Many efforts have been carried out for the standardization of multiparametric Magnetic Resonance (mp-MR) images evaluation to detect Prostate Cancer (PCa), and specifically to differentiate levels of aggressiveness, a crucial aspect for clinical decision-making. Prostate Imaging—Reporting and Data System (PI-RADS) has contributed noteworthily to this aim. Nevertheless, as pointed out by the European Association of Urology (EAU 2020), the PI-RADS still has limitations mainly due to the moderate inter-reader reproducibility of mp-MRI. In recent years, many aspects in the diagnosis of cancer have taken advantage of the use of Artificial Intelligence (AI) such as detection, segmentation of organs and/or lesions, and characterization. Here a focus on AI as a potentially important tool for the aim of standardization and reproducibility in the characterization of PCa by mp-MRI is reported. AI includes methods such as Machine Learning and Deep learning techniques that have shown to be successful in classifying mp-MR images, with similar performances obtained by radiologists. Nevertheless, they perform differently depending on the acquisition system and protocol used. Besides, these methods need a large number of samples that cover most of the variability of the lesion aspect and zone to avoid overfitting. The use of publicly available datasets could improve AI performance to achieve a higher level of generalizability, exploiting large numbers of cases and a big range of variability in the images. Here we explore the promise and the advantages, as well as emphasizing the pitfall and the warnings, outlined in some recent studies that attempted to classify clinically significant PCa and indolent lesions using AI methods. Specifically, we focus on the overfitting issue due to the scarcity of data and the lack of standardization and reproducibility in every step of the mp-MR image acquisition and the classifier implementation. In the end, we point out that a solution can be found in the use of publicly available datasets, whose usage has already been promoted by some important initiatives. Our future perspective is that AI models may become reliable tools for clinicians in PCa diagnosis, reducing inter-observer variability and evaluation time.

A series of typhoons and tropical storms have produced extreme precipitation events in Vietnam during the first part of the 2020 monsoon season: events of this magnitude pose significant challenges to remote sensing Quantitative Precipitation Estimation (QPE) techniques. The weather-monitoring needs of modern human activities require that these challenges be overcome. In order to address this issue, in this work, seven precipitation products were validated with high spatial and temporal detail against over 1200 rain gauges in Vietnam during six case studies tailored around the most intense events of 2020. The data sources included the Vietnamese weather radar network, IMERG Early run and Final run, the South Korean GEO-KOMPSAT-2A and Chinese FengYun-4A geostationary satellites, DPR on board the GPM-Core Observatory, and European ERA5-Land reanalysis. All products were resampled to a standardized 0.02° grid and compared at hourly scale with ground stations measurements. The results indicated that the radars product was the most capable of reproducing the information collected by the rain gauges during the selected extreme events, with a correlation coefficient of 0.70 and a coefficient of variation of 1.38. However, it exhibited some underestimation, approximately 30%, in both occurrence and intensity. Conversely, geostationary products tended to overestimate moderate rain rates (FY-4A) and areas with low precipitation (GK-2A). More complex products such as ERA5-Land and IMERG failed to capture the highest intensities typical of extreme events, while GPM-DPR showed promising results in detecting the highest rain rates, but its capability to observe isolated events was limited by its intermittent coverage.

In 2050, in Europe, damages due to climate change and flooding are expected to reach € 45 billion annually. Severe storms produce heavy rain, often causing landslides, and orography is crucial in triggering such events, especially in the foothills of the Alps. Due to the difficulties in conducting ground-based remote sensing observations over complex terrains, satellite observations represent a valuable alternative for monitoring high-resolution natural hazards over the Alpine region.The most recent approaches to detecting severe storms rely on integrating multiple datasets and machine learning to improve weather prediction and develop accurate nowcasting. Most of the time, the temporal dimension is used to make short-term predictions; this is done, for instance, by applying atmospheric motion vectors to radar images or by exploiting machine learning approaches. However, in the cloud's spatiotemporal evolution patterns, there is still some information on cloud systems that remains largely unexplored.In the past, deep learning self-supervised techniques have shown exciting developments in identifying spatial cloud patterns from satellite images and characterizing the conditions under which such organization occurs. In this contribution, we utilize recent deep-learning self-supervised algorithms developed to identify motions in space-time to study the evolution of cloud patterns. We aim to characterize and distinguish cloud systems based on their spatiotemporal evolution, exploiting the features that these algorithms can extract. We will characterize the rates of change in the environment and cloud parameters of the patterns identified by the deep learning architecture. We are currently testing the algorithm on Meteosat Second Generation (MSG)/OPERA radar data available on European Weather Cloud (EWC). However, we plan to exploit Meteosat Third Generation (MTG) and Deutsche Wetterndiest (DWD) radar data on a smaller domain to test the algorithm's performance of the new highly resolved MTG satellite data.

Understanding the spatial organization and transitions of convective cloud systems over complex terrain remains a major challenge for both observation-based analysis and numerical weather prediction (NWP). This limitation affects our ability to accurately represent and predict extreme precipitation and hail events, which are expected to intensify over the Alpine region under climate change.In this work, we present a data-driven framework based on self-supervised learning (SSL) to characterize convective cloud structures and their transitions using long-term geostationary satellite data records. By learning representations directly from infrared imagery without manual labeling, the model organizes cloud scenes based on their spatial and morphological similarities, providing a physically interpretable feature space of mesoscale cloud features. This learned representation is exploited in two complementary ways. First, it enables the analysis of convective cloud structures and their transitions associated with severe precipitation events by identifying dominant pathways linked to intense rainfall and hail over the Alpine region. The most severe precipitation is predominantly observed either in association with long-lasting deep convective systems or during transitions from early-stage convection to a more mature regime, highlighting two key modes linked to extreme precipitation.Second, the framework provides a novel tool for evaluating convection-permitting NWP simulations. By projecting synthetic satellite channels into the same feature space, it enables a direct comparison between modeled and observed cloud structures, both in terms of continuous embeddings and discrete cloud classes. Preliminary results indicate that ICON tends to overestimate the spatial extent of convective cells during their early development stages, suggesting biases in the representation of convective initiation and growth. Overall, this approach demonstrates the potential of self-supervised learning to bridge satellite observations and model simulations, providing a flexible framework for studying convective processes and assessing their representation in high-resolution weather models over complex terrain.

Extreme precipitation and hail events over complex terrain are strongly dependent on the multiscale evolution of convective systems, yet their development remains challenging to observe and model. In this study, we apply a self-supervised learning (SSL) framework to Meteosat infrared 10.8 μm imagery over the Alpine region to derive physically meaningful representations of convective cloud organization across the full daily cycle. The learned representation organizes convective cloud scenes into three primary regimes: early convection (EC), deep convection (DC), and overcast anvil systems (OA), each exhibiting distinct cloud-top properties, spatial structures, and day–night distributions consistent with established convective development stages. Within the developed SSL framework, reported extreme precipitation and hail events are preferentially associated with these regimes, occupying the upper tail of cloud-top height, optical thickness, and cloud coverage distributions within the latent space. This indicates that extremes correspond to rare, intense realizations of continuous convective variability. Two dominant pathways of cloud structure evolution are identified: a rapid EC→DC transition and a persistent DC mode. The former is characterized by fast cloud growth and intensification, while the latter corresponds to mature convective systems with sustained cloud properties. Overall, the results demonstrate that infrared-based SSL representations capture physically consistent convective stages and their transitions, providing a novel observational framework for characterizing extreme convective events and supporting the evaluation of convection-resolving numerical weather prediction models.

Severe hailstorms are becoming more frequent in Central Europe, showing increasing interannual variability. The Pre-Alpine and Alpine region is significantly affected due to its complex terrain, which initiates convection and can intensify many hail-favoring processes. In particular, large hail events are often very local phenomena and are becoming increasingly intense. Ground-based observations from weather radars are the most reliable for detecting hail; however, they are challenging in the Alpine region due to interference at mountain ranges.Passive Microwave satellite observations offer a valuable alternative for detecting hail: a hail probability can be directly derived from Passive Microwave channels with a high spatial coverage. However, this data is only available at certain times during satellite overpasses, thus capturing only snapshots of a few of these events. Visible, near-infrared, and infrared data from MSG give the highest spatial and temporal coverage. Though not directly sensitive to hail, its high spatiotemporal resolution can identify early stages of severe storm development leading to large hail formation by peculiar characteristics in their spatiotemporal evolution.Whereas various ML approaches already classify spatial cloud patterns from satellite measurements, the temporal component of cloud development remains less explored. This work aims at classifying the evolution of typical cloud patterns leading to severe storms over the Alpine region. In particular, learning about formation of hail storms and the conditions in which they develop.We initially adopted a supervised deep-learning framework for classifying spatiotemporal cloud evolution patterns as hail and non-hail, obtaining better performance than a simple logistic regression. We trained the network using MSG timeseries displaying cloud evolution patterns and labeled the presence of hail using a hail probability product based on passive microwave radiometry. Then, we exploited the same architecture in a self-supervised approach, using the labeled dataset as fine-tuning to capture hail development characteristics better. We characterize such classes of cloud developments in a spatiotemporal embedding, exploiting its characteristics and investigate the physical properties of the classes with ancillary datasets.