This study applies a directional distance function (DDF) data envelopment analysis (DEA) model to measure the environmental efficiency of 12 U.S. airlines 2013–2016 by considering flight delay and greenhouse gas (GHG) emissions as joint undesirable outputs. First, the environmental efficiency of airlines is compared using the CCR DEA (without flight delay) and DDF DEA (with flight delay). We find that several airlines experienced substantial changes in environmental efficiency scores when flight delay is considered. Secondly, a tobit regression is used to explore whether the environmental factors of fleet age, ownership type, freight traffic, market share, and carrier type affect airlines’ environmental efficiency. The results demonstrate that all of these factors significantly influence airline performance.

Measuring the U.S.’s COVID-19 response performance is an extremely important challenge for health care policymakers. This study integrates Data Envelopment Analysis (DEA) with four different machine learning (ML) techniques to assess the efficiency and evaluate the U.S.’s COVID-19 response performance. First, DEA is applied to measure the efficiency of fifty U.S. states considering four inputs: number of tested, public funding, number of health care employees, number of hospital beds. Then, number of recovered from COVID-19 as a desirable output and number of confirmed COVID-19 cases as a undesirable output are considered. In the second stage, Classification and Regression Tree (CART), Boosted Tree (BT), Random Forest (RF), and Logistic Regression (LR) were applied to predict the COVID-19 response performance based on fifteen environmental factors, which were classified into social distancing, health policy, and socioeconomic measures. The results showed that 23 states were efficient with an average efficiency score of 0.97. Furthermore, BT and RF models produced the best prediction results and CART performed better than LR. Lastly, urban, physical inactivity, number of tested per population, population density, and total hospital beds per population were the most influential factors on efficiency.

Faced with increasing concerns over the negative environmental impact due to human and industrial activities, biomass industry practitioners and policy makers have great interest in green supply chains to reduce carbon emissions from supply chain activities. There are many studies which model the biomass supply chain and its environmental impact. However, animal waste sourced biogas supply chain has not received much attention in the literature. Biogas from animal manure not only provides energy efficiency, but also minimizes carbon emissions compared to existing biomass products. Therefore, this study proposes a mixed integer linear program that minimizes total supply costs and carbon emissions from an animal waste sourced biogas supply chain while it also incorporates carbon price in the model to see the impact of a carbon policy on tactical and strategic supply chain decisions. To validate the model proposed, a case study of North Dakota is adopted where there is a high potential for a biogas plant to be developed. The results of our optimization experiment indicate that supply chain performance in terms of both costs and emissions is very sensitive to a carbon pricing mechanism.

Predicting nurse turnover is a growing challenge within the healthcare sector, profoundly impacting healthcare quality and the nursing profession. This study employs the Synthetic Minority Over-sampling Technique (SMOTE) to address class imbalance issues in the 2018 National Sample Survey of Registered Nurses dataset and predict nurse turnover using machine learning algorithms. Four machine learning algorithms, namely logistic regression, random forests, decision tree, and extreme gradient boosting, were applied to the SMOTE-enhanced dataset. The data were split into 80% training and 20% validation sets. Eighteen carefully selected variables from the database served as predictive features, and the machine learning model identified age, working hours, electric health record/electronic medical record, individual income, and job type as important features concerning nurse turnover. The study includes a performance comparison based on accuracy, precision, recall (sensitivity), F1-score, and AUC. In summary, the results demonstrate that SMOTE-enhanced random forests exhibit the most robust predictive power in the classical approach (with all 18 predictive variables) and an optimized approach (utilizing eight key predictive variables). Extreme gradient boosting, decision tree, and logistic regression follow in performance. Notably, age emerges as the most influential factor in nurse turnover, with working hours, electric health record/electronic medical record usability, individual income, and region also playing significant roles. This research offers valuable insights for healthcare researchers and stakeholders, aiding in selecting suitable machine learning algorithms for nurse turnover prediction.

Purpose: The purpose of this paper is to provide an input-output life cycle assessment model to estimate the carbon footprint of US manufacturing sectors. To achieve this, the paper sets out the following objectives: develop a time series carbon footprint estimation model for US manufacturing sectors; analyze the annual and cumulative carbon footprint; analyze and identify the most carbon emitting and carbon intensive manufacturing industries in the last four decades; and analyze the supply chains of US manufacturing industries to help identify the most critical carbon emitting industries. Design/methodology/approach: Initially, the economic input-output tables of US economy and carbon footprint multipliers were collected from EORA database (Lenzen et al., 2012). Then, economic input-output life cycle assessment models were developed to quantify the carbon footprint extents of the US manufacturing sectors between 1970 and 2011. The carbon footprint is assessed in metric tons of CO₂-equivalent, whereas the economic outputs were measured in million dollar economic activity. Findings: The salient finding of this paper is that the carbon footprint stock has been increasing substantially over the last four decades. The steep growth in economic output unfortunately over-shadowed the potential benefits that were obtained from lower CO₂ intensities. Analysis of specific industry results indicate that the top five manufacturing sectors based on total carbon footprint share are “petroleum refineries,” “Animal (except poultry) slaughtering, rendering, and processing,” “Other basic organic chemical manufacturing,” “Motor vehicle parts manufacturing,” and “Iron and steel mills and ferroalloy manufacturing.” Originality/value: This paper proposes a state-of-art time series input-output-based carbon footprint assessment for the US manufacturing industries considering direct (onsite) and indirect (supply chain) impacts. In addition, the paper provides carbon intensity and carbon stock variables that are assessed over time for each of the US manufacturing industries from a supply chain footprint perspective.