Comparing geomorphological maps made manually and by deep learning. Issue 4 (30th January 2022)

• Record Type: Journal Article
• Authors: van der Meij, W. Marijn; Meijles, Erik W.; Marcos, Diego; Harkema, Tom T. L.; Candel, Jasper H. J.; Maas, Gilbert J.
• Is Part Of: Earth surface processes and landforms. Volume 47:Issue 4(2022)
• Page Start: 1089
• Page End: 1107
• Publication Date: 2022-01-30
• Subjects: convolutional neural network -- deep learning -- geomorphological map -- geomorphology -- mapping -- The Netherlands -- uncertainty; Geomorphology -- Periodicals; 551.4
• DOI: 10.1002/esp.5305
• Languages: English
• ISSNs: 0197-9337

Abstract

Abstract: Geomorphological maps provide information on the relief, genesis and shape of the earth's surface and are widely used in sustainable spatial developments. The quality of geomorphological maps is however rarely assessed or reported, which limits their applicability. Moreover, older geomorphological maps often do not meet current quality requirements and require updating. This updating is time‐consuming and because of its qualitative nature difficult to reproduce, but can be supported by novel computational methods. In this paper, we address these issues by (1) quantifying the uncertainty associated with manual geomorphological mapping, (2) exploring the use of convolutional neural networks (CNNs) for semi‐automated geomorphological mapping and (3) testing the sensitivity of CNNs to uncertainties in manually created evaluation data. We selected a test area in the Dutch push‐moraine district with a pronounced relief and a high variety of landforms. For this test area we developed five manually created geomorphological maps and 27 automatically created landform maps using CNNs. The resulting manual maps are similar on a regional level. We could identify the causes of disagreement between the maps on a local level, which often related to differences in mapping experience, choices in delineation and different interpretations of the legend. Coordination of mapping efforts and field validation are necessary to create accurate and precise maps. CNNs perform well in identifying landforms and geomorphological units, but fail at correct delineation. The human geomorphologist remains necessary to correct the delineation and classification of the computed maps. The uncertainty in the manually created data that are used to train and evaluate CNNs have a large effect on the model performance and evaluation. This also advocates for coordinated mapping efforts to ensure the quality of manually created training and test data. Further model development and data processing are required before CNNs can act as standalone mapping techniques. Abstract : We compare the quality of geomorphological maps created by humans and by computers. We identify and quantify the uncertainty that is associated with manual geomorphological mapping, explore the use of convolutional neural networks (CNNs) for geomorphological mapping and assess the sensitivity of CNNs to uncertainty in manually made maps that are used for training and evaluating the CNNs. Despite the uncertainty in manually made maps, the human geomorphologist remains necessary for correct delineation and interpretation of geomorphological maps.