Deep learning for dune pattern mapping with the AW3D30 global surface model

Abstract

In this paper we present a deep learning (U‐Net)‐based workflow for classifying linear dune landforms based on the discrete Laplacian convolution of a new global elevation dataset, the AW3D30 digital surface model. Crest vectors were then derived for landscape pattern analysis. The U‐Net crest classification model was trained and evaluated on sample data from dunefields across the Australian continent. The resulting crest vectors and dune defect placement were then evaluated in typical semi‐arid and arid dune landscapes in eastern central Australia where high‐resolution (5 m horizontal) digital elevation models are available (for three out of our four study sites) as a reference dataset. The method was applied to quantify dune pattern metrics for the entire Simpson Desert dunefield, Australia. The U‐Net does a very good job of segmenting dune crests, even where dunes are less clear in the Laplacian map (intersection over union score ≈ 0.68). When crest vectors and dune defects (network nodes) were derived, the defect predictions were typically correct (0.4 to 0.79 correctness) but incomplete (0.02 to 0.64 completeness). Much of the residual error was traced to the resolution of the input data. Through the application to the Simpson Desert, we nevertheless demonstrated that our method can effectively be used for regional‐scale dune pattern analysis. Furthermore, we suggest that the combination of morphological filtering and a convolutional neural network could readily be adapted to target other geomorphic features, such as channel networks or geological lineaments. © 2020 John Wiley & Sons, Ltd.

Comparing geomorphological maps made manually and by deep learning

“…Due to the combination of spatial data generalization and segmentation, CNNs can be seen as a combination of object‐based and pixel‐based mapping techniques. This promising method is increasingly applied for mapping landforms and geomorphology (Abolt & Young, 2020; Bhuiyan et al, 2020; Du et al, 2019; Li et al, 2020; Palafox et al, 2017; Shumack et al, 2020; Verschoof‐Van der Vaart & Lambers, 2019).…”

“…This promising method is increasingly applied for mapping landforms and geomorphology (Abolt & Young, 2020;Bhuiyan et al, 2020;Du et al, 2019;Li et al, 2020;Palafox et al, 2017;Shumack et al, 2020; Verschoof- .…”

Research on the Change in Public Art Landscape Pattern Based on Deep Learning

“…In the formula, P denotes the probability of conversion between various types of land in the region, P ab denotes the probability of conversion of land use type a to b, n denotes land use type n in formula (17) and the total number of land use types in formula (17), so the matrix should satisfy the following two conditions:…”

“…erefore, when applied to a new research site, the workload of training data collection can be greatly reduced. Literature [17] is applied to urban landscape design and proposed the processing and application of urban landscape images to analyze landscape changes.…”

GC Insights: Identifying conditions that sculpted bedforms – human insights to building an effective AI (artificial intelligence)

“…Machine learning or "AI" (artificial intelligence) algorithms, such as artificial neural networks (ANNs), have great potential in geomorphology (Sofia et al, 2016;Froehlich, 2020;Valentine and Kalnins, 2016;Shumack et al, 2020) and offer an opportunity to examine this problem, as they do not assume simple (e.g. linear or one-to-one) relationships between inputs and predicted variables (Wang et al, 2009;Faruk, 2010).…”