Integrating Biomass Forecasting with Techno-Economic Analysis for Spirulina Cultivation: A Predictive Modeling Review

This review paper provides a comparative analysis of predictive modeling and techno-economic assessment in Spirulina cultivation. As a nutrient-rich microalga, Spirulina presents a sustainable solution to global food demands, yet its commercial viability hinges on optimizing production yield while minimizing costs. A significant challenge lies in the disconnect between dynamic biological forecasting and static economic analysis. Being able to predict biomass yield early and accurately-while also tracking costs in real time-gives producers the ability to make smarter, data-driven choices that improve both efficiency and profitability. This paper traces how predictive models have evolved, moving from Artificial Neural Networks (ANNs) to more advanced Long Short-Term Memory (LSTM) models, and reviews techno-economic studies that highlight the main cost drivers in Spirulina cultivation. We look closely at the datasets, performance metrics, and real-world uses of these two research areas. A key gap we identify is the absence of a unified framework that connects yield prediction with cost forecasting. To address this, we propose an integrated model that links predicted biomass directly to production costs, offering a practical path forward for building intelligent, costaware decision support systems to support sustainable microalgae farming.