An intelligent simplification method for river networks with an unsupervised variational autoencoder

Intelligent simplification of river networks is an important part in map generalisation. Traditional rule-based methods often have limitations, such as relying on the determination of parameters and thresholds. This paper describes the utilisation of the adaptive characteristics and powerful learning and representation capabilities of the variational autoencoder model to achieve intelligent simplification of river networks. The original river network data was sampled considering the characteristics of river networks, such as topological relationships, primary-secondary relationships and river bend curvatures. The sampled data was rasterised and input into the Encoder module. The Encoder extracted features from the images and mapped them to the latent space. Finally, the Decoder decoded the samples, mapped the latent variables back to the dimensions and distributions of the original data, and reconstructed the data as close as possible to the inputs and the river network based on the target scale. The experimental results showed that compared with the classical Douglas-Peucker, Wang-Müller, and Visvalingam-Whyatt algorithms, this method was superior in terms of preserving the overall structure, position, shape, and local morphology of the simplified river network.