Weather forecasting supports critical socioeconomic activities and complements environmental protection, yet operational Numerical Weather Prediction (NWP) systems remain computationally intensive, thus being inefficient for certain applications. Meanwhile, recent advances in deep data-driven models have demonstrated promising results in nowcasting tasks. This paper presents SmaAT-QMix-UNet, an enhanced variant of SmaAT-UNet that introduces two key innovations: a vector quantization (VQ) bottleneck at the encoder-decoder bridge, and mixed kernel depth-wise convolutions (MixConv) replacing selected encoder and decoder blocks. These enhancements both reduce the model's size and improve its nowcasting performance. We train and evaluate SmaAT-QMix-UNet on a Dutch radar precipitation dataset (2016-2019), predicting precipitation 30 minutes ahead. Three configurations are benchmarked: using only VQ, only MixConv, and the full SmaAT-QMix-UNet. Grad-CAM saliency maps highlight the regions influencing each nowcast, while a UMAP embedding of the codewords illustrates how the VQ layer clusters encoder outputs. The source code for SmaAT-QMix-UNet is publicly available on GitHub: https://github.com/nstavr04/MasterThesisSnellius.

翻译：天气预测支撑着关键的社会经济活动，并为环境保护提供补充，然而运行中的数值天气预报（NWP）系统计算密集，难以高效应用于特定场景。与此同时，近年来深度数据驱动模型在临近预报任务中展现出令人瞩目的成果。本文提出SmaAT-QMix-UNet——SmaAT-UNet的增强变体，其引入两项核心创新：在编码器-解码器桥接处设置向量量化（VQ）瓶颈，以及采用混合核深度可分离卷积（MixConv）替换部分编码器与解码器模块。这些改进既缩减了模型规模，又提升了临近预报性能。我们基于荷兰雷达降水数据集（2016-2019年）训练并评估SmaAT-QMix-UNet，实现30分钟降水的提前预测。实验对三种配置进行基准测试：仅含VQ、仅含MixConv以及完整SmaAT-QMix-UNet。通过Grad-CAM显著性图揭示影响各临近预报的关键区域，而码本的UMAP嵌入则展示了VQ层如何聚类编码器输出。SmaAT-QMix-UNet的源代码已公开于GitHub：https://github.com/nstavr04/MasterThesisSnellius。