frontiers in Energy Research. 6(90).|
|Decision Sciences & Visualization||Lamers, P., Nyugen,R., Hartley, D., Hansen, J. and Searcy, E., 2018. Biomass market dynamics supporting the large-scale deployment of high-octane fuel production in the United States. GCB Bioenergy. 10(7):460-472|
|Decision Sciences & Visualization||Roni, M.S., Thompson, D., Hartley, D., Searcy, E. and Nguyen, Q., 2018. Optimal blending management of Biomass Resources Used for Biochemical Conversion. Biofuels, Bioproducts and Biorefining. 12(4):624-648|
|Decision Sciences & Visualization||Griffel, L. M., Delparte, D., & Edwards, J. (2018). Using Support Vector Machines classification to differentiate spectral signatures of potato plants infected with Potato Virus Y. Computers and Electronics in Agriculture, 153, 318-324. DOI: 10.1016/j.compag.2018.08.027.|
|Decision Sciences & Visualization||Olsson, O., Roos, A., Guisson, R., Bruce, L., Lamers, P., Hektor, B., Thrän, D., Hartley, D., Ponitka, J. and Hildebrandt, J., 2018. Time to tear down the pyramids? A critique of cascading hierarchies as a policy tool. Wiley Interdisciplinary Reviews: Energy and Environment.7(2),e279|
|Decision Sciences & Visualization||Nair, S. K., Griffel, L. M., Hartley, D. S., McNunn, G. S., & Kunz, M. R. (2018). Investigating the efficacy of integrating energy crops into non-profitable subfields in Iowa. BioEnergy Research, 11, pp. 623-637. DOI: 10.1007/s12155-018-9925-0.|
|Decision Sciences & Visualization||Narani, A., Coffman, P., Gardner, J., Li, C., Ray, A.E., Hartley, D.S., Stettler, A., Konda, S.N.M., Simmons, B., Pray, T., Tanjore, D., 2017. Predictive modeling to de-risk bio-based manufacturing by adapting to variability in lignocellulosic biomass supply, Bioresource Technology.243:676-685|
|Decision Sciences & Visualization||Liu, W, Wang, J., Richard, T., Hartley, D., Spatari, S., Volk,T., 2017. Economic and Life Cycle Analyses of Biomass Utilization for Bioenergy and Bioproducts. Biofuels, Bioproducts & Biorefining. 11(4):633-647|
|Decision Sciences & Visualization||Wendt, L.M., Wahlen, B.D., Li, C., Ross, J.A., Sexton, D.A., Lukas, J.A., Hartley, D.S. and Murphy, J.A., 2017. Evaluation of a high-moisture stabilization strategy for harvested microalgae blended with herbaceous biomass: Part II- techno-economic assessment. Algal Research. 25:676-685|
|Decision Sciences & Visualization||Thompson, V.S., Lacey, J.A., Hartley, D.S., Jindra, M. A., Aston, J. E., Thompson, D. N., 2016. Application of air classification and formulation to manage feedstock cost, quality and availability for bioenergy. Fuel, 180: 497-505.|
|Practice & Culture||Coming Soon!|
|Next Gen Artificial Intelligence||Yonge, Adam, et al. "TAPsolver: A Python package for the simulation and analysis of TAP reactor experiments." arXiv preprint arXiv:2008.13584 (2020) https://arxiv.org/abs/2008.13584|
|Next Gen Artificial Intelligence||Kunz, M. Ross, et al. "Probability theory for inverse diffusion: Extracting the transport/kinetic time-dependence from transient experiments." Chemical Engineering Journal 402 (2020): 125985 https://www.sciencedirect.com/science/article/pii/S1385894720321136|
|Next Gen Artificial Intelligence||Medford, Andrew J., et al. "Extracting knowledge from data through catalysis informatics." ACS Catalysis 8.8 (2018): 7403-7429 https://pubs.acs.org/doi/10.1021/acscatal.8b01708|
|Next Gen Artificial Intelligence||Kunz, M. Ross, et al. "Pulse response analysis using the Y-procedure: A data science approach." Chemical Engineering Science 192 (2018): 46-60 https://www.sciencedirect.com/science/article/pii/S0009250918304561|
|Operational Artificial Intelligence||D.P. Guillen, N. Anderson, C. Krome, R. Boza, L. M. Griffel, J. Zouabe, and A. Al Rashdan, 2020, "A RELAP5-3D/LSTM Model for the Analysis of Drywell Cooling Fan Failure," Progress in Nuclear Energy 130, December 2020. https://doi.org/10.1016/j.pnucene.2020.103540.|
|Operational Artificial Intelligence||A. Alfonsi, C. Wang, J. Cogliati, D. Mandelli, C. Rabiti “Status of Adaptive Surrogates within the RAVEN framework”, Idaho National Laboratory, Idaho Falls, Idaho, INL/EXT 17 43438|
|Operational Artificial Intelligence||A. S. Epiney, A. Alfonsi, C. Parisi, R. Szilard, “RISMC Industry Application #1 (ECCS/LOCA): Core characterization automation: Lattice Codes interface for PHISICS/RELAP5-3D”, Nuclear Engineering and Design, 345, pp-15-27, 2019|
|Operational Artificial Intelligence||V. Narcisi, P. Lorusso, F. Giannetti, A. Alfonsi, G. Caruso, “Uncertainty Quantification method for RELAP5-3D© using RAVEN and application on NACIE experiments”, Annals of Nuclear Energy, vol. 127, pp. 419-432, 2019|
|Operational Artificial Intelligence||D. Mandelli, D. Maljovec, A. Alfonsi, C. Parisi, P. Talbot, J. Cogliati, C. Smith, “Mining data in a dynamic PRA framework”, Progress in Nuclear Energy, 108, 99-110, September 2018.|
|Operational Artificial Intelligence||A. Alfonsi, G. Mesina, A. Zoino, N. Anderson, C. Rabiti, “Combining RAVEN, RELAP5-3D and PHISICS for Fuel Cycle and Core Design Analysis”, ASME Journal of Nuclear Engineering and Radiation Science, vol. 3, num. 2, # NERS-16-1120|
|Operational Artificial Intelligence||C. Rabiti, A. Alfonsi, A. S. Epiney, “New Simulation Schemes and Capabilities for the PHISICS/RELAP5-3D Coupled Suite”, Nuclear Science and Engineering, vol.182, num. 1, pp 104-118|
|Operational Artificial Intelligence||A. Alfonsi, A. Hummel, J. Chen, G. Strydom, H. Gougar, “Decay Heat Surrogate modeling for High Temperature Reactors”, Proceedings of HTR 2018, Warsaw, Poland, October 8-10, 2018|
|Operational Artificial Intelligence||A. Alfonsi, C. Wang, D. Mandelli, C. Rabiti, “Adaptive Surrogates within the RAVEN Framework for Dynamic Probabilistic Risk Assessment Analysis”, Proceeding of Best Estimate Plus Uncertainty International Conference, Lucca, Italy, May 13-18.|
|Operational Artificial Intelligence||A. Alfonsi, C. Rabiti, D. Mandelli, "Assembling Multiple Models within the RAVEN Framework", Proceedings of 2017 American Nuclear Society Annual Meeting, June 11-15, 2017, San Francisco|
|Operational Artificial Intelligence||C. Picoco, T. Aldemir, V. Rychkov, A. Alfonsi, D. Mandelli, C. Rabiti, "Coupling of RAVEN and MAAP5 for the Dynamic Event Tree analysis of Nuclear Power Plants", proceedings of European Safety and Reliability Conference - ESREL, June 18-22, 2017, Portoroz, Slovenia|
|Operational Artificial Intelligence||D. Mandelli, A. Alfonsi, C. Smith, C. Rabiti, “Generation and Use of Reduced Order Models for Safety Applications Using RAVEN,” Proceedings American Nuclear Society 2015 Winter Meeting, November 8-12, 2015, Washington, DC, US|
|Operational Artificial Intelligence||A. Alfonsi, G. Mesina, A. Zoino, C. Rabiti “A fuel cycle and core design analysis method for new cladding acceptance criteria using PHISICS, RAVEN and RELAP5-3D” Proceedings of the 24th International Conference on Nuclear Engineering (ICONE24), June 26-30, 2016, Charlotte, USA|
|Operational Artificial Intelligence||A. Alfonsi, D. Mandelli, C. Rabiti “RAVEN Facing the Problem of assembling Multiple Models to Speed up the Uncertainty Quantification and Probabilistic Risk Assessment Analyses “Proceedings of 13th International Conference on Probabilistic Safety Assessment and Management (PSAM 13), Oct. 2-6 2016, Seul, South Korea|
|Operational Artificial Intelligence||C. Rabiti, D. Mandelli, A. Alfonsi, J. Cogliati, R. Kinoshita “Introduction of Supervised Learning Capabilities of the RAVEN Code for Limit Surface Analysis,” Proceedings American Nuclear Society 2014 Annual Meeting, June 15-19, 2014, Reno, NV, US|
|Operational Artificial Intelligence||D. Mandelli, C. Smith, C. Rabiti, A. Alfonsi, R. Youngblood, V. Pascucci, B. Wang, D. Maljovec, P. T. Bremer “Dynamic PRA: An Overview of New Algorithms to Generate, Analyze and Visualize Data,” Proceedings American Nuclear Society 2013 Winter Meeting, November 10-14, 2013, Washington, DC|
|Operational Artificial Intelligence||A. Alfonsi, C. Rabiti, D. Mandelli, J. Cogliati, S. Sen, C. Smith, "Improving Limit Surface Search Algorithms in RAVEN Using Acceleration Schemes," INL/EXT-15-36100, July 2015|