Among cartographic generalisation problems, the generalisation of sinuous bends in mountain roads has always been a popular one due to its difficulty. Recent research showed the potential of deep learning techniques to overcome some remaining research problems regarding the automation of cartographic generalisation. This paper explores this potential on the popular mountain road generalisation problem, which requires smoothing the road, enlarging the bend summits, and schematising the bend series by removing some of the bends. We modelled the mountain road generalisation as a deep learning problem by generating an image from input vector road data, and tried to generate it as an output of the model a new image of the generalised roads. Similarly to previous studies on building generalisation, we used a U-Net architecture to generate the generalised image from the ungeneralised image. The deep learning model was trained and evaluated on a dataset composed of roads in the Alps extracted from IGN (the French national mapping agency) maps at 1:250,000 (output) and 1:25,000 (input) scale. The results are encouraging as the output image looks like a generalised version of the roads and the accuracy of pixel segmentation is around 65%. The model learns how to smooth the output roads, and that it needs to displace and enlarge symbols but does not always correctly achieve these operations. This article shows the ability of deep learning to understand and manage the geographic information for generalisation, but also highlights challenges to come.

Map generalisation is a process that transforms geographic information for a cartographic at a specific scale. The goal is to produce legible and informative maps even at small scales from a detailed dataset. The potential of deep learning to help in this task is still unknown. This article examines the use case of mountain road generalisation, to explore the potential of a specific deep learning approach: generative adversarial networks (GAN). Our goal is to generate images that depict road maps generalised at the 1:250k scale, from images that depict road maps of the same area using un-generalised 1:25k data. This paper not only shows the potential of deep learning to generate generalised mountain roads, but also analyses how the process of deep learning generalisation works, compares supervised and unsupervised learning and explores possible improvements. With this experiment we have exhibited an unsupervised model that is able to generate generalised maps evaluated as good as the reference and reviewed some possible improvements for deep learning-based generalisation, including training set management and the definition of a new road connectivity loss. All our results are evaluated visually using a four questions process and validated by a user test conducted on 113 individuals.

As web maps are now extensively used by billions of users, the energy consumption of these maps is not marginal anymore. Green cartography seeks to reduce the energy consumption of maps to promote more sustainable digital tools. To reduce energy consumption, we first need to better understand the different sources of energy consumption for web maps. Among these sources, this paper focuses on the tiles that are stored on servers and then constantly transferred each time a user explores the map. This paper presents several experiments carried out with current web maps to assess this energy consumption. We first try to assess the number of map tiles that are loaded through the web when users explore web maps, and we determine which types of interaction are used with the maps, and a similar amount of tiles is loaded. Then, we try to assess which zoom levels are the most loaded by users; it appears that the medium–large scales are the most used (between zoom levels 11 and 17). Then, we explore the size of the map tiles and try to assess which ones are larger and thus require more energy to load over the web; we can find clear differences between zoom levels. Finally, we discuss how map generalization could be used to reduce energy consumption by creating lighter tiles. These experiments show that the current web maps are suboptimal regarding energy consumption, with many tiles loaded at zoom levels where the tiles are larger than necessary.