This study aims to answer the question “How do severe weather events such as snowstorms and tornadoes affect traffic patterns in Kansas?” by analyzing existing traffic data to identify disaster-induced mobility and evacuation patterns using neural network predictive modeling. Studying the impact of severe weather events on traffic volume and patterns aids in designing more resilient infrastructure and developing effective emergency response strategies. We examine the impact of historical severe-weather events obtained from the National Oceanic and Atmospheric Administration on hourly traffic across the state. We employ long-short-term-memory (LSTM) recurrent neural networks to construct a counterfactual prediction, which is compared against the actual traffic data to analyze the causal impact of severe weather events on daily traffic patterns in different regions of the state. The study considers the impact of a 24 hour snowstorm in February of 2014 located along the interstate I-135 located north of Wichita that accumulated over a foot of snow. When comparing the actual traffic counts versus the LSTM generated counterfactual, a cumulative loss of about 60,000 vehicles continued over the next 3 days. We also assess the causal impact of an EF-4 tornado traveling through Douglas County in May 2019. The resulting counterfactual suggested a shifted travel pattern consisting of an initial sharp drop in traffic volume, but quickly followed by an atypical surplus. The results of these case studies indicate unique evacuation responses depending on factors such as the type of weather event or the demographic of the impacted area (urban or rural). The varying impacts on travel patterns and volumes can be useful when designing more resilient infrastructure and developing effective emergency response strategies. The future scope of this research includes using this model to develop a spatial-temporal simulation of the population response to severe weather events.