Researchers have developed an automated method to classify changes in Electronic Navigational Charts (ENCs) used in maritime navigation. The system uses machine learning to determine whether a chart change poses a critical or non-critical risk to safety. A baseline encoding scheme is proposed, which translates complex vector data into a structured format for classification models. The approach includes two key components: a spatial context encoder and an ENC attribute encoder. Experiments show that the method achieves high accuracy (90-94%) in classifying chart changes, with potential applications in improving ENC maintenance and enhancing maritime safety. --- Why it matters: This research matters to engineers working on AI for geospatial applications because it demonstrates the effectiveness of integrating machine learning into operational pipelines to improve data maintenance and safety. The proposed method can be applied to various domains beyond maritime navigation, such as land surveying or environmental monitoring. Source: https://arxiv.org/abs/2608.20218