This paper presents a novel machine learning (ML) approach to automate the identification of a specific type of ion-scale coherent structure in the solar wind—Alfvénic solitons—characterized by distinctive magnetic field enhancements and their potential role in driving the solar wind turbulence cascade. While traditional methods, such as wavelet transforms and non-Gaussianity analysis, are effective, they are labor-intensive. Our supervised ML classifier, trained on a curated dataset of manually identified events and enhanced with data augmentation, streamlines this process. Among the models tested, the Random Forest classifier achieved the highest precision (0.901 at a classification threshold of 0.9) and consistently predicted fewer positive samples across multiple thresholds, making it the preferred choice for human validation. Applied to unseen Parker Solar Probe data within 0.25 AU (spanning three years), the classifier identified approximately 500 true events, closely aligning with traditional methods while significantly reducing analysis time. This framework demonstrates that combining small, high-quality datasets with ML techniques offers a scalable and efficient solution for detecting coherent structures across decades of spacecraft data, significantly accelerating their study and paving the way for future discoveries in space physics research.