Search

We introduce TAASRAD19, a high-resolution radar reflectivity dataset collected by the Civil Protection weather radar of the Trentino South Tyrol Region, in the Italian Alps. The dataset includes 894,916 timesteps of precipitation from more than 9 years of data, offering a novel resource to develop and benchmark analog ensemble models and machine learning solutions for precipitation nowcasting. Data are expressed as 2D images, considering the maximum reflectivity on the vertical section at 5 min sampling rate, covering an area of 240 km of diameter at 500 m horizontal resolution. The TAASRAD19 distribution also includes a curated set of 1,732 sequences, for a total of 362,233 radar images, labeled with precipitation type tags assigned by expert meteorologists. We validate TAASRAD19 as a benchmark for nowcasting methods by introducing a TrajGRU deep learning model to forecast reflectivity, and a procedure based on the UMAP dimensionality reduction algorithm for interactive exploration. Software methods for data pre-processing, model training and inference, and a pre-trained model are publicly available on GitHub ( https://github.com/MPBA/TAASRAD19 ) for study replication and reproducibility.

The process of developing of a participatory environmental monitoring network in Italy, unfolded between 2013 and 2020, is analysed in order to explore the dynamics of knowledge co-production involving collaboration between scientists and non-experts, in the present case constituted by a community of weather amateurs and practitioners. Based on a qualitative approach and 15 in-depth interviews with different stakeholders involved in the early development of the pilot network, the analysis focuses on the dynamics of collaboration between the actors involved that led to the creation of the Italian participatory environmental monitoring platform. For the analysis, we adopt the theoretical model of 'translation' proposed by Michel Callon (1984), which focuses on the dynamics of the emergence of a network of collaboration between scientists and other heterogeneous actors. In particular, we focus on the notion of 'obligatory passage point' (OPP) along the translation process. Focusing on the process of translation and the dynamics that characterise the convergence towards a common OPP in the processes of network constitution and knowledge production highlights some crucial dynamics that support the unfolding of effective forms of participatory co-production, including: the understanding of how the roles and identities of different actors are recognised, transformed, productively aligned and consolidated; the performative power of participatory processes that are able to redefine and transform the pre-existing identities and roles of actors; and the outcome of the epistemic inclusion of practices and knowledge of less powerful actors within institutional, political and scientific frameworks. [ABSTRACT FROM AUTHOR]

Nowcasting methods based on deep learning typically rely solely on radar data. However, effectively leveraging multi‐source data with diverse spatio‐temporal resolutions remains a significant challenge in the field. To address this challenge, we propose and validate a novel deep learning model for nowcasting, termed Nowcastformer. This model utilizes radar data and upper‐air atmospheric variables, and has been pretrained on satellite data from non‐target regions. Quantitative statistical assessments demonstrate that both the integration of multi‐source data and the implementation of pre‐training strategies enhance the model's performance. Additionally, we conduct a comprehensive analysis of predictor importance, revealing a trend where atmospheric variables become increasingly important as the forecast horizon increases. To illustrate the model's interpretability, we employ the integrated gradients method, which highlights critical areas in representative cases and provides insights into the model's decision‐making process. Plain Language Summary: As a sophisticated monitoring tool, weather radar occupies a pivotal position in convective nowcasting. While numerous contemporary deep learning approaches predominantly concentrate on refining network architectures using radar reflectivity as the sole input, the impact of atmospheric physical information on nowcasting remains underexplored. To incorporate the contextual backdrop of atmospheric states in nowcasting, we devise a comprehensive deep learning framework that integrates atmospheric variables across multiple levels. To enhance generalization, we employ a transfer learning strategy to extract generalized spatialtemporal features. Rather than emphasizing a specific network design, we underscore the advantages of harnessing multi‐source data and the decision mechanism of the model. By fusing atmospheric variables and radar reflectivity, and adopting a pre‐training and fine‐tuning approach, we achieve more reliable and resilient nowcasting. Overall, our successful implementation of transfer learning within this multi‐modal model offers promising insights for advancing the field of nowcasting. Key Points: We present a nowcasting model that is scalable and flexible, enabling it to incorporate heterogeneous inputsWith multi‐source data and pre‐training, performance enhancement is achieved in terms of both general statistics and representative eventThe interpretability method reveals how the model generates predictions in a physically meaningful manner [ABSTRACT FROM AUTHOR]

As a critical predisaster warning tool, landslide susceptibility assessment is crucial in disaster prevention and mitigation efforts. However, earlier methods for assessing landslide susceptibility have often ignored the impact of similarities in geographical attributes, restricting their feasibility in regions with diverse characteristics. The geographical-optimal-similarity (GOS) model effectively captures similarity relations within geospatial data and can isolate region-specific landslide features, thus overcoming this challenge. Consequently, a landslide susceptibility assessment method was developed by integrating the information value (IV) model with the GOS model. Huangshan City in Anhui Province, China, was selected as the study region. This research used 11 remote sensing feature factors and 657 historical landslide points, combined with the IV model, to construct a dataset for landslide prediction and susceptibility assessment using the GOS model. The findings indicate that, compared to conventional methods such as random forest, logistic regression, and radial basis function classifier, the GOS model enhances the area under the curve (AUC) value by 2.81% to 8.92%, reaching 0.846. This demonstrates superior performance and confirms the effectiveness and accuracy of the method in landslide susceptibility assessment. Furthermore, compared to the basic-configuration-similarity (BCS) model, the GOS model increases the AUC value by 9.64%, achieving 0.846. This approach substantially diminishes the effects of historical data accuracy, revealing upgraded applicability in landslide susceptibility evaluations. Landslides in Huangshan City are primarily influenced by rainfall and vegetation cover. High-susceptibility zones are predominantly located in areas with high precipitation and low vegetation cover. In contrast, low-susceptible and non-susceptible zones are primarily found in flat areas with high vegetation cover and farther from fault lines. The majority of the study region lies within landslide-prone zones, with non-susceptible areas comprising only 12.43% of the total area. Historical landslides are largely concentrated in moderate- to high-susceptibility zones, accounting for 92.24% of all landslide occurrences. Landslide density increases with the susceptibility level, with a density of 0.15 landslides per square kilometre in high-susceptibility zones. This study brings forward a reliable strategy for establishing the spatial relationship between geographical attribute similarity and landslide susceptibility, bolstering the method's adaptability across various regions. [ABSTRACT FROM AUTHOR]

In recent years traditional numerical methods for accurate weather prediction have been increasingly challenged by deep learning methods. Numerous historical datasets used for short and medium-range weather forecasts are typically organized into a regular spatial grid structure. This arrangement closely resembles images: each weather variable can be visualized as a map or, when considering the temporal axis, as a video. Several classes of generative models, comprising Generative Adversarial Networks, Variational Autoencoders, or the recent Denoising Diffusion Models have largely proved their applicability to the next-frame prediction problem, and is thus natural to test their performance on the weather prediction benchmarks. Diffusion models are particularly appealing in this context, due to the intrinsically probabilistic nature of weather forecasting: what we are really interested to model is the probability distribution of weather indicators, whose expected value is the most likely prediction. In our study, we focus on a specific subset of the ERA-5 dataset, which includes hourly data pertaining to Central Europe from the years 2016 to 2021. Within this context, we examine the efficacy of diffusion models in handling the task of precipitation nowcasting, with a lead time of 1 to 3 hours. Our work is conducted in comparison to the performance of well-established U-Net models, as documented in the existing literature. An additional comparative analysis has been done with the forecasting capabilities of the CERRA system, part of the Copernicus Climate Change Service. The novelty of our approach, Generative Ensemble Diffusion (GED), lies in its innovative use of a diffusion model to generate a diverse set of possible weather scenarios. These scenarios are then amalgamated into a single prediction in a post-processing phase. This approach mimics the usual weather forecasting technique consisting in running an ensemble of numerical simulations under slightly different initial conditions by exploiting instead the intrinsic stochasticity of the generative model. In comparison to recent deep learning models addressing the same problem, our approach results in approximately a 25% reduction in the mean squared error. Reverse diffusion is a core concept in our GED approach, is particularly relevant to weather forecasting. In the context of diffusion models, reverse diffusion refers to the process of iteratively refining a noisy initial prediction into a coherent and realistic forecast. By leveraging reverse diffusion, our model effectively simulates the complex temporal dynamics of weather systems, mirroring the inherent uncertainty and variability in weather patterns. [ABSTRACT FROM AUTHOR]

In the field of precipitation nowcasting, deep learning (DL) has emerged as an alternative to conventional tracking and extrapolation techniques. However, DL struggles to adequately predict heavy precipitation, which is essential in early warning. By taking into account specific user requirements, though, we can simplify the training task and boost predictive skill. As an example, we predict the cumulative precipitation of the next hour (instead of 5 min increments) and the exceedance of thresholds (instead of numerical values). A dialogue between developers and users should identify the requirements to a nowcast and how to consider these in model training. [ABSTRACT FROM AUTHOR]

Background: Although C-reactive protein (CRP) has proved useful in the assessment of post-operative infections, its value at those time points useful to assess organ-space surgical site infection (OSI) after open and laparoscopic colorectal surgery has not been clarified., Methods: We compared values of CRP on post-operative days two and five and percentage of change between those days (Δ%D2-5) in patients with and without OSI, after open (OPEN) and laparoscopic (LAP) colo-rectal surgery. Receiver-operating characteristic analysis was performed and indices of test performance of sensitivity, specificity, positive (PPV) and negative (NPV) predictive values, and likelihood ratios (LR+ and LR-) were assessed., Results: The best CRP predictive values for OSI were D5 >120 mg/L (area under the curve [AUC] 0.959; 95% confidence interval [CI] 0.890-0.990) and Δ%D2-5 <40% (AUC 0.968; 95% CI 0.901-0.994; p=0.0001) in OPEN and D5 >66 mg/L (AUC 0.921; 95% CI 0.841-0.969) and Δ%D2-5 <48% (AUC 0.894-95% CI 0.806-0.952; p=0.0001) in LAP. The best measure was NPV (100%; CI 93.6%-100% for D5 and Δ%D2-5 in OPEN and 98.4%, CI 91.3%-99.7% for D5 and 100%, CI 93.4%-100% for Δ%D2-5 in LAP)., Conclusions: In patients with CRP <120.66 mg/L on post-operative day 5 or a decay from post-operative day two to five of >40%-48% in OPEN and LAP, respectively, OSI may be ruled out and the patient discharged safely. Careful workup is needed in those patients with higher postoperative CRP concentrations or lower apparent decay values.

Accurate and timely precipitation nowcasting is essential for numerous applications including emergency services, infrastructure management, and agriculture. Recently, deep learning (DL) techniques have shown promise in enhancing nowcasting capabilities. This study introduces a novel Physical‐Driven Diffusion Network (PDDN) model that leverages both radar and numerical weather prediction (NWP) data to improve the accuracy and physical consistency of precipitation nowcasts. Our approach integrates the strengths of data‐driven DL techniques with physics‐based NWP models. The PDDN model utilizes latent diffusion models and autoencoders within a two‐stage architecture to predict future radar images, incorporating the Weather Research and Forecasting (WRF) model data to enhance understanding of atmospheric dynamics. Our results demonstrate significant improvements over traditional models, particularly in short‐term forecasting up to 6 hr. This research highlights the potential of combining advanced machine learning techniques with conventional meteorological data, offering new directions for enhancing the accuracy and reliability of weather forecasting. Plain Language Summary: Traditional methods for predicting rainfall often lose accuracy over time, especially in fast‐changing weather conditions. Deep learning techniques have recently shown promise in improving these predictions. To enhance rainfall nowcasting, we developed the Physical‐Driven Diffusion Network (PDDN). This new model combines radar data and numerical weather prediction (NWP) data to improve the accuracy and consistency of forecasts. By integrating advanced machine learning with physics‐based models, the PDDN excels in predicting rainfall for up to 6 hr. Our results show that the PDDN significantly outperforms traditional methods, providing more accurate and reliable short‐term weather forecasts. Key Points: Our PDDN model outperforms baseline models, exhibiting high proficiency in predicting precipitation up to 6 hr aheadThe integration of physical data from WRF enhances the model's understanding of atmospheric dynamics and improves forecasting accuracyThe novel design of latent diffusion models in a two‐stage architecture enables more accurate and robust precipitation nowcasts [ABSTRACT FROM AUTHOR]

The editorial discusses the concept of pharmacophylogeny, which explores the relationship between plant phylogeny, chemical composition, and medicinal efficacy. Volume III of the research topic focuses on the phylogenomics, metabolomics, and bioactivity of various medicinal species, including algae, monocots, and eudicots. The research aims to deepen the understanding of phylogeny, phytometabolites, and poly-pharmacology of specific plant genera and families, contributing to the sustainable conservation and utilization of medicinal plant resources. Fermentation techniques are highlighted as important in enhancing the active ingredients of herbal medicine, expanding the potential applications of fermented botanical drugs. [Extracted from the article]

The development of artificial intelligence makes it possible to rapidly segment landslides. However, there are still some challenges in landslide segmentation based on remote sensing images, such as low segmentation accuracy, caused by similar features, inhomogeneous features, and blurred boundaries. To address these issues, we propose a novel deep learning model called AST-UNet in this paper. This model is based on structure of SwinUNet, attaching a channel Attention and spatial intersection (CASI) module as a parallel branch of the encoder, and a spatial detail enhancement (SDE) module in the skip connection. Specifically, (1) the spatial intersection module expands the spatial attention range, alleviating noise in the image and enhances the continuity of landslides in segmentation results; (2) the channel attention module refines the spatial attention weights by feature modeling in the channel dimension, improving the model's ability to differentiate targets that closely resemble landslides; and (3) the spatial detail enhancement module increases the accuracy for landslide boundaries by strengthening the attention of the decoder to detailed features. We use the landslide data from the area of Luding, Sichuan to conduct experiments. The comparative analyses with state-of-the-art (SOTA) models, including FCN, UNet, DeepLab V3+, TransFuse, TranUNet, and SwinUNet, prove the superiority of our AST-UNet for landslide segmentation. The generalization of our model is also verified in the experiments. The proposed AST-UNet obtains an F1-score of 90.14%, mIoU of 83.45%, foreground IoU of 70.81%, and Hausdorff distance of 3.73, respectively, on the experimental datasets. [ABSTRACT FROM AUTHOR]

Existing tools for predicting postoperative complications in women undergoing surgery for gynecological neoplasms are evaluated in this narrative review. Although surgery is a very efficient therapy for gynecological tumors, it is not devoid of the possibility of negative postoperative outcomes. Widely used tools at present, such as the Surgical Apgar Score and the Modified Frailty Index, fail to consider the complex characteristics of gynecological malignancies and their related risk factors. A thorough search of the PubMed database was conducted for our review, specifically targeting studies that investigate several aspects impacting postoperative outcomes, including nutritional status, obesity, albumin levels, sodium levels, fluid management, and psychological well-being. Research has shown that both malnutrition and obesity have a substantial impact on postoperative mortality and morbidity. Diminished sodium and albumin levels together with compromised psychological well-being can serve as reliable indicators of negative consequences. The role of appropriate fluid management in enhancing patient recovery was also investigated. The evidence indicates that although current mechanisms are useful, they have limitations in terms of their range and do not thoroughly address these recently identified risk factors. Therefore, there is a need for a new, more comprehensive tool that combines these developing elements to more accurately forecast postoperative problems and enhance patient results in gynecological oncology. This paper highlights the need to create such a tool to improve clinical practice and the treatment of patients. [ABSTRACT FROM AUTHOR]

We introduce deep generative diffusion for multivariate and regional surrogate modeling learned from sea‐ice simulations. Given initial conditions and atmospheric forcings, the model is trained to generate forecasts for a 12‐hr lead time from simulations by the state‐of‐the‐art sea‐ice model neXtSIM. For our regional model setup, the diffusion model outperforms as ensemble forecast all other tested models, including a free‐drift model and a stochastic extension of a deterministic data‐driven surrogate model. The diffusion model additionally retains information at all scales, resolving smoothing issues of deterministic models. Furthermore, by generating physically consistent forecasts, previously unseen for such kind of completely data‐driven surrogates, the model can almost match the scaling properties of neXtSIM, as similarly deduced from sea‐ice observations. With these results, we provide a strong indication that diffusion models can achieve similar results as traditional geophysical models with the significant advantage of being orders of magnitude faster and solely learned from data. Plain Language Summary: Thanks to generative deep learning, computers can generate images that are almost indistinguishable from real images. We use this technology to forecast the sea‐ice with models that are solely learned from data, here from simulation data. Doing so for a region North of Svalbard, we enhance the accuracy of the model and maintain their sharpness. The learned model further depicts physical processes as similarly observed for the targeted physical‐driven model. Therefore, this technology could provide us with the necessary tools to learn faster models from data that have similar properties to those based on physical equations. Key Points: We introduce the first denoising diffusion model designed for sea‐ice physicsGenerative diffusion outperforms deterministic surrogates and retains the sharpness in the forecasts as observed in the targeted simulationsOur model generates forecasts that exhibit physical consistency between variables in space and time [ABSTRACT FROM AUTHOR]

Earth system models (ESMs) are essential for understanding the interaction between human activities and the Earth's climate. However, the computational demands of ESMs often limit the number of simulations that can be run, hindering the robust analysis of risks associated with extreme weather events. While low‐cost climate emulators have emerged as an alternative to emulate ESMs and enable rapid analysis of future climate, many of these emulators only provide output on at most a monthly frequency. This temporal resolution is insufficient for analyzing events that require daily characterization, such as heat waves or heavy precipitation. We propose using diffusion models, a class of generative deep learning models, to effectively downscale ESM output from a monthly to a daily frequency. Trained on a handful of ESM realizations, reflecting a wide range of radiative forcings, our DiffESM model takes monthly mean precipitation or temperature as input, and is capable of producing daily values with statistical characteristics close to ESM output. Combined with a low‐cost emulator providing monthly means, this approach requires only a small fraction of the computational resources needed to run a large ensemble. We evaluate model behavior using a number of extreme metrics, showing that DiffESM closely matches the spatio‐temporal behavior of the ESM output it emulates in terms of the frequency and spatial characteristics of phenomena such as heat waves, dry spells, or rainfall intensity. Plain Language Summary: Ideally, to study how damaging phenomena like heatwaves, droughts and downpours will change in the future under global warming, we would want a large number of climate model runs producing many realizations of climate futures that we can analyze and from which the new characteristics of climate extremes can be quantified. Currently, emulators can rapidly generate simulations of future climate, but often to relatively low frequencies, as decadal, annual or monthly output at best in most cases, which is insufficient for studying extreme events that occur on a daily timescale. We show how it is possible to train a machine learning model to produce daily series of temperature or precipitation from monthly averages, thus facilitating a more robust investigation into how extreme events will change in the future. Key Points: Earth system models (ESMs) are key devices for understanding how human actions will affect the future global climateComputational demands prevent us from running them for more than a handful of scenarios. ESM emulators are most commonly limited to the monthly frequencyWe present DiffESM as a data‐driven emulator of ESMs that closely matches the spatiotemporal distributions of ESMs at daily frequency [ABSTRACT FROM AUTHOR]

Idiopathic fibrosing pancreatitis has been associated with Sjögren's syndrome, primary biliary cirrhosis and primary sclerosing cholangitis. This condition frequently develops in childhood and youth, and has also been related to ulcerative colitis and pericholangitis. Pancreatic complications have been rarely described as systemic complications of ulcerative colitis. A 25-year-old man presented with epigastric pain and jaundice. Abdominal ultrasonography, computed tomography (CT), magnetic resonance cholangiopancreatography (MRCP) and endoscopic retrograde cholangiopancreatography (ERCP) revealed a diffuse enlargement of the pancreas, filiform distal stenosis of the common bile duct and intrahepatic bile ducts, and pancreatic duct dilatation. At operation, a rock-hard and nodular pancreas was noted. Cholecystectomy and Roux-en-Y hepaticojejunostomy, with an access loop, was successfully performed. Idiopathic fibrosing pancreatitis should be considered in young patients with obstructive jaundice, especially those affected with chronic inflammatory or autoimmune diseases. Glucocorticoid therapy would be the first-line treatment, although many patients require operation.

Background: Immunosuppression associated with homologous blood transfusion was first observed in renal allograft transplantation. Clinical effects of transfusion-induced immunosuppression in surgical patients have been debated in the literature for more than a decade with contradictory results., Objective: To investigate whether homologous blood transfusions significantly affect postoperative septic morbidity and mortality in patients undergoing elective surgery for gastric cancer., Design: Case series., Setting: Hospitalized care., Patients: The hospital records of 209 patients who underwent elective surgery for gastric cancer at the Department of Surgery of the Hospital del Mar, Autonomous University of Barcelona in Spain, and at the Department of Surgery of the Catholic University of Rome in Italy from April 1984 to December 1990 were reviewed, and 179 patients were included in the study., Main Outcome Measures: The following variables were entered into univariate and multivariate analyses to identify factors potentially affecting postoperative septic morbidity: demographic data, weight loss, preoperative serum albumin level and lymphocyte count, type and duration of operative procedure, amount and timing of blood transfusion, and stage of disease., Results: Univariate analysis showed that a large quantity of blood transfused (> 1500 mL) and transfusion in the postoperative period (group C) were associated with a worse clinical outcome. Postoperative transfusion was an independent predictor of septic morbidity in multivariate analysis., Conclusions: Despite transfusion-induced immunomodulation, homologous blood transfusion should not be considered a risk factor for postoperative septic morbidity in patients undergoing elective major abdominal surgery. The timing-response relationship between transfusions and septic morbidity in multivariate analysis may be the effect of uncontrolled confounders such as variation of volemia induced by stress response in patients who were developing or had just developed infectious complications.

ECW, and particularly its interstitial component, expands easily with malnutrition, sepsis, and trauma and after aggressive intravenous fluid therapy. In this scenario, hypoalbuminemia is usually the result of both an increased capillary escape rate due to leaky endothelium and increased distribution volume; this can be worsened by artificial intravenous nutrition with sodium, water, and glucose. Monitoring ECW is essential during TPN. Short-term changes in weight and serum albumin concentration are helpful to control ECW volume and prevent ECW expansion. Tetrapolar bioimpedance analysis is a promising technique for accurate bedside measurement of changes in body fluid compartments.

Background: There are many doubts as to the efficacy of systemic antibiotic prophylaxis versus the methods of local treatment in the prevention of infection of the contaminated surgical wound. A controlled prospective study was designed to compare the effectiveness of a combination of parenteral antibiotics with lavage with physiologic serum of the surgical wound to prevent infection of the postappendectomy wound., Methods: The patients in group A (antibiotic, n = 70) received a sole preoperative dose of methronidazol and gentamicin while in those in group I (irrigation, n = 71) the wounds were irrigated with physiologic serum prior to and following closure of aponeurosis. The patients were controlled at one week and one month after the intervention., Results: The global rate of infection was 9.3%. Six patients of group A and five of group I developed wound infection (p = 0.06), The age and length of the intervention were significantly higher in the infected patients (41 vs 23 years, p = 0.0001 and 53 vs 41 minutes, p = 0.03, respectively). Intraperitoneal culture was positive in 70% of the patients who posteriorly developed wound infection, being positive in only 9.4% of the uninfected patients (p = 0.0001). Eight of the infections (73%) were detected following discharge from hospital. The cost of prophylaxis in group A was seven-fold higher than that of group I., Conclusions: Lavage of the surgical wound with physiologic serum may be an effective, safe and inexpensive method to prevent infection of the wound following appendicectomy for unperforated appendicitis.

Large Language Models (LLMs) combined with visual foundation models have demonstrated significant advancements, achieving intelligence levels comparable to human capabilities. This study analyzes the latest Multimodal LLMs (MLLMs), including Multimodal-GPT, GPT-4 Vision, Gemini, and LLaVa, with a focus on hydrological applications such as flood management, water level monitoring, agricultural water discharge, and water pollution management. We evaluated these MLLMs on hydrology-specific tasks, testing their response generation and real-time suitability in complex real-world scenarios. Prompts were designed to enhance the models' visual inference capabilities and contextual comprehension from images. Our findings reveal that GPT-4 Vision demonstrated exceptional proficiency in interpreting visual data, providing accurate assessments of flood severity and water quality. Additionally, MLLMs showed potential in various hydrological applications, including drought prediction, streamflow forecasting, groundwater management, and wetland conservation. These models can optimize water resource management by predicting rainfall, evaporation rates, and soil moisture levels, thereby promoting sustainable agricultural practices. This research provides valuable insights into the potential applications of advanced AI models in addressing complex hydrological challenges and improving real-time decision-making in water resource management [ABSTRACT FROM AUTHOR]

Recent flood disasters caused by extreme meteorological events highlight the need of fast and reliable tools for flooding forecast. For our purposes, the danger associated with floods is embodied in a single risk-level flag which considers both local water depth and velocity. The methodology here derived is applied and validated for the case study of the St. Lucia island in the eastern Caribbean Sea that experiences flash flooding as a result of combined intense rainfall and steep slopes, difficult to predict with traditional early-warning systems. A multi-layer perceptron neural network is trained on a high-fidelity dataset generated through full two-dimensional shallow water simulations of real and synthetic events. The dataset is validated against social markers obtained from real events. The predictive capabilities of the neural network model are tested on the out-of-box case of the Dean and Tomas hurricanes and compared with the solutions of the shallow water solver. The surrogate solver allows a significant speed-up in the prediction time with respect to traditional CFD (seconds vs hours), showing a high precision and accuracy, with accuracy, precision and F1-score above 0.99. [ABSTRACT FROM AUTHOR]

Background There is controversy regarding the maximum number of elements that can be included in a surgical site infection prevention bundle. In addition, it is unclear whether a bundle of this type can be implemented at a multicentre level. Methods A pragmatic, multicentre cohort study was designed to analyse surgical site infection rates in elective colorectal surgery after the sequential implementation of two preventive bundle protocols. Secondary outcomes were to determine compliance with individual measures and to establish their effectiveness, duration of stay, microbiology and 30-day mortality rate. Results A total of 32 205 patients were included. A 50% reduction in surgical site infection was achieved after the implementation of two sequential sets of bundles: from 18.16% in the Baseline group to 10.03% with Bundle-1 and 8.19% with Bundle-2. Bundle-2 reduced superficial-surgical site infection (OR 0.74 (95% c.i. 0.58 to 0.95); P = 0.018) and deep-surgical site infection (OR 0.66 (95% c.i. 0.46 to 0.93); P = 0.018) but not organ/space-surgical site infection (OR 0.88 (95% c.i. 0.74 to 1.06); P = 0.172). Compliance increased after the addition of four measures to Bundle-2. In the multivariable analysis, for organ/space-surgical site infection, laparoscopy, oral antibiotic prophylaxis and mechanical bowel preparation were protective factors in colonic procedures, while no protective factors were found in rectal surgery. Duration of stay fell significantly over time, from 7 in the Baseline group to 6 and 5 days for Bundle-1 and Bundle-2 respectively (P < 0.001). The mortality rate fell from 1.4% in the Baseline group to 0.59% and 0.6% for Bundle-1 and Bundle-2 respectively (P < 0.001). There was an increase in Gram-positive bacteria and yeast isolation, and reduction in Gram-negative bacteria and anaerobes in organ/space-surgical site infection. Conclusions The addition of measures to create a final 10-measure protocol had a cumulative protective effect on reducing surgical site infection. However, organ/space-surgical site infection did not benefit from the addition. No protective measures were found for organ/space-surgical site infection in rectal surgery. Compliance with preventive measures increased from Bundle-1 to Bundle-2. [ABSTRACT FROM AUTHOR]

There is a growing need for proactive planning for natural hazards in a changing climate. Computational modeling of climate hazards provides an opportunity to inform planning, particularly in areas approaching ecosystem state changes, such as Interior Alaska, where future hazards are expected to differ significantly from historical events in frequency and severity. This paper considers improved modeling approaches from a physical process perspective and contextualizes the results within the complexities and limitations of hazard planning efforts and management concerns. Therefore, the aim is not only to improve the understanding of potential climate impacts on streamflow within this region but also to further explore the steps needed to evaluate local-scale hazards from global drivers and the potential challenges that may be present. This study used dynamically downscaled climate forcing data from ERA-Interim reanalysis datasets and projected climate scenarios from two General Circulation Models under a single Representative Concentration Pathway (RCP 8.5) to simulate an observational gage-calibrated WRF-Hydro model to assess shifts in streamflow and flooding potential in three Interior Alaska rivers over a historical period (2008–2017) and two future periods (2038–2047 and 2068–2077). Outputs were assessed for seasonality, streamflow, extreme events, and the comparison between existing flood control infrastructure in the region. The results indicate that streamflow in this region is likely to experience increases in seasonal length and baseflow, while the potential for extreme events and variable short-term streamflow behavior is likely to see greater uncertainty, based on the divergence between the models. [ABSTRACT FROM AUTHOR]

Climate change in the Mediterranean region is manifesting itself as an increase in average air temperature and a change in the rainfall regime: the value of cumulative annual rainfall generally appears to be constant, but the intensity of annual rainfall maxima, between 1 and 24 h , is increasing, especially in the period between late summer and early autumn. The associated ground effects in urban areas consist of flash floods and pluvial floods, often in very small areas, depending on the physical-geographical layout of the region. In the context of global warming, it is therefore important to have an adequate monitoring network for rain events that are highly concentrated in space and time. This research analyses the meteo-hydrological features of the 27 and 28 August 2023 event that occurred in the city of Genoa, Italy, just 4 d after the record maximum air temperature was recorded: between 19:00 and 02:00 UTC almost 400 mm of rainfall was recorded in the eastern sector of the historic centre of Genoa, with significant ground effects such as flooding episodes and the overflowing of pressurised culverts. Rainfall observations and estimates were made using both official or "authoritative" networks (rain gauges and meteorological radar) and rain gauge networks inspired by citizen science principles. The combined analysis of observations from authoritative and citizen science networks reveals, for the event analysed, a spatial variability of the precipitation field at an hourly and a sub-hourly timescale that cannot be captured by the current spatial density of the authoritative measurement stations (which have one of the highest densities in Italy). Monthly total rainfall and short-duration annual maximum time series recorded by the authoritative rain gauge network of the Genoa area are then analysed. The results show significant variation even at distances of less than 2 km in the average rainfall depth accumulated over sub-hourly duration. Extreme weather monitoring activity is confirmed as one of the most important aspects in terms of flood prevention and protection in urban areas. The integration between authoritative and citizen science networks can prove to be a valid contribution to the monitoring of extreme events. [ABSTRACT FROM AUTHOR]

Given a long time series, the distance profile of a query time series computes distances between the query and every possible subsequence of a long time series. MASS (Mueen's Algorithm for Similarity Search) is an algorithm to efficiently compute distance profile under z-normalized Euclidean distance (Mueen et al. in The fastest similarity search algorithm for time series subsequences under Euclidean distance. http://www.cs.unm.edu/~mueen/FastestSimilaritySearch.html, 2017). MASS is recognized as a useful tool in many data mining works. However, complete documentation of the increasingly efficient versions of the algorithm does not exist. In this paper, we formalize the notion of a distance profile, describe four versions of the MASS algorithm, show several extensions of distance profiles under various operating conditions, describe how MASS improves performances of existing data mining algorithms, and finally, show utility of MASS in domains including seismology, robotics and power grids. [ABSTRACT FROM AUTHOR]

This paper proposes a novel GAN framework with self-clustering approach for precipitation nowcasting (ClusterCast). Previous studies have primarily captured the motion vector using only a single latent space, making the models difficult to adapt to disparate space-time distribution of precipitation. Environmental factors (e.g., regional characteristics and precipitation scale) have an impact on precipitation systems and can cause non-stationary distribution. To tackle this problem, our key idea is to train a generator network to predict future radar frames by learning a sub-network that automatically labels precipitation types from a generative model. The training process consists of (i) clustering the hierarchical features derived from the generator stem using a sub-network and (ii) predicting future radar frames according to the self-supervised labels, enabling heterogeneous latent representation. Additionally, we attempt an ensemble forecast that prescribes random perturbations to improve performance. With the flexibility of representation learning, ClusterCast enables the model to learn precipitation distribution more accurately. Results indicate that our method generates non-blurry future frames by preventing mode collapse, and the proposed method demonstrates robustness across various precipitation scenarios. Extensive experiments demonstrate that our method outperforms four benchmarks on a 2-h prediction basis with a mean squared error (MSE) of 8.9% on unseen datasets. [ABSTRACT FROM AUTHOR]

A novel generation of sea-ice models with elasto-brittle rheologies, such as neXtSIM, can represent sea-ice processes with an unprecedented accuracy at the mesoscale for resolutions of around 10 km. As these models are computationally expensive, we introduce supervised deep learning techniques for surrogate modeling of the sea-ice thickness from neXtSIM simulations. We adapt a convolutional U-Net architecture to an Arctic-wide setup by taking the land–sea mask with partial convolutions into account. Trained to emulate the sea-ice thickness at a lead time of 12 h, the neural network can be iteratively applied to predictions for up to 1 year. The improvements of the surrogate model over a persistence forecast persist from 12 h to roughly 1 year, with improvements of up to 50 % in the forecast error. Moreover, the predictability gain for the sea-ice thickness measured against the daily climatology extends to over 6 months. By using atmospheric forcings as additional input, the surrogate model can represent advective and thermodynamical processes which influence the sea-ice thickness and the growth and melting therein. While iterating, the surrogate model experiences diffusive processes which result in a loss of fine-scale structures. However, this smoothing increases the coherence of large-scale features and thereby the stability of the model. Therefore, based on these results, we see huge potential for surrogate modeling of state-of-the-art sea-ice models with neural networks. [ABSTRACT FROM AUTHOR]

Archives of composite weather radar images represent an invaluable resource to study the predictability of precipitation. In this paper, we compare two distinct approaches to construct empirical low-dimensional attractors from radar precipitation fields. In the first approach, the phase space variables of the attractor are defined using the domain-scale statistics of precipitation fields, such as the mean precipitation, fraction of rain, and spatial and temporal correlations. The second type of attractor considers the spatial distribution of precipitation and is built by principal component analysis (PCA). For both attractors, we investigate the density of trajectories in phase space, growth of errors from analogue states, and fractal properties. To represent different scales and climatic and orographic conditions, the analyses are done using multi-year radar archives over the continental United States (≈4000×4000 km 2 , 21 years) and the Swiss Alpine region (≈500×500 km 2 , 6 years). [ABSTRACT FROM AUTHOR]

During the last 2 years, tremendous progress has been made in global data-driven weather models trained on numerical weather prediction (NWP) reanalysis data. The most recent models trained on the ERA5 reanalysis at 0.25° resolution demonstrate forecast quality on par with ECMWF's high-resolution model with respect to a wide selection of verification metrics. In this study, one of these models, Pangu-Weather, is compared to several NWP models with and without probabilistic post-processing for 2 m temperature and 10 m wind speed forecasting at 183 Norwegian SYNOP (surface synoptic observation) stations up to +60 h ahead. The NWP models included are the ECMWF HRES, ECMWF ENS and the HARMONIE-AROME ensemble model MEPS with 2.5 km spatial resolution. Results show that the performances of the global models are on the same level, with Pangu-Weather being slightly better than the ECMWF models for temperature and slightly worse for wind speed. The MEPS model clearly provided the best forecasts for both parameters. The post-processing improved the forecast quality considerably for all models but to a larger extent for the coarse-resolution global models due to stronger systematic deficiencies in these. Apart from this, the main characteristics in the scores were more or less the same with and without post-processing. Our results thus confirm the conclusions from other studies that global data-driven models are promising for operational weather forecasting. [ABSTRACT FROM AUTHOR]

Quantitative precipitation forecasting in numerical weather prediction (NWP) models is contingent upon physicals parameterization schemes. However, uncertainties abound due to limited knowledge of the precipitating processes, leading to degraded forecasting skills. In light of this, our study explores the application of a Swin‐Transformer based deep learning (DL) model as a supplementary tool for enhancing the mapping trajectory between the NWP fundamental variables and the most downstream variable precipitation. Constrained by the observational satellite precipitation product from NOAA CPC Morphing Technique (CMORPH), the DL model serves as the post‐processing tool that can better resolve the precipitation patterns compared to solely based on NWP estimation. Compared to the baseline Weather Research and Forecasting simulation, the DL post‐processing effectively extracts features over meteorological variables, leading to improved precipitation skill scores of 21.7%, 60.5%, and 45.5% for light rain, moderate rain, and heavy rain, respectively, on an hourly basis. We also evaluate two case studies under different driven synoptic conditions and show promising results in estimating heavy precipitation during strong convective precipitation events. Overall, the proposed DL model can provide a vital reference for capturing precipitation‐triggering mechanisms and enhancing precipitation forecasting skills. Additionally, we discuss the sensitivities of the fundamental meteorological variables used in this study, training strategies, and performance limitations. Plain Language Summary: Numerical weather prediction models depend on certain empirical formulations known as parameterizations to estimate precipitation. However, these methods often fall short due to the intricate dynamics of rainfall, which involves numerous small‐scale interactions that these models are unable to fully capture. To counteract these limitations, our study deploys a form of machine learning known as deep learning (DL) to predict precipitation. This DL model utilizes fundamental weather variables derived from NWP models to make its estimations, serving as a remedy for the inherent weaknesses of traditional models caused by the uncertainties in their parameterization schemes. The implementation of our DL model resulted in a significant enhancement in rainfall prediction accuracy, particularly in the case of extreme precipitation events. This suggests that the application of machine learning strategies could be a promising approach to improve the reliability of rainfall forecasts, a crucial element for effective weather prediction and water resource management. Key Points: We employ a transformer based deep learning model to improve the accuracy of precipitation estimation in numerical weather prediction modelsVarious training strategies were implemented to manage the highly skewed precipitation data leading to improvements in heavy rainfall eventsEvaluation conducted with multiple metrics including skill score, quantile and spatial distribution as well as two case studies [ABSTRACT FROM AUTHOR]

Copyright of Beni Suef Journal of Physical Education & Sports Sciences. is the property of Beni Suef University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Flood forecasting remains a significant challenge, particularly when dealing with basins characterized by small drainage areas (i.e., 103 km2 or lower with response time in the range 0.5–10 h) especially because of the rainfall prediction uncertainties. This study aims to investigate the performances of streamflow predictions using two short-term rainfall forecast methods. These methods utilize a combination of a nowcasting extrapolation algorithm and numerical weather predictions by employing a three-dimensional variational assimilation system, and nudging assimilation techniques, meteorological radar, and lightning data that are frequently updated, allowing new forecasts with high temporal frequency (i.e., 1–3 h). A distributed hydrological model is used to convert rainfall forecasts into streamflow prediction. The potential of assimilating radar and lightning data, or radar data alone, is also discussed. A hindcast experiment on two rainy periods in the northwest region of Italy was designed. The selected skill scores were analyzed to assess their degradation with increasing lead time, and the results were further aggregated based on basin dimensions to investigate the catchment integration effect. The findings indicate that both rainfall forecast methods yield good performance, with neither definitively outperforming the other. Furthermore, the results demonstrate that, on average, assimilating both radar and lightning data enhances the performance. [ABSTRACT FROM AUTHOR]

Ground-based radar precipitation products typically need adjustment with rain gauge accumulations to achieve a reasonable accuracy. This is certainly the case for the pan-European radar precipitation products. The density of (near) real-time rain gauge accumulations from official networks is often relatively low. Crowdsourced rain gauge networks have a much higher density than conventional ones and are a potentially interesting (complementary) source to merge with radar precipitation accumulations. Here, a 1-year personal weather station (PWS) rain gauge dataset of ∼ 5 min accumulations is obtained from the private company Netatmo over the period 1 September 2019–31 August 2020, which is subjected to quality control using neighbouring PWSs and, after aggregating to 1 h accumulations, using unadjusted radar data. The PWS 1 h gauge accumulations are employed to spatially adjust OPERA radar accumulations, covering 78 % of geographical Europe. The performance of the merged dataset is evaluated against daily and disaggregated 1 h gauge accumulations from weather stations in the European Climate Assessment & Dataset (ECA&D). Results are contrasted to those from an unadjusted OPERA-based radar dataset and from EURADCLIM. The severe average underestimation for daily precipitation of ∼ 28 % from the unadjusted radar dataset diminishes to ∼ 3 % for the merged radar–PWS dataset. A station-based spatial verification shows that the relative bias in 1 h precipitation is still quite variable and suggests stronger underestimations for colder climates. A dedicated evaluation with scatter density plots reveals that the performance is indeed less good for lower temperatures, which points to limitations in observing solid precipitation by PWS gauges. The outcome of this study confirms the potential of crowdsourcing to improve radar precipitation products in (near) real time. [ABSTRACT FROM AUTHOR]

Understanding climate-related risks and stresses is an emerging area of interest for life insurers globally. However, there are complexities in quantifying climate risk stress impacts due to the long-term nature of these risks, and the interactions between physical and transition risks over time. In this paper, we build on understanding the financial impacts of climate risk stresses for life insurers in Australia, by identifying key climate-related mortality risks, and quantifying these by applying short- and long-term stresses from existing literature to two synthetic life insurers. We perform sensitivity tests to demonstrate the variability and range of plausible results. Overall, results show that the expected financial impacts from short-term events in isolation are small relative to expected long-term changes in mortality. Furthermore, the value of a mortality hedge is even more apparent given the increased mortality risk for yearly renewable-term insurers in the short to medium term. [ABSTRACT FROM AUTHOR]