Preventive machine learning models incorporating health checkup data and hair mineral analysis for low bone mass identification.

Machine learning (ML) models have been increasingly employed to predict osteoporosis. However, the incorporation of hair minerals into ML models remains unexplored. This study aimed to develop ML models for predicting low bone mass (LBM) using health checkup data and hair mineral analysis. A total of 1206 postmenopausal women and 820 men aged 50 years or older at a health promotion center were included in this study. LBM was defined as a T-score below - 1 at the lumbar, femur neck, or total hip area. The proportion of individuals with LBM was 59.4% (n = 1205). The features used in the models comprised 50 health checkup items and 22 hair minerals. The ML algorithms employed were Extreme Gradient Boosting (XGB), Random Forest (RF), Gradient Boosting (GB), and Adaptive Boosting (AdaBoost). The subjects were divided into training and test datasets with an 80:20 ratio. The area under the receiver operating characteristic curve (AUROC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and an F1 score were evaluated to measure the performances of the models. Through 50 repetitions, the mean (standard deviation) AUROC for LBM was 0.744 (± 0.021) for XGB, the highest among the models, followed by 0.737 (± 0.023) for AdaBoost, and 0.733 (± 0.023) for GB, and 0.732 (± 0.021) for RF. The XGB model had an accuracy of 68.7%, sensitivity of 80.7%, specificity of 51.1%, PPV of 70.9%, NPV of 64.3%, and an F1 score of 0.754. However, these performance metrics did not demonstrate notable differences among the models. The XGB model identified sulfur, sodium, mercury, copper, magnesium, arsenic, and phosphate as crucial hair mineral features. The study findings emphasize the significance of employing ML algorithms for predicting LBM. Integrating health checkup data and hair mineral analysis into these models may provide valuable insights into identifying individuals at risk of LBM.

Comparison of Cox regression and generalized Cox regression models to machine learning in predicting survival of children with diffuse large B-cell lymphoma.

Background: The incidence of diffuse large B-cell lymphoma (DLBCL) in children is increasing globally. Due to the immature immune system in children, the prognosis of DLBCL is quite different from that of adults. We aim to use the multicenter large retrospective analysis for prognosis study of the disease. Methods: For our retrospective analysis, we retrieved data from the Surveillance, Epidemiology and End Results (SEER) database that included 836 DLBCL patients under 18 years old who were treated at 22 central institutions between 2000 and 2019. The patients were randomly divided into a modeling group and a validation group based on the ratio of 7:3. Cox stepwise regression, generalized Cox regression and eXtreme Gradient Boosting (XGBoost) were used to screen all variables. The selected prognostic variables were used to construct a nomogram through Cox stepwise regression. The importance of variables was ranked using XGBoost. The predictive performance of the model was assessed by using C-index, area under the curve (AUC) of receiver operating characteristic (ROC) curve, sensitivity and specificity. The consistency of the model was evaluated by using a calibration curve. The clinical practicality of the model was verified through decision curve analysis (DCA). Results: ROC curve demonstrated that all models except the non-proportional hazards and non-log linearity (NPHNLL) model, achieved AUC values above 0.7, indicating high accuracy. The calibration curve and DCA further confirmed strong predictive performance and clinical practicability. Conclusions: In this study, we successfully constructed a machine learning model by combining XGBoost with Cox and generalized Cox regression models. This integrated approach accurately predicts the prognosis of children with DLBCL from multiple dimensions. These findings provide a scientific basis for accurate clinical prognosis prediction.

One-step purification and characterization of a haloprotease from Micrococcus sp. PC7 for the production of protein hydrolysates from Andean legumes.

The high content and quality of protein in Andean legumes make them valuable for producing protein hydrolysates using proteases from bacteria isolated from extreme environments. This study aimed to carry out a single-step purification of a haloprotease from Micrococcus sp. PC7 isolated from Peru salterns. In addition, characterize and apply the enzyme for the production of bioactive protein hydrolysates from underutilized Andean legumes. The PC7 protease was fully purified using only tangential flow filtration (TFF) and exhibited maximum activity at pH 7.5 and 40 °C. It was characterized as a serine protease with an estimated molecular weight of 130 kDa. PC7 activity was enhanced by Cu2+ (1.7-fold) and remained active in the presence of most surfactants and acetonitrile. Furthermore, it stayed completely active up to 6% NaCl and kept Ì´ 60% of its activity up to 8%. The protease maintained over 50% of its activity at 25 °C and 40 °C and over 70% at pH from 6 to 10 for up to 24 h. The determined Km and Vmax were 0.1098 mg mL-1 and 273.7 U mL-1, respectively. PC7 protease hydrolyzed 43%, 22% and 11% of the Lupinus mutabilis, Phaseolus lunatus and Erythrina edulis protein concentrates, respectively. Likewise, the hydrolysates from Lupinus mutabilis and Erythrina edulis presented the maximum antioxidant and antihypertensive activities, respectively. Our results demonstrated the feasibility of a simple purification step for the PC7 protease and its potential to be applied in industrial and biotechnological processes. Bioactive protein hydrolysates produced from Andean legumes may lead to the development of nutraceuticals and functional foods contributing to address some United Nations Sustainable Development Goals (SDGs).

Prediction of neurologic outcome after out-of-hospital cardiac arrest: an interpretable approach with machine learning.

Out-of-hospital cardiac arrest (OHCA) is a critical condition with low survival rates. In patients with a return of spontaneous circulation, brain injury is a leading cause of death. In this study, we propose an interpretable machine learning approach for predicting neurologic outcome after OHCA, using information available at the time of hospital admission. METHODS: The study population were 55 615 OHCA cases registered in the Swedish Cardiopulmonary Resuscitation Registry between 2010 and 2020. The dataset was split to training and validation sets (for model development) and test set (for evaluation of the final model). We used an XGBoost algorithm with stratified, repeated 10-fold cross-validation along with Optuna framework for hyperparameters tuning. The final model was trained on 10 features selected based on the importance scores and evaluated on the test set in terms of discrimination, calibration and bias-variance tradeoff. We used SHapley Additive exPlanations to address the 'black-box' model and align with eXplainable artificial intelligence. RESULTS: The final model achieved: area under the receiver operating characteristic value 0.964 (95% confidence interval (CI) [0.960-0.968]), sensitivity 0.606 (95% CI [0.573-0.634]), specificity 0.975 (95% CI [0.972-0.978]), positive predictive value (PPV) 0.664 (95% CI [0.625-0.696]), negative predictive value (NPV) 0.969 (95% CI [0.966-0.972]), macro F1 0.803 (95% CI [0.788-0.816]), and showed a very good calibration. SHAP features with the highest impact on the model's output were: 'ROSC on arrival to hospital', 'Initial rhythm asystole' and 'Conscious on arrival to hospital'. CONCLUSIONS: The XGBoost machine learning model with 10 features available at the time of hospital admission showed good performance for predicting neurologic outcome after OHCA, with no apparent signs of overfitting.

Application of machine learning approaches to predict ammonium nitrogen transport in different soil types and evaluate the contribution of control factors.

The loss of nitrogen in soil damages the environment. Clarifying the mechanism of ammonium nitrogen (NH4+-N) transport in soil and increasing the fixation of NH4+-N after N application are effective methods for improving N use efficiency. However, the main factors are not easily identified because of the complicated transport and retardation factors in different soils. This study employed machine learning (ML) to identify the main influencing factors that contribute to the retardation factor (Rf) of NH4+-N in soil. First, NH4+-N transport in the soil was investigated using column experiments and a transport model. The Rf (1.29 - 17.42) was calculated and used as a proxy for the efficacy of NH4+-N transport. Second, the physicochemical parameters of the soil were determined and screened using lasso and ridge regressions as inputs for the ML model. Third, six machine learning models were evaluated: Adaptive Boosting, Extreme Gradient Boosting (XGB), Random Forest, Gradient Boosting Regression, Multilayer Perceptron, and Support Vector Regression. The optimal ML model of the XGB model with a low mean absolute error (0.81), mean squared error (0.50), and high test r2 (0.97) was obtained by random sampling and five-fold cross-validation. Finally, SHapely Additive exPlanations, entropy-based feature importance, and permutation characteristic importance were used for global interpretation. The cation exchange capacity (CEC), total organic carbon (TOC), and Kaolin had the greatest effects on NH4+-N transport in the soil. The accumulated local effect offered a fundamental insight: When CEC > 6 cmol+ kg-1, and TOC > 40 g kg-1, the maximum resistance to NH4+-N transport within the soil was observed. This study provides a novel approach for predicting the impact of the soil environment on NH4+-N transport and guiding the establishment of an early-warning system of nutrient loss.

Influence of extreme 2022 heatwave on megacities' anthropogenic CO2 emissions in lower-middle reaches of the Yangtze River.

An unprecedented heatwave hit the Yangtze River Basin (YRB) in August 2022. We analyzed changes of anthropogenic CO2 emissions in 8 megacities over lower-middle reaches of the YRB, using a near-real-time gridded daily CO2 emissions dataset. We suggest that the predominant sources of CO2 emissions in these 8 megacities are from the power and industrial sectors. In comparison to the average emissions for August in 2020 and 2021, the heatwave event led to a total increase in power sector emissions of approximately 2.70 Mt CO2, potentially due to the increase in urban cooling demand. Suzhou experienced the largest increase, with a rise of 1.12 Mt CO2 (12.88 %). Importantly, we observed that changes in daily power emissions exhibited strong linear relationships with temperatures during the heatwave, albeit varying sensitivities across different megacities (with an average of 0.0079 ±â€¯0.0076 Mt d-1 °C-1). Conversely, we find that industrial emissions decreased by a total of 8.45 Mt CO2, with Shanghai seeing the largest decrease of 4.71 Mt CO2, while Hangzhou experienced the largest relative decrease (-21.22 %). It is noteworthy that the majority of megacities rebounded in industrial emissions following the conclusion of the heatwave. We convincingly suggest a tight linkage between the reductions in industrial emissions and China's policy to ensure household power supply. Overall, the reduction in industrial emissions offset the increase in power sector emissions, resulting in weaker emissions for majority of megacities during the heatwave. Despite remaining uncertainties in the emissions data, our study may offer valuable insights into the complexities of anthropogenic CO2 emissions in megacities amidst frequent summer heatwaves intensified by greenhouse warming.

Impacts of marine heatwaves in coastal ecosystems depend on local environmental conditions.

Marine heatwaves (MHWs), increasing in duration and intensity because of climate change, are now a major threat to marine life and can have lasting effects on the structure and function of ecosystems. However, the responses of marine taxa and ecosystems to MHWs can be highly variable, making predicting and interpreting biological outcomes a challenge. Here, we review how biological responses to MHWs, from individuals to ecosystems, are mediated by fine-scale spatial variability in the coastal marine environment (hereafter, local gradients). Viewing observed responses through a lens of ecological theory, we present a simple framework of three 'resilience processes' (RPs) by which local gradients can influence the responses of marine taxa to MHWs. Local gradients (1) influence the amount of stress directly experienced by individuals, (2) facilitate local adaptation and acclimatization of individuals and populations, and (3) shape community composition which then influences responses to MHWs. We then synthesize known examples of fine-scale gradients that have affected responses of benthic foundation species to MHWs, including kelp forests, coral reefs, and seagrass meadows and link these varying responses to the RPs. We present a series of case studies from various marine ecosystems to illustrate the differential impacts of MHWs mediated by gradients in both temperature and other co-occurring drivers. In many cases, these gradients had large effect sizes with several examples of local gradients causing a 10-fold difference in impacts or more (e.g., survival, coverage). This review highlights the need for high-resolution environmental data to accurately predict and manage the consequences of MHWs in the context of ongoing climate change. While current tools may capture some of these gradients already, we advocate for enhanced monitoring and finer scale integration of local environmental heterogeneity into climate models. This will be essential for developing effective conservation strategies and mitigating future marine biodiversity loss.

Metagenomic insights into the prokaryotic communities of heavy metal-contaminated hypersaline soils.

Saline soils and their microbial communities have recently been studied in response to ongoing desertification of agricultural soils caused by anthropogenic impacts and climate change. Here we describe the prokaryotic microbiota of hypersaline soils in the Odiel Saltmarshes Natural Area of Southwest Spain. This region has been strongly affected by mining and industrial activity and feature high levels of certain heavy metals. We sequenced 18 shotgun metagenomes through Illumina NovaSeq from samples obtained from three different areas in 2020 and 2021. Taxogenomic analyses demonstrate that these soils harbored equal proportions of archaea and bacteria, with Methanobacteriota, Pseudomonadota, Bacteroidota, Gemmatimonadota, and Balneolota as most abundant phyla. Functions related to the transport of heavy metal outside the cytoplasm are among the most relevant features of the community (i.e., ZntA and CopA enzymes). They seem to be indispensable to avoid the increase of zinc and copper concentration inside the cell. Besides, the archaeal phylum Methanobacteriota is the main arsenic detoxifier within the microbiota although arsenic related genes are widely distributed in the community. Regarding the osmoregulation strategies, "salt-out" mechanism was identified in part of the bacterial population, whereas "salt-in" mechanism was present in both domains, Bacteria and Archaea. De novo biosynthesis of two of the most universal compatible solutes was detected, with predominance of glycine betaine biosynthesis (betAB genes) over ectoine (ectABC genes). Furthermore, doeABCD gene cluster related to the use of ectoine as carbon and energy source was solely identified in Pseudomonadota and Methanobacteriota.

Estimation of return dates and return levels of extreme rainfall in the city of Douala, Cameroon.

The problem of extreme phenomena with a more precise estimation of their return periods for early warnings, notably to preserve the safety of populations and properties, arises all over the world. This work develops another aspect in the estimation of Return Levels (RLs) and Return Periods (RPs) of extreme precipitation in particular and natural risk in general. In particular, it gives the Return Dates (RDs) with their Confidence Intervals (CIs). The RPs, the RLs and their CIs for extreme rainfall were also investigated. These estimates were made by approaching the peak over a threshold chosen by the Generalized Pareto Distribution (GPD). The CIs of RPs and RLs were determined by the Delta method. The daily rainfall data used were obtained from the data of the synoptic report for the period 2011 to 2021 for the Douala weather station (more details can be found on http://www.ogimet.com/guia.phtml.en). To validate the methods used, real cases of floods occurred in Douala city were considered: for example, a local press compiled flood dates and mentioned that a flood occurred on the April 16, 2013 in this city. Following the data of synoptic report, the corresponding amount of rainfall was around 150 mm. The results obtained have shown a RD on the August 12, 2014. The confidence intervals of return levels and return dates determined by the Delta method were [131.66, 168.456] and [June 23, 2014, January 02, 2015], respectively. These results are in agreement with the data of synoptic report since the rainfall amounts was 132.2 mm (belonging to the confidence interval of return levels), on the August 11, 2014 (belonging to the confidence interval of return dates). These predictions of RDs and RLs with their CIs, at reasonable time scales, can help for efficient management of floods and thus, improve early warnings for safety of populations and goods.

Modified median quartile double ranked set sampling for estimation of population mean.

Environmental monitoring and assessment aim to gather data economically, without bias, using efficient and cost-effective sampling methods. One such traditional method is Ranked Set Sampling (RSS), often employed to achieve observational economy. This article introduces an innovative two-stage sampling approach for ranked set sampling (RSS) to get a more precise estimate of the population mean. Modified Median Quartile Double Ranked Set Sampling (MMQDRSS) highlights the ranked base technique's potential as a cost-effective sampling method. To evaluate the performance of the proposed estimator by using real-life data and conducting a simulation study to compare the relative efficiency of the proposed estimator with some existing methods.

Lessons from Extremophiles: Functional Adaptations and Genomic Innovations across the Eukaryotic Tree of Life.

From hydrothermal vents, to glaciers, to deserts, research in extreme environments has reshaped our understanding of how and where life can persist. Contained within the genomes of extremophilic organisms are the blueprints for a toolkit to tackle the multitude of challenges of survival in inhospitable environments. As new sequencing technologies have rapidly developed, so too has our understanding of the molecular and genomic mechanisms that have facilitated the success of extremophiles. Although eukaryotic extremophiles remain relatively understudied compared to bacteria and archaea, an increasing number of studies have begun to leverage 'omics tools to shed light on eukaryotic life in harsh conditions. In this perspective paper, we highlight a diverse breadth of research on extremophilic lineages across the eukaryotic tree of life, from microbes to macrobes, that are collectively reshaping our understanding of molecular innovations at life's extremes. These studies are not only advancing our understanding of evolution and biological processes but are also offering a valuable roadmap on how emerging technologies can be applied to identify cellular mechanisms of adaptation to cope with life in stressful conditions, including high and low temperatures, limited water availability, and heavy metal habitats. We shed light on patterns of molecular and organismal adaptation across the eukaryotic tree of life and discuss a few promising research directions, including investigations into the role of horizontal gene transfer in eukaryotic extremophiles and the importance of increasing phylogenetic diversity of model systems.

ICDXML: enhancing ICD coding with probabilistic label trees and dynamic semantic representations.

Accurately assigning standardized diagnosis and procedure codes from clinical text is crucial for healthcare applications. However, this remains challenging due to the complexity of medical language. This paper proposes a novel model that incorporates extreme multi-label classification tasks to enhance International Classification of Diseases (ICD) coding. The model utilizes deformable convolutional neural networks to fuse representations from hidden layer outputs of pre-trained language models and external medical knowledge embeddings fused using a multimodal approach to provide rich semantic encodings for each code. A probabilistic label tree is constructed based on the hierarchical structure existing in ICD labels to incorporate ontological relationships between ICD codes and enable structured output prediction. Experiments on medical code prediction on the MIMIC-III database demonstrate competitive performance, highlighting the benefits of this technique for robust clinical code assignment.

Variation of nitrate sources affected by precipitation with different intensities in groundwater in the piedmont plain area of alluvial-pluvial fan.

A substantial reservoir of nitrogen (N) in soil poses a threat to the quality and safety of shallow groundwater, especially under extreme precipitation that hastens nitrogen leaching into groundwater. However, the specific impact of varying precipitation intensities on the concentration and sources of nitrate (NO3-) in groundwater across diverse hydrogeological zones and land uses remains unclear. This study aims to elucidate the fluctuations in NO3- concentration, sources, and controlling factors in shallow groundwater under different intensities of precipitation (extreme heavy precipitation and continuous heavy precipitation) in a typical alluvial-pluvial fan of the North China Plain by using stable isotopes (δ2H-H2O, δ18O-H2O, δ15N-NO3-, δ18O-NO3-), hydrochemical analyses and the SIAR model. Affected by extreme heavy precipitation the depleted isotopes of δ2H-H2O and δ18O-H2O in groundwater of the entire area suggested the rapid recharge of fast flow by precipitation. The enriched isotopes of δ2H-H2O and δ18O-H2O of north part in alluvial fan after continuous heavy precipitation showed the recharge of translatory flow of soil water. NO3-concentrations increased to 78.9 mg/L after extreme heavy precipitation and increased to 105.3 mg/L after continuous heavy precipitation when compared to those in normal year (56.8 mg/L) of north part of the alluvial fan. However, NO3- concentrations had slight variation after continuous heavy precipitation of south part of the fan due to the deep vadose zone. The contribution ratio of sources of NO3- in groundwater by using SIAR analysis revealed manure & sewage (MS) as the primary NO3- source (accounting for 59.7-78.1%) before extreme heavy precipitation, chemical fertilizer (CF) making a minor contribution (6.9-17.3%). Different precipitation events and land use types lead to changes in NO3- sources. Affected by extreme heavy precipitation, the contribution of MS decreased while CF increased, particularly in vegetables (26.2-28.1%) and farmland (29.2-34.7%). After continuous heavy precipitation, MS increased again, particularly in vegetables (50.0%) and farmlands (20.4-66.4%), with CF either increasing or remaining steady. This indicated that continuous heavy precipitation accelerated the leaching of nitrogen (organic manure application) stored in deep soil to groundwater and it has a larger influence on the increasing of NO3- concentrations of groundwater than extreme heavy precipitation which carried nitrogen (chemical fertilizer application) in shallow soil to groundwater by fast flow. These findings underscore the importance of considering soil chemical N stores and their implications for groundwater contamination mitigation under future extreme climate scenarios, particularly in agricultural management practices.

Wildfires impact on PM2.5 concentration in galicia Spain.

Wildfire intensity and severity have been increasing in the Iberian Peninsula in recent years, particularly in the Galicia region, due to rising temperatures and accumulating drier combustible vegetation in unmanaged lands. This leads to substantial emissions of air pollutants, notably fine particles (PM2.5), posing a risk to public health. This study aims to assess the impact of local and regional wildfires on PM2.5 levels in Galicia's main cities and their implications for air quality and public health. Over a decade (2013-2022), PM2.5 data during wildfire seasons were analyzed using statistical methods and Lagrangian tracking to monitor smoke plume evolution. The results reveal a notable increase in PM2.5 concentration during the wildfire season (June-November) in Galicia, surpassing health guidelines during extreme events and posing a significant health risk to the population. Regional wildfire analyses indicate that smoke plumes from Northern Portugal contribute to pollution in Galician cities, influencing the seasonality of heightened PM2.5 levels. During extensive wildfires, elevated PM2.5 concentration values persisted for several days, potentially exacerbating health concerns in Galicia. These findings underscore the urgency of implementing air pollution prevention and management measures in the region, including developing effective alerts for large-scale events and improved wildfire management strategies to mitigate their impact on air quality in Galician cities.

Are we joining the One Health dots? A scoping review of research on the one health effects of extreme weather events in eastern Australia.

Extreme weather events such as floods, bushfires, cyclones, and drought, are projected to increase in eastern Australia. Understanding how these events influence the combined, sustainable well-being of humans, animals, and ecosystems - that is One Health - will enable development of transdisciplinary and ultimately more effective interventions. A scoping review was conducted to explore the research associated with the effects of extreme weather events in eastern Australia using a One Health lens, specifically identifying the type of extreme weather events studied, the research conducted in the context of One Health, and gaps to inform improved One Health implementation. The review followed JBI guidelines (based on PRISMA). Eligible research was peer-reviewed, in English, and published since 2007, in which primary research studies investigated the impact of extreme weather events in eastern Australia on at least two of ecosystems, human health, and animal health. Using structured search terms, six databases were searched. Following removal of duplicates, 870 records were screened by two reviewers. Eleven records were eligible for data extraction and charting. The scope of extreme weather events studied was relatively limited, with studies in flood and bushfire settings predominating, but relatively little research on cyclones. Major health themes included more than the impact of extreme weather events on physical health (zoonotic and vector-borne diseases) through investigation of social well-being and mental health in the context of the human-animal bond in evacuation behaviors and drought. Research gaps include studies across a broader range of extreme weather events and health topics, as well as a more comprehensive approach to including the impacts of extreme weather events on all three domains of One Health. The limited research focus inevitably translates to limited recommendations for policy, planning and response to manage extreme weather event emergencies. Given the expected increase in frequency of these events, there is a critical need for more comprehensive primary research to better identify strategies and facilitate implementation of One Health promotion for improved outcomes in extreme weather event emergencies.

Shifting from traditional landslide occurrence modeling to scenario estimation with a "glass-box" machine learning.

Extreme rainfall events represent one of the main triggers of landslides. As climate change continues to reshape global weather patterns, the frequency and intensity of such events are increasing, amplifying landslide occurrences and associated threats to communities. In this contribution, we analyze relationships between landslide occurrence and extreme rainfall events by using a "glass-box" machine learning model, namely Explainable Boosting Machine. What sets these models as a "glass-box" technique is their exact intelligibility, offering transparent explanations for their predictions. We leverage these capabilities to model the landslide occurrence induced by an extreme rainfall event in the form of spatial probability (i.e., susceptibility). In doing so, we use the heavy rainfall event in the Misa River Basin (Central Italy) on September 15, 2022. Notably, we introduce a rainfall anomaly among our set of predictors to express the intensity of the event compared to past rainfall patterns. Spatial variable selection and model evaluation through random and spatial routines are incorporated into our protocol. Our findings highlight the critical role of the rainfall anomaly as the most important variable in modeling landslide susceptibility. Furthermore, we leverage the dynamic nature of such a variable to estimate landslide occurrence under different rainfall scenarios.

Research on a Method for Classifying Bolt Corrosion Based on an Acoustic Emission Sensor System.

High-strength bolts play a crucial role in ultra-high-pressure equipment such as bridges and railway tracks. Effective monitoring of bolt conditions is of paramount importance for common fault repair and accident prevention. This paper aims to detect and classify bolt corrosion levels accurately. We design and implement a bolt corrosion classification system based on a Wireless Acoustic Emission Sensor Network (WASN). Initially, WASN nodes collect high-speed acoustic emission (AE) signals from bolts. Then, the ReliefF feature selection algorithm is applied to identify the optimal feature combination. Subsequently, the Extreme Learning Machine (ELM) model is utilized for bolt corrosion classification. Additionally, to achieve high prediction accuracy, an improved goose algorithm (GOOSE) is employed to ensure the most suitable parameter combination for the ELM model. Experimental measurements were conducted on five classes of bolt corrosion levels: 0%, 25%, 50%, 75%, and 100%. The classification accuracy obtained using the proposed method was at least 98.04%. Compared to state-of-the-art classification diagnostic models, our approach exhibits superior AE signal recognition performance and stronger generalization ability to adapt to variations in working conditions.

Aerosol atmospheric rivers: patterns, impacts, and societal insights.

This study focuses on understanding how aerosols are transported over long distances, especially during extreme events. Leveraging the integrated vapour transport (IVT) based atmospheric river (AR) algorithm to integrated aerosol transport (IAT) to detect the aerosol atmospheric rivers (AARs) for key aerosol species such as black carbon (BC), organic carbon (OC), dust (DU), sea salt (SS), and sulphate (SU). The present study also assesses the occurrence, intensity, and societal impacts of AARs globally during 2015-2022 on a spatiotemporal resolution of 1.5° × 1.5° and 6 h, respectively. The detection algorithm found a total number of 128,261 AARs found globally for key aerosol species. However, the availability of BC, OC, and SU AARs is most common and intense in densely populated areas like the Indus-Brahmaputra-Ganga (IBG) plains (~ 15-20 AAR days/year), Eastern China (~ 25-40 AAR days/year), and Japan (~ 20-30 AAR days/year), where human activities including agriculture burning contribute to their formation. DU AARs, on the other hand, are more prevalent in Northern Africa (~ 15 AAR days/year), the Gulf (~ 5-10 AAR days/year), the USA, and the Amazon rainforests. SS AARs share similar characteristics with atmospheric rivers and are more intense in higher latitudes and over the oceans (~ 30-40 AAR days/year). The study also validates its findings by analysing recent extreme events involving BC and DU worldwide. The potential applications of specific AARs could assist us in identifying the causes of snow darkening, reducing snow cover area, and accelerating melting rate. Moreover, AARs could aid in quantifying the health risks associated with severe air pollution.

AIE-YOLO: Effective object detection method in extreme driving scenarios via adaptive image enhancement.

The widespread research and implementation of visual object detection technology have significantly transformed the autonomous driving industry. Autonomous driving relies heavily on visual sensors to perceive and analyze the environment. However, under extreme weather conditions, such as heavy rain, fog, or low light, these sensors may encounter disruptions, resulting in decreased image quality and reduced detection accuracy, thereby increasing the risk for autonomous driving. To address these challenges, we propose adaptive image enhancement (AIE)-YOLO, a novel object detection method to enhance road object detection accuracy under extreme weather conditions. To tackle the issue of image quality degradation in extreme weather, we designed an improved adaptive image enhancement module. This module dynamically adjusts the pixel features of road images based on different scene conditions, thereby enhancing object visibility and suppressing irrelevant background interference. Additionally, we introduce a spatial feature extraction module to adaptively enhance the model's spatial modeling capability under complex backgrounds. Furthermore, a channel feature extraction module is designed to adaptively enhance the model's representation and generalization abilities. Due to the difficulty in acquiring real-world data for various extreme weather conditions, we constructed a novel benchmark dataset named extreme weather simulation-rare object dataset. This dataset comprises ten types of simulated extreme weather scenarios and is built upon a publicly available rare object detection dataset. Extensive experiments conducted on the extreme weather simulation-rare object dataset demonstrate that AIE-YOLO outperforms existing state-of-the-art methods, achieving excellent detection performance under extreme weather conditions.