Deep learning ancient map segmentation to assess historical landscape changes
ABSTRACTAncient geographical maps are our window into the past for understanding the spatial dynamics of last centuries. This paper proposes a novel approach to address this problem using deep learning. Convolutional neural networks (CNNs) are today the state-of-the-art methods in handling a variety...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Taylor & Francis Group
2023-12-01
|
Series: | Journal of Maps |
Subjects: | |
Online Access: | https://www.tandfonline.com/doi/10.1080/17445647.2023.2225071 |
_version_ | 1797788517783306240 |
---|---|
author | Théo Martinez Adam Hammoumi Gabriel Ducret Maxime Moreaud Rémy Deschamps Hervé Piegay Jean-François Berger |
author_facet | Théo Martinez Adam Hammoumi Gabriel Ducret Maxime Moreaud Rémy Deschamps Hervé Piegay Jean-François Berger |
author_sort | Théo Martinez |
collection | DOAJ |
description | ABSTRACTAncient geographical maps are our window into the past for understanding the spatial dynamics of last centuries. This paper proposes a novel approach to address this problem using deep learning. Convolutional neural networks (CNNs) are today the state-of-the-art methods in handling a variety of problems in the fields of image processing. The Cassini map, created in the eighteenth century, is used to illustrate our methodology. This approach enables us to extract the surfaces of classes of lands in the Cassini map: forests, heaths, arboricultural, and hydrological. The evolution of land use between the end of the eighteenth century andtoday was quantified by comparison with Corine Land Cover (CLC) database. For the Rhone watershed, the results show that forests, arboriculture, and heaths are more extensive on the CLC map, in contrast to the hydrological network. These unprecedented results are new findings that reveal the major anthropo-climatic changes. |
first_indexed | 2024-03-13T01:37:42Z |
format | Article |
id | doaj.art-440be3ed2a0349f0acb2bfd3ea7c6121 |
institution | Directory Open Access Journal |
issn | 1744-5647 |
language | English |
last_indexed | 2024-03-13T01:37:42Z |
publishDate | 2023-12-01 |
publisher | Taylor & Francis Group |
record_format | Article |
series | Journal of Maps |
spelling | doaj.art-440be3ed2a0349f0acb2bfd3ea7c61212023-07-03T22:34:23ZengTaylor & Francis GroupJournal of Maps1744-56472023-12-0119110.1080/17445647.2023.2225071Deep learning ancient map segmentation to assess historical landscape changesThéo Martinez0Adam Hammoumi1Gabriel Ducret2Maxime Moreaud3Rémy Deschamps4Hervé Piegay5Jean-François Berger6IFP Energies nouvelles, Rueil-Malmaison, FranceIFP Energies nouvelles, Rueil-Malmaison, FranceIFP Energies nouvelles, Rueil-Malmaison, FranceIFP Energies nouvelles, Solaize, FranceIFP Energies nouvelles, Rueil-Malmaison, FranceUniversité de Lyon, Lyon, FranceUniversité de Lyon, CNRS, Université Lyon 2-Lumière, Lyon, FranceABSTRACTAncient geographical maps are our window into the past for understanding the spatial dynamics of last centuries. This paper proposes a novel approach to address this problem using deep learning. Convolutional neural networks (CNNs) are today the state-of-the-art methods in handling a variety of problems in the fields of image processing. The Cassini map, created in the eighteenth century, is used to illustrate our methodology. This approach enables us to extract the surfaces of classes of lands in the Cassini map: forests, heaths, arboricultural, and hydrological. The evolution of land use between the end of the eighteenth century andtoday was quantified by comparison with Corine Land Cover (CLC) database. For the Rhone watershed, the results show that forests, arboriculture, and heaths are more extensive on the CLC map, in contrast to the hydrological network. These unprecedented results are new findings that reveal the major anthropo-climatic changes.https://www.tandfonline.com/doi/10.1080/17445647.2023.2225071Land-use changeHuman pressurePaleogeographic studySemantic segmentationRhône basin |
spellingShingle | Théo Martinez Adam Hammoumi Gabriel Ducret Maxime Moreaud Rémy Deschamps Hervé Piegay Jean-François Berger Deep learning ancient map segmentation to assess historical landscape changes Journal of Maps Land-use change Human pressure Paleogeographic study Semantic segmentation Rhône basin |
title | Deep learning ancient map segmentation to assess historical landscape changes |
title_full | Deep learning ancient map segmentation to assess historical landscape changes |
title_fullStr | Deep learning ancient map segmentation to assess historical landscape changes |
title_full_unstemmed | Deep learning ancient map segmentation to assess historical landscape changes |
title_short | Deep learning ancient map segmentation to assess historical landscape changes |
title_sort | deep learning ancient map segmentation to assess historical landscape changes |
topic | Land-use change Human pressure Paleogeographic study Semantic segmentation Rhône basin |
url | https://www.tandfonline.com/doi/10.1080/17445647.2023.2225071 |
work_keys_str_mv | AT theomartinez deeplearningancientmapsegmentationtoassesshistoricallandscapechanges AT adamhammoumi deeplearningancientmapsegmentationtoassesshistoricallandscapechanges AT gabrielducret deeplearningancientmapsegmentationtoassesshistoricallandscapechanges AT maximemoreaud deeplearningancientmapsegmentationtoassesshistoricallandscapechanges AT remydeschamps deeplearningancientmapsegmentationtoassesshistoricallandscapechanges AT hervepiegay deeplearningancientmapsegmentationtoassesshistoricallandscapechanges AT jeanfrancoisberger deeplearningancientmapsegmentationtoassesshistoricallandscapechanges |