Comparing geomorphological maps made manually and by deep learning

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.

Intelligent classification and analysis of regional landforms based on automatic feature selection

“…Traditional image features were often extracted through convolutional layers, pooling layers and forward and backward propagation parameters (Du et al, 2019). However, such multiple pooling operations are liable to cause spatial information loss, resulting in the gradient features being mistaken, the segmentation boundaries being ambiguous and the fine accuracy being insufficient among landform types (van der Meij et al, 2022). To address the existing questions, the UNet model has been put forward to break the deadlock, which not only applies contextual semantic information to predict the type of each pixel but also uses the jump structure connection to combine deep and shallow features (Sun et al, 2023).…”

Exploring the Influence of Input Feature Space on CNN‐Based Geomorphic Feature Extraction From Digital Terrain Data

“…Saha et al, 2021;Schönfeldt et al, 2022;Thi Ngo et al, 2021), landform and geomorphic feature extraction (e.g., Bickel et al, 2021;Du et al, 2019;S. Li et al, 2020;Moseley et al, 2021;Robson et al, 2020;van der Meij et al, 2022;Xie et al, 2020;Xu et al, 2021;W. Zhang et al, 2018W.…”

“…More recently, DL methods have been explored for slope failure mapping or susceptibility modelling (e.g., Gholami et al., 2021; Huang et al., 2020; S. Li et al., 2020; Prakash et al., 2020; S. Saha et al., 2021; Schönfeldt et al., 2022; Thi Ngo et al., 2021), landform and geomorphic feature extraction (e.g., Bickel et al., 2021; Du et al., 2019; S. Li et al., 2020; Moseley et al., 2021; Robson et al., 2020; van der Meij et al., 2022; Xie et al., 2020; Xu et al., 2021; W. Zhang et al., 2018, 2020), mapping of anthropogenic landscape alterations or archaeological features (e.g., Guyot et al., 2018; Maxwell et al., 2020; Suh et al., 2021; Trier et al., 2015, 2019), and digital soil unit mapping (e.g., Behrens et al., 2018; Padarian et al., 2019; Wadoux, 2019). Generally, these studies highlight the value of modelling spatial patterns in LSPs and/or other spatial data to improve the use of such data for geomorphic mapping and feature extraction.…”

Explanation of the influence of geomorphometric variables on the landform classification based on selected areas in Poland

“…Recent research on the application of convolutional neural networks in geomorphology includes the use of a multi-channel deep neural network architecture to classify landforms 13 , a comparison of Random Forests and U-Net models to classify loess formations 14 , a comparison between traditional and automated U-Net-based approaches 15 , and classification using textural properties of the terrain 16 .…”