Despite the crucial importance of maritime transport for world trade and economic development, dedicated tools to map the evolution of vessel movements remain lacking.Such movements, especially those recorded by the maritime insurance company Lloyd's List, represent the only available information documenting the changing spatial distribution of the world's shipping routes in the last century or so. This chapter tackles the lacuna head on by discussing how this particular type of shipping data can be accurately represented on a map (see Chapter 1 for a review of the field). Such an exercise poses specific issues in terms of geovisualization, as it necessitates, among other developments, the creation of a virtual maritime grid to which port nodes and their mutual vessel flows are assigned. Beyond geomatics, this research is also an opportunity to shed new light on a vibrant research question in maritime history, namely how steam has replaced sail shipping in space and time.We extracted snapshots of global maritime flows every five years from the Lloyd's Shipping Index between 1890 and 1925 in order to test the capacity of the geoportal to visualize such flows, and at the same time verify the spatio-temporal evolution of a bi-layered maritime network. The remainder of this chapter is organized as follows: the next section discusses the scarcity of maritime data cartography until recent years in the light of general knowledge on flow mapping in geography and elsewhere. It is followed by a description of how vessel movement data had been incorporated into a dedicated visualization system. Lastly, it provides the first-ever cartographies of such movements while discussing the gaps between our results and the existing literature on the transition from sail to steam shipping.Conclusions point to a number of ways how the visualization system may be improved in the future, and how it can contribute toward addressing numerous other issues in global transport studies in general.
Updated information on the spatial distribution of mangrove forests is of high importance for management plans. Yet, access to mangrove distribution maps is limited, even-though remote sensing data is currently freely available and deep learning algorithms score high performances in automatic classification tasks. The methodologies developed in this paper are based on a deep convolutional neural network and have been tested on WorldView 2 and Sentinel-2 images. The obtained results are highly satisfactory and open perspectives for automatically mapping mangrove distribution over large areas.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.