A review of artificial intelligence in marine science

Abstract

Utilization and exploitation of marine resources by humans have contributed to the growth of marine research. As technology progresses, artificial intelligence (AI) approaches are progressively being applied to maritime research, complementing traditional marine forecasting models and observation techniques to some degree. This article takes the artificial intelligence algorithmic model as its starting point, references several application trials, and methodically elaborates on the emerging research trend of mixing machine learning and physical modeling concepts. This article discusses the evolution of methodologies for the building of ocean observations, the application of artificial intelligence to remote sensing satellites, smart sensors, and intelligent underwater robots, and the construction of ocean big data. We also cover the method of identifying internal waves (IW), heatwaves, El Niño-Southern Oscillation (ENSO), and sea ice using artificial intelligence algorithms. In addition, we analyze the applications of artificial intelligence models in the prediction of ocean components, including physics-driven numerical models, model-driven statistical models, traditional machine learning models, data-driven deep learning models, and physical models combined with artificial intelligence models. This review shows the growth routes of the application of artificial intelligence in ocean observation, ocean phenomena identification, and ocean elements forecasting, with examples and forecasts of their future development trends from several angles and points of view, by categorizing the various uses of artificial intelligence in the ocean sector.

NN-TOC v1: global prediction of total organic carbon in marine sediments using deep neural networks

“…Deep Neural Networks (DNNs) have achieved state of the art results on a variety of tasks in ocean observation, prediction, and forecasting of ocean phenomena (Song et al, 2023). DNN architectures, that are intrinsically non-parametric and non linear, are less susceptible to the curse of dimensionality.…”

A Review of Application of Machine Learning in Storm Surge Problems

“…To construct a typhoon storm surge forecast model, Park et al [78] combined a CNN to identify spatial characteristics of 2D global forecast system (GFS) data and a DNN to incorporate station-based data. Since CNN alone focuses on extracting spatial feature information, it may not perform optimally for storm surge forecasting tasks that require the consideration of both spatial and temporal features [35]. This challenge is expected to be tackled through a combination with LSTM.…”

“…The unprecedented confluence of powerful computers, sophisticated algorithms, and big ocean data with the five-V (volume, variety, value, velocity and veracity) characteristics enables the ML to make inroads in the oceanography [25,26]. Many reviews have been provided to introduce beginners and experts in fluid dynamics, marine science and engineering and earth system modeling to AI methodologies [8,[25][26][27][28][29][30][31][32][33][34][35]. In the last five years, the number of studies investigating the feasibility of ML methodologies in storm surge problems has been increasing, as depicted in Figure 1.…”

Utilizing Artificial Intelligence (AI) for the Identification and Management of Marine Protected Areas (MPAs): A Review

“…Using them improves the monitoring and management of marine resources, forecasting of ocean conditions, and data collection and analysis. Further research is needed to fully realize the potential of these technologies, even though they are still in their infancy (Song et al, 2023).…”