So2Sat LCZ42: A Benchmark Data Set for the Classification of Global Local Climate Zones [Software and Data Sets]

Abstract

This article was submitted to IEEE Geoscience and Remote Sensing Magazine.Access to labeled reference data is one of the grand challenges in supervised machine learning endeavors. This is especially true for an automated analysis of remote sensing images on a global scale, which enables us to address global challenges such as urbanization and climate change using state-of-theart machine learning techniques. To meet these pressing needs, especially in urban research, we provide open access to a valuable benchmark dataset named "So2Sat LCZ42," which consists of local climate zone (LCZ) labels of about half a million Sentinel-1 and Sentinel-2 image patches in 42 urban agglomerations (plus 10 additional smaller areas) across the globe. This dataset was labeled by 15 domain experts following a carefully designed labeling work flow and evaluation process over a period of six months. As rarely done in other labeled remote sensing dataset, we conducted rigorous quality assessment by domain experts. The dataset achieved an overall confidence of 85%. We believe this LCZ dataset is a first step towards an unbiased globallydistributed dataset for urban growth monitoring using machine learning methods, because LCZ provide a rather objective measure other than many other semantic land use and land cover classifications. It provides measures of the morphology, compactness, and height of urban areas, which are less dependent on human and culture. This dataset can be accessed from

A framework for large-scale mapping of human settlement extent from Sentinel-2 images via fully convolutional neural networks

“…2 illustrates the processed Sentinel-2 image of central Munich, Germany, and the reference data. There are two approaches for remote sensing image classification via deep learning: working with either patch-based CNNs designed for image classification [24,26,30,31,32,49,50,51] or encoder-decoder-like neural networks designed for semantic segmentation [25,27,28,29]. The former works under the assumption of just a single label for each image patch, and applies the trained model to the image of a study area via a sliding window approach, with the target GSD as the stride of the sliding window.…”

Mapping Human Settlements with Multi-seasonal Sentinel-2 Imagery and Attention-based ResNeXt

“…The ground truth labels available for selected neighborhoods in the seven cities are taken from the So2Sat LCZ42 dataset [13], which was hand-labeled for LCZ mapping. The 17 LCZs are: Compact high-rise, Compact mid-rise, Compact low-rise, Open high-rise, Open mid-rise, Open low-rise, Lightweight low-rise, Large low-rise, Sparsely built, Heavy industry, Dense trees, Scattered trees, Bush or scrub, Low plants, Bare rock or paved, Bare soil or sand and water, respectively.…”

Fusing Multi-Seasonal Sentinel-2 Images with Residual Convolutional Neural Networks for Local Climate Zone-Derived Urban Land Cover Classification

“…The (mostly) cloud free multiseasonal Sentinel-2 imagery is processed with Google Earth Engine (GEE) [8] and the 10 meter and 20 meter bands are used. The reference ground truth data is from the LCZ42 dataset [9], and is further prepared by class combination and data augmentation as in [5]. Also, the accuracy assessment is carried out on absolutely balanced samples.…”