Mapping horizontal and vertical urban densification in Denmark with Landsat time-series from 1985 to 2018: a semantic segmentation solution

TL;DR

This paper presents a deep learning approach using Landsat time-series data to accurately map three-dimensional urban densification in Denmark, demonstrating improved transferability and generalization across different cities and years.

Contribution

It introduces a transferable deep learning method with multi-scale contextual information for long-term urban form mapping from Landsat imagery, outperforming traditional models.

Findings

DeepLab outperforms FCN and RF in accuracy.

Model trained on Danish data generalizes well to other European cities.

Urban growth patterns differ between Copenhagen and Aarhus.

Abstract

Landsat imagery is an unparalleled freely available data source that allows reconstructing horizontal and vertical urban form. This paper addresses the challenge of using Landsat data, particularly its 30m spatial resolution, for monitoring three-dimensional urban densification. We compare temporal and spatial transferability of an adapted DeepLab model with a simple fully convolutional network (FCN) and a texture-based random forest (RF) model to map urban density in the two morphological dimensions: horizontal (compact, open, sparse) and vertical (high rise, low rise). We test whether a model trained on the 2014 data can be applied to 2006 and 1995 for Denmark, and examine whether we could use the model trained on the Danish data to accurately map other European cities. Our results show that an implementation of deep networks and the inclusion of multi-scale contextual information greatly improve the classification and the model's ability to generalize across space and time. DeepLab provides more accurate horizontal and vertical classifications than FCN when sufficient training data is available. By using DeepLab, the F1 score can be increased by 4 and 10 percentage points for detecting vertical urban growth compared to FCN and RF for Denmark. For mapping the other European cities with training data from Denmark, DeepLab also shows an advantage of 6 percentage points over RF for both the dimensions. The resulting maps across the years 1985 to 2018 reveal different patterns of urban growth between Copenhagen and Aarhus, the two largest cities in Denmark, illustrating that those cities have used various planning policies in addressing population growth and housing supply challenges. In summary, we propose a transferable deep learning approach for automated, long-term mapping of urban form from Landsat images.