Transportation networks play a critical role in modern societies due to their importance in human mobility, and the exchange of goods and ideas. However, transportation networks are also the primary vehicles for the worldwide spread of infections, and account for a significant fraction of CO2 emissions. We investigate the edge removal dynamics of two mature transportation networks: the Brazilian domestic bus transportation network and the U.S. domestic air transportation network. Specifically, we apply a suite of machine learning algorithms to predict edge removals on a monthly time scale and find that several algorithms predict edge removals with high accuracy and low error variance. We find that even when using the best algorithm identified by our analysis (XGBoost Classifier) and use the model built for a given time, we cannot predict edge removals in bus transportation networks better than chance for other times. However, we can develop a model to predict edge removals in the U.S. domestic air transportation network. We take advantage of this model to forecast the impact of a hypothetical dramatic reduction in the scale of the U.S. air transportation network as a result of policies to reduce CO2 emissions. Our model was robust to make predictions even under the COVID-19 pandemic’s travel restrictions. Our forecast could be helpful in building scenarios for planning future infrastructure, such as high-speed rail systems, that could replace lost air connections.