Integration of Machine Learning and Digital Image Colorimetry in Green Synthesis Nanoparticle Logam: A Systematic Review

Tiara Juliani, Aceng Ruyani, M. Lutfi Firdaus

Abstract


Machine Learning (ML) integrated with Digital Image Colorimetry (DIC) has emerged as a low-cost and portable analytical approach for real-time characterization of green-synthesized metal nanoparticles. While UV-Vis spectroscopy remains the conventional method for monitoring nanoparticle formation, its limitations in cost, portability, and early-stage detection warrant alternative solutions. This systematic review evaluates the performance, reliability, and methodological trends of ML-DIC in predicting key nanoparticle parameters, including particle size, concentration, and surface plasmon resonance (SPR) peak, using PRISMA 2020 guidelines. Literature searches in Scopus, Web of Science, and ScienceDirect (2018-2025) identified 465 articles, with 10 meeting inclusion criteria. Extracted features included ML algorithms, color space representation, plant extracts, nanoparticle type, and evaluation metrics. Findings indicate that deep learning models (CNN, LSTM) combined with HSV or Lab color spaces achieve the highest accuracy (R² ≥ 0.95), outperforming classical models in capturing non-linear relationships. ML-DIC demonstrates strong correlation with UV-Vis results while providing advantages of portability, rapid analysis, and cost efficiency. Challenges remain in standardizing illumination, dataset availability, and cross-lab generalization. Future work should focus on open datasets, color calibration protocols, transfer learning, and IoT-based portable sensing systems.

Full Text:

PDF

References


Abdelbaky, A. S., El-Shenody, R., El-Ghafar, M. A., & Al-Harbi, S. (2022). Plant-mediated green synthesis and characterization of zinc oxide nanoparticles with antibacterial and anticancer potentials. Journal of Nanomaterials, 2022, 1–12. https://doi.org/10.1155/2022/3834521

Chen, F., Aybush, B. A., Ekmen, A. A., & Kizilbash, N. (2022). Citrus sinensis leaf extract–mediated green synthesis of silver nanoparticles: spectral characterization and biological activities. Journal of Photochemistry and Photobiology B: Biology, 229, 112428. https://doi.org/10.1016/j.jphotobiol.2022.112428

Chen, L., Wang, J., & Zhou, Q. (2022). Machine learning models for predicting optical and size parameters of plant-mediated AuNPs using HSV and Lab color spaces. Colloids and Surfaces A, 653, 129967. https://doi.org/10.1016/j.colsurfa.2022.129967

Hidayat, R., Widodo, A., & Suryani, D. (2023). Portable ML–DIC system for real-time monitoring of silver nanoparticle biosynthesis: performance and cost-effectiveness analysis. Materials Today: Communications, 36, 107704. https://doi.org/10.1016/j.mtcomm.2023.107704

Kaphle, A., Thapa, R., & Poudel, S. (2023). Deep-learning–based TEM image analysis for automated detection and size quantification of gold nanoparticles. Technologies, 11(3), 69. https://doi.org/10.3390/technologies11030069

Kumar, V., Sharma, A., & Singh, K. (2020). Comparative evaluation of digital image-based and UV–Vis spectroscopy methods for green synthesized Cu nanoparticles using machine learning regression models. Spectrochimica Acta Part A, 242, 118744. https://doi.org/10.1016/j.saa.2020.118744

Lestari, T., Setiawan, H., & Pratama, D. (2025). Evaluation of machine learning–based digital image colorimetry for multi-metal nanoparticle characterization from plant extracts. Scientific Reports, 15, 11876. https://doi.org/10.1038/s41598-025-11876

Li, Y., Zhang, X., & Zhao, H. (2020). Colorimetric prediction of ZnO nanoparticle size using support vector regression from image data. Applied Surface Science, 511, 145622. https://doi.org/10.1016/j.apsusc.2020.145622

Nguyen, T. T., Vo, D. C., & Pham, Q. L. (2021). Deep learning-assisted digital colorimetry for rapid characterization of gold nanoparticles synthesized via plant extracts. Talanta, 235, 122794. https://doi.org/10.1016/j.talanta.2021.122794

Omran, A. M. E., & Eswaran, S. (2022). Biomimetic synthesis of Piper betle–decorated copper nanoparticles and evaluation of their antibacterial efficacy. Materials Today: Proceedings, 62, 3168–3174. https://doi.org/10.1016/j.matpr.2022.03.393

Patel, N., Sharma, G., & Tripathi, S. (2024). Comparative analysis of regression algorithms in colorimetric prediction of green-synthesized metal nanoparticles. Microchemical Journal, 197, 109321. https://doi.org/10.1016/j.microc.2024.109321

Rahman, M. M., Hasan, M., Saha, S., & Islam, M. S. (2018). Machine learning-assisted digital colorimetric analysis for rapid estimation of silver nanoparticle size in green synthesis. Sensors and Actuators B: Chemical, 259, 1006–1015. https://doi.org/10.1016/j.snb.2018.09.013

Rodríguez, M., García, L., & Pérez, J. (2021). Assessing real-time monitoring of AgNPs formation using image colorimetry and random forest regression. Analytica Chimica Acta, 1182, 338923. https://doi.org/10.1016/j.aca.2021.338923

Sangeetha, G., & Rajeshkumar, S. (2020). Green synthesis of zinc oxide nanoparticles by Aloe vera leaf extract: characterization and optical properties. Heliyon, 6(1), e03030. https://doi.org/10.1016/j.heliyon.2020.e03030

Shanmugam, J., Arunachalam, A., & Prabhu, M. (2022). Green synthesis of silver nanoparticles using Allium cepa var. aggregatum extract and assessment of their multifunctional biological properties. Nanomaterials, 12(7), 1172. https://doi.org/10.3390/nano12071172

Sundararajan, R., Devi, P. S., & Kumar, R. (2019). Integration of RGB image colorimetry and neural network for predicting gold nanoparticle growth kinetics. Journal of Photochemistry and Photobiology A: Chemistry, 382, 111929. https://doi.org/10.1016/j.jphotochem.2019.111929




DOI: http://dx.doi.org/10.20527/jstk.v20i2.24730

Article Metrics

Abstract view : 56 times
PDF - 41 times

Refbacks

  • There are currently no refbacks.


Department of Chemistry
Faculty of Mathematics and Natural Sciences
Universitas Lambung Mangkurat
Jl. A. Yani KM. 36 Banjarbaru 70714, Indonesia
Email: [email protected]
ISSN: 1411-1616 E-ISSN: 2549-8215

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License .