Deep-learning-based information mining from ocean remote-sensing imagery

Abstract

With the continuous development of space and sensor technologies during the recent 40 years, ocean remote sensing has entered into the Big Data era with typical Five-V (volume, variety, value, velocity, and veracity) characteristics. Ocean remote sensing data archives reach several tens of petabytes, and massive satellite data are acquired worldwide daily. To precisely, efficiently and intelligently mining the useful information submerged in such ocean remote sensing data sets is a big challenge. Deep learning, a powerful technology recently emerging in the machine-learning field, has demonstrated its more significant superiority over traditional physical- or statistical-based algorithms for image information extraction in many industrial-field applications and starts to draw interest in ocean remote sensing applications. In this review paper, we first systematically reviewed two deep learning frameworks that carry out ocean remote sensing image classifications and then presented eight typical applications in ocean internal wave/eddy/oil spill/coastal inundation/sea-ice/green algae/ship/coral reef mapping from different types of ocean remote sensing imagery to show how effective of these deep learning frameworks. Researchers can also readily modify these existing frameworks for information mining of other kinds of remote sensing imagery.

Managing Marine Environmental Pollution using Artificial Intelligence

“…Ocean remote sensing entering the big-data era (Source: adapted from Li et al, 2020). † Such as those under the UNEP in the Baltic Sea, the North Sea and the NE Atlantic, the Mediterranean, the Red Sea, the Persian Gulf, the waters of the Caribbean, the sea off West Africa and the West Coast of South America, and East Asian waters.…”

Subsurface Temperature Estimation from Sea Surface Data Using Neural Network Models in the Western Pacific Ocean

“…In recent years, with the development of remote sensing data, model simulation data, and Argo datasets, multisource sea surface data with a high level of quality have become more and more abundant. Artificial intelligence applications in the oceanography field have been widely studied [19,20]. In particular, machine learning methods based on various sea surface parameters have been used to reconstruct the OST with many outstanding results [6,[21][22][23][24].…”

“…Recently, Su et al also estimated the global ocean subsurface temperature and salt anomalies using the extreme gradient boosting (XGBoost) model by combining sea surface remote sensing data and Argo buoy observations [6]. There have been other valuable studies on the ocean's interior that have employed multisource observations [19,20,25].…”

Instance Segmentation for Large, Multi-Channel Remote Sensing Imagery Using Mask-RCNN and a Mosaicking Approach

“…This approach achieves state-of-the-art results in different applications in remote sensing digital image processing [5]: pan-sharpening [6][7][8][9]; image registration [10][11][12][13], change detection [14][15][16][17], object detection [18][19][20][21], semantic segmentation [22][23][24][25], and time series analysis [26][27][28][29]. The classification algorithms applied in remote sensing imagery uses spatial, spectral, and temporal information to extract characteristics from the targets, where a wide variety of targets show significant results: clouds [30][31][32][33], dust-related air pollutant [34][35][36][37] land-cover/land-use [38][39][40][41], urban features [42][43][44][45], and ocean [46][47][48][49], among others.…”