Accurately predicting short-term precipitation is critical for weather-sensitive applications such as disaster management, aviation, and urban planning. Traditional numerical weather prediction can be computationally intensive at high resolution and short lead times. In this work, we propose a lightweight UNet-based encoder-decoder augmented with axial-attention blocks that attend along image rows and columns to capture long-range spatial interactions, while temporal context is provided by conditioning on multiple past radar frames. Our hybrid architecture captures both local and long-range spatio-temporal dependencies from radar image sequences, enabling fixed lead-time precipitation nowcasting with modest compute. Experimental results on a preprocessed subset of the HKO-7 radar dataset demonstrate that our model outperforms ConvLSTM, pix2pix-style cGANs, and a plain UNet in pixel-fidelity metrics, reaching PSNR 47.67 and SSIM 0.9943. We report PSNR/SSIM here; extending evaluation to meteorology-oriented skill measures (e.g., CSI/FSS) is left to future work. The approach is simple, scalable, and effective for resource-constrained, real-time forecasting scenarios.

The increasing frequency of heavy rainfall events, which are a major cause of urban flooding, underscores the urgent need for accurate precipitation forecasting - particularly in urban areas where localized events often go undetected by ground-based sensors. In Germany, only 17.3% of hourly heavy rain events between 2001 and 2018 were recorded by rain gauges, highlighting the limitations of traditional monitoring systems. Radar data are another source that effectively tracks ongoing precipitation; however, forecasting the development of heavy rain using radar alone remains challenging due to the brief and unpredictable nature of such events. Our focus is on evaluating the effectiveness of fusing satellite and radar data for nowcasting. We develop a multimodal nowcasting model that combines both radar and satellite imagery for predicting precipitation at lead times of 5, 15, and 30 minutes. We demonstrate that this multimodal strategy significantly outperforms radar-only approaches. Experimental results show that integrating satellite data improves prediction accuracy, particularly for intense precipitation. The proposed model increases the Critical Success Index for heavy rain by 4% and for violent rain by 3% at a 5-minute lead time. Moreover, it maintains higher predictive skill at longer lead times, where radar-only performance declines. A qualitative analysis of the severe flooding event in the state of North Rhine-Westphalia, Germany in 2021 further illustrates the superior performance of the multimodal model. Unlike the radar-only model, which captures general precipitation patterns, the multimodal model yields more detailed and accurate forecasts for regions affected by heavy rain. This improved precision enables timely, reliable, life-saving warnings. Implementation available at https://github.com/RamaKassoumeh/Multimodal_heavy_rain

Precipitation nowcasting predicts future radar sequences based on current observations, which is a highly challenging task driven by the inherent complexity of the Earth system. Accurate nowcasting is of utmost importance for addressing various societal needs, including disaster management, agriculture, transportation, and energy optimization. As a complementary to existing non-autoregressive nowcasting approaches, we investigate the impact of prediction horizons on nowcasting models and propose SimCast, a novel training pipeline featuring a short-to-long term knowledge distillation technique coupled with a weighted MSE loss to prioritize heavy rainfall regions. Improved nowcasting predictions can be obtained without introducing additional overhead during inference. As SimCast generates deterministic predictions, we further integrate it into a diffusion-based framework named CasCast, leveraging the strengths from probabilistic models to overcome limitations such as blurriness and distribution shift in deterministic outputs. Extensive experimental results on three benchmark datasets validate the effectiveness of the proposed framework, achieving mean CSI scores of 0.452 on SEVIR, 0.474 on HKO-7, and 0.361 on MeteoNet, which outperforms existing approaches by a significant margin.

Transparent objects are prevalent in everyday environments, but their distinct physical properties pose significant challenges for camera-guided robotic arms. Current research is mainly dependent on camera-only approaches, which often falter in suboptimal conditions, such as low-light environments. In response to this challenge, we present FuseGrasp, the first radar-camera fusion system tailored to enhance the transparent objects manipulation. FuseGrasp exploits the weak penetrating property of millimeter-wave (mmWave) signals, which causes transparent materials to appear opaque, and combines it with the precise motion control of a robotic arm to acquire high-quality mmWave radar images of transparent objects. The system employs a carefully designed deep neural network to fuse radar and camera imagery, thereby improving depth completion and elevating the success rate of object grasping. Nevertheless, training FuseGrasp effectively is non-trivial, due to limited radar image datasets for transparent objects. We address this issue utilizing large RGB-D dataset, and propose an effective two-stage training approach: we first pre-train FuseGrasp on a large public RGB-D dataset of transparent objects, then fine-tune it on a self-built small RGB-D-Radar dataset. Furthermore, as a byproduct, FuseGrasp can determine the composition of transparent objects, such as glass or plastic, leveraging the material identification capability of mmWave radar. This identification result facilitates the robotic arm in modulating its grip force appropriately. Extensive testing reveals that FuseGrasp significantly improves the accuracy of depth reconstruction and material identification for transparent objects. Moreover, real-world robotic trials have confirmed that FuseGrasp markedly enhances the handling of transparent items. A video demonstration of FuseGrasp is available at https://youtu.be/MWDqv0sRSok.

The 3D reconstruction of faces gains wide attention in computer vision and is used in many fields of application, for example, animation, virtual reality, and even forensics. This work is motivated by monitoring patients in sleep laboratories. Due to their unique characteristics, sensors from the radar domain have advantages compared to optical sensors, namely penetration of electrically non-conductive materials and independence of light. These advantages of radar signals unlock new applications and require adaptation of 3D reconstruction frameworks. We propose a novel model-based method for 3D reconstruction from radar images. We generate a dataset of synthetic radar images with a physics-based but non-differentiable radar renderer. This dataset is used to train a CNN-based encoder to estimate the parameters of a 3D morphable face model. Whilst the encoder alone already leads to strong reconstructions of synthetic data, we extend our reconstruction in an Analysis-by-Synthesis fashion to a model-based autoencoder. This is enabled by learning the rendering process in the decoder, which acts as an object-specific differentiable radar renderer. Subsequently, the combination of both network parts is trained to minimize both, the loss of the parameters and the loss of the resulting reconstructed radar image. This leads to the additional benefit, that at test time the parameters can be further optimized by finetuning the autoencoder unsupervised on the image loss. We evaluated our framework on generated synthetic face images as well as on real radar images with 3D ground truth of four individuals.

Deep learning models have made remarkable strides in precipitation prediction, yet they continue to struggle with capturing the spatial details of the features of radar images, particularly over high precipitation intensity areas. This shortcoming is evident in the form of low forecast accuracy in the spatial positioning of radar echo images across varying precipitation intensity regions. To address this challenge, we introduce the multi-task latent diffusion model(MTLDM), a novel approach for precipitation prediction. The basic concept of the MTLDM is based on the understanding that the radar image representing precipitation is the result of multiple factors. Therefore, we adopt a divide-and-conquer approach, that is, we decompose the radar image using decomposition technology and then predict the decomposed sub-images separately. We conceptualize the precipitation image as a composition of various components corresponding to different precipitation intensities. The MTLDM decomposes the precipitation image into these distinct components and employs a dedicated task to predict each one. This method enables spatiotemporally consistent prediction of real-world precipitation areas up to 5-80 min in advance, outperforming existing state-of-the-art techniques across multiple evaluation metrics.

Place recognition plays an important role in achieving robust long-term autonomy. Real-world robots face a wide range of weather conditions (e.g. overcast, heavy rain, and snowing) and most sensors (i.e. camera, LiDAR) essentially functioning within or near-visible electromagnetic waves are sensitive to adverse weather conditions, making reliable localization difficult. In contrast, radar is gaining traction due to long electromagnetic waves, which are less affected by environmental changes and weather independence. In this work, we propose a radar-based lightweight and robust place recognition. We achieve rotational invariance and lightweight by selecting a one-dimensional ring-shaped description and robustness by mitigating the impact of false detection utilizing opposite noise characteristics between free space and feature. In addition, the initial heading can be estimated, which can assist in building a SLAM pipeline that combines odometry and registration, which takes into account onboard computing. The proposed method was tested for rigorous validation across various scenarios (i.e. single session, multi-session, and different weather conditions). In particular, we validate our descriptor achieving reliable place recognition performance through the results of extreme environments that lacked structural information such as an OORD dataset.

This paper presents a generative adversarial network (GAN) based approach for radar image enhancement. Although radar sensors remain robust for operations under adverse weather conditions, their application in autonomous vehicles (AVs) is commonly limited by the low-resolution data they produce. The primary goal of this study is to enhance the radar images to better depict the details and features of the environment, thereby facilitating more accurate object identification in AVs. The proposed method utilizes high-resolution, two-dimensional (2D) projected light detection and ranging (LiDAR) point clouds as ground truth images and low-resolution radar images as inputs to train the GAN. The ground truth images were obtained through two main steps. First, a LiDAR point cloud map was generated by accumulating raw LiDAR scans. Then, a customized LiDAR point cloud cropping and projection method was employed to obtain 2D projected LiDAR point clouds. The inference process of the proposed method relies solely on radar images to generate an enhanced version of them. The effectiveness of the proposed method is demonstrated through both qualitative and quantitative results. These results show that the proposed method can generate enhanced images with clearer object representation compared to the input radar images, even under adverse weather conditions.

The increasing generation of data in different areas of life, such as the environment, highlights the need to explore new techniques for processing and exploiting data for useful purposes. In this context, artificial intelligence techniques, especially through deep learning models, are key tools to be used on the large amount of data that can be obtained, for example, from weather radars. In many cases, the information collected by these radars is not open, or belongs to different institutions, thus needing to deal with the distributed nature of this data. In this work, the applicability of a personalized federated learning architecture, which has been called adapFL, on distributed weather radar images is addressed. To this end, given a single available radar covering 400 km in diameter, the captured images are divided in such a way that they are disjointly distributed into four different federated clients. The results obtained with adapFL are analyzed in each zone, as well as in a central area covering part of the surface of each of the previously distributed areas. The ultimate goal of this work is to study the generalization capability of this type of learning technique for its extrapolation to use cases in which a representative number of radars is available, whose data can not be centralized due to technical, legal or administrative concerns. The results of this preliminary study indicate that the performance obtained in each zone with the adapFL approach allows improving the results of the federated learning approach, the individual deep learning models and the classical Continuity Tracking Radar Echoes by Correlation approach.

Detecting flying animals (e.g., birds, bats, and insects) using weather radar helps gain insights into animal movement and migration patterns, aids in management efforts (such as biosecurity) and enhances our understanding of the ecosystem.The conventional approach to detecting animals in weather radar involves thresholding: defining and applying thresholds for the radar variables, based on expert opinion. More recently, Deep Learning approaches have been shown to provide improved performance in detection. However, obtaining sufficient labelled weather radar data for flying animals to build learning-based models is time-consuming and labor-intensive. To address the challenge of data labelling, we propose a self-supervised learning method for detecting animal movement. In our proposed method, we pre-train our model on a large dataset with noisy labels produced by a threshold approach. The key advantage is that the pre-trained dataset size is limited only by the number of radar images available. We then fine-tune the model on a small human-labelled dataset. Our experiments on Australian weather radar data for waterbird segmentation show that the proposed method outperforms the current state-of-the art approach by 43.53% in the dice co-efficient statistic.