Climate models (CM) are used to evaluate the impact of climate change on the risk of floods and heavy precipitation events. However, these numerical simulators produce outputs with low spatial resolution that exhibit difficulties representing precipitation events accurately. This is mainly due to computational limitations on the spatial resolution used when simulating multi-scale weather dynamics in the atmosphere. To improve the prediction of high resolution precipitation we apply a Deep Learning (DL) approach using input data from a reanalysis product, that is comparable to a climate model’s output, but can be directly related to precipitation observations at a given time and location. Further, our input excludes local precipitation, but includes model fields (weather variables) that are more predictable and generalizable than local precipitation. To this end, we present TRU-NET (Temporal Recurrent U-Net), an encoder-decoder model featuring a novel 2D cross attention mechanism between contiguous convolutional-recurrent layers to effectively model multi-scale spatio-temporal weather processes. We also propose a non-stochastic variant of the conditional-continuous (CC) loss function to capture the zero-skewed patterns of rainfall. Experiments show that our models, trained with our CC loss, consistently attain lower RMSE and MAE scores than a DL model prevalent in precipitation downscaling and outperform a state-of-the-art dynamical weather model. Moreover, by evaluating the performance of our model under various data formulation strategies, for the training and test sets, we show that there is enough data for our deep learning approach to output robust, high-quality results across seasons and varying regions.

气候模型 (CM) 用于评估气候变化对洪水和强降水事件风险的影响。然而，这些数值模拟器产生的输出空间分辨率低，难以准确表示降水事件。这主要是由于模拟大气中多尺度天气动态时使用的空间分辨率的计算限制。为了改进高分辨率降水的预测，我们使用来自再分析产品的输入数据应用深度学习 (DL) 方法，该方法与气候模型的输出相当，但可以与给定时间和位置的降水观测直接相关。此外，我们的输入不包括当地降水，但包括比局部降水更可预测和可概括的模型场（天气变量）。为此，我们提出了 TRU-NET（时间循环 U-Net），这是一种编码器-解码器模型，在连续卷积循环层之间具有新颖的 2D 交叉注意机制，可有效模拟多尺度时空天气过程。我们还提出了条件连续 (CC) 损失函数的非随机变体，以捕获降雨的零偏斜模式。实验表明，我们的模型，使用我们的 CC 损失进行训练，始终比在降水降尺度中普遍使用的 DL 模型获得更低的 RMSE 和 MAE 分数，并且优于最先进的动态天气模型。此外，通过评估我们模型在各种数据制定策略下的性能，对于训练和测试集，