Spatial downscaling of precipitation, in which finegrained regional precipitation patterns are recovered from coarse-resolution images, plays a crucial role in various weather and meteorological analyses. However, the intricate noise information presented in the observation data intertwines with the fine-scale characteristics, which poses challenges for subsequent feature extraction. Regional precipitation suffers from complex spatial patterns. Moreover, the real observatory data contains information inconsistent with the established physical principle, due either to inaccurate or incomplete physical models or limited data quality, thus making the implementation of physicallyinformed deep learning more difficult. For example, strong physical constraints may lead to over-regularization, in which the model becomes too rigid and fails to capture certain complexities in the data. In this work, we propose RainScaler, a physicsinspired deep neural network, to tackle these issues. First, to remove the noise and preserve the vital precipitation patterns effectively, the proposed RainScaler exploits an Inconsistencyaware Denoising Net to explicitly model the spatial variability of noise in the input. In addition, a graph module is designed to learn the geographical-dependent fine-grained patterns in high dimensional feature space at a moderate computation cost. Finally, multi-scale physical constraints are skillfully embedded to incorporate additional insights into the data-driven framework. We test our approach on a public dataset consisting of over 60,000 real low-resolution and high-resolution precipitation map pairs collected by different sensors. Our method produces realisticlooking precipitation maps with better discernment capability and corrects the structural error of precipitation distribution, especially for extreme events. Moreover, we evaluate the potential risks of incorporating physical constraints in real-world data applications. Our method unveils opportunities for multi-source data fusion and provides possible solutions to improve the physical feasibility of data-driven models. The codes are available in https://github.com/zhu-xlab/RainScaler.git.

Subseasonal forecasting, which is pivotal for agriculture, water resource management, and early warning of disasters, faces challenges due to the chaotic nature of the atmosphere. Recent advances in machine learning (ML) have revolutionized weather forecasting by achieving competitive predictive skills to numerical models. However, training such foundation models requires thousands of GPU days, which causes substantial carbon emissions and limits their broader applicability. Moreover, ML models tend to fool the pixel-wise error scores by producing smoothed results which lack physical consistency and meteorological meaning. To deal with the aforementioned problems, we propose a teleconnection-informed transformer. Our architecture leverages the pretrained Pangu model to achieve good initial weights and integrates a teleconnection-informed temporal module to improve predictability in an extended temporal range. Remarkably, by adjusting 1.1% of the Pangu model’s parameters, our method enhances predictability on four surface and five upper-level atmospheric variables at a two-week lead time. Furthermore, the teleconnection-filtered features improve the spatial granularity of outputs significantly, indicating their potential physical consistency. Our research underscores the importance of atmospheric and oceanic teleconnections in driving future weather conditions. Besides, it presents a resource-efficient pathway for researchers to leverage existing foundation models on versatile downstream tasks.

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.

Distribution shift may pose significant challenges in Earth observation, especially when dealing with significantly differ-ent sensors like multispectral optical and Synthetic Aperture Radar (SAR). Deep learning models trained for optical image classification generally do not generalize well for SAR images. This is due to very marked differences between them. Though there is a considerable amount of works on domain adaptation, only few deal with such strong differences. Towards this, we propose a co-teaching based domain adaptation method using dual classifier head, a Multi-layer Perceptron (MLP) classi-fier and a Graph Neural Network (GNN) classifier. The two classifier heads teach each other in an iterative manner, thus gradually adapting both of them for target classification. We experimentally demonstrate the efficacy of the proposed approach on Sentinel 2 (optical) as source and Sentinel 1 (SAR) images as target - both product of Copernicus program of European Space Agency.

Remote sensing deals with huge variations in geography, acquisition season, and a plethora of sensors. Considering the difficulty of collecting labeled data uniformly representing all scenarios, data-hungry deep learning models are often trained with labeled data in a source domain that is limited in the above-mentioned aspects. Domain adaptation (DA) methods can adapt such model for applying on target domains with different distributions from the source domain. However, most remote sensing DA methods are designed for single-target, thus requiring a separate target classifier to be trained for each target domain. To mitigate this, we propose multitarget DA in which a single classifier is learned for multiple unlabeled target domains. To build a multitarget classifier, it may be beneficial to effectively aggregate features from the labeled source and different unlabeled target domains. Toward this, we exploit coteaching based on the graph neural network that is capable of leveraging unlabeled data. We use a sequential adaptation strategy that first adapts on the easier target domains assuming that the network finds it easier to adapt to the closest target domain. We validate the proposed method on two different datasets, representing geographical and seasonal variation. Code is available athttps://gitlab.lrz.de/ai4eo/da-multitarget-gnn/.