基于深度学习的南海海表面温度的智能化预测研究
海表面温度(sea surface temperature, SST)是影响海洋和气候变化的重要因素之一,准确预测SST的变化对于海洋生态环境、气象和航行等至关重要。传统的SST预测方法通常依赖于数值模式,但是其计算成本较高。该文基于深度学习模型(3D U-Net),将SST、海表面高度异常(sea surface height anomalies, …
海表面温度(sea surface temperature, SST)是影响海洋和气候变化的重要因素之一,准确预测SST的变化对于海洋生态环境、气象和航行等至关重要。传统的SST预测方法通常依赖于数值模式,但是其计算成本较高。该文基于深度学习模型(3D U-Net),将SST、海表面高度异常(sea surface height anomalies, …
针对提升利用卫星观测海面信息重构三维温盐场精度的问题,本文提出了一种基于多尺度耦合正交分解的三维温盐场重构方法。该方法利用多尺度耦合正交分解对历史温盐剖面进行从大尺度到小尺度的迭代分解,以分层提取不同尺度三维温盐场的特征信息,然后分别建立海洋表面卫星观测与不同尺度的三维温盐场特征信息的重构模型,从而达到三维温盐场重构的目的。本文分别利用多尺度耦合正交分解法与 …
Sound event detection (SED) is a widely studied field that has achieved considerable success. The dynamic routing mechanism of capsule networks has been used for SED, but its …
A recent study by Liu et al.(2020) suggested that due to the saturation of equatorially trapped planetary waves with different dynamical types, temporal periods, meridional and …
This paper presents the description of the First Institute of Oceanography-Earth System Model version 2.1 (FIO-ESM v2.1) and evaluates its performance in simulating sea ice. …
Atlantification, the shift of Arctic waters to Atlantic-like conditions, is accelerating. We demonstrate that recent warming has shifted the Arctic into a state where …
For a class of stochastic nonlinear systems, this paper proposes a novel event-triggered adaptive control scheme by means of multi-dimensional Taylor network (MTN) approach for the …
Marine heatwaves (MHWs) and total heat exposures (THEs), extreme warming events occurring across the global oceans, seriously threaten marine ecosystems and coastal communities as …