Recent research has demonstrated that UV-Visible (UV-Vis) spectroscopy combined with machine learning (ML) can provide a fast, cost-effective, automated method for detecting biological contamination in microalgae cultures. This study published in the journal Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopyled by Eduardo Maia Paiva at the VTT Technology Research Centre in Finland, detailing how this new method improves traditional methods for detecting biological contamination of microalgae (1).
Microalgae cultivation usually consists of five stages. Stock separation. Cultivation stage; Growth stage; Harvest stage; and finally, the formulation stage (2). This process is important in a variety of industries, from feed production to pharmaceuticals and biofuels. However, due to the number of steps involved, there can be many challenges and complications. For example, contamination by microorganisms such as flagellar rocks and spinning agents threatens the stability and survival of these cultures, often resulting in catastrophic losses (1). Traditional detection techniques such as microscopy and cytometry are labor intensive and rely on expert interpretation, slow response times and limits on scalability (1).
Algae macro of algae. Biotechnology science. It is generated by AI. | Image credit: ©Zaifa Art Mart -Stock.adobe.com
In their study, the researchers demonstrated that UV-VIS spectroscopy could be a potential solution to these challenges. Although spectroscopy has been used for this purpose in the past, studies have found that techniques such as Raman and Fourier transform infrared (FT-IR) spectroscopy struggle to analyze live microalgae in aqueous environments or require sampling strategies over time (1). Raman spectroscopy struggles to monitor large-scale microalgae cultures due to limited sampling volumes (1). On the other hand, FT-IR spectroscopy is not suitable for in vivo monitoring in aqueous media, as water absorbs in infrared light strongly (1).
UV-VIS spectroscopy, on the other hand, benefits from the natural pigment chemistry of microalgae (1). This chemistry generates clear spectral fingerprints that can be exploited for real-time automated contamination detection (1).
Researchers explained in their study that UV-VIS spectra are good at picking up chlorophyll, carotenoids and lipids.
As part of the experimental procedure, the researchers have put together a setup that includes a wavelength of 200-1000 nm, a 10 mm cuvette holder, and a UV light source covering a handheld spectrometer for data collection. By comparing uncontaminated cultures with contaminated cultures, they distinguished microalgae well. Tetradesmus obliquusflagellum Poterioochromonas malhamensisand rotifer brachionus plicatilis In bulk colllellella vulgaris solution (1).
Researchers found that their approach was sensitive enough to detect contamination even under difficult conditions. For example, one of these conditions is when the salt stress medium was a habitat used to grow microalgae cultures (1). Salt stress changes the balance of pigments, and what this occurs is a spectral change that can obscure detection (1). However, by using principal component analysis (PCA), researchers found that differences in these spectral differences could be classified with accuracy (1).
This study has important implications. One, this study provides a pathway to reduce the need for manual sample analysis. Automating contamination detection will allow scientists to save both labor costs and time (1). Furthermore, compatibility with technology with inline monitoring and camera-based imaging offers exciting possibilities for scalable, real-world deployments (1).
By exploiting the synergistic effects of spectroscopy and artificial intelligence, this study demonstrates how chemical and biological signals embedded in spectral data can be decoded into practical information. The result is a streamlined and cost-effective system for maintaining the integrity of microalgae cultures (1).
The findings show important advances in the application of light-based spectroscopic techniques to biological monitoring. As industry becomes increasingly transformed into microalgae for sustainable solutions, it ensures that cultural stability is essential, and this study provides a promising tool to achieve its goals (1).
reference
- Paiva, em; Hyttinen, E. ; Donsberg, T. ; Barth, D. Biological contaminant analysis in microalgae cultures using UV-Vis spectroscopy and machine learning. Spectrochimica Acta Part A: Mol. Biomol. Spectroscopy. 2025, 330, 125690. doi: 10.1016/j.saa.2024.125690
- Kousaman, CN; Senthil Kumar, P. ;Selvan, Vam;Ganesh, D. Comprehensive insights from microalgae production processes to characterizing biofuels for sustainable energy. fuel 2022, 310122320. doi: 10.1016/j.fuel.2021.122320.
