Microalgae are well-known photosynthetic microorganisms used as cell factories for the production of relevant biotechnological compounds. Despite the outstanding characteristics attributed to microalgae, their industrial-scale production still struggles with scale-up problems and economic feasibility. One important bottleneck is the lack of suitable online sensors for the reliable monitoring of biological parameters, mostly concentrations of intracellular components, in microalgae bioprocesses. Software sensors provide an approach to improving the monitoring of those process parameters that are difficult to quantify directly and are therefore only indirectly accessible. Their use aims to improve the productivity of microalgal bioprocesses through better monitoring, control and automation, according to the current demands of Industry 4.0. In this review, a description of the microalgae components of interest as candidates for monitoring in a cultivation, an overview of software sensors, some of the available approaches and tools, and the current state-of-the-art of the design and use of software sensors in microalgae cultivation are presented. The latter is grouped on the basis of measurement methods used as software sensor inputs, employing either optical or non-optical techniques, or a combination of both. Some examples of software sensor design using simulated process data are also given, grouped according to their design, either as model-driven or data-driven estimators.

Agro-industrial residues correspond to all the materials generated from activities that involve the transformation of both crops and livestock to obtain processed or semi-finished products. In Costa Rica, the primary sector of economy generates more than 6.3 trillion tons of organic residues per year. The daily generation of this residues pose environmental and economic problems. In recent years, biotechnological-based alternatives have emerged with the purpose of taking advantage of the high nutritional content of these residues to cultivate microorganisms capable of producing compounds with high demand at a commercial level. The present study evaluates six agro-industrial residues produced in Costa Rica, in order to growth Bacillus subtilis 168. An optimization of the culture medium was carried out under a complete factorial design 23, where the variables evaluated were carbon, nitrogen and phosphorus sources. Molasses at 10% m/v, wheat bran at 0.5% m/v, and K2HPO4 at 0.01%, as a carbon, nitrogen, and phosphorus sources, respectively, were identified as optimal for the growth of Bacillus subtilis 168.

Acquiring real-time biological data is essential for effective control of microalgae cultivation processes, yet routine monitoring still depended on laborious offline analyses that relied on time-consuming wet-chemical techniques. This study introduces a flow-through, multi-wavelength visible-light (VIS) sensor for real-time monitoring of biomass and pigment concentrations in microalgae cultivation processes. Based on 209 experimental data points, six machine-learning regression models were developed to estimate dry biomass, chlorophyll $\alpha$, chlorophyll $\beta$, total chlorophyll, total carotenoid, and astaxanthin concentrations. Validation under realistic continuous operation showed that potential remains within improved hydrodynamics and operation automatics to reduced biofilm formation. The independent dataset demonstrated that biomass and astaxanthin predictions were within ±10% of offline reference measurements. The proposed low-cost and versatile multi-wavelength sensor platform, together with machine-learning-based calibration, provides a practical soft-sensor concept for real-time monitoring of microalgal bioprocesses and offers a foundation for future integration of model-based and predictive control strategies.

Acquiring real-time biological data is essential for effective control of microalgae cultivation processes, yet routine monitoring still depended on laborious offline analyses that relied on time-consuming wet-chemical techniques. This study introduces a flow-through, multi-wavelength visible-light (VIS) sensor for real-time monitoring of biomass and pigment concentrations in microalgae cultivation processes. Based on 209 experimental data points, six machine-learning regression models were developed to estimate dry biomass, chlorophyll α, chlorophyll β, total chlorophyll, total carotenoids, and astaxanthin concentrations. Validation under realistic continuous operation with an independent dataset demonstrated that biomass and astaxanthin predictions were within ± 10% of offline reference measurements. The proposed low-cost and versatile multi-wavelength platform, together with machine-learning-based calibration, provides a practical soft-sensor concept for real-time monitoring of microalgal bioprocesses and offers a foundation for future integration of model-based and predictive control strategies.