Abstract
Algal blooms have recently become a critical global environmental concern which might put economic development and sustainability at risk. However, the accurate prediction of algal blooms remains a challenging scientific problem. In this study, a novel prediction approach for algal blooms based on deep learning is presented—a powerful tool to represent and predict highly dynamic and complex phenomena. The proposed approach constructs a five-layered model to extract detailed relationships between the density of phytoplankton cells and various environmental parameters. The algal blooms can be predicted by the phytoplankton density obtained from the output layer. A case study is conducted in coastal waters of East China using both our model and a traditional back-propagation neural network for comparison. The results show that the deep-learning-based model yields better generalization and greater accuracy in predicting algal blooms than a traditional shallow neural network does.
Highlights
The increasing pace of human and socioeconomic dynamics around the world has been at the cost of environmental deterioration over the same time period
The results showed that a deep belief networks (DBN)-based model is superior to the traditional BP neural network in terms of accuracy and efficiency
This study adopts DBN as the deep learning architecture which is one of the most widely used framewwoorrkkss
Summary
The increasing pace of human and socioeconomic dynamics around the world has been at the cost of environmental deterioration over the same time period. Algal blooms refer to the explosive increase and high concentration of phytoplankton in local waters, posing an enormous threat to the marine ecosystem, fisheries, and human health at unprecedented rates in recent years. Several studies have revealed the successful application of data-driven techniques in the field of algal blooms prediction that mainly include artificial neural networks (ANN) and evolutionary algorithms [9,11,12,13]. Most data-driven models such as the back-propagation neural network (BPNN) and support vector machine (SVM) possess limitations in representing highly nonlinear phenomena using a single hidden layer of computation architecture, which is shallow learning.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
