Effective molecular representation learning is of great importance to facilitate molecular property prediction. Recent advances for molecular representation learning have shown great promise in applying graph neural networks to model molecules. Moreover, a few recent studies design self-supervised learning methods for molecular representation to address insufficient labelled molecules; however, these self-supervised frameworks treat the molecules as topological graphs without fully utilizing the molecular geometry information. The molecular geometry, also known as the three-dimensional spatial structure of a molecule, is critical for determining molecular properties. To this end, we propose a novel geometry-enhanced molecular representation learning method (GEM). The proposed GEM has a specially designed geometry-based graph neural network architecture as well as several dedicated geometry-level self-supervised learning strategies to learn the molecular geometry knowledge. We compare GEM with various state-of-the-art baselines on different benchmarks and show that it can considerably outperform them all, demonstrating the superiority of the proposed method.

With the continuous development of space and sensor technologies during the last 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 mine 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 these deep-learning frameworks are. Researchers can also readily modify these existing frameworks for information mining of other kinds of remote-sensing imagery.

Mesoscale eddy properties in the northwestern subtropical Pacific Ocean are investigated by analyzing 22,567 cyclonic eddies (CEs) and 26,365 anticyclonic eddies (AEs) detected from 19 year altimetric sea level records. Eddy occurrence frequency and kinetic energy are prevailingly high in the Subtropical Countercurrent zonal band between 19°N and 26°N and further elevated near the Luzon‐Taiwan coast. A general superiority of AEs is observed at most latitudes except between 19°N and 22°N, where the CE number is larger. The modal radius and mean lifespan of the CEs (AEs) are 134 km and 11.2 weeks (121 km and 10.9 weeks), respectively. After generation, most eddies propagate westward with a mean speed of 7.2 cm s⁻¹ and deflect northward following the Kuroshio along the Luzon‐Taiwan coast. Three‐dimensional eddy structures are further explored with composite eddy images in five subregions constructed by surfacing Argo temperature/salinity data into altimeter‐detected eddy areas. Due to the existence of mode waters in the main thermocline, eddy‐induced temperature anomaly exhibits a double‐core vertical structure which is especially evident in CE images. Because of the vertical water mass distribution, salinity anomaly features a sandwich‐like pattern which is more evident in AE images. Also revealed is the significant structure difference in these five subregions. Eddies are greatly intensified as they approach the western boundary, inducing larger temperature and salinity anomalies and influencing deeper ocean. Along the Luzon‐Taiwan coast, AEs are preferentially strengthened by the northward background flow.

The global mean ocean circulation from surface to deep oceans has accelerated over the past two decades.