Hydroponics Monitoring Through UV-Vis Spectroscopy and Artificial Intelligence: Quantification of Nitrogen, Phosphorous and Potassium

Anibal Filipe Silva, Klara Löfkvist, Mikael Gilbertsson, E.A. van Os, G.C. Franken, J. Balendonck, Tatiana M. Pinho, Jose Boaventura-Cunha, Luis Coelho, Pedro Jorge, Rui Martins*

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review


In hydroponic cultivation, monitoring and quantification of nutrients is of paramount importance. Accurate, robust sensors for detection of Nitrogen, Phosphorus and Potassium (NPK) would be desired in horticultural production. Spectroscopy can be used for this, but other nutrients interfere and hinder accurate and reliable quantification.

In order to better understand and solve nutrients’ interferences, an orthogonal experimental design has been used, based on Hoagland fertilizer solutions, a widely used complete and complex nutrient mixture. The experimental factorial design consisted of eight orthogonal levels of N, P and K rendered on 83 of different samples of Hoagland solution, each one with its own specific concentration of NPK. Concentration ranges were varied in a target analyte independent style: [N]= [103.17-554.85] ppm; [P]= [15.06-515.35] ppm; [K]= [113.78-516.45] ppm, by dilution from individual stock solutions. This strategy allowed the variation of each parameter individually, maintaining the remaining constant, enabling the individual variations as well as their correlations to be obtained. A UV-Vis-based Artificial Intelligence-enhanced (AI) system was used for quantification of NPK on the analysed samples. It featured an advanced processing algorithm named Self-Learning Artificial Intelligence (SL-AI).

From the analysis of the acquired and processed data, it was possible to understand that N spectral features are dominant, whereas P and K will behave as interferents, with information on P properties not being very evident on spectra. The obtained results allowed very good quantifications for N and K, with errors of 6.7% (0.997) and 3.8% (0.987), respectively, to be achieved. Regarding P, as expected, only satisfactory results were obtained, corresponding to a qualitative grade. The developed system can be of great potential for monitoring and quantification of NPK in hydroponic platforms.
Original languageEnglish
Article number88
Pages (from-to)181-186
Number of pages4
JournalChemistry Proceedings
Issue number1
Early online date30 Jun 2021
Publication statusPublished - 30 Jun 2021


Dive into the research topics of 'Hydroponics Monitoring Through UV-Vis Spectroscopy and Artificial Intelligence: Quantification of Nitrogen, Phosphorous and Potassium'. Together they form a unique fingerprint.

Cite this