The evaporation duct is a special atmospheric stratification that significantly influences the propagation path of electromagnetic waves at sea, and hence, it is crucial for the stability of the radio communication systems. Affected by physical parameters that are not universal, traditional evaporation duct theoretical models often have limited accuracy and poor generalization ability, e.g., the remote sensing method is limited by the inversion algorithm. The accuracy, generalization ability and scientific interpretability of the existing pure data-driven evaporation duct height prediction models still need to be improved. To address these issues, in this paper, we use the voyage observation data and propose the physically constrained LightGBM evaporation duct height prediction model (LGB-PHY). The proposed model integrates the Babin–Young–Carton (BYC) physical model into a custom loss function. Compared with the eXtreme Gradient Boosting (XGB) model, the LGB-PHY based on a 5-day voyage data set of the South China Sea provides significant improvement where the RMSE index is reduced by 68%, while the SCC index is improved by 6.5%. We further carried out a cross-comparison experiment of regional generalization and show that in the sea area with high latitude and strong adaptability of the BYC model, the LGB-PHY model has a stronger regional generalization performance than that of the XGB model.

<p><em>Sea surface salinity (SSS) is an important indicator of hydrological cycle, oceanic processes and climate variability, and has been obtained from various methods including remote sensing, in-situ observations and numerical modelings. Due to the differences of instruments used, error correction algorithm and gridding strategy, each dataset has unique strengths and weaknesses. In this study, we conducted a multi-scale comparison of SSS among eight datasets, including satellite-based, in-situ-based and ocean reanalysis products from 2012 to 2020. Compared with WOA18 climatology, all products show good consistency in describing the dominant mode of global SSS distribution. Among eight datasets, the ISAS20 product is of the best quality, and observation-based products are generally more accurate than reanalysis products. Analysis on zonal average shows that positive bias appears in subtropic regions while negative bias distributes in subpolar areas. It was found that reanalysis products have significantly large negative biases at the polar region compared with satellite products and in-situ observations. On both the seasonal and interannual scales, high correlation coefficients (0.65-0.95) are found in the global mean SSSs between individual satellite products, in-situ analysis and ocean reanalysis products, with the differences relatively smaller among the same types of datasets. This analysis provides information on the consistency and discrepancy of different SSS products to guide future use, such as improvements to ocean data assimilation and the quality of satellite-based data.</em></p>

No abstract

No abstract

Sea surface temperature (SST) prediction has attracted increasing attention, due to its crucial role in understanding the Earth’s climate and ocean system. Existing SST prediction methods are typically based on either physics-based numerical methods or data-driven methods. Physics-based numerical methods rely on marine physics equations and have stable and explicable outputs, while data-driven methods are flexible in adapting to data and are capable of detecting unexpected patterns. We believe that these two types of method are complementary to each other, and their combination can potentially achieve better performances. In this paper, a space-time partial differential equation (PDE) is employed to form a novel physics-based deep learning framework, named the space-time PDE-guided neural network (STPDE-Net), to predict daily SST. Comprehensive experiments for SST prediction were conducted, and the results proved that our method could outperform the traditional finite-difference forecast method and several state-of-the-art deep learning and physics-guided deep learning methods.