Sparse Modeling of an Extended X-Ray Absorption Fine-Structure Spectrum Based on a Single-Scattering Formalism

Akai, Ichiro; Iwamitsu, Kazunori; Igarashi, Yasuhiko; Okada, Masato; Setoyama, Hiroyuki; Okajima, Toshihiro; Hirai, Yasuharu

doi:10.7566/jpsj.87.074003

Cited by 16 publications

(21 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In Table I we report the obtained parameters, compared with the same parameters obtained through the conventional peak-fitting scheme within GNXAS for the same data and literature references. Similar to previous works [11,14], the error on the Debye-Waller is the standard deviation of the mean over the CV datasets. The error on the average distance, instead, comes from a non-structural parameter, the energy shift ∆E, which is the difference between the experimental energy scale and the energy scale of the phase shift and amplitude calculations.…”

Section: A Cumentioning

confidence: 81%

“…We tested the method on different systems. Without using any prior information about the structure, other than knowing which elements are present in the material, we were able to obtain peak positions of the RDF for metals and cuprous oxide, which is a step forward respect to previous formulation [11]. A quantitative analysis can then be performed on the nearest-neighbor peaks to retrieve structural parameters, like average distances and Debye-Waller factors.…”

Section: Discussionmentioning

confidence: 99%

“…To choose the appropriate value of the hyper-parameter λ five-fold cross validation analysis and the one-standarderror (1SE) rule are employed [11,24,25]. We divide the data into five different subset randomly and then iteratively use each subset to test the result obtained from applying LASSO to the remaining data points.…”

Section: Methodsmentioning

confidence: 99%

“…To overcome these limitations, an alternative approach that does not require prior knowledge about the structure is to use sparse modeling [11]. This method falls within the so-called regularization technique [12]: in our case we utilize the 1 -norm as regularization condition, which tends to find sparse solutions [13], hence the name sparse modeling.…”

Section: Introductionmentioning

confidence: 99%

“…This is because, in general, the L 1 -regularizer prioritize relevant features and keep the others to zero to avoid overfitting of the data. In previous implementation of the method [11,14], simple sine and cosine functions were used as basis to describe the oscillations of the EXAFS signals together with few parameters and could obtain Debye-Waller factors for various metals. In this paper, we show progress of this method using a more refined model: starting from the two-body expansion of the EXAFS signal and including calculations for amplitudes and phase shifts, we are able to extract the peak positions of the RDF and to treat multi-atomic cases.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Sparse Modeling analysis of Extended X-ray Absorption Fine Structure data using two-body expansion

Iesari¹,

Setoyama²,

Igarashi³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Analysis of extended X-ray absorption fine structure (EXAFS) data by the use of sparse modeling is presented. We consider the two-body term in the n-body expansion of the EXAFS signal to implement the method, together with calculations of amplitudes and phase shifts to distinguish between different back-scattering elements. Within this approach no a priori assumption about the structure is used, other than the elements present inside the material. We apply the method to the experimental EXAFS signal of metals and oxides, for which we were able to extract the radial distribution function peak positions, and the Debye-Waller factor for first neighbors.

show abstract

Section: A Cumentioning

confidence: 81%

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Sparse Modeling analysis of Extended X-ray Absorption Fine Structure data using two-body expansion

Iesari¹,

Setoyama²,

Igarashi³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Toward Excellence of Electrocatalyst Design by Emerging Descriptor‐Oriented Machine Learning

Liu

Luo

Wang

et al. 2022

Adv Funct Materials

View full text Add to dashboard Cite

(1 of 25)development, it is still far from meeting the increased demand. [3] The emergence of artificial intelligence (AI) has fundamentally changed the situation, which has significantly accelerated the discovery process, owing to greatly improved algorithms and developments in data science. [4] Machine learning (ML), a simple and practical AI framework based on computer and statistical science, is used to develop algorithms to learn from historic data without being explicitly programmed to obtain specific results. [5] It can investigate relationships that are hard to clearly and definitely model mathematically, providing insights for new scientific advancements related to highly complex with many uncertain twisted together factors. [6] There are usually three factors that govern the learning and prediction process of an ML: algorithms, data/database, and descriptors. [4] The algorithms involve data extraction, data filing, and propagation from mathematical derivation. [5,7] The data can be derived not only from experiments but also from theoretical calculations. [4] A number of databases based on experiments [8] and calculations [9] have already been established. The descriptors depend to a large extent on the predicted material or properties. Based on the algorithm, databases, and descriptors, the ML applications have been successfully implemented to support various energy materials with analysis tools (e.g., Python-based SciKit-Learn [10] and TensorFlow [11] ) in combination with workflow management tools (e.g., ASE [12] and Atomate [13] ). However, the prediction accuracy depends highly on the descriptors, as descriptors have a certain uniqueness for various materials and properties as long as the algorithm is selected correctly and the data set is complete. [14] For catalysis, the descriptors contain the essence from the physicochemical nature. Based on effective descriptors, ML can uncover the relationship bridging structure and its activity, selectivity, and stability. [5,15] Thus, suitable descriptors must be established to understand the structure-activity relationship. Although many efforts have been made to accelerate the rational design of homogeneous catalysts, [7b,16] heterogeneous catalysts, [7b,16b,17] and electrocatalysis, [3,18] the development of ML-assisted real catalysts is still in its infancy. Despite these considerable research efforts, the lack of universal selection tactics for descriptors bridging the gap between activity and structures impedes the application

show abstract

Machine Learning for Catalysis Informatics: Recent Applications and Prospects

et al. 2019

View full text Add to dashboard Cite

The discovery and development of catalysts and catalytic processes are essential components to maintaining an ecological balance in the future. Recent revolutions made in data science could have a great impact on traditional catalysis research in both industry and academia and could accelerate the development of catalysts. Machine learning (ML), a subfield of data science, can play a central role in this paradigm shift away from the use of traditional approaches. In this review, we present a user’s guide for ML that we believe will be helpful for scientists performing research in the field of catalysis and summarize recent progress that has been made in utilizing ML to create homogeneous and heterogeneous catalysts. The focus of the review is on the design, synthesis, and characterization of catalytic materials/compounds as well as their applications to catalyzed processes. The ML technique not only enhances ways to discover catalysts but also serves as a powerful tool to establish a deeper understanding of relationships between the properties of materials/compounds and their catalytic activities, selectivities, and stabilities. This knowledge facilitates the establishment of principles employed to design catalysts and to enhance their efficiencies. Despite such advantages of ML, it is noteworthly that the current ML-assisted development of real catalysts remains in its infancy, mainly because of the complexity of catalysis associated with the fact that catalysis is a time-dependent dynamic event. In this review, we discuss how seamless integration of experiment, theory, and data science can be used to accelerate catalyst development and to guide future studies aimed at applications that will impact society’s need to produce energy, materials, and chemicals. Moreover, the limitations and difficulties of ML in catalysis research originating from the complex nature of catalysis are discussed in order to make the catalysis community aware of challenges that need to be addressed for effective and practical use of ML in the field.

show abstract

Sparse Modeling of an Extended X-Ray Absorption Fine-Structure Spectrum Based on a Single-Scattering Formalism

Cited by 16 publications

References 17 publications

Sparse Modeling analysis of Extended X-ray Absorption Fine Structure data using two-body expansion

Sparse Modeling analysis of Extended X-ray Absorption Fine Structure data using two-body expansion

Toward Excellence of Electrocatalyst Design by Emerging Descriptor‐Oriented Machine Learning

Machine Learning for Catalysis Informatics: Recent Applications and Prospects

Contact Info

Product

Resources

About