Average Time Series Research Articles

Time series modeling of rainfall and lake elevation in relation to breaching events at the Lake Earl and Tolowa lagoon system, coastal northern California

I evaluated trends in spatial and temporal variability in historical levels of rainfall, water elevation, and breach events for lakes Earl, Tolowa, and their combined lagoon system along the coast of northern California. I examined the efficacy of time series analyses to model and forecast rainfall and lake elevation at a regional scale from 2008 to 2021. I employed semi-parametric Generalized Additive Model regression to investigate the historical relationship between anthropogenic breaching of the lagoon and simultaneous occurrences of environmental parameters to better understand conditions surrounding each breach event. Evaluation of the central tendency of rainfall and surface lake elevation showed high fluctuations in their mean, positive skewed, and leptokurtic curves. Augmented Dickey-Fuller tests found that seasonal rainfall was stationary, but surface lake elevation attained stationarity only after the first seasonal difference. Decomposition of each time series and MannKendall and Sen’s slope estimators, found a significant decreasing trend in seasonal surface lake elevation but no trend was found in rainfall. Seasonal Autoregressive Integrated Moving Average (SARIMA) time series analysis and diagnostic tests of stability and reliability found best fit models for rainfall (SARIMA[1,0,0] [2,1,1]12) and surface lake elevation (SARIMA [1,1,2] [1,0,0]12) used to forecast future values for each parameter. Multiple regression of variables obtained at each breach event showed that the proportion of variance (55.0%) and null deviance (72.1%) explained by the combination of rainfall, hightide, and wave height was the “best” model with the lowest Generalized Cross-Validation statistic of all other models evaluated. All models agreed that rainfall was the most significant factor within each set of predictor attributes used to model surface lake elevation. A declining trend in surface elevation in combination with variation in the historical area and extent of wetland plant communities may be attributable to systematic breaching of the lagoon annually.

How the COVID-19 Pandemic Affected the Volume and Quality of Surgery in 2020: Data from NSQIP

INTRODUCTION: The COVID-19 pandemic led to an unprecedented contraction in surgical volume during 2020. Using the American College of Surgeons NSQIP database, the current study assesses the impact of COVID-19 on surgical volume during each quarter of 2020 in comparison to 2019. Quality of surgical care during 2020 was also investigated by assessing postoperative complication, readmission, and reoperation during 2020 in comparison to the previous 5 years. METHODS: The NSQIP database was queried from 2015 to 2020. Descriptive statistics and a chi-square test were used to compare demographic variables. A seasonal auto regressive integrated moving average time-series model was fit to assess the trend and seasonality of complication from 2015 to 2019 and was used to forecast the proportion of complication in the year 2020 and compared the forecast with the actual proportions graphically. RESULTS: There were fewer patients operated on in every quarter of 2020 compared with 2019, with the most dramatic drop in Q2 with a nearly 27% decrease. Patients with American Society of Anesthesiologists (ASA) Class III or greater were operated on at a greater proportion in every quarter of 2020. Q2 of 2020 represented the highest proportion of any operative complication since 2015 at ~13%. Q4 of 2020 demonstrated a return to 2020 Q1 complication proportions (Figure).FigureCONCLUSION: Surgical volume was heavily affected in 2020, particularly in Q2. Patients during Q2 of 2020 were generally of a higher ASA class and had increased operative complication. Operative volume and overall surgical complication rate normalized over the next two quarters.

Machine learning and automatic ARIMA/Prophet models-based forecasting of COVID-19: methodology, evaluation, and case study in SAARC countries.

Machine learning (ML) has proved to be a prominent study field while solving complex real-world problems. The whole globe has suffered and continues suffering from Coronavirus disease 2019 (COVID-19), and its projections need to be forecasted. In this article, we propose and derive an autoregressive modeling framework based on ML and statistical methods to predict confirmed cases of COVID-19 in the South Asian Association for Regional Cooperation (SAARC) countries. Automatic forecasting models based on autoregressive integrated moving average (ARIMA) and Prophet time series structures, as well as extreme gradient boosting, generalized linear model elastic net (GLMNet), and random forest ML techniques, are introduced and applied to COVID-19 data from the SAARC countries. Different forecasting models are compared by means of selection criteria. By using evaluation metrics, the best and suitable models are selected. Results prove that the ARIMA model is found to be suitable and ideal for forecasting confirmed infected cases of COVID-19 in these countries. For the confirmed cases in Afghanistan, Bangladesh, India, Maldives, and Sri Lanka, the ARIMA model is superior to the other models. In Bhutan, the Prophet time series model is appropriate for predicting such cases. The GLMNet model is more accurate than other time-series models for Nepal and Pakistan. The random forest model is excluded from forecasting because of its poor fit.

Time-series analysis of presentations to four syringe dispensing machines and a needle and syringe programme during COVID-19 lockdowns in Melbourne, Australia

BackgroundAustralian harm reduction services are provided via a mix of modalities, including fixed-site needle and syringe programmes (NSP) and syringe-dispensing machines (SDMs). SDMs are cost-effective and provide 24-h anonymous access to needles/syringes, often to underserved geographic areas, and can attract clientele who may choose not to use NSPs. The introduction of COVID-19 control measures saw disruptions and adaptations to the provision of harm reduction services. It is possible that SDMs filled the gap in otherwise disrupted harm reduction services in Melbourne. In this paper, we use data from four SDMs and an NSP to explore changes to harm reduction usage during periods of COVID-19 lockdowns in Melbourne, Australia, in 2020.MethodsOur data span September 2017–December 2020. We analysed daily counts of SDM use and monthly counts of NSP use, according to unique presentations to both. Auto-regressive integrated moving average (ARIMA) time-series models were fitted to the data with the effects of lockdowns estimated via a step function.ResultsAcross the study period, we estimated 85,851 SDM presentations and 29,051 NSP presentations. Usage across both the SDMs and the NSP declined during the COVID-19 lockdowns, but only the decline in SDM usage was significant in ARIMA analysis.ConclusionsThe slight, but significant decline in SDM use suggests barriers to access, though this may have been mitigated by SDM users acquiring needles/syringes from other sources. The decline, however, may be a concern if it led to lowered needle/syringe coverage and a subsequent increase in injecting risk. Further work is needed to properly explore potential changes in preference for needle/syringe acquisition site and associated barriers. Importantly, this work adds to the body of literature around the impacts of COVID-19 on harm reduction provision and potential areas of improvement.

Combination of Wilcoxon test and scatter diagram for trend analysis of hydrological data

• An alternative trend analysis method is proposed in this study. • The approach includes combination of scatter diagram and Wilcoxon test. • Suggested methodology provides visual representation and numerical results. • The method can be compared with both Şen’s ITA and Mann-Kendall results. In this study, time series data is divided into two equal parts, as in the basic principle of the Innovative Trend Analysis (ITA) method. However, unlike the ITA, the data are not ordered when comparing the halves to avoid any change in the time series. Wilcoxon Signed Rank Test is used to consider the differences between the two equal halves and to determine if there is any trend in time series. A graphical presentation is provided like ITA approach and is expressed as the Mann-Kendall (MK) test for trend detection at a given confidence interval (significance level). In the application phase, minimum, maximum and average discharge time series measured at Yakabaşı, Söğütlühan, Arıcılar, and Topluca stations along the northern line from west to east of Turkey are used. The trend conditions of the data are determined by the proposed method and compared with ITA and MK tests results. No trend is observed in 8 out of 12 cases for stations at the 95% confidence interval. While decreasing trends are detected in the maximum discharge of Yakabaşı station, the minimum discharge of Arıcılar station, and the average discharge of Yakabaşı station, an increasing trend is detected in the average discharge records of Topluca station. Here, an easy-to-use model for decision-makers is proposed that presents numerical as well as graphical analyses of trend identification studies.

A Study on Cryptocurrency Log-Return Price Prediction Using Multivariate Time-Series Model

Cryptocurrencies are highly volatile investment assets and are difficult to predict. In this study, various cryptocurrency data are used as features to predict the log-return price of major cryptocurrencies. The original contribution of this study is the selection of the most influential major features for each cryptocurrency using the volatility features of cryptocurrency, derived from the autoregressive conditional heteroskedasticity (ARCH) and generalized autoregressive conditional heteroskedasticity (GARCH) models, along with the closing price of the cryptocurrency. In addition, we sought to predict the log-return price of cryptocurrencies by implementing various types of time-series model. Based on the selected major features, the log-return price of cryptocurrency was predicted through the autoregressive integrated moving average (ARIMA) time-series prediction model and the artificial neural network-based time-series prediction model. As a result of log-return price prediction, the neural-network-based time-series prediction models showed superior predictive power compared to the traditional time-series prediction model.

Non-linear feature analysis of public emotion evolution for online teaching during the COVID-19 pandemic

PurposeNowadays, the breakout of the COVID-19 pandemic has caused an important change in teaching models. The emotional experience of this change has an important impact on online teaching. This paper aims to explore its time evolution characteristics and provide reference for the development of online teaching in the post epidemic era.Design/methodology/approachThe article firstly crawls the online teaching-related comment text data on Zhihu platform and performs emotional calculation to obtain a one-dimensional time series of daily average emotional values. Then, by using non-linear time-series analysis, this paper reconstructs the daily average emotion value time series in high-dimensional phase space, calculates the maximum Lyapunov exponent and correlation dimension and finally, explores the feature patterns through recurrence plot and recurrence quantification analysis.FindingsIt was found that the sequence has typical non-linear chaotic characteristics; its correlation dimension indicates that it contains obvious fractal characteristics; the public emotional evolution shows a cyclical rise and fall. By text mining and temporal evolution analysis, this paper explores the evolution law over chronically of the daily average emotion value time series, provides feasible strategies to improve students' online learning experience and quality and continuously optimizes this new teaching model in the era of pandemic.Originality/valueBased on social knowledge sharing platform of Q&A, this paper models and analyzes users interaction data under online teaching-related topics. This paper explores the evolution law over a long time period of the daily average emotion value time series using text mining and temporal evolution analysis. It then offers workable solutions to enhance the quality and experience of students' online learning, and it continuously improves this new teaching model in the age of pandemics.

High-order brain functional network for electroencephalography-based diagnosis of major depressive disorder.

Brain functional network (BFN) based on electroencephalography (EEG) has been widely used to diagnose brain diseases, such as major depressive disorder (MDD). However, most existing BFNs only consider the correlation between two channels, ignoring the high-level interaction among multiple channels that contain more rich information for diagnosing brain diseases. In such a sense, the BFN is called low-order BFN (LO-BFN). In order to fully explore the high-level interactive information among multiple channels of the EEG signals, a scheme for constructing a high-order BFN (HO-BFN) based on the “correlation’s correlation” strategy is proposed in this paper. Specifically, the entire EEG time series is firstly divided into multiple epochs by sliding window. For each epoch, the short-term correlation between channels is calculated to construct a LO-BFN. The correlation time series of all channel pairs are formulated by these LO-BFNs obtained from all epochs to describe the dynamic change of short-term correlation along the time. To construct HO-BFN, we cluster all correlation time series to avoid the problems caused by high dimensionality, and the correlation of the average correlation time series from different clusters is calculated to reflect the high-order correlation among multiple channels. Experimental results demonstrate the efficiency of the proposed HO-BFN in MDD identification, and its integration with the LO-BFN can further improve the recognition rate.

Measuring precise radial velocities on individual spectral lines

Context. To enable radial velocity (RV) precision on the order of ~0.1 m s−1 required for the detection of Earth-like exoplanets orbiting solar-type stars, the main obstacle lies in mitigating the impact of stellar activity. Aims. This study investigates the dependence of derived RVs with respect to the formation temperature of spectral line segments. Methods. Using spectral synthesis, we computed the stellar temperature below which 50% of the emergent flux originates for each observed wavelength point of unblended spectral lines. We then constructed RV time series for different temperature ranges using template matching. Results. With HARPS-N solar data and HARPS α Cen B measurements, we demonstrate on time intervals of prominent stellar activity that the activity-induced RV signal has different amplitude and periodicity depending on the temperature range considered. We compare the solar measurements with simulated contributions from active surface regions seen in simultaneous images, and find that the suppression of convective motion is the dominant effect. Conclusions. From a carefully selected set of spectral lines, we are able to measure the RV impact of stellar activity at various stellar temperatures ranges. We are able to strongly correlate the effect of convective suppression with spectral line segments formed in hotter temperature ranges. At cooler temperatures, the derived RVs exhibit oppositely directed variations compared to the average RV time series and stronger anticorrelations with chromospheric emission.

Individual Response to Botulinum Toxin Therapy in Movement Disorders: A Time Series Analysis Approach.

On a group level, satisfaction with botulinum neurotoxin (BoNT) treatment in neurological indications is high. However, it is well known that a relevant amount of patients may not respond as expected. The aim of this study is to evaluate the BoNT treatment outcome on an individual level using a statistical single-case analysis as an adjunct to traditional group statistics. The course of the daily perceived severity of symptoms across a BoNT cycle was analyzed in 20 cervical dystonia (CD) and 15 hemifacial spasm (HFS) patients. A parametric single-case autoregressive integrated moving average (ARIMA) time series analysis was used to detect individual responsiveness to BoNT treatment. Overall, both CD and HFS patients significantly responded to BoNT treatment with a gradual worsening of symptom intensities towards BoNT reinjection. However, only 8/20 CD patients (40%) and 5/15 HFS patients (33.3%) displayed the expected U-shaped curve of BoNT efficacy across a single treatment cycle. CD (but not HFS) patients who followed the expected outcome course had longer BoNT injection intervals, showed a better match to objective symptom assessments, and were characterized by a stronger certainty to control their somatic symptoms (i.e., internal medical locus of control). In addition to standard evaluation procedures, patients should be identified who do not follow the mean course-of-treatment effect. Thus, the ARIMA single-case time series analysis seems to be an appropriate addition to clinical treatment studies in order to detect individual courses of subjective symptom intensities.

Characterizing the volume of surgery and post-operative complications during the COVID-19 pandemic.

PurposeThe COVID-19 pandemic led to unprecedented changes in volume and quality of surgery. Utilizing the American College of Surgeons National Surgical Quality Improvement Program (NSQIP) database, the current study assesses the impact of COVID-19 on surgical volume during each quarter of 2020 in comparison to 2019. Quality of surgical care during 2020 was also investigated by assessing postoperative complications, readmissions, and reoperations during 2020 in comparison to the previous 5 years.Materials and methodsThe NSQIP database was queried from 2015 to 2020. Descriptive statistics and a chi-squared test were utilized to compare demographic variables. A seasonal autoregressive integrated moving average time-series model was fit to assess the trend and seasonality of complications from 2015 to 2019 and was used to forecast the proportion of complications in the year 2020 and compared the forecast with the actual proportions graphically.ResultsThere were fewer patients operated on in 2020 compared to 2019, with the most dramatic drop in Q2 with a nearly 27% decrease. Patients with ASA class 3 or greater were operated on at a greater proportion in every quarter of 2020. Q2 of 2020 represented the highest proportion of any operative complications since 2015 at ~13%. Q4 of 2020 demonstrated a return to 2020 Q1 complication proportions.ConclusionSurgical volume was heavily affected in 2020, particularly in Q2. Patients during Q2 of 2020 were generally of a higher ASA class and had increased operative complications. Operative volume and overall surgical complication rate normalized over the next two quarters.Supplementary InformationThe online version contains supplementary material available at 10.1007/s00423-022-02605-6.

Global influenza surveillance systems to detect the spread of influenza-negative influenza-like illness during the COVID-19 pandemic: Time series outlier analyses from 2015-2020.

BackgroundSurveillance systems are important in detecting changes in disease patterns and can act as early warning systems for emerging disease outbreaks. We hypothesized that analysis of data from existing global influenza surveillance networks early in the COVID-19 pandemic could identify outliers in influenza-negative influenza-like illness (ILI). We used data-driven methods to detect outliers in ILI that preceded the first reported peaks of COVID-19.Methods and findingsWe used data from the World Health Organization’s Global Influenza Surveillance and Response System to evaluate time series outliers in influenza-negative ILI. Using automated autoregressive integrated moving average (ARIMA) time series outlier detection models and baseline influenza-negative ILI training data from 2015–2019, we analyzed 8,792 country-weeks across 28 countries to identify the first week in 2020 with a positive outlier in influenza-negative ILI. We present the difference in weeks between identified outliers and the first reported COVID-19 peaks in these 28 countries with high levels of data completeness for influenza surveillance data and the highest number of reported COVID-19 cases globally in 2020. To account for missing data, we also performed a sensitivity analysis using linear interpolation for missing observations of influenza-negative ILI. In 16 of the 28 countries (57%) included in this study, we identified positive outliers in cases of influenza-negative ILI that predated the first reported COVID-19 peak in each country; the average lag between the first positive ILI outlier and the reported COVID-19 peak was 13.3 weeks (standard deviation 6.8). In our primary analysis, the earliest outliers occurred during the week of January 13, 2020, in Peru, the Philippines, Poland, and Spain. Using linear interpolation for missing data, the earliest outliers were detected during the weeks beginning December 30, 2019, and January 20, 2020, in Poland and Peru, respectively. This contrasts with the reported COVID-19 peaks, which occurred on April 6 in Poland and June 1 in Peru. In many low- and middle-income countries in particular, the lag between detected outliers and COVID-19 peaks exceeded 12 weeks. These outliers may represent undetected spread of SARS-CoV-2, although a limitation of this study is that we could not evaluate SARS-CoV-2 positivity.ConclusionsUsing an automated system of influenza-negative ILI outlier monitoring may have informed countries of the spread of COVID-19 more than 13 weeks before the first reported COVID-19 peaks. This proof-of-concept paper suggests that a system of influenza-negative ILI outlier monitoring could have informed national and global responses to SARS-CoV-2 during the rapid spread of this novel pathogen in early 2020.

Assessing Thailand’s 1-3-7 surveillance strategy in accelerating malaria elimination

BackgroundThailand’s strong malaria elimination programme relies on effective implementation of its 1-3-7 surveillance strategy, which was endorsed and implemented nationwide in 2016. For each confirmed malaria patient, the Ministry of Public Health’s Division of Vector Borne Diseases (DVBD) ensures completion of case notification within 1 day, case investigation within 3 days, and foci investigation within 7 days. To date, there has not been a comprehensive assessment of the performance and achievements of the 1-3-7 surveillance strategy although such results could help Thailand’s future malaria elimination strategic planning.MethodsThis study examined adherence to the 1-3-7 protocols, tracked progress against set targets, and examined geographic variations in implementation of the 1-3-7 strategy in the programme’s initial 5 years. An auto-regressive integrated moving average (ARIMA) time series analysis with seasonal decomposition assessed the plausible implementation effect of the 1-3-7 strategy on malaria incidence in the programme’s initial 5 years. The quantitative analysis included all confirmed malaria cases from public health and non-governmental community facilities from October 2014 to September 2021 (fiscal year [FY] 2015 to FY 2021) (n = 77,405). The spatial analysis included active foci with known geocoordinates that reported more than five cases from FY 2018 to FY 2021.ResultsFrom FY 2017 to FY 2021, on-time case notification improved from 24.4% to 89.3%, case investigations from 58.0% to 96.5%, and foci investigations from 37.9% to 87.2%. Adherence to timeliness protocols did not show statistically significant variation by area risk classification. However, adherence to 1-3-7 protocols showed a marked spatial heterogeneity among active foci, and the ARIMA model showed a statistically significant acceleration in the reduction of malaria incidence. The 1-3-7 strategy national indicators and targets in Thailand have shown progressive success, and most targets were achieved for FY 2021.ConclusionThe results of Thailand’s 1-3-7 surveillance strategy are associated with a decreased incidence in the period following the adoption of the strategy although there is notable geographic variation. The DVBD will continue to implement and adapt the 1-3-7 strategy to accelerate progress toward malaria elimination. This assessment may be useful for domestic strategic planning and to other countries considering more intensive case and foci investigation and response strategies.

Taylor-based optimized recursive extended exponential smoothed neural networks forecasting method

The development of a Time series Forecasting System is a major concern for Artificial Intelligence researchers. Commonly, existing systems only assess temporal features and analyze the behavior of the data over time, thus, resulting in uncertain forecasting accuracy. Although many forecasting systems were proposed in the literature; they have not yet answered the attending question. Hence, to overcome this problematic, we propose an innovative method called Taylor-based Optimized Recursive Extended Exponential Smoothed Neural Networks Forecasting method, abbreviated as TOREESNN. Briefly explained, the proposed technique introduces three ideas to solve this issue: First, building an innovative framework for forecasting univariate time series based on Exponential Smoothed theory. Second, designing an Elman Classifier model for uncertainty prediction in order to correct the forecasted values. And finally hybrading the two recurrent systems in one framework to obtain the final results. Experimental results demonstrate that the proposed method has a high accuracy both in training and testing data in terms of Mean Squared Error (MSE) and outperforms the state-of-the-art Recurrent Neural Networks models on Mackey-Glass, Nonlinear Auto-Regressive Moving Average time series (NARMA), Lorenz, and Henon map datasets.

Estimating Excess Deaths by Race/Ethnicity in the State of California During the COVID-19 Pandemic.

IntroductionTo examine excess mortality among minorities in California during the COVID-19 pandemic.MethodsUsing seasonal autoregressive integrated moving average time series, we estimated counterfactual total deaths using historical data (2014–2019) of all-cause mortality by race/ethnicity. Estimates were compared to pandemic mortality trends (January 2020 to January 2021) to predict excess deaths during the pandemic for each race/ethnic group.ResultsOur findings show a significant disparity among minority excess deaths, including 7892 (24.6% increase), 4903 (20.4%), 30,186 (47.7%), and 22,027 (12.6%) excess deaths, including deaths identified as COVID-19-related, for Asian, Black, Hispanic, and White non-Hispanic individuals, respectively. Estimated increases in all-cause deaths excluding COVID-19 deaths were 1331, 1436, 3009, and 5194 for Asian, Black, Hispanic, and White non-Hispanic individuals, respectively. However, the rate of excess deaths excluding COVID-19 recorded deaths per 100 k was disproportionately high for Black (66 per 100 k) compared to White non-Hispanic (36 per 100 k). The rates for Asians and Hispanics were 23 and 19 per 100 k.ConclusionsOur findings emphasize the importance of targeted policies for minority populations to lessen the disproportionate impact of COVID-19 on their communities.

The substantial role of May soil temperature over Central Asia for summer surface air temperature variation and prediction over Northeastern China

The slowly varying soil temperature can exert local and nonlocal influences on regional climate system, and may thus provide a critical source of subseasonal-to-seasonal climate prediction. In this study, we identify that soil temperature in May over the key region of Central Asia (42 °N–50 °N, 62 °E–80°E, KRCA) from Noah, Mosaic, CLM and ERA-interim datasets is closely linked to variations of the surface air temperature, daily maximum temperature and hot days over Northeastern China in summer (June–July–August), with correlation coefficients of regional average detrended time series ranging from 0.42 to 0.54, and all significant at the 99% confidence level for the period of 1979–2018. The possible physical mechanism behind the substantial downstream impacts of soil temperature over Central Asia are explored via diagnostical analysis combined with regional climate model experiments. Warmer soil temperature in May over the KRCA can keep to the summer and cause positive anomalies of geopotential height in summer over Northeastern China through the Rossby wave propagation, and associated stronger subsidence warming, less cloud cover, more solar radiation reaching the surface, higher planetary boundary layer, and stronger thermal advection at 850 hPa, which provide favorable conditions for warmer surface air temperature particularly in the daytime as well as more hot days. This study further reveals that soil temperature over Central Asia in May makes important contribution to prediction of summer surface air temperature, daily maximum temperature and hot days over Northeastern China in terms of regional average time series and spatial patterns. Our findings highlight the previously-unknown substantial role of antecedent soil temperature condition over Central Asia for summer surface air temperature variation and prediction over Northeastern China.

Влияние изменений потока космических лучей на общую циркуляцию атмосферы

A comparison of average daily values time series of the axial component of the global wind angular moment and galactic cosmic ray (GCR) flux was made. Using the superposed epoch method it is shown that the Forbush decreases of the GCR flux are accompanied by an increase in the average angular velocity of atmosphericcirculation and, accordingly, by an increase in the zonal transfer.

The impact of California wildfires on patient access to prescription opioids

BackgroundPatients on long-term opioid therapy are particularly vulnerable to disruptions in medication access, especially during traumatic and chaotic events such as wildfires and other natural disasters. ObjectivesTo determine whether past highly destructive California wildfires were associated with disrupted access to prescription opioids for patients receiving long-term, and therefore physically dependent on, opioid medications. MethodsUsing California prescription drug monitoring program data, this retrospective study selected patients with long-term prescription opioid use episodes residing in ZIP code tabulation areas impacted by either the Camp Fire or Tubbs Fire. Autoregressive integrated moving average time series models were fit to pre-fire data to forecast post-fire expected values and then compared with observed post-fire data, specifically for weekly proportions of long-term episodes with early fills, late fills, changes in patients’ prescriber and pharmacy, and fills within a different ZIP code tabulation area than the patient’s residence. ResultsAfter the Camp Fire, there were significant spikes in the proportions of early fills (peak at 56% of total, week 1 after fire), late fills (peak at 29%, week 6), and immediate significant increases in prescriber (peak at 37%, week 3) and pharmacy changes (peak at 71%, week 1) in high-impact ZIP code tabulation areas. Low-impact ZIP code tabulation areas experienced no similar disruptions. Disruptions due to the Tubbs Fire were far less severe. ConclusionAccess to prescription opioids was greatly disrupted for patients living in areas most impacted by the Camp Fire. Future research should explore effectiveness of current state and federal controlled substance prescribing policies to determine what improvements are needed to minimize disruptions in medication access due to wildfires and other natural disasters.

A data-driven prediction model for aircraft taxi time by considering time series about gate and real-time factors

The prediction of taxi time plays a primary role. To improve the accuracy and portability of prediction, the Informer-RFR (Informer-Random Forest Regression) model was proposed. First, each gate's average taxi time series is clustered, and then an Informer model is trained for each cluster. Second, the RFR model was used to predict the taxi time of flight with the result of Informer and real-time factors. The proposed model can be directly trained by the historical database of a new airport, which can reduce the data processing time. Finally, the model was trained and verified using the data for Beijing Capital International Airport, China (PEK). The results show that the gates of PEK can be divided into four clusters, and the time series of each cluster differ in peak value and changing trend. Our model’s accuracy of predicting within ±5 min is 96.62%, and the mean absolute error is 147.59 s.

Wind turbine generator prognostics using field SCADA data

This paper presents a novel prognostic method to estimate the remaining useful life (RUL) of generators using the SCADA (Supervisory Control And Data Acquisition) systems installed in wind turbines. A data-driven wind turbine anomaly classification method is developed. The anomalies are quantified into a health indicator to measure the component degradation over time. An Autoregressive Integrated Moving Average (ARIMA) time series forecasting technique is then applied to predict the RUL of the wind turbine generator. The proposed method has been validated using industry field data showing accurate predictions of RUL with a 21 day lead time for maintenance of the turbine.