Shared micromobility services provide a flexible and sustainable alternative for urban and suburban mobility, especially for the first and last mile problems. It is crucial to understand the mobility patterns in the operating areas to provide the best experience for users of shared micromobility services. Effective demand modeling can provide data to test and evaluate fleet configurations in different but relevant mobility scenarios. This study utilizes statistical and deep learning techniques for demand modeling of a shared e-moped service operating in the urban and suburban areas of Stuttgart, Germany. It addresses the research gap of demand modeling in both urban and suburban areas by developing approaches based on models used in urban areas. Such models are usually presented in isolation for their use case, making them difficult to compare with each other. For this reason, in this work we also compare multiple model configurations based on different models and processing techniques. The results show that deep learning models, specifically LSTMs, provide the best results, outperforming the baseline and traditional models on most metrics. Using Voronoi partitioning and community clustering to aggregate trips and reduce spatial complexity led to better results for all evaluated models. Surprisingly, with the exception of Kullback-Leibler (KL) divergence, the inclusion of weather data resulted in worse performance for all other metrics.