[论文解读] Climate Downscaling: A Deep-Learning Based Super-resolution Model of Precipitation Data with Attention Block and Skip Connections

Chia-Hao Chiang, Zheng-Han Huang+7 more|arXiv (Cornell University)|Mar 26, 2024

Cryospheric studies and observations被引用 6

一句话总结

该论文提出了一种带残差注意块、跳跃连接和辅助地形数据的深度卷积神经网络架构，用于在台湾将异质降水数据（ERA5降尺度至TCCIP）下采样，同时在多项指标上优于替代方法。

ABSTRACT

Human activities accelerate consumption of fossil fuels and produce greenhouse gases, resulting in urgent issues today: global warming and the climate change. These indirectly cause severe natural disasters, plenty of lives suffering and huge losses of agricultural properties. To mitigate impacts on our lands, scientists are developing renewable, reusable, and clean energies and climatologists are trying to predict the extremes. Meanwhile, governments are publicizing resource-saving policies for a more eco-friendly society and arousing environment awareness. One of the most influencing factors is the precipitation, bringing condensed water vapor onto lands. Water resources are the most significant but basic needs in society, not only supporting our livings, but also economics. In Taiwan, although the average annual precipitation is up to 2,500 millimeter (mm), the water allocation for each person is lower than the global average due to drastically geographical elevation changes and uneven distribution through the year. Thus, it is crucial to track and predict the rainfall to make the most use of it and to prevent the floods. However, climate models have limited resolution and require intensive computational power for local-scale use. Therefore, we proposed a deep convolutional neural network with skip connections, attention blocks, and auxiliary data concatenation, in order to downscale the low-resolution precipitation data into high-resolution one. Eventually, we compare with other climate downscaling methods and show better performance in metrics of Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Pearson Correlation, structural similarity index (SSIM), and forecast indicators.

研究动机与目标

• 在气候强烈强制和数据异质性显著的区域，动机是需要高分辨率的降水下采样。
• 开发一个深度学习架构，能够纠正偏差并从低分辨率输入生成高分辨率降水。
• 结合辅助地形数据以提高降尺度精度。
• 将所提出的方法与统计和机器学习基线进行比较，以证明性能提升。

提出的方法

• 采用级联卷积偏差校正主干，将低分辨率输入转换为高分辨率特征图。
• 引入跳跃连接以促进残差学习并融合多层特征图。
• 集成残差注意块（基于CBAM），在学习过程中强调通道和空间特征。
• 应用使用像素重排的一步上采样层，随后进行更正卷积以减少伪影。
• 将辅助高程/地形数据与处理后的特征融合集成，以提升降水降尺度精度。
• 在监督学习框架下端到端训练，使用ERA5作为输入、以TCCIP观测值作为真值，损失函数为MSE。

实验结果

研究问题

• RQ1 带有残差注意和跳跃连接的深度CNN是否能够有效地将ERA5的异质降水数据降尺度为高分辨率观测？
• RQ2 在像台湾这样的强气候强迫区域，加入地形辅助数据是否能提升降尺度性能？
• RQ3 在多种评估指标上，所提出的模型与统计降尺度及其他ML/DL气候降尺度方法相比如何？

主要发现

• 所提出的模型在多项指标上优于基线，包括MAE、RMSE、皮尔逊相关和SSIM。
• 该架构专为处理异质数据对和强区域强迫而设计，改进偏差纠正。
• 地形数据融合有助于提高降尺度降水输出的质量。
• 在本研究中，该模型相对于YNet、FSRCNN-ESM、DeepSD、QM、BCSD等方法展示了有利的定性和定量结果。
• 在台湾区域以ERA5输入、以TCCIP每日降水目标进行训练，显示出有效的降尺度，且输入到输出的缩放因子较小。