arxiv: 2605.04067 · v1 · submitted 2026-04-11 · 💻 cs.HC · cond-mat.mtrl-sci· cs.LG

Recognition: unknown

SemiConLens: Visual Analytics for 2D Semiconductor Discovery

Kavinda Athapaththu , Shiwei Chen , Yuan Fang , Sanchali Mitra , Yee Sin Ang , Yong Wang

Authors on Pith no claims yet

Pith reviewed 2026-05-10 16:28 UTC · model grok-4.3

classification 💻 cs.HC cond-mat.mtrl-scics.LG

keywords 2D semiconductorsvisual analyticsmachine learningmaterial discoveryuncertainty visualizationimputation methodshuman-AI collaborationdata visualization

0 comments

The pith

SemiConLens merges CAMI imputation, autoencoders, and linked visualizations to support reliable 2D semiconductor discovery from sparse data.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper proposes SemiConLens to help discover new 2D semiconductor materials that could solve performance limits in traditional silicon electronics as layers thin out. It introduces a Correlation Aware Multivariate Imputation method and autoencoder models that work with small, incomplete datasets while also estimating prediction uncertainties. Three connected visualization views then let researchers interactively filter candidates, compare their properties, and weigh risks using novel circular glyphs and optimized cluster layouts. This setup aims to make machine learning outputs trustworthy enough for experts to use in actual material selection decisions.

Core claim

SemiConLens is a visual analytics system that applies CAMI for multivariate imputation on sparse data and autoencoder models to predict semiconductivity while exposing uncertainties, then overlays three linked views with circular glyph designs and cluster-aware layout optimization so that material researchers can filter, discover, and compare 2D semiconductor candidates in a reliable, human-guided manner.

What carries the argument

The SemiConLens pipeline that combines CAMI imputation and autoencoder uncertainty modeling with three interactive visualization views, circular glyphs, and cluster-aware layouts to display attributes and uncertainties for each candidate.

Load-bearing premise

The machine learning models trained on small sparse datasets will generate uncertainty estimates that are accurate enough for material researchers to trust when selecting discovery candidates.

What would settle it

A test in which the uncertainties shown by the glyphs do not match actual prediction errors on new 2D material data, or in which experts using the tool select fewer high-performing candidates than they do with standard DFT screening alone.

Figures

Figures reproduced from arXiv: 2605.04067 by Kavinda Athapaththu, Sanchali Mitra, Shiwei Chen, Yee Sin Ang, Yong Wang, Yuan Fang.

**Figure 2.** Figure 2: An illustration of the proposed Correlation Aware Mul [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗

**Figure 3.** Figure 3: System interface for SemiConLens. Filter View provides an overview of the compound space, applies range-based filters, and tracks exploration history for a more targeted and efficient analysis. Discovery View visualizes clusters and influencing factors of the key attributes, enabling users to discover patterns in the compound space. Comparison View facilitates the comparison of compounds across all attribu… view at source ↗

**Figure 4.** Figure 4: Design alternatives: (A) current glyph design; (B) a cir [PITH_FULL_IMAGE:figures/full_fig_p007_4.png] view at source ↗

**Figure 5.** Figure 5: The expert interview questionnaire results. [PITH_FULL_IMAGE:figures/full_fig_p009_5.png] view at source ↗

**Figure 6.** Figure 6: With SemiConLens an expert has identified WS2 as a similar material to MoS2, suitable for hydrogen evolution reaction in water splitting. First, they applied 2 filters, CBM GW > -4.44eV and VBM GW < -5.67 eV using the Filter View. Then they selected MoS2 as the reference compound ( ). From the resulting Discovery View, they identified the cluster with MoS2 and selected it by lassoing the cluster ( ). The… view at source ↗

read the original abstract

The past few years have witnessed vibrant efforts in discovering new two-dimensional (2D) semiconductor materials from both academia and the industry, due to their promising potential in resolving the severe performance deterioration of traditional semiconductors resulting from condensed silicon thickness. However, existing methods (e.g., Density Functional Theory (DFT) or machine-learning-based approaches) suffer from various challenges such as small datasets, and reliability and trustworthiness issues. To bridge this gap, we propose SemiConLens, a visual analytics approach to combine human expertise with the power of ML to enable effective and reliable 2D semiconductor discovery. Specifically, we first develop a new Correlation Aware Multivariate Imputation (CAMI) method and use ML models like autoencoder, which can better learn from limited data and reveal uncertainty, to address the challenge of sparse data in semiconductivity prediction. Built upon this, our visualization module, consisting of three visualization views with linked interactions, allows material researchers to interactively filter, discover and compare 2D semiconductor candidates. A novel circular glyph design and a new cluster-aware layout optimization approach are proposed to effectively display all the user-configurable key attributes and possible prediction uncertainties of each semiconductor candidate, ensuring a reliable and trustable 2D semiconductor discovery. We assess SemiConLens through quantitative evaluations, expert interviews, and use cases. The results demonstrate SemiConLens's capability to help material researchers conduct effective discovery of desirable 2D semiconductors.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

SemiConLens adds a correlation-aware imputation method and circular uncertainty glyphs to visual analytics for 2D materials screening, but its reliability claims rest on thin validation of the uncertainty estimates.

read the letter

The main point is a visual analytics system that pairs a new CAMI imputation step with autoencoder predictions and linked views to help researchers explore sparse 2D semiconductor candidates while seeing uncertainty. The circular glyph and cluster-aware layout are the clearest technical additions over prior materials viz work. These pieces address a real workflow need where datasets are small and DFT or ML outputs carry noise. The paper does a solid job laying out the domain constraints and showing how interactive filtering plus multi-attribute display can let users compare options without treating the model as a black box. The evaluation outline—quantitative checks, expert interviews, and use cases—fits the contribution type and could surface practical feedback if the numbers are reported clearly. The soft spot is exactly the one the stress-test flags. The abstract states that the models reveal uncertainty and the design ensures reliable decisions, yet it gives no concrete calibration results, baseline comparisons, or held-out checks showing that reported uncertainty tracks actual error. Without that, the trust claim stays unproven even if the glyphs look good. The full paper would need to supply those metrics for the central promise to land. This work is aimed at visual analytics researchers who build tools for scientific domains and at materials scientists who screen 2D candidates. A reader working on human-in-the-loop systems for sparse-data problems would pick up usable design patterns. It deserves peer review because the system is complete, the components are new, and the evaluation plan is in place; the uncertainty validation is fixable in revision rather than a load-bearing flaw that kills the paper outright. Send it out.

Referee Report

2 major / 2 minor

Summary. The paper proposes SemiConLens, a visual analytics system for 2D semiconductor material discovery that integrates a new Correlation Aware Multivariate Imputation (CAMI) method and autoencoder models to address sparse data and provide uncertainty estimates, combined with linked visualization views featuring a novel circular glyph design and cluster-aware layout optimization. The system supports interactive filtering, discovery, and comparison of candidates, with evaluation via quantitative evaluations, expert interviews, and use cases demonstrating its capability for effective and reliable discovery by combining human expertise with ML.

Significance. If the uncertainty estimates are shown to be calibrated and the visualizations demonstrably improve discovery outcomes, the work could meaningfully advance visual analytics applications in materials science, where small and sparse datasets are common. The integration of imputation, uncertainty-aware ML, and domain-specific glyphs offers a practical human-in-the-loop approach; the expert interviews and use cases provide grounded evidence of utility beyond purely technical contributions.

major comments (2)

[Methods and Evaluation sections (CAMI/autoencoder and quantitative evaluations)] The central claim that SemiConLens enables 'reliable and trustable' discovery rests on CAMI and autoencoder uncertainty estimates being accurate enough for material researchers to act upon. However, the manuscript provides no calibration analysis (e.g., reliability diagrams, expected calibration error, or correlation between reported uncertainty and actual prediction error on held-out or external data) for these models trained on small, sparse datasets. This validation is load-bearing and absent from the methods and results descriptions.
[Evaluation section] Quantitative evaluations are asserted to demonstrate effectiveness, yet the manuscript supplies no concrete metrics, baselines (e.g., vs. mean imputation, standard autoencoders, or other VA tools), or statistical details. Without these, it is impossible to assess whether the claimed improvements in learning from limited data or decision reliability hold.

minor comments (2)

[Abstract] The abstract would be strengthened by including one or two key quantitative results or specific findings from the expert interviews to ground the effectiveness claims.
[Visualization module description] Notation for uncertainty in the glyph design and layout optimization could be clarified with explicit formulas or pseudocode to aid reproducibility.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments, which highlight important aspects of validation for our claims regarding reliable discovery. We address each major comment below and will revise the manuscript to incorporate additional analyses where needed.

read point-by-point responses

Referee: [Methods and Evaluation sections (CAMI/autoencoder and quantitative evaluations)] The central claim that SemiConLens enables 'reliable and trustable' discovery rests on CAMI and autoencoder uncertainty estimates being accurate enough for material researchers to act upon. However, the manuscript provides no calibration analysis (e.g., reliability diagrams, expected calibration error, or correlation between reported uncertainty and actual prediction error on held-out or external data) for these models trained on small, sparse datasets. This validation is load-bearing and absent from the methods and results descriptions.

Authors: We agree that calibration analysis is essential to substantiate the reliability of the uncertainty estimates, especially on small, sparse datasets. In the revised manuscript, we will include reliability diagrams, expected calibration error, and correlation analysis between reported uncertainty and actual prediction error using held-out data for both CAMI and the autoencoder models. revision: yes
Referee: [Evaluation section] Quantitative evaluations are asserted to demonstrate effectiveness, yet the manuscript supplies no concrete metrics, baselines (e.g., vs. mean imputation, standard autoencoders, or other VA tools), or statistical details. Without these, it is impossible to assess whether the claimed improvements in learning from limited data or decision reliability hold.

Authors: We acknowledge that the quantitative evaluation section requires more detail to allow proper assessment. We will expand it in the revision to report concrete metrics (e.g., imputation and prediction errors), explicit baselines including mean imputation and standard autoencoders, and statistical details such as error distributions and significance tests. revision: yes

Circularity Check

0 steps flagged

No significant circularity: system-building paper with empirical evaluation

full rationale

The paper proposes a visual analytics system (SemiConLens) that integrates a new CAMI imputation method and autoencoder models for sparse 2D semiconductor data, followed by interactive visualizations with glyphs and layouts. No mathematical derivation chain, equations, or 'predictions' derived from fitted parameters are described in the abstract or claimed structure. The contribution rests on system design, quantitative evaluations, expert interviews, and use cases rather than reducing any result to its own inputs by construction. Any self-citations (if present in full text) are not load-bearing for a uniqueness theorem or ansatz that would force the central claims. This is a standard non-circular empirical/systems paper.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 2 invented entities

Only the abstract is available, so the ledger is necessarily incomplete. The work implicitly relies on standard ML assumptions about autoencoders learning useful representations from imputed data and on the premise that visual encodings of uncertainty improve human decision quality. No explicit free parameters or invented physical entities are named.

axioms (2)

domain assumption Autoencoders can learn meaningful latent representations and uncertainty estimates from small, imputed semiconductor datasets
Invoked when stating that ML models 'can better learn from limited data and reveal uncertainty'
domain assumption Human experts can effectively use linked interactive views and uncertainty glyphs to filter and compare candidates
Central to the claim that the visualization module enables 'reliable and trustable' discovery

invented entities (2)

CAMI (Correlation Aware Multivariate Imputation) method no independent evidence
purpose: To address sparse data in semiconductivity prediction by leveraging correlations
Newly proposed technique whose independent validation is not described in the abstract
Circular glyph design no independent evidence
purpose: To display all user-configurable key attributes and prediction uncertainties
Novel visual encoding introduced to support reliable comparison

pith-pipeline@v0.9.0 · 5575 in / 1555 out tokens · 45155 ms · 2026-05-10T16:28:50.915501+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

144 extracted references · 7 canonical work pages · 1 internal anchor

[1]

A., Roy R

Addepalli S., Zhao Y., Erkoyuncu J. A., Roy R. : Quantifying Uncertainty in Pulsed Thermographic Inspection by Analysing the Thermal Diffusivity Measurements of Metals and Composites . Sensors 21, 16 (Aug. 2021), 5480

2021
[2]

: Tiny Autoencoders are Effective Few - Shot Generative Model Detectors

Bindini L., Bertazzini G., Baracchi D., Shullani D., Frasconi P., Piva A. : Tiny Autoencoders are Effective Few - Shot Generative Model Detectors . In 2024 IEEE International Workshop on Information Forensics and Security ( WIFS ) (Rome, Italy, Dec. 2024), IEEE, pp. 1--6

2024
[3]

T., Davies D

Butler K. T., Davies D. W., Cartwright H., Isayev O., Walsh A. : Machine learning for molecular and materials science. Nature 559, 7715 (2018), 547--555

2018
[4]

B., Dobkin D

Barber C. B., Dobkin D. P., Huhdanpaa H. : The quickhull algorithm for convex hulls. ACM Transactions on Mathematical Software (TOMS) 22, 4 (1996), 469--483

1996
[5]

H., Maguire E., Laramee R

Borgo R., Kehrer J., Chung D. H., Maguire E., Laramee R. S., Hauser H., Ward M., Chen M. : Glyph-based visualization: Foundations, design guidelines, techniques and applications. In Eurographics (state of the art reports) (2013), pp. 39--63

2013
[6]

A., Dennig F

Blumberg D., Wang Y., Telea A., Keim D. A., Dennig F. L. : Multiinv: Inverting multidimensional scaling projections and computing classifier maps by multilateration. Available at SSRN 5108314 (2025)

2025
[7]

K., Van Dover R

Bai J., Xue Y., Bjorck J., Le Bras R., Rappazzo B., Bernstein R., Suram S. K., Van Dover R. B., Gregoire J. M., Gomes C. P. : Phase mapper: Accelerating materials discovery with ai. AI Magazine 39, 1 (2018), 15--26

2018
[8]

R., Stevanovic V., Wadia C., Guha S., Buonassisi T

Correa-Baena J.-P., Hippalgaonkar K., van Duren J., Jaffer S., Chandrasekhar V. R., Stevanovic V., Wadia C., Guha S., Buonassisi T. : Accelerating materials development via automation, machine learning, and high-performance computing. Joule 2, 8 (2018), 1410--1420

2018
[9]

Chen C.-h., H \"a rdle W., Unwin A., Ward M. O. : Multivariate data glyphs: Principles and practice. Handbook of data visualization (2008), 179--198

2008
[10]

: Prediction of transport properties of fuels in supercritical conditions by molecular dynamics simulation

Chen C., Jiang X., Sui Y. : Prediction of transport properties of fuels in supercritical conditions by molecular dynamics simulation. Energy Procedia 158 (Feb. 2019), 1700--1705

2019
[12]

: Towards overcoming data scarcity in materials science: unifying models and datasets with a mixture of experts framework

Chang R., Wang Y.-X., Ertekin E. : Towards overcoming data scarcity in materials science: unifying models and datasets with a mixture of experts framework. npj Computational Materials 8, 1 (2022), 242

2022
[13]

: Machine learning: accelerating materials development for energy storage and conversion

Chen A., Zhang X., Zhou Z. : Machine learning: accelerating materials development for energy storage and conversion. InfoMat 2, 3 (2020), 553--576

2020
[14]

Y., Thai K

Duan T., Avati A., Ding D. Y., Thai K. K., Basu S., Ng A. Y., Schuler A. : NGBoost : Natural Gradient Boosting for Probabilistic Prediction , June 2020. arXiv:1910.03225 [cs]

work page arXiv 2020
[15]

: Benchmarking materials property prediction methods: the Matbench test set and Automatminer reference algorithm

Dunn A., Wang Q., Ganose A., Dopp D., Jain A. : Benchmarking materials property prediction methods: the Matbench test set and Automatminer reference algorithm. npj Computational Materials 6, 1 (Sept. 2020), 138

2020
[16]

W., Nabney I., Blanco I

Endert A., Ribarsky W., Turkay C., Wong B. W., Nabney I., Blanco I. D., Rossi F. : The state of the art in integrating machine learning into visual analytics. In Computer Graphics Forum (2017), vol. 36, Wiley Online Library, pp. 458--486

2017
[17]

: Evaluation of alternative glyph designs for time series data in a small multiple setting

Fuchs J., Fischer F., Mansmann F., Bertini E., Isenberg P. : Evaluation of alternative glyph designs for time series data in a small multiple setting. In Proceedings of the SIGCHI conference on human factors in computing systems (2013), pp. 3237--3246

2013
[18]

: Feature selection based on visual analytics for quality prediction in aluminium die casting

Gellrich S., Beganovic T., Mattheus A., Herrmann C., Thiede S. : Feature selection based on visual analytics for quality prediction in aluminium die casting. In 2019 IEEE 17th International Conference on Industrial Informatics (INDIN) (2019), vol. 1, pp. 66--72

2019
[19]

: Overlap Removal by Stochastic Gradient Descent With (out) Shape Awareness

Giovannangeli L., Lalanne F., Giot R., Bourqui R. : Overlap Removal by Stochastic Gradient Descent With (out) Shape Awareness . IEEE Transactions on Visualization and Computer Graphics 30, 12 (Dec. 2024), 7500--7517

2024
[20]

T., Newman M

Gastner M. T., Newman M. E. : Diffusion-based method for producing density-equalizing maps. Proceedings of the National Academy of Sciences 101, 20 (2004), 7499--7504

2004
[21]

N., Taghizadeh A., Rasmussen A., Ali S., Bertoldo F., Deilmann T., Kn sgaard N

Gjerding M. N., Taghizadeh A., Rasmussen A., Ali S., Bertoldo F., Deilmann T., Kn sgaard N. R., Kruse M., Larsen A. H., Manti S., et al. : Recent progress of the computational 2d materials database (c2db). 2D Materials 8, 4 (2021), 044002

2021
[22]

M., Marc \'i lio-Jr W

Hilasaca G. M., Marc \'i lio-Jr W. E., Eler D. M., Martins R. M., Paulovich F. V. : A Grid-Based Method for Removing Overlaps of Dimensionality Reduction Scatterplot Layouts . IEEE Transactions on Visualization and Computer Graphics 30, 8 (Aug. 2024), 5733--5749

2024
[23]

E., Ernzerhof M

Heyd J., Scuseria G. E., Ernzerhof M. : Hybrid functionals based on a screened Coulomb potential. The Journal of Chemical Physics 118, 18 (May 2003), 8207--8215

2003
[24]

: Efficient, high-quality force-directed graph drawing

Hu Y. : Efficient, high-quality force-directed graph drawing. Mathematica journal 10, 1 (2005), 37--71

2005
[25]

: Silicon Device Scaling to the Sub -10-nm Regime

Ieong M., Doris B., Kedzierski J., Rim K., Yang M. : Silicon Device Scaling to the Sub -10-nm Regime . Science 306, 5704 (Dec. 2004), 2057--2060

2004
[26]

P., Hautier G., Chen W., Richards W

Jain A., Ong S. P., Hautier G., Chen W., Richards W. D., Dacek S., Cholia S., Gunter D., Skinner D., Ceder G., et al. : Commentary: The materials project: A materials genome approach to accelerating materials innovation. APL materials 1, 1 (2013)

2013
[27]

Klinkert \'A . S. C., Campi D., Stieger C., Marzari N., Luisier M. : Ab initio simulation of band-to-band tunneling FETs with single- and few-layer 2- D materials as channels. IEEE Transactions on Electron Devices 65, 10 (Oct. 2018), 4180--4187

2018
[28]

Kailkhura B., Gallagher B., Kim S., Hiszpanski A., Han T. Y.-J. : Reliable and explainable machine-learning methods for accelerated material discovery. npj Computational Materials 5, 1 (2019), 108

2019
[29]

: High-throughput computational screening for solid-state li-ion conductors

Kahle L., Marcolongo A., Marzari N. : High-throughput computational screening for solid-state li-ion conductors. Energy & Environmental Science 13, 3 (2020), 928--948

2020
[30]

Lewis J. R. : Psychometric Evaluation of the Post - Study System Usability Questionnaire : The PSSUQ . Proceedings of the Human Factors Society Annual Meeting 36, 16 (Oct. 1992), 1259--1260

1992
[31]

M., Lee S.-I

Lundberg S. M., Lee S.-I. : A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems (2017), Guyon I., Luxburg U. V., Bengio S., Wallach H., Fergus R., Vishwanathan S., Garnett R., (Eds.), vol. 30, Curran Associates, Inc

2017
[32]

: High-throughput computational materials screening and discovery of optoelectronic semiconductors

Luo S., Li T., Wang X., Faizan M., Zhang L. : High-throughput computational materials screening and discovery of optoelectronic semiconductors. Wiley Interdisciplinary Reviews: Computational Molecular Science 11, 1 (2021), e1489

2021
[33]

P., Li L.-J

Li M.-Y., Su S.-K., Wong H.-S. P., Li L.-J. : How 2d semiconductors could extend moore’s law. Nature 567, 7747 (2019), 169--170

2019
[34]

: Machine learning for semiconductors

Liu D.-Y., Xu L.-M., Lin X.-M., Wei X., Yu W.-J., Wang Y., Wei Z.-M. : Machine learning for semiconductors. Chip 1, 4 (2022), 100033

2022
[35]

: Materials discovery and design using machine learning

Liu Y., Zhao T., Ju W., Shi S. : Materials discovery and design using machine learning. Journal of Materiomics 3, 3 (2017), 159--177

2017
[36]

: Accelerated discovery of stable lead-free hybrid organic-inorganic perovskites via machine learning

Lu S., Zhou Q., Ouyang Y., Guo Y., Li Q., Wang J. : Accelerated discovery of stable lead-free hybrid organic-inorganic perovskites via machine learning. Nature communications 9, 1 (2018)

2018
[37]

E., Doak J

Meredig B., Agrawal A., Kirklin S., Saal J. E., Doak J. W., Thompson A., Zhang K., Choudhary A., Wolverton C. : Combinatorial screening for new materials in unconstrained composition space with machine learning. Physical Review B 89, 9 (2014), 094104

2014
[38]

Martin R. M. : Electronic structure: basic theory and practical methods. Cambridge university press, 2020

2020
[39]

J., Naveiro R., Soto A

Martínez M. J., Naveiro R., Soto A. J., Talavante P., Kim Lee S.-H., Gómez Arrayas R., Franco M., Mauleón P., Lozano Ordóñez H., Revilla López G., Bernabei M., Campillo N. E., Ponzoni I. : Design of New Dispersants Using Machine Learning and Visual Analytics . Polymers 15, 5 (Mar. 2023), 1324

2023
[40]

: Deep learning in two-dimensional materials: Characterization, prediction, and design

Meng X., Qin C., Liang X., Zhang G., Chen R., Hu J., Yang Z., Huo J., Xiao L., Jia S. : Deep learning in two-dimensional materials: Characterization, prediction, and design. Frontiers of Physics 19, 5 (2024), 53601

2024
[41]

: The mastery of details in the workflow of materials machine learning

Ma Y., Xu P., Li M., Ji X., Zhao W., Lu W. : The mastery of details in the workflow of materials machine learning. npj Computational Materials 10, 1 (July 2024), 141

2024
[42]

S., Geim A

Novoselov K. S., Geim A. K., Morozov S. V., Jiang D., Zhang Y., Dubonos S. V., Grigorieva I. V., Firsov A. A. : Electric field effect in atomically thin carbon films. Science 306, 5696 (2004), 666--669

2004
[43]

O., Mar A

Oliynyk A. O., Mar A. : Discovery of intermetallic compounds from traditional to machine-learning approaches. Accounts of chemical research 51, 1 (2018), 59--68

2018
[44]

P., Burke K., Ernzerhof M

Perdew J. P., Burke K., Ernzerhof M. : Generalized Gradient Approximation Made Simple . Physical Review Letters 77, 18 (Oct. 1996), 3865--3868

1996
[45]

A., Clifton D

Pimentel M. A., Clifton D. A., Clifton L., Tarassenko L. : A review of novelty detection. Signal Processing 99 (June 2014), 215--249

2014
[46]

: First-principles calculations of charge carrier mobility and conductivity in bulk semiconductors and two-dimensional materials

Ponc \'e S., Li W., Reichardt S., Giustino F. : First-principles calculations of charge carrier mobility and conductivity in bulk semiconductors and two-dimensional materials. Reports on Progress in Physics 83, 3 (2020), 036501

2020
[47]

: Matexplorer: Visual exploration on predicting ionic conductivity for solid-state electrolytes

Pu J., Shao H., Gao B., Zhu Z., Zhu Y., Rao Y., Xiang Y. : Matexplorer: Visual exploration on predicting ionic conductivity for solid-state electrolytes. IEEE Transactions on Visualization and Computer Graphics 28, 1 (2021), 65--75

2021
[48]

E., Hinton G

Rumelhart D. E., Hinton G. E., Williams R. J. : Learning internal representations by error propagation. MIT Press, Cambridge, MA, USA, 1986, p. 318–362

1986
[49]

G., Banerjee S., et al

Streetman B. G., Banerjee S., et al. : Solid state electronic devices, vol. 4. Prentice hall New Jersey, 2000

2000
[50]

F., Romero A

Schmidt J., Cerqueira T. F., Romero A. H., Loew A., J \"a ger F., Wang H.-C., Botti S., Marques M. A. : Improving machine-learning models in materials science through large datasets. Materials Today Physics 48 (2024), 101560

2024
[51]

URL: semiconductors.org/wp-content/uploads/2023/05/SIA-2023-Factbook_1.pdf

Semiconductor Industry Association (SIA) : Factbook 2023 , 2023. URL: semiconductors.org/wp-content/uploads/2023/05/SIA-2023-Factbook_1.pdf

2023
[52]

URL: semiconductors.org/wp-content/uploads/2024/05/SIA-2024-Factbook.pdf

Semiconductor Industry Association (SIA) : Factbook 2024 , 2024. URL: semiconductors.org/wp-content/uploads/2024/05/SIA-2024-Factbook.pdf

2024
[53]

M., Li Y., Ng K

Sze S. M., Li Y., Ng K. K. : Physics of semiconductor devices. John wiley & sons, 2021

2021
[54]

: Intrinsic Electronic Transport Properties and Carrier Densities in PtS _ 2 and SnSe _ 2 : Exploration of n ^ + ‐ Source for 2D Tunnel FETs

Sato Y., Nishimura T., Duanfei D., Ueno K., Shinokita K., Matsuda K., Nagashio K. : Intrinsic Electronic Transport Properties and Carrier Densities in PtS _ 2 and SnSe _ 2 : Exploration of n ^ + ‐ Source for 2D Tunnel FETs . Advanced Electronic Materials 7, 12 (Dec. 2021), 2100292

2021
[55]

V., Ulbrich P., Selzer M., Byška J., Mičan J., Ponzoni I., Soto A

Sabando M. V., Ulbrich P., Selzer M., Byška J., Mičan J., Ponzoni I., Soto A. J., Ganuza M. L., Kozlíková B. : ChemVA : Interactive Visual Analysis of Chemical Compound Similarity in Virtual Screening , Aug. 2020. arXiv:2008.13150 [cs]

work page arXiv 2020
[56]

: Optical properties of CeO2 using screened hybrid functional and GW + U methods, Jan

Shi H., Zhang P., Li S.-S. : Optical properties of CeO2 using screened hybrid functional and GW + U methods, Jan. 2010. arXiv:1001.2899 [cond-mat]

work page arXiv 2010
[57]

: A Comparative Study of Material Impact on Tunnel Field - Effect Transistor ( TFET ) Performance

Verma M., Dutta P., Basak A., Kumar R. : A Comparative Study of Material Impact on Tunnel Field - Effect Transistor ( TFET ) Performance . In 2024 International Conference on Emerging Trends in Networks and Computer Communications ( ETNCC ) (Windhoek, Namibia, July 2024), IEEE, pp. 472--477

2024
[58]

D., Ruan S., Shen Q., Sun J., Zhu F., Wang Y

Wen X., Nguyen T. D., Ruan S., Shen Q., Sun J., Zhu F., Wang Y. : PonziLens + : Visualizing Bytecode Actions for Smart Ponzi Scheme Identification . IEEE Transactions on Visualization and Computer Graphics (2024), 1--14

2024
[59]

WTO, Nov

World Trade Organization : Global Value Chain Development Report 2023: Resilient and Sustainable Global Value Chains in Turbulent Times . WTO, Nov. 2023

2023
[60]

C., Brocks G., Er S

Wang Y., Sorkun M. C., Brocks G., Er S. : ML - Aided Computational Screening of 2D Materials for Photocatalytic Water Splitting . The Journal of Physical Chemistry Letters 15, 18 (May 2024), 4983--4991

2024
[61]

: Drawing a materials map with an autoencoder for lithium ionic conductors

Yamaguchi Y., Atsumi T., Kanamori K., Tanibata N., Takeda H., Nakayama M., Karasuyama M., Takeuchi I. : Drawing a materials map with an autoencoder for lithium ionic conductors. Scientific Reports 13, 1 (Oct. 2023), 16799

2023
[62]

: Recent Advancements and Future Prospects in Ultrathin 2D Semiconductor - Based Photocatalysts for Water Splitting

Yang X., Singh D., Ahuja R. : Recent Advancements and Future Prospects in Ultrathin 2D Semiconductor - Based Photocatalysts for Water Splitting . Catalysts 10, 10 (Sept. 2020), 1111

2020
[63]

: The Advanced Progress of MoS2 and WS2 for Multi - Catalytic Hydrogen Evolution Reaction Systems

Yu H., Zhang M., Cai Y., Zhuang Y., Wang L. : The Advanced Progress of MoS2 and WS2 for Multi - Catalytic Hydrogen Evolution Reaction Systems . Catalysts 13, 8 (July 2023), 1148

2023
[64]

: A strategy to apply machine learning to small datasets in materials science

Zhang Y., Ling C. : A strategy to apply machine learning to small datasets in materials science. Npj Computational Materials 4, 1 (2018), 25

2018
[65]

D., Persson K

Zhou J., Shen L., Costa M. D., Persson K. A., Ong S. P., Huck P., Lu Y., Ma X., Chen Y., Tang H., et al. : 2dmatpedia, an open computational database of two-dimensional materials from top-down and bottom-up approaches. Scientific data 6, 1 (2019), 86

2019
[66]

: A Review of the Effect of Defect Modulation on the Photocatalytic Reduction Performance of Carbon Dioxide

Zuo C., Tang X., Wang H., Su Q. : A Review of the Effect of Defect Modulation on the Photocatalytic Reduction Performance of Carbon Dioxide . Molecules 29, 10 (May 2024), 2308

2024
[67]

: Two-dimensional semiconductors with high intrinsic carrier mobility at room temperature

Zhang C., Wang R., Mishra H., Liu Y. : Two-dimensional semiconductors with high intrinsic carrier mobility at room temperature. Phys. Rev. Lett. 130 (Feb 2023), 087001

2023
[68]

: Cluster- Aware Grid Layout

Zhou Y., Yang W., Chen J., Chen C., Shen Z. : Cluster- Aware Grid Layout . IEEE Transactions on Visualization and Computer Graphics 30, 1 (Jan. 2024), 240--250

2024
[69]

J. M. Buhmann and D. W. Fellner and M. Held and J. Ketterer and J. Puzicha , TITLE =. 1998 , PAGES =. doi:10.1111/1467-8659.00269 , NOTE =

work page doi:10.1111/1467-8659.00269 1998
[70]

and Helmberg, Christoph , TITLE =

Fellner, Dieter W. and Helmberg, Christoph , TITLE =. 1993 , PAGES =

1993
[71]

Kobbelt and M

L. Kobbelt and M. Stamminger and H.-P. Seidel , title =. doi:10.1111/1467-8659.16.3conferenceissue.36 , note =

work page doi:10.1111/1467-8659.16.3conferenceissue.36
[72]

Lafortune and Sing-Choong Foo and Kenneth E

Eric P. Lafortune and Sing-Choong Foo and Kenneth E. Torrance and Donald P. Greenberg , title =. Proc. SIGGRAPH '97 , volume = 31, pages =
[73]

IEEE Transactions on Visualization and Computer Graphics , volume=

Matexplorer: Visual exploration on predicting ionic conductivity for solid-state electrolytes , author=. IEEE Transactions on Visualization and Computer Graphics , volume=. 2021 , publisher=

2021
[74]

AI Magazine , volume=

Phase mapper: Accelerating materials discovery with AI , author=. AI Magazine , volume=
[75]

2D Materials , volume=

Recent progress of the computational 2D materials database (C2DB) , author=. 2D Materials , volume=. 2021 , publisher=

2021
[76]

APL materials , volume=

Commentary: The Materials Project: A materials genome approach to accelerating materials innovation , author=. APL materials , volume=. 2013 , publisher=

2013
[77]

Scientific data , volume=

2DMatPedia, an open computational database of two-dimensional materials from top-down and bottom-up approaches , author=. Scientific data , volume=. 2019 , publisher=

2019
[78]

arXiv preprint arXiv:2101.04383 , year=

Interpretable discovery of new semiconductors with machine learning , author=. arXiv preprint arXiv:2101.04383 , year=

work page arXiv
[79]

npj Computational Materials , volume=

Reliable and explainable machine-learning methods for accelerated material discovery , author=. npj Computational Materials , volume=. 2019 , publisher=

2019
[80]

Chemical science , volume=

Computer-aided design of metal chalcohalide semiconductors: from chemical composition to crystal structure , author=. Chemical science , volume=. 2018 , publisher=

2018
[81]

2022 , issn =

Machine learning for semiconductors , journal =. 2022 , issn =

2022

Showing first 80 references.