Optimizing Nutrient Detection in Hydroponic Solutions through UV-Vis-NIR Spectroscopy and Machine Learning Modelling

Authors

  • Rozita Sulaiman Photonics Technology Laboratory, Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 43600 Bangi, Selangor, Malaysia.
  • Nur Hidayah Azeman Institute of Microengineering and Nanoelectronics, Universiti Kebangsaan Malaysia, 43600 Bangi, Selangor, Malaysia. https://orcid.org/0000-0001-5799-143X
  • Athiyah Sakinah Masran Photonics Technology Laboratory, Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 43600 Bangi, Selangor, Malaysia. https://orcid.org/0009-0002-4413-5495
  • Muhammad Qayyum Othman Photonics Technology Laboratory, Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 43600 Bangi, Selangor, Malaysia. https://orcid.org/0009-0006-5037-3579
  • Nur Afifah Ahmad Nazri Institute of Microengineering and Nanoelectronics, Universiti Kebangsaan Malaysia, 43600 Bangi, Selangor, Malaysia.
  • Azween Hadiera Hishamuddin School of Electrical Engineering, College of Engineering, Universiti Teknologi MARA, 40450, Shah Alam, Selangor, Malaysia.
  • Mohd Hafiz Abu Bakar Institute of Power Engineering, Universiti Tenaga Nasional,43000 Kajang, Selangor, UNITEN, Malaysia.
  • Ahmad Ashrif A Bakar Photonics Technology Laboratory, Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, 43600 Bangi, Selangor, Malaysia.

DOI:

https://doi.org/10.53655/joe.t5740v

Keywords:

Spectroscopy, Regression, Macronutrient, Hydroponics, Efficiency.

Abstract

Accurate nutrient determination is crucial for optimizing hydroponic systems. Traditional methods like electrical conductivity (EC), ion-selective electrodes (ISE), and colourimetry are hindered by limited ion specificity, high maintenance, and prolonged analysis times. Current spectroscopy-based AI methods also require extensive sample sizes, complicating real-time use. This study presents a rapid UV-Vis-NIR spectroscopy technique integrated with machine learning (ML) for predicting nitrogen and phosphorus levels using minimal samples. Among five regression models tested Support Vector Machine Regression (SVR), Linear Regression (LR), Partial Least Squares Regression (PLSR), Random Forest Regression (RFR), and Gradient Boosting Trees Regression (GBTR) linear regression (LR) excelled for nitrogen prediction (R²=0.9734; RMSE=19.2345 ppm), although its performance slightly dropped during external validation (R²=0.923; RMSE=30.6666 ppm). Random forest regression (RFR) showed superior accuracy for phosphorus prediction (R²=0.9578, 0.9468). Integration of SVM classification with LR and RFR further improved accuracy (R²=0.96) despite 26 samples. This ML-based spectroscopy model enables rapid, precise nutrient monitoring, enhancing crop yield and sustainability in hydroponics.

References

R. Sulaiman, N. H. Azeman, M. H. H. Mokhtar, N. N. Mobarak, M. H. Abu Bakar, and A. A. A. Bakar, “Hybrid ensemble-based machine learning model for predicting phosphorus concentrations in hydroponic solution,” Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, vol. 304, p. 123 327, Jan. 2024, ISSN: 1386-1425. DOI: 10.1016/j.saa.2023.123327

F. Monteiro-Silva, P. A. S. Jorge, and R. C. Martins, “Optical sensing of nitrogen, phosphorus and potassium: A spectrophotometrical approach toward smart nutrient deployment,” Chemosensors, vol. 7, no. 4, p. 51, Oct. 2019, ISSN: 2227-9040. DOI: 10.3390/chemosensors7040051

F. Silva et al., “Reagent-less spectroscopy towards npk sensing for hydroponics nutrient solutions,” Sensors and Actuators B: Chemical, vol. 395, p. 134 442, Nov. 2023, ISSN: 0925-4005. DOI: 10.1016/j.snb.2023.134442

Downloads

Published

02-11-2025

How to Cite

Sulaiman, R. ., Azeman, N. H. ., Masran, A. S., Othman, M. Q., Ahmad Nazri, N. A. ., Hishamuddin, A. H. ., Abu Bakar, M. H., & A Bakar, A. A. (2025). Optimizing Nutrient Detection in Hydroponic Solutions through UV-Vis-NIR Spectroscopy and Machine Learning Modelling. Jurnal OptoElektronik, 1–3. https://doi.org/10.53655/joe.t5740v

Issue

Volume 4 (2025)

Section

TMP2025: Regular

License

Copyright (c) 2025 Rozita Sulaiman, Nur Hidayah Azeman, Athiyah Sakinah Masran, Muhammad Qayyum Othman, Nur Afifah Ahmad Nazri, Azween Hadiera Hishamuddin, Mohd Hafiz Abu Bakar, Ahmad Ashrif A Bakar

Creative Commons License

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

By submitting documents to Jurnal OptoElektronik, the authors agree to the followings:
1. Articles are published under a Creative Commons CC BY-NC 4.0 license that allows third parties to read, download, copy and share their work provided proper acknowledgement are given.
2. The authors retain copyright and grant Jurnal OptoElektronik rights of first publication.
3. The authors are permitted and encouraged to share their work online (e.g., in institutional repositories or on their website)
4. The authors verifies that the submission has not been previously published, nor is it before another journal for consideration. If submitting an article for resubmission, the submitting author will need to notify the editor through the Comments for the Editor section in the submission process.
5. The authors are responsible to secure all necessary copyright permissions for the use of 3rd-party materials in their manuscript.
6. The author declares that this is their original work and has been written by the stated authors.