Polyethylene terephthalate (PET) water bottles are widely used in the United Arab Emirates (UAE); however, their production and disposal adversely affect the environment. In collaboration with the private sector, the UAE government has taken serious steps to reduce these impacts, including (i) encouraging people to stop using PET water bottles and to separate their waste, (ii) establishing material recovery facilities, (iii) constructing facilities for incineration with energy recovery, and (iv) creating business opportunities to downcycle and recycle PET water bottles. This paper models the PET supply chain (PSC) using system dynamics (SD) to simulate the current PSC in the UAE and to project its possible evolution from 2023 to 2050, taking greenhouse gas (GHG) emissions into consideration. For decision-makers, the SD model shows that PET reductions must equal population growth to maintain GHG emissions associated with the PSC for the coming years. In addition, the separation efficiency must exceed 33% of PET consumption to meet the current demand for used PET. Moreover, if PET consumption decreases by more than 1.5%, then businesses relying on used PET will face a supply shortage in the year 2050. As for environmental impacts, it is found that if downcycling and recycling capabilities are fully utilized, GHG emissions will decrease by 35%. Furthermore, if demand for recycled PET reaches 10,000 tons, this reduction will exceed 47%, reaching $177,861MtC{O}_{2}e$.

The prediction of new COVID-19 cases is crucial for decision makers in many countries. Researchers are continually proposing new models to forecast the future tendencies of this pandemic, among which long short-term memory (LSTM) artificial neural networks have exhibited relative superiority compared to other forecasting techniques. Moreover, the correlation between the spread of COVID-19 and exogenous factors, specifically weather features, has been explored to improve forecasting models. However, contradictory results have been reported regarding the incorporation of weather features into COVID-19 forecasting models. Therefore, this study compares uni-variate with bi- and multi-variate LSTM forecasting models for predicting COVID-19 cases, among which the latter models consider weather features. LSTM models were used to forecast COVID-19 cases in the six Gulf Cooperation Council countries. The root mean square error (RMSE) and coefficient of determination ($R^2$) were employed to measure the accuracy of the LSTM forecasting models. Despite similar weather conditions, the weather features that exhibited the strongest correlation with COVID-19 cases differed among the six countries. Moreover, according to the statistical comparisons that were conducted, the improvements gained by including weather features were insignificant in terms of the RMSE values and marginally significant in terms of the $R^2$ values. Consequently, it is concluded that the uni-variate LSTM models were as good as the best bi- and multi-variate LSTM models; therefore, weather features need not be included. Furthermore, we could not identify a single weather feature that can consistently improve the forecasting accuracy.

Dubai, a popular vacation spot, has launched an initiative to reduce reliance on single-use plastic water bottles. Tourists in Dubai widely utilize PET (Polyethylene Terephthalate) water bottles, and significant quantities of greenhouse gases (GHG) are released during the production and disposal of PET bottles. In response to Dubai’s initiative, some hotels eliminated PET bottles and substituted them with environmentally favorable alternatives. These hotels are considered adopters of the initiative, while other hotels that might follow are imitators. Thus, innovation diffusion theory (IDT) is used in this work to forecast the transition of hotels to non-PET bottles. The diffusion of this new behavior is simulated using a system dynamic (SD) model, where factors pushing imitators to abolish PET bottles are found using the Delphi method and hotel surveying. Moreover, the importance of each identified factor is found using an analytical hierarchical process (AHP). Since hotels are divided into several categories based on their service quality, the analysis shows that hotels are affected by other hotels in their category or better categories. Using this conceptual understanding, Bass and generalized Bass modeling are used in the SD model to study how imitating hotels will follow the adopters. Best-, average-, and worst-case scenarios are studied to help decision-makers understand what to expect in the future. For the best- and average-case scenarios, the SD simulation shows that all hotels will potentially have abolished PET bottles in 25 years. However, only 16% of hotels will have cancelled PET bottles in 25 years if the worst-case scenario occurs; thus, decision-makers need to intervene to expedite the process.