Melanin-based color variation in response to changing climates in snakes.

Melanism, the process of heavier melanin deposition, can interact with climate variation at both micro and macro scales, ultimately influencing color evolution in organisms. While the ecological processes regulating melanin production in relation to climate have been extensively studied, intraspecific variations of melanism are seldom considered. Such scientific gap hampers our understanding of how species adapt to rapidly changing climates. For example, dark coloration may lead to higher heat absorption and be advantageous in cool climates, but also in hot environments as a UV or antimicrobial protection mechanism. To disentangle such opposing predictions, here we examined the effect of climate on shaping melanism variation in 150 barred grass snakes (Natrix helvetica) and 383 green whip snakes (Hierophis viridiflavus) across Italy. By utilizing melanistic morphs (charcoal and picturata in N. helvetica, charcoal and abundistic in H. viridiflavus) and compiling observations from 2002 to 2021, we predicted that charcoal morphs in H. viridiflavus would optimize heat absorption in cold environments, while offering protection from excessive UV radiation in N. helvetica within warm habitats; whereas picturata and abundistic morphs would thrive in humid environments, which naturally have a denser vegetation and wetter substrates producing darker ambient light, thus providing concealment advantages. While picturata and abundistic morphs did not align with our initial humidity expectations, the charcoal morph in N. helvetica is associated with UV environments, suggesting protection mechanisms against damaging solar radiation. H. viridiflavus is associated with high precipitations, which might offer antimicrobial protection. Overall, our results provide insights into the correlations between melanin-based color morphs and climate variables in snake populations. While suggestive of potential adaptive responses, future research should delve deeper into the underlying mechanisms regulating this relationship.

Multi-step ahead forecasting of electrical conductivity in rivers by using a hybrid Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) model enhanced by Boruta-XGBoost feature selection algorithm.

Electrical conductivity (EC) is widely recognized as one of the most essential water quality metrics for predicting salinity and mineralization. In the current research, the EC of two Australian rivers (Albert River and Barratta Creek) was forecasted for up to 10 days using a novel deep learning algorithm (Convolutional Neural Network combined with Long Short-Term Memory Model, CNN-LSTM). The Boruta-XGBoost feature selection method was used to determine the significant inputs (time series lagged data) to the model. To compare the performance of Boruta-XGB-CNN-LSTM models, three machine learning approaches-multi-layer perceptron neural network (MLP), K-nearest neighbour (KNN), and extreme gradient boosting (XGBoost) were used. Different statistical metrics, such as correlation coefficient (R), root mean square error (RMSE), and mean absolute percentage error, were used to assess the models' performance. From 10 years of data in both rivers, 7 years (2012-2018) were used as a training set, and 3 years (2019-2021) were used for testing the models. Application of the Boruta-XGB-CNN-LSTM model in forecasting one day ahead of EC showed that in both stations, Boruta-XGB-CNN-LSTM can forecast the EC parameter better than other machine learning models for the test dataset (R = 0.9429, RMSE = 45.6896, MAPE = 5.9749 for Albert River, and R = 0.9215, RMSE = 43.8315, MAPE = 7.6029 for Barratta Creek). Considering the better performance of the Boruta-XGB-CNN-LSTM model in both rivers, this model was used to forecast 3-10 days ahead of EC. The results showed that the Boruta-XGB-CNN-LSTM model is very capable of forecasting the EC for the next 10 days. The results showed that by increasing the forecasting horizon from 3 to 10 days, the performance of the Boruta-XGB-CNN-LSTM model slightly decreased. The results of this study show that the Boruta-XGB-CNN-LSTM model can be used as a good soft computing method for accurately predicting how the EC will change in rivers.

Temporal dynamics of depressive symptoms and cognitive decline in the oldest old: dynamic time warp analysis of the Leiden 85-plus study.

BACKGROUND: The prevalence of depressive symptoms and cognitive decline increases with age. We investigated their temporal dynamics in individuals aged 85 and older across a 5-year follow-up period. METHODS: Participants were selected from the Leiden 85-plus study and were eligible if at least three follow-up measurements were available (325 of 599 participants). Depressive symptoms were assessed at baseline and at yearly assessments during a follow-up period of up to 5 years, using the 15-item Geriatric Depression Scale (GDS-15). Cognitive decline was measured through various tests, including the Mini Mental State Exam, Stroop test, Letter Digit Coding test and immediate and delayed recall. A novel method, dynamic time warping analysis, was employed to model their temporal dynamics within individuals, in undirected and directed time-lag analyses, to ascertain whether depressive symptoms precede cognitive decline in group-level aggregated results or vice versa. RESULTS: The 325 participants were all 85 years of age at baseline; 68% were female, and 45% received intermediate to higher education. Depressive symptoms and cognitive functioning significantly covaried in time, and directed analyses showed that depressive symptoms preceded most of the constituents of cognitive impairment in the oldest old. Of the GDS-15 symptoms, those with the strongest outstrength, indicating changes in these symptoms preceded subsequent changes in other symptoms, were worthlessness, hopelessness, low happiness, dropping activities/interests, and low satisfaction with life (all P's < 0.01). CONCLUSION: Depressive symptoms preceded cognitive impairment in a population based sample of the oldest old.

A causal machine-learning framework for studying policy impact on air pollution: A case-study in COVID-19 lockdowns.

When studying the impact of policy interventions or natural experiments on air pollution, such as new environmental policies and opening or closing an industrial facility, careful statistical analysis is needed to separate causal changes from other confounding factors. Using COVID-19 lockdowns as a case-study, we present a comprehensive framework for estimating and validating causal changes from such perturbations. We propose using flexible machine learning-based comparative interrupted time series (CITS) models for estimating such a causal effect. We outline the assumptions required to identify causal effects, showing that many common methods rely on strong assumptions that are relaxed by machine learning models. For empirical validation, we also propose a simple diagnostic criterion, guarding against false effects in baseline years when there was no intervention. The framework is applied to study the impact of COVID-19 lockdowns on NO2 in the eastern US. The machine learning approaches guard against false effects better than common methods and suggest decreases in NO2 in Boston, New York City, Baltimore, and Washington D.C. The study showcases the importance of our validation framework in selecting a suitable method and the utility of a machine learning based CITS model for studying causal changes in air pollution time series.

Did the COVID-19 quarantine policies applied in Cochabamba, Bolivia mitigated cases successfully? an interrupted time series analysis.

BACKGROUND: The COVID-19 pandemic prompted varied policy responses globally, with Latin America facing unique challenges. A detailed examination of these policies' impacts on health systems is crucial, particularly in Bolivia, where information about policy implementation and outcomes is limited. OBJECTIVE: To describe the COVID-19 testing trends and evaluate the effects of quarantine measures on these trends in Cochabamba, Bolivia. METHODS: Utilizing COVID-19 testing data from the Cochabamba Department Health Service for the 2020-2022 period. Stratified testing rates in the health system sectors were first estimated followed by an interrupted time series analysis using a quasi-Poisson regression model for assessing the quarantine effects on the mitigation of cases during surge periods. RESULTS: The public sector reported the larger percentage of tests (65%), followed by the private sector (23%) with almost double as many tests as the public-social security sector (11%). In the time series analysis, a correlation between the implementation of quarantine policies and a decrease in the slope of positive rates of COVID-19 cases was observed compared to periods without or with reduced quarantine policies. CONCLUSION: This research underscores the local health system disparities and the effectiveness of stringent quarantine measures in curbing COVID-19 transmission in the Cochabamba region. The findings stress the importance of the measures' intensity and duration, providing valuable lessons for Bolivia and beyond. As the global community learns from the pandemic, these insights are critical for shaping resilient and effective health policy responses.

Main findings: The findings highlight the importance of stringent quarantine measures in managing infectious disease outbreaks, offering valuable insights for policymakers worldwide in strategizing effective public health interventions.Added knowledge: By providing a detailed analysis of testing disparities and quarantine policies' effectiveness within a specific Latin American context, our research fills a critical gap in understanding their impacts on health system responses and disease control.Global health impact for policy and action: The findings highlight the importance of stringent quarantine measures in managing infectious disease outbreaks, offering valuable insights for policymakers worldwide in strategizing effective public health interventions.

A Bayesian non-stationary heteroskedastic time series model for multivariate critical care data.

We propose a multivariate GARCH model for non-stationary health time series by modifying the observation-level variance of the standard state space model. The proposed model provides an intuitive and novel way of dealing with heteroskedastic data using the conditional nature of state-space models. We follow the Bayesian paradigm to perform the inference procedure. In particular, we use Markov chain Monte Carlo methods to obtain samples from the resultant posterior distribution. We use the forward filtering backward sampling algorithm to efficiently obtain samples from the posterior distribution of the latent state. The proposed model also handles missing data in a fully Bayesian fashion. We validate our model on synthetic data and analyze a data set obtained from an intensive care unit in a Montreal hospital and the MIMIC dataset. We further show that our proposed models offer better performance, in terms of WAIC than standard state space models. The proposed model provides a new way to model multivariate heteroskedastic non-stationary time series data. Model comparison can then be easily performed using the WAIC.

Erratum: Effects of COVID-19-targeted non-pharmaceutical interventions on pediatric hospital admissions in North Italian hospitals, 2017 to 2022: a quasi-experimental study interrupted time-series analysis.

[This corrects the article DOI: 10.3389/fpubh.2024.1393677.].

Leveraging VQ-VAE tokenization for autoregressive modeling of medical time series.

In this work, we present CodeAR, a medical time series generative model for electronic health record (EHR) synthesis. CodeAR employs autoregressive modeling on discrete tokens obtained using a vector quantized-variational autoencoder (VQ-VAE), which addresses key challenges of accurate distribution modeling and patient privacy preservation in the medical domain. The proposed model is trained with next-token prediction instead of a regression problem for more accurate distribution modeling, where the autoregressive property of CodeAR is useful to capture the inherent causality in time series data. In addition, the compressive property of the VQ-VAE prevents CodeAR from memorizing the original training data, which ensures patient privacy. Experimental results demonstrate that CodeAR outperforms the baseline autoregressive-based and GAN-based models in terms of maximum mean discrepancy (MMD) and Train on Synthetic, Test on Real tests. Our results highlight the effectiveness of autoregressive modeling on discrete tokens, the utility of CodeAR in causal modeling, and its robustness against data memorization.

The Role of Robotics in Meeting Institutional Goals: A Unified Strategy to Facilitate Program Excellence.

PURPOSE: The rapid expansion of robotic surgical equipment necessitates a review of the needs and challenges faced by hospitals introducing robots for the first time to compete with experienced institutions. The aim of this study was to analyze the impact of robotic surgery on our hospital compared to open and laparoscopic surgery, examine internal transformations, and assess regional, domestic, and international implications. METHODS: A retrospective review was conducted of electronic medical records (EMRs) from 2019 to 2022 at Inha University Hospital, including patients who underwent common robotic procedures and equivalent open and laparoscopic operations. The study investigated clinical and operational performance changes in the hospital after the introduction of robotic technology. It also evaluated the operational effectiveness of robot implementation in local, national, and international contexts. To facilitate comparison with other hospitals, the data were transmitted to Intuitive Surgical, Inc. for analysis. The study was conducted in compliance with domestic personal information regulations and received approval from our Institutional Review Board. RESULTS: We analyzed EMR data from 3,147 patients who underwent surgical treatment. Over a period of 3.5 years, the adoption of robotic technology in a hospital setting significantly enhanced the technical skills of all professors involved. The introduction of robotic systems led to increased patient utilization of conventional surgical techniques, as well as a rise in the number of patients choosing robotic surgery. This collective trend contributed to an overall increase in patient numbers. This favorable evaluation of the operational effectiveness of our hospital's robot implementation in the context of local, national, and global factors is expected to positively influence policy changes. CONCLUSION: Stakeholders should embrace data science and evidence-based techniques to generate valuable insights from objective data, assess the health of robot-assisted surgery programs, and identify opportunities for improvement and excellence.

Innovative use of Australian cancer registry data for early detection of the effects of epidemics and other mass disruptions on cancer incidence.

BACKGROUND: Predictive modelling using pre-epidemic data have long been used to guide public health responses to communicable disease outbreaks and other health disruptions. In this study, cancer registry and related health data available 2-3 months from diagnosis were used to predict changes in cancer detection that otherwise would not have been identified until full registry processing was completed about 18-24 months later. A key question was whether these earlier data could be used to predict cancer incidence ahead of full processing by the cancer registry as a guide to more timely health responses. The setting was the Australian State of New South Wales, covering 31 % of the Australian population. The study year was 2020, the year of emergence of the COVID-19 pandemic. METHODS: Cancer detection in 2020 was modelled using data available 2-3 months after diagnosis. This was compared with data from full registry processing available from 2022. Data from pre-pandemic 2018 were used for exploratory model building. Models were tested using pre-pandemic 2019 data. Candidate predictor variables included pathology, surgery and radiation therapy reports, numbers of breast screens, colonoscopies, PSA tests, and melanoma excisions recorded by the universal Medical Benefits Schedule (MBS). Data were analysed for all cancers collectively and 5 leading types. RESULTS: Compared with full registry processing, modelled data for 2020 had a >95 % accuracy overall, indicating key points of inflexion of cancer detection over the COVID-disrupted 2020 period. These findings highlight the potential of predictive modelling of cancer-related data soon after diagnosis to reveal changes in cancer detection during epidemics and other health disruptions. CONCLUSIONS: Data available 2-3 months from diagnosis in the pandemic year indicated changes in cancer detection that were ultimately confirmed by fully-processed cancer registry data about 24 months later. This indicates the potential utility of using these early data in an early-warning system.

Marsh decrease was much faster than the water increase among the Yellow River Source wetlands during 1986-2022.

Wetlands are valuable and sensitive ecosystems that make them imperative to tracking the dynamics in their extent for sustainable management under global warming. Here we focused on the Yellow River Source (YRS) wetlands, which is renowned for hosting the world's largest plateau peat bog, unfortunately, it had experienced sharp degradation, threatening the safety of water supply for approximately 110 million people of the lower Yellow River basin. However, the lack of long-term, dense time-series data makes it challenging to assess its evolution trends and driving factors. Therefore, we developed a decision tree sample migration method based on Euclidean distance (ED) and Land Surface Water Index (LSWI), and successfully generated annual wetland mapping of YRS from 1986 to 2022 by utilizing the Landsat 5/7/8 datasets and Random Forest method. The average sample migration rate was 89.21 %, with an average overall accuracy of 95.49 %. We observed that the marsh area decreased by 2031 km2, marking a decline of 12.98 %, while the water area increased by 710 km2 (31.24 %) compared to 1986. Spatially, 10.96 % of marsh composition presents significant (P < 0.05) decline trend, which are mainly converted to grass (86 %), followed by impervious (10 %). There were 6.69 % of water composition showing significant (P < 0.05) increase trend, which are mainly sourced from impervious (82 %) and marsh (12 %). Grazing activities were more important forces than climate change for marsh degradation, while the water expansion was associated with recent rising temperature in YRS. The sample migration method we developed is proved to be feasible, robust, and effective for long-term wetland mapping. We suggest that wetland decision-makers need to focus on marsh degradation and reduce grazing intensity, so that fostering the sustainable and healthy wetlands in the Qinghai-Tibetan Plateau.

Machine learning-based prediction of clinical outcomes after traumatic brain injury: Hidden information of early physiological time series.

AIMS: To assess the predictive value of early-stage physiological time-series (PTS) data and non-interrogative electronic health record (EHR) signals, collected within 24 h of ICU admission, for traumatic brain injury (TBI) patient outcomes. METHODS: Using data from TBI patients in the multi-center eICU database, we focused on in-hospital mortality, neurological status based on the Glasgow Coma Score (mGCS) motor subscore at discharge, and prolonged ICU stay (PLOS). Three machine learning (ML) models were developed, utilizing EHR features, PTS signals collected 24 h after ICU admission, and their combination. External validation was performed using the MIMIC III dataset, and interpretability was enhanced using the Shapley Additive Explanations (SHAP) algorithm. RESULTS: The analysis included 1085 TBI patients. Compared to individual models and existing scoring systems, the combination of EHR and PTS features demonstrated comparable or even superior performance in predicting in-hospital mortality (AUROC = 0.878), neurological outcomes (AUROC = 0.877), and PLOS (AUROC = 0.835). The model's performance was validated in the MIMIC III dataset, and SHAP algorithms identified six key intervention points for EHR features related to prognostic outcomes. Moreover, the EHR results (All AUROC >0.8) were translated into online tools for clinical use. CONCLUSION: Our study highlights the importance of early-stage PTS signals in predicting TBI patient outcomes. The integration of interpretable algorithms and simplified prediction tools can support treatment decision-making, contributing to the development of accurate prediction models and timely clinical intervention.

Dataset of air pollutants (PM2.5, PM10, CO) concentrations in the export processing area of Dhaka, Bangladesh.

This study presents a valuable dataset on air quality in the densely populated Dhaka Export Processing Zone (DEPZ) of Bangladesh. It included a dataset of Particulate Matter (PM2.5, PM10) and CO concentrations with Air Quality Index (AQI) values. PM data was collected 24h, and CO data was collected 8h monthly from 2019 to 2023 using respirable dust sampler APS-113NL for PM2.5, APS-113BL for PM10, and LUTRON AQ9901SD Air Quality Monitor Data Logger used to measure CO concentration data. Data sampling locations are selected based on population density, and employment data for DEPZ is also included, highlighting a potential rise in population density. This article also forecasted pollutant concentrations, AQI values, and health hazards associated with air pollutants using the Auto Regressive Moving Average (ARIMA) model. The performance of the ARIMA model was also measured using root mean squared error (RMSE) and mean absolute error (MAE). However, this can be used to raise awareness among the public about the health hazards associated with air pollution and encourage them to take measures to reduce their exposure to air pollutants. In addition, this data can be instrumental for researchers and policymakers to assess air pollution risks, develop control strategies, and improve air quality in the DEPZ.

Changes in cannabis involvement in emergency department visits for anxiety disorders after cannabis legalization: a repeated cross-sectional study.

Background: An increasing number of countries have or are considering legalizing cannabis. One concern is that legalization of cannabis will result in increased cannabis use and in turn a higher prevalence of anxiety disorders. We examined changes in emergency department (ED) visits for anxiety disorders with cannabis involvement in Ontario, over a period that involved medical and non-medical cannabis legalization. Methods: This repeated cross-sectional population-based study identified all ED visits for anxiety disorders from residents of Ontario, Canada aged 10-105 between 2008 and 2022 (n = 15.7 million individuals). We used interrupted time series analyses to examine immediate and gradual changes in cannabis-involvement and alcohol-involvement (control condition) over four policy periods: medical cannabis legalization (January 2008-November 2015), expanded medical access (December 2015-September 2018), non-medical cannabis legalization with restrictions (October 2018-February 2020), and commercialization which overlapped with the COVID-19 pandemic (March 2020-December 2022). Poisson models were used to generate incidence rate ratios with 95% confidence intervals. Findings: Over the 14-year study, there were 438,700 individuals with one or more ED visits for anxiety disorders of which 3880 (0.89%) individuals had cannabis involvement and 6329 (1.45%) individuals had alcohol involvement. During the commercialization/COVID-19 period monthly rates of anxiety disorders with cannabis-involvement were 156% higher (0.11 vs 0.29 per 100,000 individuals) relative to the pre-legalization period, compared to a 27% increase for alcohol-involvement (0.27 vs 0.35 per 1100,000 individuals). Rates of anxiety ED visits with cannabis involvement per 100,000 individuals increased gradually over the study period with no immediate or gradual changes after expanded medical access, legalization with restrictions or commercialization/COVID-19. However, during the commercialization/COVID-19 period there were large declines in total anxiety disorder ED visits and anxiety disorder ED visits with alcohol-involvement. Consequently, during this period there was an immediate 31.4% relative increase in the proportion of anxiety visits with cannabis-involvement (incidence rate ratio [IRR], 1.31; 95% CI 1.05-1.65). Interpretation: We found large relative increases in anxiety disorder ED visits with cannabis involvement over a 14-year period involving medical and non-medical cannabis legalization. These findings may reflect increasing anxiety disorder problems from cannabis use, increasing self-medication of anxiety disorders with cannabis use, or both. The proportion of anxiety ED visits with cannabis involvement increased during the final period of the study but could have been the results of the market commercialization, COVID-19 or both and ongoing monitoring is indicated. Funding: Canadian Institutes of Health Research (grant #452360).

Impacts of Major Changes in China's COVID-19 Prevention and Control Policies on Emergency Department Visits: A Quasi-Experiment.

Objective: This study aims to evaluate the impact of COVID-19 prevention and control policies on the frequency of emergency department (ED) visits in a large tertiary hospital in central China, from January 2018 to September 2023. Methods: We conducted a multi-stage interrupted time series analysis to investigate the impact of various epidemic control policies on weekly ED visits at a tertiary hospital in Hunan Province, China. The study period ranged from January 1, 2018, to September 30, 2023, and was divided into four distinct periods: pre-epidemic, pandemic, normalized control, and end of control. Using a quasi-Poisson regression model, we examined the specific effects of these policies on emergency visits, with a particular focus on stratifying patients based on respiratory versus non-respiratory diseases. Results: Compared to the pre-pandemic period, the number of ED visits in a tertiary hospital decreased by 38.5% (95% CI: 25.1% to 49.8%) during the COVID-19 pandemic, of which the number of ED visits for respiratory diseases increased by 79.4% (95% CI: 13.2% to 177.2%) and the number of ED visits for non-respiratory diseases decreased by 45.9% (95% CI: -55.7% to -34.2%). After the end of the epidemic control, the total number of ED visits increased by 31.5% (95% CI: 19.1% to 45.0%), with the number of ED visits for respiratory diseases rising by 379.2% (95% CI: 275.9% to 511.8%), but with no significant change in the number of ED visits for non-respiratory emergencies. Conclusion: Control policies were associated with people avoiding emergency care for non-respiratory related reasons during the pandemic, while the end of control policies was associated with a sharp rise in emergency care for respiratory diseases. This study provides a scientific basis for the different changes in ED visits under the implementation of varying epidemic prevention and control policies.

Effects of pay-for-performance based antimicrobial stewardship on antimicrobial consumption and expenditure: An interrupted time series analysis.

Objectives: To evaluate the impact of pay-for-performance on antimicrobial consumption and antimicrobial expenditure in a large teaching hospital in Guangzhou, China. Methods: We collected data from hospital information system from January 2018 through September 2022 in the inpatient wards. Antimicrobial consumption was evaluated using antibiotic use density (AUD) and antibiotic use rate (AUR). The economic impact of intervention was assessed by antimicrobial expenditure percentage. The data was analyzed using interrupted time series (ITS) analysis. Results: Following the implementation of the intervention, immediate decreases in the level of AUD were observed in Department of Hematology Unit 3 (ß = -66.93 DDDs/100PD, P = 0.002), Urology (ß = -32.80 DDDs/100PD, P < 0.001), Gastrointestinal Surgery Unit 3 (ß = -11.44 DDDs/100PD, P = 0.03), Cardiac Surgery (ß = -14.30 DDDs/100PD, P = 0.01), ICU, Unit 2 (ß = -81.91 DDDs/100PD, P = 0.02) and Cardiothoracic Surgery ICU (ß = -41.52 DDDs/100PD, P = 0.05). Long-term downward trends in AUD were also identified in Organ Transplant Unit (ß = -1.64 DDDs/100PD, P = 0.02). However, only Urology (ß = -6.56 DDDs/100PD, P = 0.02) and Gastrointestinal Surgery Unit 3 (ß = -8.50 %, P = 0.01) showed an immediate decrease in AUR, and long-term downward trends in AUR were observed in Pediatric ICU (ß = -1.88 %, P = 0.05) and ICU Unit 1 (ß = -0.55 %, P = 0.02). Conclusion: This study demonstrates that the adoption of pay-for-performance effectively reduces antibiotic consumption in specific departments of a hospital in Guangzhou in the short term. However, it is important to recognize that the long-term impact of such interventions is often limited. Additionally, it should be noted that the overall effectiveness of the intervention across the entire hospital was not significant.

Intra-annual vegetation changes and spatial variation in China over the past two decades based on remote sensing and time-series clustering.

Vegetation is an important link between land, atmosphere, and water, making its changes of great significance. However, existing research has predominantly focused on long-term vegetation changes, neglecting the intra-annual variations of vegetation. Hence, this study is based on the Enhanced Vegetation Index (EVI) data from 2000 to 2022, with a time step of 16 days, to analyze the intra-annual patterns of vegetation changes in China. The average intra-annual EVI values for each municipal-level administrative region were calculated, and the time-series k-means clustering algorithm was employed to divide these regions, exploring the spatial variations in China's intra-annual vegetation changes. Finally, the ridge regression and random forest methods were utilized to assess the drivers of intra-annual vegetation changes. The results showed that: (1) China's vegetation status exhibits a notable intra-annual variation pattern of "high in summer and low in winter," and the changes are more pronounced in the northern regions than in the southern regions; (2) the intra-annual vegetation changes exhibit remarkable regional disparities, and China can be optimally clustered into four distinct clusters, which align well with China's temperature and precipitation zones; and (3) the intra-annual vegetation changes demonstrate significant correlations with meteorological factors such as dew point temperature, precipitation, maximum temperature, and sea-level pressure. In conclusion, our study reveals the characteristics, spatial patterns and driving forces of intra-annual vegetation changes in China, which contribute to explaining ecosystem response mechanisms, providing valuable insights for ecological research and the formulation of ecological conservation and management strategies.

A data-driven method for estimating sewer inflow and infiltration based on temperature and conductivity monitoring.

Quantitation of sewer inflow and infiltration (I/I) is important for maintaining efficient wastewater transport and treatment. I/I flows can be quantified based on flow rate and water quality measurements. Flow rate-based methods require continuous monitoring of flow rates using flow meters that are costly and prone to fouling. In comparison, conductivity and temperature, as simple water quality parameters, are more easily measurable with more cost-effective and reliable sensors. In this study, a data-driven methodology is developed for estimating I/I flows based on online conductivity and temperature measurements. A Prophet-model-based analytic algorithm is first developed to reconstruct the temperature and conductivity profiles of the base wastewater flow (BWF) from the measured temperature and conductivity time series. The algorithm is shown to be able to reconstruct the BWF temperature and conductivity profiles in two monitored catchments. The reconstructed BWF data are then incorporated into mass/energy balance equations for estimating I/I flows from the measured temperature and conductivity data. The overall I/I quantification method is finally demonstrated using simulation studies of a real-life sewer network and validated against the known I/I flows. This work provides a reliable method for I/I quantification based on simple measurements.

Research on Active Safety Situation of Road Passenger Transportation Enterprises: Evaluation, Prediction, and Analysis.

The road passenger transportation enterprise is a complex system, requiring a clear understanding of their active safety situation (ASS), trends, and influencing factors. This facilitates transportation authorities to promptly receive signals and take effective measures. Through exploratory factor analysis and confirmatory factor analysis, we delved into potential factors for evaluating ASS and extracted an ASS index. To predict obtaining a higher ASS information rate, we compared multiple time series models, including GRU (gated recurrent unit), LSTM (long short-term memory), ARIMA, Prophet, Conv_LSTM, and TCN (temporal convolutional network). This paper proposed the WDA-DBN (water drop algorithm-Deep Belief Network) model and employed DEEPSHAP to identify factors with higher ASS information content. TCN and GRU performed well in the prediction. Compared to the other models, WDA-DBN exhibited the best performance in terms of MSE and MAE. Overall, deep learning models outperform econometric models in terms of information processing. The total time spent processing alarms positively influences ASS, while variables such as fatigue driving occurrences, abnormal driving occurrences, and nighttime driving alarm occurrences have a negative impact on ASS.

A TCN-Linear Hybrid Model for Chaotic Time Series Forecasting.

The applications of deep learning and artificial intelligence have permeated daily life, with time series prediction emerging as a focal area of research due to its significance in data analysis. The evolution of deep learning methods for time series prediction has progressed from the Convolutional Neural Network (CNN) and the Recurrent Neural Network (RNN) to the recently popularized Transformer network. However, each of these methods has encountered specific issues. Recent studies have questioned the effectiveness of the self-attention mechanism in Transformers for time series prediction, prompting a reevaluation of approaches to LTSF (Long Time Series Forecasting) problems. To circumvent the limitations present in current models, this paper introduces a novel hybrid network, Temporal Convolutional Network-Linear (TCN-Linear), which leverages the temporal prediction capabilities of the Temporal Convolutional Network (TCN) to enhance the capacity of LSTF-Linear. Time series from three classical chaotic systems (Lorenz, Mackey-Glass, and Rossler) and real-world stock data serve as experimental datasets. Numerical simulation results indicate that, compared to classical networks and novel hybrid models, our model achieves the lowest RMSE, MAE, and MSE with the fewest training parameters, and its R2 value is the closest to 1.