With the advancement of meteorological instruments, abundant data has become available. However, due to instruments’ intrinsic limitations such as environmental sensitivity and orbital constraints, raw data often suffer from temporal or spatial gaps, making it urgent to leverage data synthesis techniques to fill in missing information. Current approaches are typically focus on single-variable, single-region tasks and primarily rely on deterministic modeling. This limits unified synthesis across variables and regions, overlooks cross-variable complementarity and often leads to over-smoothed results. To address above challenges, we introduce SynWeather, the first dataset designed for Unified Multi-region and Multi-variable Weather Observation Data Synthesis. SynWeather covers four representative regions: the Continental United States, Europe, East Asia, and Tropical Cyclone regions, as well as provides high-resolution observations of key weather variables, including Composite Radar Reflectivity, Hourly Precipitation, Visible Light, and Microwave Brightness Temperature. In addition, we introduce SynWeatherDiff, a general and probabilistic weather synthesis model built upon the Diffusion Transformer framework to address the over-smoothed problem. Experiments on the SynWeather dataset demonstrate the effectiveness of our network compared with both task-specific and general models. Moreover, SynWeatherDiff is able to generate results that are both fine-grained and accurate in high-value regions. Through the dataset and baseline model, we aim to advance meteorological downstream tasks and promote the development of general models for weather variable synthesis.

Underwater bioinspired robots’ pursuit of high speed locomotion is fundamentally limited by a well-recognized physical trade-off. Increasing the flapping frequency to achieve higher speeds induces a quadratic increase in hydrodynamic resistance, which severely attenuates the oscillation amplitude of the fin and consequently limits the maximum thrust that can be generated. To address this core limitation, this paper presents the design, modeling, and experimental validation of a magnetically actuated rigid-flexible coupling robotic manta ray (MARRM). The robot’s design strategy is to address both aspects of this tradeoff simultaneously: coil-magnet (CM) pairs enable high-frequency actuation, while a biomimetic pectoral fin structure, coupling a rigid leading edge with a flexible membrane, is designed to passively maintain large undulatory amplitudes. We develop a comprehensive dynamic model to analyze and optimize this system. The model integrates an analytical magnetic torque calculation, an underactuated joint dynamics formulation, and a boundary-constrained mechanical wave function that captures the compound deformation of the fin for hydrodynamic force prediction. Simulations and comparative experiments validate the model and the design’s effectiveness. Fabricated based on this design, an untethered prototype achieves a linear swimming speed of 322.4 mm/s (3.27 body lengths per second), a turning speed of 290 °/s, and a minimal turning radius of 23.9 mm. This work demonstrates an integrated approach to mitigating the frequency-amplitude trade-off in oscillatory propulsion and provides a modeling framework applicable to the design of rigid-flexible underwater robots.

Precipitation nowcasting based on radar echoes plays a crucial role in monitoring extreme weather and supporting disaster prevention. Although deep learning approaches have achieved significant progress, they still face notable limitations. For example, deterministic models tend to produce over-smoothed predictions, which struggle to capture extreme events and fine-scale precipitation patterns. Probabilistic generative models, due to their inherent randomness, often show fluctuating performance across different metrics and rarely achieve consistently optimal results. Furthermore, precipitation nowcasting is typically evaluated using multiple metrics, some of which are inherently conflicting. For instance, there is often a trade-off between the Critical Success Index (CSI) and the False Alarm Ratio (FAR), making it challenging for existing models to deliver forecasts that perform well on both metrics simultaneously. To address these challenges, we introduce preference optimization into precipitation nowcasting for the first time, motivated by the success of reinforcement learning from human feedback in large language models. Specifically, we propose SynCast, which lever-ages the two-stage post-training framework of Diffusion Sequential Preference Optimization (Diffusion-SPO) to progressively align conflicting metrics. In the first stage, the framework focuses on reducing FAR to deliver clean and high-precision predictions. Building on this foundation, the second stage further optimizes CSI under strict FAR constraints, thereby achieving synergistic improvements across these conflicting metrics. Experiments on three radar precipitation datasets demonstrate that SynCast reduces FAR while improving CSI, and achieves performance comparable to state-of-the-art methods. Furthermore, we verify that the post-training framework of Diffusion-SPO is compatible with multiple diffusion models for precipitation nowcasting, demonstrating its generalizability. The code for SynCast is available at https://github.com/Dtdtxuky/SynCast.