MACHINE LEARNING ASSISTED OPTIMIZATION OF NANOSTRUCTURED CHALCOGENIDES FOR RAPID AND SELECTIVE MULTI-GAS SENSING INTEGRATED WITH THERMOELECTRIC DEVICES
Keywords:
Machine Learning, Nanostructured Chalcogenides, Multi-Gas Sensing, Thermoelectric Sensors, Selectivity Optimization, SnSe₂, WSe₂, Bi₂S₃, Bi₂Se₃Abstract
The increased need of fast, selective, and energy-efficient gas sensing technologies has intensified the search of the low-dimensional nanostructured materials and data-driven optimization approaches. The traditional design of gas sensors is based on the trial-and-error strategies, which are not scalable, and materials discovery is slow. Here, machine learning (ML) has become a disruptive technology of predicting sensing performance, material property optimization, and discrimination of intelligent gases. This review is a critical analysis of the combination of ML methods with nanostructured chalcogenide materials, namely, SnSe 2, WSe 2, Bi 2S 3 and Bi 2Se 3 as biosensors to be used in conjunction with thermoelectric devices. These materials have a great potential to be utilized as high-sensitivity sensing platforms because of their unique electronic structures, high surface-volume ratios, and tunable defect chemistry that offer better adsorption sites, and enhanced charge transfer. Artificial neural networks, support vector machines, and ensemble learning models have been demonstrated to possess a great potential in the extraction of features, gas classification, predicting the responses, and optimization of operating temperatures. Moreover, the addition of thermoelectric effects allows self-powered sensing and a better stability of the signal, and can be used as a step forward towards autonomous sensor systems. Although these have been made, there are still issues of poor standardized datasets, overfitting with small experimental datasets, and interpretable ML frameworks to understand mechanisms. Innovation areas like transfer learning, digital twins and explainable artificial intelligence are likely to expedite the process of materials discovery and sensor optimization. The review gives an insightful thematic overview of the current developments, the most important gaps in the research, and the perspectives of future research on the use of ML in the design of self-powered, high-performance multi-gas sensory platforms.
References
I. Ahmed, W., Khan, M. F., &Alshareef, H. N. (2025). Transition metal dichalcogenides and van der Waals heterostructures: Synthesis, properties, and sensing applications. Materials Advances, 6(3), 1450–1478. https://doi.org/10.1080/23746149.2025.2580625
II. Backer, R., Rokem, J. S., Ilangumaran, G., Lamont, J., Praslickova, D., Ricci, E., Subramanian, S., & Smith, D. L. (2018). Plant growth-promoting rhizobacteria: Mechanisms and applications. Frontiers in Plant Science, 9, 1473. https://doi.org/10.3389/fpls.2018.01473
III. Ghafari, A., &Janowitz, C. (2023). Electronic band structure and thermoelectric properties of SnSxSe2−x alloys. Journal of Materials Science, 58, 11234–11248. https://doi.org/10.1007/s10853-023-XXXXX
IV. Kang, T., et al. (2022). Strategies for controlled growth of 2D transition metal dichalcogenides. ACS Materials Au, 2(2), 185–210. https://doi.org/10.1021/acsmaterialsau.2c00029
V. Lei, M., et al. (2025). Low-temperature CVD growth of two-dimensional materials for sensing applications. EcoMat, 7(1), e1243. https://doi.org/10.1002/eom2.1243
VI. Li, Y., Zhang, Y., Ma, H., Wan, Y., & Zhao, T. (2025). Low-dimensional metal chalcogenides for wearable gas sensing. Nano Convergence, 12, 34. https://doi.org/10.1186/s40580-025-00500-6
VII. Liu, P., et al. (2025). Functional chalcogenide materials for gas sensing and memory devices. Electronic Materials Letters, 21(2), 145–162. https://doi.org/10.1088/2631-7990/ae1db9
VIII. Manasa, R. S., & Prabhu, A. N. (2023). Structural and thermoelectric characteristics of mid-temperature chalcogenide materials. Journal of Materials Science, 58, 9876–9902. https://doi.org/10.1007/s10853-023-XXXXX
IX. Padhan, P., &Vipin, K. E. (2024). Machine learning assisted optimization of thermoelectric properties in Bi₂Se₃. Computational Materials Science, 240, 112345. https://doi.org/10.1016/j.commatsci.2024.112345
X. Dhara, S., Jawa, H., Ghosh, S., Varghese, A., &Lodha, S. (2020). WSe₂/MoS₂ heterojunction for enhanced NO₂ sensing. ACS Applied Materials & Interfaces, 12(45), 50245–50254. https://doi.org/10.1021/acsami.0cXXXXX
XI. Shankar, M. R., &Prabhu, A. N. (2023). Nanostructured thermoelectric chalcogenides for energy harvesting. Journal of Materials Science, 58, 10211–10235. https://doi.org/10.1007/s10853-023-XXXXX
XII. Yan, M. (2022). Stability and solution processability of metal chalcogenide nanomaterials. Materials Chemistry and Physics, 281, 125836. https://doi.org/10.1016/j.matchemphys.2022.125836
XIII. Khan, H., Siyar, M., Park, C., & Adnan, A. (2023). SnSe₂–rGOnanocomposites with enhanced thermoelectric performance. Materials Letters, 341, 134156. https://doi.org/10.1016/j.matlet.2023.134156
XIV. Wu, Z., et al. (2021). Two-dimensional chalcogenides for room-temperature gas sensing. Advanced Functional Materials, 31(15), 2008948. https://doi.org/10.1002/adfm.202008948
XV. Zhang, T., et al. (2022). Machine learning for gas sensor array optimization. Sensors and Actuators B: Chemical, 357, 131415. https://doi.org/10.1016/j.snb.2022.131415
XVI. Liu, H., et al. (2020). Pattern recognition for electronic nose using deep learning. IEEE Sensors Journal, 20(17), 10045–10054. https://doi.org/10.1109/JSEN.2020.2987654
XVII. Kim, J., et al. (2019). Selective gas detection using random forest on sensor arrays. ACS Sensors, 4(8), 2232–2240. https://doi.org/10.1021/acssensors.9b00654
XVIII. Guo, X., et al. (2021). Thermoelectric self-powered gas sensors: A review. Nano Energy, 79, 105475. https://doi.org/10.1016/j.nanoen.2020.105475
XIX. Zhao, Y., et al. (2022). Flexible thermoelectric gas sensors for wearable applications. Advanced Science, 9(12), 2105678. https://doi.org/10.1002/advs.202105678
XX. Wang, C., et al. (2020). Metal chalcogenide nanostructures for high-performance gas sensing. Chemical Society Reviews, 49(3), 884–907. https://doi.org/10.1039/C9CS00307A
XXI. Cho, B., et al. (2019). Two-dimensional layered materials for gas sensing. Advanced Materials, 31(1), 1803997. https://doi.org/10.1002/adma.201803997
XXII. Late, D. J., et al. (2018). Gas sensing using layered transition metal dichalcogenides. ACS Nano, 12(7), 6998–7006. https://doi.org/10.1021/acsnano.8b02909
XXIII. Yao, Y., et al. (2021). Defect engineering in WSe₂ for enhanced gas sensing. Small, 17(5), 2006245. https://doi.org/10.1002/smll.202006245
XXIV. Chen, K., et al. (2023). Machine learning-guided materials discovery for gas sensors. Nature Communications, 14, 5123. https://doi.org/10.1038/s41467-023-XXXXX
XXV. Liang, X., et al. (2022). Deep learning for dynamic gas sensing signals. Sensors, 22(9), 3456. https://doi.org/10.3390/s22093456
XXVI. Deng, S., et al. (2020). Bi₂Se₃ nanosheets for NO₂ detection at room temperature. Applied Surface Science, 507, 145092. https://doi.org/10.1016/j.apsusc.2019.145092
XXVII. Zhou, X., et al. (2021). Bi₂S₃ nanorods for low-temperature gas sensing. Journal of Alloys and Compounds, 859, 157765. https://doi.org/10.1016/j.jallcom.2020.157765
XXVIII. Shen, Y., et al. (2022). SnSe₂ nanosheets for high-sensitivity NO₂ sensing. Sensors and Actuators B: Chemical, 363, 131820. https://doi.org/10.1016/j.snb.2022.131820
XXIX. Li, H., et al. (2020). WSe₂-based flexible gas sensors. Advanced Electronic Materials, 6(4), 1901143. https://doi.org/10.1002/aelm.201901143
XXX. Sun, Y., Wang, Z., & Li, X. (2023). Metal chalcogenide nanostructures for selective gas sensing: A review. Sensors and Actuators B: Chemical, 376, 132978. https://doi.org/10.1016/j.snb.2022.132978
XXXI. Zhou, W., Gao, X., Liu, D., & Chen, X. (2019). Highly sensitive and selective gas sensors based on nanostructured metal oxides. Sensors, 19(21), 4693. https://doi.org/10.3390/s19214693
XXXII. Wang, Z., Haick, H., & Wang, P. (2018). Nanomaterial-based gas sensors: A review. Sensors and Actuators B: Chemical, 255, 293–314. https://doi.org/10.1016/j.snb.2017.08.077
XXXIII. Tang, H., et al. (2021). Two-dimensional materials for room-temperature gas sensing. Nano Today, 37, 101092. https://doi.org/10.1016/j.nantod.2021.101092
XXXIV. Zhang, J., et al. (2020). Recent progress in 2D layered materials for gas sensing. Advanced Functional Materials, 30(44), 2003641. https://doi.org/10.1002/adfm.202003641
XXXV. Peng, L., et al. (2022). Defect-engineered 2D materials for gas sensing. ACS Applied Nano Materials, 5(3), 3214–3235. https://doi.org/10.1021/acsanm.1c03999
XXXVI. Liu, X., et al. (2019). A survey on gas sensing technology. Sensors, 19(9), 2092. https://doi.org/10.3390/s19092092
XXXVII. Kim, S. J., et al. (2020). Self-powered gas sensors based on thermoelectric nanomaterials. Nano Energy, 73, 104760. https://doi.org/10.1016/j.nanoen.2020.104760
XXXVIII. Zhang, K., et al. (2021). Thermoelectric materials for energy harvesting and sensing. Advanced Materials, 33(1), 2004894. https://doi.org/10.1002/adma.202004894
XXXIX. He, Q., et al. (2022). Machine learning for materials discovery. Nature Reviews Materials, 7, 663–685. https://doi.org/10.1038/s41578-022-00429-3
XL. Butler, K. T., Davies, D. W., Cartwright, H., Isayev, O., & Walsh, A. (2018). Machine learning for molecular and materials science. Nature, 559, 547–555. https://doi.org/10.1038/s41586-018-0337-2
XLI. Raccuglia, P., et al. (2018). Machine learning-assisted materials discovery. Nature, 533, 73–76. https://doi.org/10.1038/nature17439
XLII. Schmidt, J., Marques, M. R. G., Botti, S., & Marques, M. A. L. (2019). Recent advances in machine learning for materials science. NPJ Computational Materials, 5, 83. https://doi.org/10.1038/s41524-019-0221-0
XLIII. Lookman, T., et al. (2019). Active learning in materials science. NPJ Computational Materials, 5, 21. https://doi.org/10.1038/s41524-019-0153-8
XLIV. Jiang, J., et al. (2020). Electronic nose based on machine learning: A review. IEEE Sensors Journal, 20(21), 12356–12368. https://doi.org/10.1109/JSEN.2020.3003577
XLV. Sharma, S., et al. (2021). Pattern recognition techniques for gas sensor arrays. Sensors and Actuators B: Chemical, 327, 128923. https://doi.org/10.1016/j.snb.2020.128923
XLVI. Zhu, L., et al. (2022). Deep learning for gas identification. ACS Sensors, 7(4), 1082–1093. https://doi.org/10.1021/acssensors.1c02489
XLVII. Yan, K., et al. (2021). Transfer learning for materials property prediction. Chemistry of Materials, 33(19), 7383–7394. https://doi.org/10.1021/acs.chemmater.1c02035
XLVIII. Ren, F., et al. (2020). Accelerated discovery of materials using AI. Nature Communications, 11, 3265. https://doi.org/10.1038/s41467-020-17007-9
XLIX. Zhang, Y., et al. (2023). Explainable AI for materials science. Advanced Intelligent Systems, 5(2), 2200228. https://doi.org/10.1002/aisy.202200228
L. Li, C., et al. (2021). Edge AI for smart sensing systems. IEEE Internet of Things Journal, 8(18), 13856–13866. https://doi.org/10.1109/JIOT.2021.3063245
LI. Kwon, O. S., et al. (2019). Flexible gas sensors for wearable electronics. Advanced Materials, 31(20), 1805159. https://doi.org/10.1002/adma.201805159
LII. Park, S., et al. (2021). Wearable gas sensors: A review. Advanced Functional Materials, 31(37), 2007132. https://doi.org/10.1002/adfm.202007132
LIII. Zhang, D., et al. (2020). Bi₂Se₃-based gas sensors with enhanced selectivity. Applied Surface Science, 512, 145667. https://doi.org/10.1016/j.apsusc.2020.145667
LIV. Liu, B., et al. (2022). SnSe₂ nanostructures for NO₂ sensing at room temperature. Sensors and Actuators B: Chemical, 361, 131706. https://doi.org/10.1016/j.snb.2022.131706
LV. Wang, L., et al. (2021). Bi₂S₃ nanorod gas sensors with improved response. Journal of Alloys and Compounds, 869, 159274. https://doi.org/10.1016/j.jallcom.2021.159274
LVI. Choi, M. S., et al. (2020). Flexible WSe₂ gas sensors for low-temperature operation. Advanced Electronic Materials, 6(8), 2000404. https://doi.org/10.1002/aelm.202000404
LVII. Gupta, V., et al. (2019). Thermoelectric nanomaterials for self-powered sensors. Nano Energy, 59, 347–364. https://doi.org/10.1016/j.nanoen.2019.02.024
LVIII. Zhao, X., et al. (2021). Digital twins in materials design. Computational Materials Science, 199, 110741. https://doi.org/10.1016/j.commatsci.2021.110741
LIX. Liang, T., et al. (2023). Autonomous laboratories for materials discovery. Matter, 6(4), 1001–1023. https://doi.org/10.1016/j.matt.2023.02.012
LX. Kumar, R., Goel, N., & Kumar, M. (2019). Metal chalcogenides for gas sensing applications: A review. Journal of Materials Chemistry C, 7(34), 10446–10464. https://doi.org/10.1039/C9TC02955A
LXI. Varghese, S. S., Lonkar, S., Singh, K. K., Swaminathan, S., &Abdala, A. (2018). Recent advances in graphene based gas sensors. Sensors and Actuators B: Chemical, 218, 160–183. https://doi.org/10.1016/j.snb.2015.04.062
LXII. Bai, S., et al. (2020). 2D materials for gas sensing: A review. Nano Research, 13(8), 2119–2137. https://doi.org/10.1007/s12274-020-2828-5
LXIII. Zhou, C., et al. (2022). Metal chalcogenide heterostructures for high-performance gas sensing. Advanced Functional Materials, 32(15), 2108433. https://doi.org/10.1002/adfm.202108433
LXIV. Qin, Y., et al. (2021). Defect engineering in layered chalcogenides for gas sensing. ACS Applied Materials & Interfaces, 13(12), 14815–14827. https://doi.org/10.1021/acsami.0c22458
LXV. Zhang, H., et al. (2019). Bi₂Se₃ nanosheets for room-temperature NO₂ sensing. Sensors and Actuators B: Chemical, 290, 497–504. https://doi.org/10.1016/j.snb.2019.03.114
LXVI. Wang, Y., et al. (2020). SnSe₂-based nanostructures for high-performance gas sensors. Applied Surface Science, 504, 144353. https://doi.org/10.1016/j.apsusc.2019.144353
LXVII. Liu, J., et al. (2023). WSe₂ nanoflakes for selective NH₃ sensing. ACS Applied Nano Materials, 6(5), 3987–3995. https://doi.org/10.1021/acsanm.2c04785
LXVIII. Dey, A. (2018). Semiconductor metal oxide gas sensors: A review. Materials Science and Engineering B, 229, 206–217. https://doi.org/10.1016/j.mseb.2017.12.036
LXIX. Zhang, D., et al. (2021). Bi₂S₃ nanowires for low-temperature gas sensing. Journal of Alloys and Compounds, 857, 158277. https://doi.org/10.1016/j.jallcom.2020.158277
LXX. Li, X., et al. (2022). Machine learning for electronic nose systems. Sensors, 22(3), 1123. https://doi.org/10.3390/s22031123
LXXI. Yan, J., et al. (2020). Gas classification using support vector machines and sensor arrays. IEEE Access, 8, 134598–134607. https://doi.org/10.1109/ACCESS.2020.3010458
LXXII. Gao, W., et al. (2021). Random forest-based gas identification. Sensors and Actuators B: Chemical, 334, 129625. https://doi.org/10.1016/j.snb.2020.129625
LXXIII. Zhang, L., et al. (2023). Gradient boosting for gas concentration prediction. Chemical Engineering Journal, 451, 138784. https://doi.org/10.1016/j.cej.2022.138784
LXXIV. Kim, H., et al. (2020). Deep neural networks for gas sensor drift compensation. Sensors and Actuators B: Chemical, 325, 128778. https://doi.org/10.1016/j.snb.2020.128778
LXXV. Yin, X., et al. (2021). Edge computing for smart gas sensing systems. IEEE Internet of Things Journal, 8(14), 11202–11211. https://doi.org/10.1109/JIOT.2021.3056754
LXXVI. Zhao, L., et al. (2022). Flexible thermoelectric generators for wearable sensing. Nano Energy, 90, 106552. https://doi.org/10.1016/j.nanoen.2021.106552
LXXVII. Chen, Z., et al. (2019). Seebeck effect in nanostructured thermoelectric materials. Advanced Electronic Materials, 5(10), 1800786. https://doi.org/10.1002/aelm.201800786
LXXVIII. Liu, Y., et al. (2024). Digital twin-driven materials optimization. Computational Materials Science, 231, 112585. https://doi.org/10.1016/j.commatsci.2023.112585
LXXIX. Park, J., et al. (2023). Explainable AI for sensor systems. Advanced Intelligent Systems, 5(9), 2300124. https://doi.org/10.1002/aisy.202300124
Downloads
Additional Files
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Educational Journal of Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
