journal article·2025-02-01Open access

Predictive modeling of electrochromic performance in ammonium metatungstate solutions using machine learning algorithms

Bocheng Jiang, Honglong Ning, Muyun Li, Rihui Yao, Chenxiao Guo, Yucheng Huang, Zijie Guo, Dongxiang Luo, Dong Yuan, Junbiao Peng

AIP Advances· Volume 15· Issue 2

Abstract

This research explores the application of machine learning (ML) in the domain of electrochromic (EC) technology, focusing specifically on liquid-state electrochromic devices (ECDs). Unlike traditional solid-state ECDs, liquid devices offer a simpler structure, reducing manufacturing variables and potentially improving prediction accuracy with minimal input data. Two types of ECDs were developed using solutions of ammonium metatungstate-iron(II) chloride and ammonium metatungstate-iron(II) sulfate, resulting in 20 different devices with varying concentration gradients. Transmittance alterations under different current densities were measured to determine modulation range and time response, serving as training data for ML models. Seven regression models were employed to construct EC models and predict optimal device solutions. Subsequent manufacturing and testing of new ECDs validated the predictions, with a comparative analysis of EC characteristics and model fitting performance conducted between the two types of ECDs. For ammonium metatungstate-iron(II) chloride ECDs, under a 5 mA applied current, the maximum optical modulation reached 23.67%, with a coloration efficiency of 17.54 cm2/C (under 700 nm). For ammonium metatungstate-iron(II) sulfate ECDs, under a 5 mA applied current, the maximum optical modulation reached 18.92%, with a coloration efficiency of 17.05 cm2/C (under 700 nm). The coloring time (tc) and bleaching time (tb) for ammonium metatungstate-iron(II) chloride ECDs were ∼14 and 8 s, respectively. The predicted maximum optical modulation for ammonium metatungstate-iron(II) chloride and ammonium metatungstate-iron(II) sulfate ECDs were 23.67% and 18.92%, respectively, with prediction accuracies reaching 97.90% and 96.97%, respectively. Decision tree regression (DTR) and kernel ridge regression (KRR) emerged as the most effective ML methods for these ECDs.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Transition Metal Oxide Nanomaterials · Conducting polymers and applications · Gas Sensing Nanomaterials and Sensors

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Guangdong Basic Research Center of Excellence for Energy and Information Polymer Materials, State Key Laboratory of Luminescent Materials and Devices, School of Materials Sciences and Engineering, South China University of Technology 1 , Guangzhou 510640,

Department of Mechanical Engineering, University of Southampton 2 , Southampton SO17 1BJ,

Huangpu Hydrogen Innovation Center/Guangzhou Key Laboratory for Clean Energy and Materials, School of Chemistry and Chemical Engineering, Guangzhou University 3 , Guangzhou 510006,

Guangdong Provincial Key Laboratory of Optical Information Materials and Technology, South China Academy of Advanced Optoelectronics, South China Normal University 4 , Guangzhou 510006,

Key Laboratory of Optoelectronic Devices and Systems of Ministry of Education and Guangdong Province, College of Physics and Optoelectronic Engineering, Shenzhen University 5 , Shenzhen 518060,

Guangdong Provincial Key Laboratory of Optical Information Materials and Technology and Institute of Electronic Paper Displays, South China Academy of Advanced Optoelectronics, South China Normal University 6 , Guangzhou 510006,

Funding

CUI CAN Program of Guangdong Province · Na-tional Natural Science Foundation of China · Guangdong Natural Science Foundation · Educational Commission of Guangdong Province · Key R&D Plan of Guangdong Province · State Key Lab of Luminescent Materials and Devices · Southwest Institute of Technology and Engineering Cooperation Fund · The open Research Fund of Songshan Lake Materials Laboratory · Science and Technology Program of Guangdong · Guangdong Basic and Applied Basic Research Foundation · Science and Technology Program of Guangzhou · Research Project of Guangzhou University · The Guangdong Provincial Key Laboratory of Optical Information Materials and Technology · The Key Laboratory of Optoelectronic Devices and Systems of Ministry of Education and Guangdong Province

References (42)

Show source-provided references
1. Energy Technol. · 2018 · 6 · 3310.1002/ente.201700705 ↗
2. Opt. Mater. · 2022 · 133 · 11284810.1016/j.optmat.2022.112848 ↗
3. IEEE Electron Device Lett. · 2000 · 21 · 21510.1109/55.841300 ↗
4. Mol. Cryst. Liq. Cryst. · 2008 · 491 · 7410.1080/15421400802329178 ↗
5. Sol. Energy Mater. Sol. Cells · 2020 · 215 · 11066110.1016/j.solmat.2020.110661 ↗
6. Synth. Met. · 2023 · 297 · 11740710.1016/j.synthmet.2023.117407 ↗
7. Adv. Electron. Mater. · 2016 · 2 · 150041410.1002/aelm.201670049 ↗
8. J. Inorg. Mater. · 2006 · 21 · 50310.1134/S0020168506050104 ↗
9. Innovative Technologies for Printing, Packaging and Digital Media
10. Micromachines · 2024 · 15 · 107310.3390/mi15091073 ↗
11. ACS Appl. Mater. Interfaces · 2024 · 16 · 2879810.1021/acsami.4c01277 ↗
12. J. Mater. Chem. C · 2023 · 11 · 1277610.1039/d3tc02522e ↗
13. ACS Sens. · 2023 · 8 · 428110.1021/acssensors.3c01637 ↗
14. Mater. Today Commun. · 2023 · 36 · 10678010.1016/j.mtcomm.2023.106780 ↗
15. Optik · 2023 · 291 · 17131010.1016/j.ijleo.2023.171310 ↗
16. Energy Build. · 2016 · 110 · 18210.1016/j.enbuild.2015.10.045 ↗
17. Phys. Scr. · 2024 · 99 · 09601010.1088/1402-4896/ad6fde ↗
18. J. King Saud Univ.-Sci. · 2023 · 35 · 10275410.1016/j.jksus.2023.102754 ↗
19. Energy Rep. · 2024 · 12 · 365410.1016/j.egyr.2024.09.056 ↗
20. J. Phys. Chem. Lett. · 2023 · 14 · 967710.1021/acs.jpclett.3c02288 ↗
21. Adv. Opt. Mater. · 2022 · 10 · 210178310.1002/adom.202101783 ↗
22. J. Phys. Chem. Lett. · 2022 · 13 · 811110.1021/acs.jpclett.2c02248 ↗
23. ACS Omega · 2020 · 5 · 2325710.1021/acsomega.0c03048 ↗
24. 2008 · 102
25. Acoust. Sci. Technol. · 2020 · 41 · 45710.1250/ast.41.457 ↗
26. Stat. Comput. · 2004 · 14 · 19910.1023/b:stco.0000035301.49549.88 ↗
27. J. Alloys Compd. · 2024 · 1003 · 17559810.1016/j.jallcom.2024.175598 ↗
28. Front. Artif. Intell. · 2023 · 6 · 112455310.3389/frai.2023.1124553 ↗
29. Adv. Sci. · 2023 · 10 · 230358910.1002/advs.202303589 ↗
30. Neuroimaging Clin. N. Am. · 2020 · 30 · 43310.1016/j.nic.2020.08.004 ↗
31. Manuf. Lett. · 2023 · 35 · 103110.1016/j.mfglet.2023.08.056 ↗
32. Appl. Soft Comput. · 2024 · 154 · 11136210.1016/j.asoc.2024.111362 ↗
33. Comput. Geosci. · 2022 · 165 · 10514010.1016/j.cageo.2022.105140 ↗
34. 2021
35. Measurement · 2022 · 189 · 11066010.1016/j.measurement.2021.110660 ↗
36. Electrochim. Acta · 2015 · 178 · 67310.1016/j.electacta.2015.08.069 ↗
37. ACS Publ. · 2016 · 8 · 386110.1021/acsami.5b10665 ↗
38. Mater. Sci. Semicond. Process. · 2015 · 29 · 20110.1016/j.mssp.2014.02.051 ↗
39. Mater. Today: Proc. · 2016 · 3 · S3010.1016/j.matpr.2016.01.005 ↗
40. Mater. Lett. · 2022 · 324 · 13269210.1016/j.matlet.2022.132692 ↗
41. Mater. Today Phys. · 2023 · 30 · 10095810.1016/j.mtphys.2022.100958 ↗
42. Sol. Energy Mater. Sol. Cells · 2023 · 257 · 11234510.1016/j.solmat.2023.112345 ↗