Machine learning for microalgae detection and utilization

Abstract

Microalgae are essential parts of marine ecology, and they play a key role in species balance. Microalgae also have significant economic value. However, microalgae are too tiny, and there are many different kinds of microalgae in a single drop of seawater. It is challenging to identify microalgae species and monitor microalgae changes. Machine learning techniques have achieved massive success in object recognition and classification, and have attracted a wide range of attention. Many researchers have introduced machine learning algorithms into microalgae applications, and similarly significant effects are gained. The paper summarizes recent advances based on various machine learning algorithms in microalgae applications, such as microalgae classification, bioenergy generation from microalgae, environment purification with microalgae, and microalgae growth monitor. Finally, we prospect development of machine learning algorithms in microalgae treatment in the future.

Machine learning for algal biofuels: a critical review and perspective for the future

“…10 In recent years, some review papers were published on datadriven modeling of biofuel production. [13][14][15][16] For instance, Ning et al reviewed the performance of ML algorithms used in microalgae species identification and monitoring and also summarized their advantages and disadvantages. 15 Wang et al, on the other hand, presented a comprehensive review on ML application in bioenergy, microalgae cultivation, and biofuel conversion processes without any particular focus on microalgae applications.…”

“…[13][14][15][16] For instance, Ning et al reviewed the performance of ML algorithms used in microalgae species identification and monitoring and also summarized their advantages and disadvantages. 15 Wang et al, on the other hand, presented a comprehensive review on ML application in bioenergy, microalgae cultivation, and biofuel conversion processes without any particular focus on microalgae applications. 16 Ascher et al focused on the application of ML in the thermochemical conversion methods of various biomass sources including microalgae and waste, 14 while Aghbashlo et al systematically reviewed biodiesel production from various biomass sources, their certification, and engine application.…”

Freshwater Microscopic Algae Detection Based on Deep Neural Network with GAN-Based Augmentation for Imbalanced Algal Data

“…Recent advancements in machine learning and hardware have enabled automated image classification with computer vision technology, particularly for highly repeatable images such as microscopic algal images. Early studies used support vector machines and convolutional neural networks (CNNs) to classify single-genus algal images. Technological breakthroughs have now made multigenera algae detection possible. − However, the lack of labeled freshwater algae training data remains a challenge in machine-learning training, as it limits the understanding of rare algae genera, leading to poor detection performance.…”

Smartphone-Based Microalgae Monitoring Platform Using Machine Learning

“…Microalgae are one of the most influential aquatic organisms and suitable sources of carbon capture and sequestering, biofuel, and commercial products for human healthcare and cosmetics. − On the other hand, some microalgae species are responsible for harmful algal blooms (HABs) when they reproduce too rapidly while consuming all the dissolved oxygen and release toxic chemicals. − While a moderate concentration of harmless microalgae provides nursery nutrients to fishes and shellfishes, rapid HABs kill them, leading to economic losses. , Harmful algal blooms (HABs) have been reported worldwide for decades. This disaster occurs with a sudden bloom of harmful microalgae species that have toxins, causing risks to human health and the deaths of marine organisms.…”