海洋要素智能预报

Attention-Enhanced Deep Learning Model for Reconstruction and Downscaling of Thermocline Depth in the Tropical Indian Ocean featured image
Thermocline Depth

Attention-Enhanced Deep Learning Model for Reconstruction and Downscaling of Thermocline Depth in the Tropical Indian Ocean

Accurate estimation of high-resolution thermocline depth is important for investigating ocean processes and climate variability on multiple scales. Due to the sparse coverage and …

Zhongkun Feng
•
阅读更多
Sea Surface Temperature and Marine Heat Wave Predictions in the South China Sea: A 3D U-Net Deep Learning Model Integrating Multi-Source Data featured image
Sea Surface Temperature

Sea Surface Temperature and Marine Heat Wave Predictions in the South China Sea: A 3D U-Net Deep Learning Model Integrating Multi-Source Data

Accurate sea surface temperature (SST) prediction is vital for disaster prevention, ocean circulation, and climate change. Traditional SST prediction methods, predominantly reliant …

Bowen Xie
•
阅读更多
Oil Spill Drift Prediction Enhanced by Correcting Numerically Forecasted Sea Surface Dynamic Fields With Adversarial Temporal Convolutional Networks featured image
Adversarial Temporal Convolutional Networks(ATCNs)

Oil Spill Drift Prediction Enhanced by Correcting Numerically Forecasted Sea Surface Dynamic Fields With Adversarial Temporal Convolutional Networks

Timely and accurate representation of sea surface dynamic fields is crucial for oil spill drift prediction. Numerically forecasted sea surface dynamic fields are available in a …

Peng Ren
•
阅读更多
Attention-Enhanced Deep Learning Approach for Marine Heatwave Forecasting featured image
Sea Surface Temperature Forecasting

Attention-Enhanced Deep Learning Approach for Marine Heatwave Forecasting

Marine heatwave(MHW) events refer to periods of significantly elevated sea surface temperatures(SST), persisting from days to months, with significant impacts on marine ecosystems, …

Yiyun Liu
•
阅读更多
Estimating Subsurface Thermohaline Structure in the Tropical Western Pacific Using DO-ResNet Model featured image
Oceanography

Estimating Subsurface Thermohaline Structure in the Tropical Western Pacific Using DO-ResNet Model

Estimating the ocean’s subsurface thermohaline information from satellite measurements is essential for understanding ocean dynamics and the El Niño phenomenon. This paper proposes …

avatar
周献梅
•
阅读更多
Role of Strong Sea Surface Temperature Diurnal Variation in Triggering the Summer Monsoon Onset Over the Bay of Bengal in a Climate Model featured image
Air-Sea Interaction

Role of Strong Sea Surface Temperature Diurnal Variation in Triggering the Summer Monsoon Onset Over the Bay of Bengal in a Climate Model

The earliest Asian summer monsoon onset (SMO) occurs in the Bay of Bengal (BoB), heralding the coming of the rainy season. In late April or early May, the strong sea surface …

Yajuan Song
•
阅读更多
GWSM4C: A Global Wave Surrogate Model for Climate Simulation Based on a Convolutional Architecture featured image
Climate Simulation

GWSM4C: A Global Wave Surrogate Model for Climate Simulation Based on a Convolutional Architecture

Ocean waves are a critical component of the Earth system, yet directly coupling wave models in climate simulations is computationally expensive. We introduce GWSM4C, a Global Wave …

Quan Jin
•
阅读更多
基于自注意力机制的深度学习的海洋三维温度场预测 featured image
Sa-Convlstm

基于自注意力机制的深度学习的海洋三维温度场预测

目前主要从时空角度出发对海洋三维温度场进行预测，却忽略了相邻位置的海温相关关系。为弥补这一不足，构建一种融合了自注意力记忆模块与卷积式长短时记忆神经网络（ConvLSTM）模型的SA-ConvLSTM三维温度场预测模型，不仅可以从历史三维温度场中提取海温时空特征，还能获取并记忆相邻点位置信息，从而实现对三维温度场时空变化的把握。实验结果表明：相较于 …

Weihao Yue
•
阅读更多
The Development of a Weather-Type Statistical Downscaling Model for Wave Climate Based on Wave Clustering featured image
Statistical Downscaling

The Development of a Weather-Type Statistical Downscaling Model for Wave Climate Based on Wave Clustering

Reliable long-term wave data are significant for understanding changes and variability of ocean waves, which has important implications for coastal engineering, land erosion, and …

Guangfeng Zhao
•
阅读更多
基于深度学习的南海海表面温度的智能化预测研究 featured image
3D U-Net模型

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, …

Bowen Xie
•
阅读更多