Joshua Michalenko
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Joshua Michalenko has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
Albuquerque Sandia National Laboratories (Snl-Nm)
2 shared publications- Alan J. Van Omen
Sandia National Laboratories, Albuquerque, NM 87123, USA
1 shared publication - Brandon Berman
Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
1 shared publication - Christopher Murzyn
Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
1 shared publication - Dylan Anderson
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
1 shared publication - James Derek Tucker
Sandia National Laboratories, Albuquerque, NM, USA
1 shared publication
Latest Publications
- Open Access
- 1 September 2026
- Published by Office of Scientific and Technical Information (OSTI)
Demonstrating Novelty Discovery with Data Discovery
The Analytic Discovery Venture Data Discovery system finds relevant or novel data in sources that are effectively infinite, streaming, and costly to query, when the target is real but underspecified. This report demonstrates a second kind of novelty: not novelty as retrieval, but novelty as revealed structure. Because the discovery policy must express its hypotheses as queries executable by the data source, the fitted decision tree at its core is inherently interpretable: every split is a readab
- 1 September 2026
- Published by Office of Scientific and Technical Information (OSTI)
Open AccessDemonstrating Novelty Discovery with Data Discovery
The Analytic Discovery Venture Data Discovery system finds relevant or novel data in sources that are effectively infinite, streaming, and costly to query, when the target is real but underspecified. This report demonstrates a second kind of novelty: not novelty as retrieval, but novelty as revealed structure. Because the discovery policy must express its hypotheses as queries executable by the data source, the fitted decision tree at its core is inherently interpretable: every split is a readab
- Open Access
Machine Learning Predictions of Transition Probabilities in Atomic Spectra
Forward modeling of optical spectra with absolute radiometric intensities requires knowledge of the individual transition probabilities for every transition in the spectrum. In many cases, these transition probabilities, or Einstein A-coefficients, quickly become practically impossible to obtain through either theoretical or experimental methods. Complicated electronic orbitals with higher order effects will reduce the accuracy of theoretical models. Experimental measurements can be prohibitively expensive and are rarely comprehensive due to physical constraints and sheer volume of required measurements. Due to these limitations, spectral predictions for many element transitions are not attainable. In this work, we investigate the efficacy of using machine learning models, specifically fully connected neural networks (FCNN), to predict Einstein A-coefficients using data from the NIST Atomic Spectra Database. For simple elements where closed form quantum calculations are possible, the data-driven modeling workflow performs well but can still have lower precision than theoretical calculations. For more complicated nuclei, deep learning emerged more comparable to theoretical predictions, such as Hartree–Fock. Unlike experiment or theory, the deep learning approach scales favorably with the number of transitions in a spectrum, especially if the transition probabilities are distributed across a wide range of values. It is also capable of being trained on both theoretical and experimental values simultaneously. In addition, the model performance improves when training on multiple elements prior to testing. The scalability of the machine learning approach makes it a potentially promising technique for estimating transition probabilities in previously inaccessible regions of the spectral and thermal domains on a significantly reduced timeline.
Open AccessMachine Learning Predictions of Transition Probabilities in Atomic Spectra
Forward modeling of optical spectra with absolute radiometric intensities requires knowledge of the individual transition probabilities for every transition in the spectrum. In many cases, these transition probabilities, or Einstein A-coefficients, quickly become practically impossible to obtain through either theoretical or experimental methods. Complicated electronic orbitals with higher order effects will reduce the accuracy of theoretical models. Experimental measurements can be prohibitively expensive and are rarely comprehensive due to physical constraints and sheer volume of required measurements. Due to these limitations, spectral predictions for many element transitions are not attainable. In this work, we investigate the efficacy of using machine learning models, specifically fully connected neural networks (FCNN), to predict Einstein A-coefficients using data from the NIST Atomic Spectra Database. For simple elements where closed form quantum calculations are possible, the data-driven modeling workflow performs well but can still have lower precision than theoretical calculations. For more complicated nuclei, deep learning emerged more comparable to theoretical predictions, such as Hartree–Fock. Unlike experiment or theory, the deep learning approach scales favorably with the number of transitions in a spectrum, especially if the transition probabilities are distributed across a wide range of values. It is also capable of being trained on both theoretical and experimental values simultaneously. In addition, the model performance improves when training on multiple elements prior to testing. The scalability of the machine learning approach makes it a potentially promising technique for estimating transition probabilities in previously inaccessible regions of the spectral and thermal domains on a significantly reduced timeline.