A Robust Algae Biomass Growth Rate Estimation using RGB Imaging

Abstract

The growing demand for sustainable bioresources has spurred research into algae biomass estimation, a crucial aspect of biofuel production, carbon capture, and wastewater treatment. Despite the development of several methods to estimate algae biomass, a lack of standardized, scalable, and non-invasive biomass estimation models for outdoor environments persists. This study introduces a novel method that utilizes digital image-based RGB analysis of image models, integrated with machine learning (ML) algorithms. Traditional biomass estimation methods typically involve spectrophotometric or chemical analyses, which are labour-intensive and expensive. In contrast, the proposed approach employs low-cost RGB imaging, which enables real-time biomass quantification through image-based analysis. The research process involves data collection from controlled algae cultivation experiments, image preprocessing, and feature extraction using advanced computer vision techniques applied to Chlorella sorokiniana cultivated outdoors. Key features, such as colour indices, texture patterns, and pixel intensity distributions, were extracted from the RGB images. Various ML models, including Random Forest regressor (RFR), Extreme Gradient Boosting regressor (XGBR), and Convolutional Neural Networks (CNNs), were trained and validated to predict algal biomass concentrations. Experimental results demonstrated that the ML models accurately predicted algae biomass, with a correlation coefficient (R²) exceeding 90% in test datasets, showcasing the robustness of the proposed framework. Future research will explore multispectral extensions, adaptive ML models for various algal species, and deployment in real-world industrial settings.