Lattice Thermal Conductivity: An Accelerated Discovery Guided by Machine Learning
The DOI matches its Crossref record; 36 of the 36 references it cites were found in a registry or an index.
Abstract
In the present work, we used machine learning (ML) techniques to build a crystal-based model that can predict the lattice thermal conductivity (LTC) of crystalline materials. To achieve this, first, LTCs of 119 compounds at various temperatures (100–1000 K) were obtained based on density functional theory (DFT) and phonon calculations, and then, these data were employed in the next learning process to build a predictive model using various ML algorithms. The ML results showed that the model built based on the random forest (RF) algorithm with an R 2 score of 0.957 was the most accurate compared with the models built using other algorithms. Additionally, the accuracy of this model was validated using new cases of four compounds, which was not seen for the model before, where a good matching between calculated and predicted LTCs of the new compounds was found. To find candidates with ultralow LTCs (<1 W m –1 K –1 ) at room temperature, the model was used to screen compounds (32116) in the Inorganic Crystal Structure Database. From the screened compounds, Cs 2 SnI 6 and SrS were selected to validate the ML prediction using the counterpart theoretical calculations (DFT and phonon), and it was found that the outcome behaviors by both methods (ML prediction and DFT/phonon calculations) are fairly consistent. Considering the type of employed feature, the prime novelty in this work is that the built model can credibly predict the LTC–temperature behaviors of new compounds that are constructed based on prototype structures and chemical compositions, without the use of any DFT-relaxed structure parameters. Accordingly, using the periodic table, prototype structures, and the RF-based model, the LTC–temperature behavior of a huge number of compounds can be predicated.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Before training, the dataset was randomly divided into a training set and a test set at a ratio of 7:3 and then standardized [16].”
From Machine learning-driven prediction model for successful weaning of patients from mechanical ventilation in ICU (2026) · cites this paper as [16]
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
XGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939785 · Cited by 54,569
Greedy function approximation: A gradient boosting machine
Friedman, J. H. (2001) · The Annals of Statistics · doi:10.1214/aos/1013203451 · Cited by 30,731
QUANTUM ESPRESSO: a modular and open-source software project for quantum simulations of materials
Giannozzi, P., Baroni, S., Bonini, N., Calandra, M., Car, R., Cavazzoni, C., Ceresoli, D., Chiarotti, G. L., Cococcioni, M., Dabo, I., et al. (2009) · Journal of Physics: Condensed Matter · doi:10.1088/0953-8984/21/39/395502 · Cited by 29,281
Quinlan, J. R. (1986) · Machine Learning · doi:10.1007/bf00116251 · Cited by 21,439
First principles phonon calculations in materials science
Togo, A., & Tanaka, I. (2015) · Scripta Materialia · doi:10.1016/j.scriptamat.2015.07.021 · Cited by 11,549
Ab‐initio simulations of materials using VASP: Density‐functional theory and beyond
Hafner, J. (2008) · Journal of Computational Chemistry · doi:10.1002/jcc.21057 · Cited by 5,192
Machine learning for molecular and materials science
Butler, K. T., Davies, D. W., Cartwright, H., Isayev, O., & Walsh, A. (2018) · Nature · doi:10.1038/s41586-018-0337-2 · Cited by 4,968
Voronoi, G. (1908) · Journal für die reine und angewandte Mathematik (Crelles Journal) · doi:10.1515/crll.1908.134.198 · Cited by 2,248
A general-purpose machine learning framework for predicting properties of inorganic materials
Ward, L., Agrawal, A., Choudhary, A., & Wolverton, C. (2016) · npj Computational Materials · doi:10.1038/npjcompumats.2016.28 · Cited by 1,831
Cited by
Recent advances in designing thermoelectric materials
Mukherjee, M., Srivastava, A., & Singh, A. K. (2022) · Journal of Materials Chemistry C · doi:10.1039/d2tc02448a · Cited by 169
Zhang, Z., Xi, B. J., Ma, X., Chen, W., Feng, J., & Xiong, S. L. (2022) · SusMat · doi:10.1002/sus2.53 · Cited by 162
Predicting lattice thermal conductivity via machine learning: a mini review
Luo, Y., Li, M., Yuan, H., Liu, H., & Fang, Y. (2023) · npj Computational Materials · doi:10.1038/s41524-023-00964-2 · Cited by 130
“Alternatively, Jaafreh et al. utilized the crystal features of a series prototype structures to establish a RF-based model, which can be applied to related systems without the use of any DFT-relaxed structural parameters 16 .”
BackgroundMethodInfluentialMachine Learning for Harnessing Thermal Energy: From Materials Discovery to System Optimization
Li, M., Dai, L., & Hu, Y. (2022) · ACS Energy Letters · doi:10.1021/acsenergylett.2c01836 · Cited by 99
Machine Learning-Assisted Synthesis of Two-Dimensional Materials.
Lu, M., Ji, H., Zhao, Y., Chen, Y., Tao, J., Ou, Y., Wang, Y., Huang, Y., Wang, J.-L., & Hao, G. (2022) · ACS Applied Materials and Interfaces · doi:10.1021/acsami.2c18167 · Cited by 61
Guo, S., Huang, X., Situ, Y., Huang, Q., Guan, K., Huang, J., Wang, W., Bai, X., Liu, Z., Wu, Y., et al. (2023) · Advanced Science · doi:10.1002/advs.202301461 · Cited by 78
Zhang, H., He, Q., Zhang, F., Duan, Y., Qin, M., & Feng, W. (2025) · Advanced Materials · doi:10.1002/adma.202503140 · Cited by 83
Zhang, Y., Ren, K., Wang, W. Y., Gao, X., Yuan, R., Wang, J., Wang, Y., Song, H., Liang, X., & Li, J. (2023) · Journal of Material Science and Technology · doi:10.1016/j.jmst.2023.05.060 · Cited by 48
Thermal Transport Properties of Phonons in Halide Perovskites
Jung, Y., Lee, W., Han, S., Kim, B., Yoo, S., & Jang, H. (2022) · Advanced Materials · doi:10.1002/adma.202204872 · Cited by 40
Gurunathan, R. L., Choudhary, K. K., & Tavazza, F. (2023) · Physical Review Materials · doi:10.1103/physrevmaterials.7.023803 · Cited by 45
Xie, J., Zhou, Y., Faizan, M., Li, Z., Li, T., Fu, Y., Wang, X., & Zhang, L. (2024) · Nature Computational Science · doi:10.1038/s43588-024-00632-5 · Cited by 49
“In addition, some methods can predict thermal conductivity from crystal structures 91,92 .”
Ojih, J., Onyekpe, U., Rodriguez, A. D., Hu, J., Peng, C., & Hu, M. (2022) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.2c11350 · Cited by 40
Graph isomorphism network for materials property prediction along with explainability analysis
Xiao, J., Li, Y., & Wang, S. (2023) · Computational Materials Science · doi:10.1016/j.commatsci.2023.112619 · Cited by 33
Predicting thermoelectric transport properties from composition with attention-based deep learning
Antunes, L. M., Butler, K. T., & Grau‐Crespo, R. (2023) · Machine Learning Science and Technology · doi:10.1088/2632-2153/acc4a9 · Cited by 42
Machine-Learning-Based Thermal Conductivity Prediction for Additively Manufactured Alloys
Bhandari, U., Chen, Y., Ding, H. W., Zeng, C., Emanet, S., Gradl, P., & Guo, S. (2023) · Journal of Manufacturing and Materials Processing · doi:10.3390/jmmp7050160 · Cited by 27
A deep learning perspective into the figure-of-merit of thermoelectric materials
Jaafreh, R., Seong, K. Y., Kim, J.-G., & Hamad, K. (2022) · Materials Letters · doi:10.1016/j.matlet.2022.132299 · Cited by 26
Self-citationAlzamer, H., Jaafreh, R., Kim, J.-G., & Hamad, K. (2025) · Crystals · doi:10.3390/cryst15020114 · Cited by 26
Self-citationHuang, X. Y., Ma, S., Wu, Y., Wan, C., Zhao, C., Wang, H., & Ju, S. (2023) · Journal of Materials Chemistry A · doi:10.1039/d3ta03370h · Cited by 23
Jaafreh, R., Sharan, A., Sajjad, M., Singh, N., & Hamad, K. (2023) · Advanced Functional Materials · doi:10.1002/adfm.202210374 · Cited by 22
Self-citationLiu, Z., Jiang, M., & Luo, T. (2022) · Materials Today Physics · doi:10.1016/j.mtphys.2022.100868 · Cited by 26
“38 The average factor difference (AFD), 36 TL for target task: For our target task, which is establishing ML models for the high-fidelity TC, we first directly train the DNN using the 170 high-fidelity data.”
Barua, N. K., Golabek, A., Oliynyk, A. O., & Kleinke, H. (2023) · Journal of Materials Chemistry C · doi:10.1039/d3tc01450a · Cited by 23
A moment tensor potential for lattice thermal conductivity calculations of α and β phases of Ga2O3
Rybin, N., & Shapeev, A. V. (2024) · Journal of Applied Physics · doi:10.1063/5.0206215 · Cited by 20
“In some cases ML models are trained in a supervised manner 23–25 and in some cases machine-learned interatomic potentials (MLIPs) 26,27 are used to either compute IFCs 28–30 or to directly perform MD simulations 28,31–33 .”
MethodPrediction of lattice thermal conductivity with two-stage interpretable machine learning
Hu, J., Zuo, Y., Hao, Y., Shu, G., Wang, Y., Feng, M., Li, X., Wang, X., Sun, J., Ding, X., et al. (2023) · Chinese Physics B · doi:10.1088/1674-1056/acbaf4 · Cited by 18
Various types of A.C conduction mechanism models for solid polymer electrolytes (SPE): A review
Yong, J., Winie, T., Khandaker, M. U., Chen, Y., & Woo, H. J. (2025) · Journal of Power Sources · doi:10.1016/j.jpowsour.2025.237217 · Cited by 17
Machine learning for next-generation thermoelectrics
Sağlık, K., Srinivasan, S., Victor, V., Wang, X., Zhang, W., & Yan, Q. (2024) · Materials Today Energy · doi:10.1016/j.mtener.2024.101700 · Cited by 16
Machine Learning Approaches for Accelerating the Discovery of Thermoelectric Materials
Antunes, L. M., Vikram, V., Plata, J. J., Powell, A. V., Butler, K. T., & Grau‐Crespo, R. (2022) · ACS symposium series · doi:10.1021/bk-2022-1416.ch001 · Cited by 28
Analytical approach to structural chemistry origins of mechanical, acoustical and thermal properties
Chen, Z., Liu, W., Shan, B., & Pei, Y. (2024) · National Science Review · doi:10.1093/nsr/nwae269 · Cited by 14
“However, these approaches largely depend on the amount and quality of known inputs and involve numerical fittings [20 ].”
BackgroundTiryaki, H., Yusuf, A., & Ballıkaya, S. (2024) · Energy · doi:10.1016/j.energy.2024.130597 · Cited by 13
Xu, Y., Liu, X., & Wang, J. (2024) · Journal of Applied Physics · doi:10.1063/5.0183545 · Cited by 14
Hu, M. (2024) · Journal of Applied Physics · doi:10.1063/5.0201778 · Cited by 14
Machine learning for accelerated prediction of lattice thermal conductivity at arbitrary temperature
Li, Z., Li, M., Luo, Y., Cao, H., Liu, H., & Fang, Y. (2024) · Digital Discovery · doi:10.1039/d4dd00286e · Cited by 14
Accurate prediction of second harmonic generation coefficients using graph neural networks
Xiao, J., Li, Y., Wang, S., & He, Z. Y. (2024) · Computational Materials Science · doi:10.1016/j.commatsci.2024.113203 · Cited by 12
Yao, H., Shan, D., Pan, K., Xie, S., He, Z., Lei, C., & Liu, Y. (2024) · International Journal of Heat and Mass Transfer · doi:10.1016/j.ijheatmasstransfer.2024.126268 · Cited by 12
Wu, M., Yan, S., & Ren, J. (2025) · npj Computational Materials · doi:10.1038/s41524-025-01583-9 · Cited by 17
Jaafreh, R., Kim, J., & Hamad, K. (2022) · Crystals · doi:10.3390/cryst12091247 · Cited by 11
Self-citationJaafreh, R., Kim, J., & Hamad, K. (2024) · Journal of Power Sources · doi:10.1016/j.jpowsour.2024.234575 · Cited by 10
Self-citationBarua, N. K., Lee, S., Oliynyk, A. O., & Kleinke, H. (2025) · Journal of Physics Energy · doi:10.1088/2515-7655/adba87 · Cited by 14
“This was followed by several studies focusing on the prediction of κ l using compositional features [64, 78, 116].”
InfluentialJaafreh, R., Pereznieto, S., Jeong, S., Widiantara, I. P., Oh, J. M., Kang, J.-H., Mun, J., Ko, Y. G., Kim, J., & Hamad, K. (2024) · International Journal of Energy Research · doi:10.1155/2024/2138847 · Cited by 9
Self-citationThermal conductivity of low-dimensional materials: Recent progress, prospects, and challenges
Sheraz, A., Korotchenkov, O. A., Nasiri, M. A., de la Torre, M. A. L., & Cantarero, A. (2025) · Applied Physics Reviews · doi:10.1063/5.0274620 · Cited by 8
Máximo‐Canadas, M., Duarte, J. C., Nichele, J., Alves, L. S. D. B., Pereira, L. O. V., Ramos, R., & Borges, I. (2025) · ACS Engineering Au · doi:10.1021/acsengineeringau.5c00001 · Cited by 8
Xia, H., & Sha, Z.-D. (2025) · Materials Today Communications · doi:10.1016/j.mtcomm.2025.112842 · Cited by 11
A Review of Artificial Intelligence-Driven Approaches for Nanoscale Heat Conduction and Radiation
Guo, Z., Carne, D., Khot, K., Feng, D., Lin, G., & Ruan, X. (2025) · Journal of Computing and Information Science in Engineering · doi:10.1115/1.4070202 · Cited by 7
Athar, S., Mecibah, A., & Jund, P. (2025) · Materials Today Physics · doi:10.1016/j.mtphys.2025.101948 · Cited by 6
Luo, Y., Li, M., Yuan, H., Cao, H., & Liu, H. (2022) · Journal of Physics D Applied Physics · doi:10.1088/1361-6463/aca9db · Cited by 6
Hosseini‐Nasab, S. M., Mousavi, S. H. R., & Fuchs, S. (2025) · Geophysical Journal International · doi:10.1093/gji/ggaf260 · Cited by 6
Guo, Y., Wang, Y., Zhang, W., Shen, Z., & Zeng, L. (2025) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-025-10342-4 · Cited by 7
“Kotiba Hamad et al. used machine learning (ML) and DFT techniques to screen crystalline materials for target applications to construct a model that can predict the lattice thermal conductivity (LTC) of crystalline materials [77].”
Enhancing Thermal Conductivity Computation of Polymers via Machine Learning Techniques
Tu, C., Li, X., Chen, J., Sun, B., & Yu, K. (2025) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.5c03656 · Cited by 5
Athar, S., & Jund, P. (2026) · Artificial Intelligence Chemistry · doi:10.1016/j.aichem.2026.100113 · Cited by 6
Using Machine Learning Techniques to Discover Novel Thermoelectric Materials
Yildirim, E., & Yelgel, Ö. C. (2023) · IntechOpen eBooks · doi:10.5772/intechopen.1003210 · Cited by 6
Guo, Y., Guo, C., Xu, Y., Zheng, B., Ni, X., & Tian, F. (2025) · Journal of Magnetism and Magnetic Materials · doi:10.1016/j.jmmm.2025.173322 · Cited by 3
First-Principles Calculation of Mechanical Properties and Thermal Conductivity of C-Doped AlN
Shao, H., Wang, Y., Song, J., Lei, L., Liu, X., Hou, X., & Zhang, J. (2025) · Ceramics · doi:10.3390/ceramics8030117 · Cited by 3
“The lattice component ( κ L ) is the main contributor to the κ total of ceramic materials at lower temperatures [45,46].”
A multiclass classification model for predicting the thermal conductivity of uranium compounds
Sun, Y., Kumagai, M., Jin, M., Sato, E., Aoki, M., Ohishi, Y., & Kurosaki, K. (2023) · Journal of Nuclear Science and Technology · doi:10.1080/00223131.2023.2269974 · Cited by 3
Paliwal, P., & Alam, A. (2025) · Physical Review Materials · doi:10.1103/l92g-tkds · Cited by 3
“For instance, Jaafreh et al. developed a random forest-based model capable of predicting κ L at arbitrary temperatures[18], while Li et al. proposed a neural network-based framework to model temperature-dependent κ L with improved flexibility and accuracy[19].”
In silico modeling of inorganic thermoelectric materials
Plata, J. J., Nath, P., Sanz, J. F., & Márquez, A. M. (2022) · Elsevier eBooks · doi:10.1016/b978-0-12-823144-9.00133-3 · Cited by 2
Qiu, C., Tang, L., Zhuang, Y., Chi, C., Zheng, K., & Zhu, X. (2026) · Intensive Care Medicine Experimental · doi:10.1186/s40635-026-00859-8 · Cited by 1
“Before training, the dataset was randomly divided into a training set and a test set at a ratio of 7:3 and then standardized [16].”
Allen, T. J., Graser, J., Issa, R., & Sparks, T. D. (2024) · Advances in Applied Ceramics Structural Functional and Bioceramics · doi:10.1177/17436753231213060 · Cited by 1
“Many have used machine learning to predict the lattice thermal conductivity of crystalline solids, 10,11 and a recent report used machine learning models to identify a new aperiodic structure transition metal oxide, Ba 10 Y 6 Ti 4 O 27 , with thermal conductivity among the lowest ever measured for…”
Machine Learning Predictions of Thermopower for Thermoelectric Material Screening
Barua, N. K., & Kleinke, H. (2025) · ACS Applied Energy Materials · doi:10.1021/acsaem.5c02609 · Cited by 3
Machine Learning Accelerated Design Milk Tea-A Case of New Lemon Black TeaPreprint
Luo, S., Yao, R., Huang, M., & Jia, G. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4559197
Active Learning Approach for Accelerated Design Drink FormulasPreprint
Jia, G., Yao, R., & Huang, M. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4790012
Restianingsih, T., Shen, C., & Gohda, Y. (2026) · Scripta Materialia · doi:10.1016/j.scriptamat.2026.117431
Hu, M. (2026) · Journal of Materials Science Materials Theory · doi:10.1186/s41313-026-00083-7
“Many studies have been conducted in this transition (Jaafreh et al. 2021; Paliwal and Alam 2025; Li et al. 2024, 2025a; Hu et al. 2023; Guo et al. 2023; Filanovich et al. 2025; Qin et al. 2023a), advancing a comprehensive strategy that unites high-throughput computation, deep-learning interatomic…”
A Machine Learning‐Aided Triboelectric Sensor for Boundary Indication in Volleyball
Alzamer, H., Sultan, M. J., Kim, J. G., & Hamad, K. (2026) · Advanced Engineering Materials · doi:10.1002/adem.71163
Self-citationDu, J., Luo, S., Yao, R., Huang, M., Jia, G., & He, W. (2026) · Journal of Food Measurement & Characterization · doi:10.1007/s11694-026-04964-w
“…of new materials, including the design of multielement heterostructures [17 ], the discovery of CO₂ electrocatalysts via active machine learning techniques [18], the acceleration of lattice thermal conductivity discovery via machine learning [19], and the design of complex-composition alloys [20 ].”
Han, S., Lin, Y., Miao, N., Shu, Y., Li, Z., Zhu, L., Zhou, J., & Sun, Z. (2026) · Applied Energy · doi:10.1016/j.apenergy.2026.128925
Chong, X., Wei, Y., He, J., Lin, Y., Shang, S., Tian, F., Li, Z., Jiang, Y., Liu, Z., & Feng, J. (2026) · Research Square · doi:10.21203/rs.3.rs-11093466/v1
Metadata
- Authors
- Jaafreh, R., Kang, Y. S., & Hamad, K.
- Affiliations
- Sungkyunkwan University (KR)
- Corresponding author
- Hamad, Kotiba
- Venue
- ACS Applied Materials & Interfaces
- Publisher
- American Chemical Society (ACS)
- Published
- 2021-11-22
- Volume
- 13
- Issue
- 48
- Pages
- 57204-57213
- ISSN
- 1944-8244 (ISSN-L)
- 1944-8252
- OpenAlex
- W3215663900
- Cited by
- 66
- References
- 35
- Citations by year
- 2026: 8 · 2025: 17 · 2024: 14 · 2023: 14 · 2022: 13
- FWCI
- 3.12
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- ACS Applied Materials & Interfaces (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Research Foundation of Korea (2020R1A2C1004720)
- Topics
- Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- Physical Sciences › Materials Science › Materials Chemistry › Thermal properties of materials
- Physical Sciences › Materials Science › Materials Chemistry › Thermal Expansion and Ionic Conductivity
- Keywords
- lattice thermal conductivity, machine learning prediction, random forest, phonon calculations, low thermal conductivity materials, compound screening, Cs2SnI6, SRS, prototype structure, temperature-dependent thermal conductivity, inorganic crystals
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.