Similarity-Based Bike Station Expansion via Hybrid Denoising Autoencoders

TL;DR

This paper introduces a data-driven framework using hybrid denoising autoencoders to inform bike station expansion by capturing complex spatial patterns from multiple data sources, improving planning accuracy.

Contribution

It presents a novel autoencoder-based approach that learns latent representations from multi-source features to guide spatially coherent bike station expansion decisions.

Findings

HDAE embeddings produce more spatially coherent clusters than raw features.

The framework identifies 32 high-confidence expansion zones with consensus across parametrisations.

Representation learning captures complex patterns missed by raw features, aiding evidence-based planning.

Abstract

Urban bike-sharing systems require strategic station expansion to meet growing demand. Traditional allocation approaches rely on explicit demand modelling that may not capture the urban characteristics distinguishing successful stations. This study addresses the need to exploit patterns from existing stations to inform expansion decisions, particularly in data-constrained environments. We present a data-driven framework leveraging existing stations deemed desirable by operational metrics. A hybrid denoising autoencoder (HDAE) learns compressed latent representations from multi-source grid-level features (socio-demographic, built environment, and transport network), with a supervised classification head regularising the embedding space structure. Expansion candidates are selected via greedy allocation with spatial constraints based on latent-space similarity to existing stations. Evaluation on Trondheim's bike-sharing network demonstrates that HDAE embeddings yield more spatially coherent clusters and allocation patterns than raw features. Sensitivity analyses across similarity methods and distance metrics confirm robustness. A consensus-based procedure across multiple parametrisations distils 32 high-confidence extension zones where all parametrisations agree. The results demonstrate how representation learning captures complex patterns that raw features miss, enabling evidence-based expansion planning without explicit demand modelling. The consensus procedure strengthens recommendations by requiring agreement across parametrisations, while framework configurability allows planners to incorporate operational knowledge. The methodology generalises to any location-allocation problem where existing desirable instances inform the selection of new candidates.