Nowcasts (i.e., short-term forecasts from 5 minutes to 6 hours) of heavy rainfall are important for applications such as flash flood predictions. However, current precipitation nowcasting methods based on the extrapolation of radar echoes have a limited ability to predict the growth and decay of rainfall. While deep learning applications have recently shown improvement compared to extrapolation-based methods, they still struggle to correctly nowcast small-scale high-intensity rainfall. To address this issue, we present a novel model called the Lagrangian Convolutional Neural Network (L-CNN) that separates the growth and decay of rainfall from motion using the advection equation. In the model, differences between consecutive rain rate fields in Lagrangian coordinates are fed into a U-Net-based convolutional neural network (CNN), known as RainNet, that was trained with the Root-Mean-Squared-Error loss function. This results in a better representation of rainfall temporal evolution compared to the RainNet and the extrapolation-based LINDA model that were used as reference models. On Finnish weather radar data, L-CNN underestimates rainfall less than RainNet, demonstrated by greater POD (29% at 30 min at 1 mm h $^{-1}$ threshold) and smaller bias (98% at 15 min). The increased ETS values over LINDA for leadtimes under 15 min, with maximum increases of 7% (5 mm h $^{-1}$ threshold) and 10% (10 mm h $^{-1}$ ), show that the L-CNN represents the growth and decay of heavy rainfall more accurately than LINDA. This implies that nowcasting of heavy rainfall is improved when growth and decay are predicted using a deep learning model.

NASA’s Perseverance rover’s Mars Environmental Dynamics Analyzer is collecting data at Jezero crater, characterizing the physical processes in the lowest layer of the Martian atmosphere. Here we present measurements from the instrument’s first 250 sols of operation, revealing a spatially and temporally variable meteorology at Jezero. We find that temperature measurements at four heights capture the response of the atmospheric surface layer to multiple phenomena. We observe the transition from a stable night-time thermal inversion to a daytime, highly turbulent convective regime, with large vertical thermal gradients. Measurement of multiple daily optical depths suggests aerosol concentrations are higher in the morning than in the afternoon. Measured wind patterns are driven mainly by local topography, with a small contribution from regional winds. Daily and seasonal variability of relative humidity shows a complex hydrologic cycle. These observations suggest that changes in some local surface properties, such as surface albedo and thermal inertia, play an influential role. On a larger scale, surface pressure measurements show typical signatures of gravity waves and baroclinic eddies in a part of the seasonal cycle previously characterized as low wave activity. These observations, both combined and simultaneous, unveil the diversity of processes driving change on today’s Martian surface at Jezero crater.

The Solar Wind Anisotropies all-sky hydrogen Lyman-alpha camera on the Solar and Heliosphere Observatory observed the hydrogen coma of interstellar comet 3I/ATLAS, also called C/2025 N1 (ATLAS), beginning on 2025 November 6, 9 days after perihelion. Water production rates were calculated from each image of 3I/ATLAS using the methodology of J. T. T. Mäkinen and M. R. Combi, and fluorescence rates and g-factors were calculated using the daily solar Lyman-alpha fluxes from the LASP database ( https://lasp.colorado.edu/lisird/data ) corrected for solar rotation and for the comet’s heliocentric velocity. The method has been used for over 90 comet apparitions. A water production rate of 3.17 × 10 ²⁹ s ⁻¹ was found on November 6 when the comet was at a heliocentric distance of 1.40 au and at a sufficient solar elongation angle. It decreased over time after that, down to 1–2 × 10 ²⁸ s ⁻¹ around 40 days postperihelion (December 9).

The latest established generation of weather radars provides polarimetric measurements of a wide variety of meteorological and nonmeteorological targets. While the classification of different precipitation types based on polarimetric data has been studied extensively, nonmeteorological targets have garnered relatively less attention beyond an effort to detect them for removal from meteorological products. In this paper we present a supervised learning classification system developed in the Finnish Meteorological Institute (FMI) that uses Bayesian inference with empirical probability density distributions to assign individual range gate samples into 7 meteorological and 12 nonmeteorological classes, belonging to five top-level categories of hydrometeors, terrain, zoogenic, anthropogenic, and immaterial. We demonstrate how the accuracy of the class probability estimates provided by a basic naive Bayes classifier can be further improved by introducing synthetic channels created through limited neighborhood filtering, by properly managing partial moment nonresponse, and by considering spatial correlation of class membership of adjacent range gates. The choice of Bayesian classification provides well-substantiated quality estimates for all meteorological products, a feature that is being increasingly requested by users of weather radar products. The availability of comprehensive, fine-grained classification of nonmeteorological targets also enables a large array of emerging applications, utilizing nonprecipitation echo types and demonstrating the need to move from a single, universal quality metric of radar observations to one that depends on the application, the measured target type, and the specificity of the customers’ requirements. Significance Statement: In addition to meteorological echoes, weather radars observe a wide variety of nonmeteorological phenomena including birds, insects, and human-made objects like ships and aircraft. Conventionally, these data have been rejected as undesirable disturbance, but lately their value for applications like aeroecological monitoring of bird and insect migration has been understood. The utilization of these data, however, has been hampered by a lack of comprehensive classification of nonmeteorological echoes. In this paper we present a comprehensive, fine-grained, probabilistic classifier for all common types of nonmeteorological echoes which enables the implementation of a wide range of novel weather radar applications.

We present a method for fitting parametric probability density models using an integrated square error criterion on a continuum of weighted Lebesgue spaces formed by ultraspherical polynomials. This approach is inherently suitable for creating mixture model representations of complex distributions and allows fully autonomous cluster analysis of high-dimensional datasets. The method is also suitable for extremely large sets, allowing post facto model selection and analysis even in the absence of the original data. Furthermore, the fitting procedure only requires the parametric model to be pointwise evaluable, making it trivial to fit user-defined models through a generic algorithm.