The recent changes in global business markets have forced supply chains to include sustainability and considerable uncertainty in their decision-making processes. In this study, we propose an integrated information fusion and grey multi-criteria decision-making (MCDM) framework for solving sustainable supplier selection problems with imprecise information. We identify a series of criteria in the literature based on the economic, social, and environmental aspects of sustainability and obtain the relative importance of these criteria from experts' opinions. We then propose a best-worst method (BWM) integrated with grey theory to calculate the weights of criteria. These weights are used to evaluate a set of suppliers based on three sustainability aspects. A hybrid method composed of weighted aggregated sum product assessment (WASPAS), the technique for order of preference by similarity to ideal solution (TOPSIS), and grey theory are proposed for ranking the suppliers. We aggregate the grey MCDM results with the concept of information fusion to find an integrated score for each supplier. The final ranking is obtained by incorporating expert opinions with the integrated scores. We also present a case study to demonstrate the applicability of the proposed framework. A sensitivity analysis is performed to test the reliability and robustness of the results.
Water main breaks are a common recurring problem in water distribution networks, resulting in cascading effects in the whole system and the interconnected infrastructures such as transportation. Having integrated the physical features of pipes such as diameter and environmental factors like precipitation, we propose predictive models based on spatiotemporal data and machine learning methods. In this study, the dataset is the main breaks recorded from 2015 to 2020 in the city of Tampa, Florida. First, a spatial clustering is conducted to identify vulnerable areas to breaks. A time series analysis is also carried out for the temporal data. The result of these analyses informed the machine learning algorithms as independent variables. We then compared the predictive models based on information-based and rank-based criteria. Obtained results indicated that Boosted Regression Tree (BRT) model was superior to the others. Finally, we present predicted normalized failure rates for the water distribution network to inform rehabilitation and fortification decisions at the municipality level.
7 April 2021 in International Transactions in Operational Research