<p>Due to the COVID-19 epidemic, the importance of the pharmaceutical supply chain (PSC) has been highlighted. Since medicine is regarded as a strategic product, a slight disruption in its supply chain (SC) can trigger a drastic crisis. Thus, in this work, a novel multi-objective multi-period mixed-integer programming mathematical model is considered, which can adjust a sustainable-resilient pharmaceutical supply chain network. This study aims to reduce overall expenses as well as environmental impacts. This model also strives to maximize the SC network's social benefits and resilience levels. The cap and trade policy and technology compatibility are considered to increase the sustainability of the pharma chain. Moreover, raw material-manufacturing technology compatibility is considered in the mentioned model for the first time to make mentioned chain more sustainable. Furthermore, the seasonal-trend decomposition procedure based on Loess model predicts customer demand within one year to mitigate the amount of shortage that may happen in the network. The LP-metric method is utilized to find optimal solutions. Then the suggested model is validated. After that, the applicability of the proposed model and its suggested solution approach is examined using a case study from Tehran. Finally, to show the performance of the suggested model, numerical test problems are solved. For important parameters, a number of sensitivity analyses are carried out. Subsequently, it is revealed that having demand prediction by machine learning technique named time series can increase the resiliency of PSC and decrease shortage. In addition, by using Cap and Trade policy, the total cost and CO₂ emission are decreased.</p>