Precipitation nowcasting (up to a few hours) remains a challenge due to the highly complex local interactions that need to be captured accurately. Convolutional Neural Networks rely on convolutional kernels convolving with grid data and the extracted features are trapped by limited receptive field, typically expressed in excessively smooth output compared to ground truth. Thus they lack the capacity to model complex spatial relationships among the grids. Geometric deep learning aims to generalize neural network models to non-Euclidean domains. Such models are more flexible in defining nodes and edges and can effectively capture dynamic spatial relationship among geographical grids. Motivated by this, we explore a geometric deep learning-based temporal Graph Convolutional Network (GCN) for precipitation nowcasting. The adjacency matrix that simulates the interactions among grid cells is learned automatically by minimizing the L1 loss between prediction and ground truth pixel value during the training procedure. Then, the spatial relationship is refined by GCN layers while the temporal information is extracted by 1D convolution with various kernel lengths. The neighboring information is fed as auxiliary input layers to improve the final result. We test the model on sequences of radar reflectivity maps over the Trento/Italy area. The results show that GCNs improves the effectiveness of modeling the local details of the cloud profile as well as the prediction accuracy by achieving decreased error measures.

翻译：降水临近预报（未来几小时内）仍是一项挑战，因其需精确捕捉高度复杂的局部相互作用。卷积神经网络依赖卷积核与网格数据的卷积操作，所提取的特征受限于有限感受野，通常表现为相对于真实观测值过于平滑的输出，因此缺乏对网格间复杂空间关系的建模能力。几何深度学习旨在将神经网络模型推广至非欧几里得域，此类模型在定义节点与边时更加灵活，能够有效捕捉地理网格间的动态空间关系。受此启发，我们探索了基于几何深度学习的时间图卷积网络（GCN）用于降水临近预报。通过训练过程中最小化预测值与地面真实像素值之间的L1损失，自动学习模拟网格单元间相互作用的邻接矩阵。随后，空间关系由GCN层精化，而时间信息则通过不同核长度的一维卷积提取。相邻信息作为辅助输入层输入，以改善最终结果。我们在意大利特伦托地区雷达反射率图序列上测试模型。结果表明，GCN在降低误差指标的同时，提升了云剖面局部细节建模的有效性及预测精度。