Due to their abundance in nutrients and bioactive chemicals, as well as their application as ingredients in food products, cosmetics, nutraceuticals, fertilizers, biofuels, and other products, algae have become more and more in demand in Western nations in recent years. In order to evaluate the qualitative qualities of algae, their physicochemical and nutritional components must be evaluated in order to determine whether they are suitable for a given end use. Typically, this evaluation is carried out using costly, time-consuming, and destructive traditional chemical analyses that also require sample preparation. The Hyperspectral Imaging (HSI) methodology has shown effective in evaluating and controlling food quality, and it has promise in surmounting the constraints of conventional biochemical methods. This study used conventional methods to examine the nutritional profile (proteins, lipids, and fibers) of seventeen edible macro and microalgae species that are commonly produced worldwide. Furthermore, multi-species models for proteins, lipids, and fibers were created using Artificial Neural Network (ANN) algorithms and a Shortwave Infrared (SWIR) hyperspectral imaging apparatus. A variety of metrics were used to assess the models' predictive power, and all of them shown extremely strong predictive performances for nutritional parameters (for instance, R2=0.9952, 0.9767, and 0.9828 for proteins, lipids, and fibers, respectively). Our findings showed that Shortwave Infrared (SWIR) hyperspectral imaging in conjunction with ANN algorithms can efficiently and sustainably quantify biomolecules in algae species.
