GHS-BUILT-S ARCTIC R2025A – gridded built-up surface estimates for the Arctic region (1975-2030)

The conversion of gridded data between two grids and/or spatial reference systems, commonly referred to as “warping”, is a fundamental step in geospatial data processing workflows. This process involves data resampling, which inherently introduces uncertainty. When dealing with stacks of statistical, gridded datasets measuring cell-level densities, consistently enumerated across multiple points in time, it is crucial to employ a volume-preserving method. Such a method should not only preserve changes in observations along the temporal dimension but also maintain the total sums of measured data per point in time, and allowing for different resampling strategies, while minimizing local distortions in the warped data. Conventional raster-based warping tools available in Geographic Information Systems and coding-based geospatial data processing environments lack explicit control over these critical properties. To address this limitation, we propose a novel vector-based method for areal interpolation based on spatial overlay operations. This approach enables lossless resampling of gridded data, which we apply to the gridded built-up surface data from the Global Human Settlement Layer (GHSL) covering the period from 1975 to 2030. As vector-based spatial data operations are computationally expensive, our method leverages a parallel-processing framework, allowing efficient warping of global gridded data cubes. Furthermore, this approach facilitates the provision of statistical data cubes across various spatial reference systems and grid definitions at planetary scale and high spatial resolution, extendible to the use of areal or spatio-temporal interpolation methods. We implemented this method in Python and call it “VectorCubeWarp”.

This work introduces a new classification method in the remote sensing domain, suitably adapted to dealing with the challenges posed by the big data processing and analytics framework. The method is based on symbolic learning techniques, and it is designed to work in complex and information-abundant environments, where relationships among different data layers are assessed in model-free and computationally-effective modalities. The two main stages of the method are the data reduction-sequencing and the association analysis. The former refers to data representation; the latter searches for systematic relationships between data instances derived from images and spatial information encoded in supervisory signals. Subsequently, a new measure named the evidence-based normalized differential index, inspired by the probability-based family of objective interestingness measures, evaluates these associations. Additional information about the computational complexity of the classification algorithm and some critical remarks are briefly introduced. An application of land cover mapping where the input image features are morphological and radiometric descriptors demonstrates the capacity of the method; in this instructive application, a subset of eight classes from the Corine Land Cover is used as the reference source to guide the training phase.

Monitoring of the human-induced changes and the availability of reliable and methodologically consistent urban area maps are essential to support sustainable urban development on a global scale. The Global Human Settlement Layer (GHSL) is a project funded by the European Commission, Joint Research Centre, which aims at providing scientific methods and systems for reliable and automatic mapping of built-up areas from remote sensing data. In the frame of the GHSL, the opportunities offered by the recent availability of Sentinel-2 data are being explored using a novel image classification method, called Symbolic Machine Learning (SML), for detailed urban land cover mapping. In this paper, a preliminary test was implemented with the purpose of: (i) assessing the applicability of the SML classifier on Sentinel-2 imagery; (ii) evaluating the complementarity of Sentinel-1 and Sentinel-2; and (iii) understanding the added-value of Sentinel-2 with respect to Landsat for improving global high-resolution human settlement mapping. The overall objective is to explore areas of improvement, including the possibility of synergistic use of the different sensors. The results showed that noticeable improvement of the quality of the classification could be gained from the increased spatial detail and from the thematic contents of Sentinel-2 compared to the Landsat derived product as well as from the complementarity between Sentinel-1 and Sentinel-2 images.

Global fine-scale information extraction tasks using today’s remote sensing technologies are compared with Big Data Analytics tasks. Issues related to data classification, machine learning and evaluation of the results are discussed. A change of paradigm respect to the classical RS information processing model is proposed in order to cope with the Big RS Data characteristics.

Differential area profiles (DAPs) are point-based multiscale descriptors used in pattern analysis and image segmentation. They are defined through sets of size-based connected morphological filters that constitute a joint area opening top-hat and area closing bottom-hat scale-space of the input image. The work presented in this paper explores the properties of this image decomposition through sets of area zones. An area zone defines a single plane of the DAP vector field and contains all the peak components of the input image, whose size is between the zone’s attribute extrema. Area zones can be computed efficiently from hierarchical image representation structures, in a way similar to regular attribute filters. Operations on the DAP vector field can then be computed without the need for exporting it first, and an example with the leveling-like convex/concave segmentation scheme is given. This is referred to as the one-pass method and it is demonstrated on the Max-Tree structure. Its computational performance is tested and compared against conventional means for computing differential profiles, relying on iterative application of area openings and closings. Applications making use of the area zone decomposition are demonstrated in problems related to remote sensing and medical image analysis.

The location and identification of human settlements is a key information in any assessment related to human security and safety decision process, from the preparedness to and mitigation of natural hazards to postdisaster response and reconstruction. The human settlements can be defined as infrastructures build on earth surface for living, trading or any social activity.

In order to cover and analyze large areas where scarce and heterogeneous data may exist, the automatic information extraction from Earth Observation is the only sustainable strategy. Several studies about the detection of built-up presence from high resolution satellite were performed during the past few years. Among the various methods, a built-up index aggregating anisotropic textural co-occurence measures (PanTex) was demonstrated to be a robust indicator, where 54 high resolution optical images representing cities distributed around the world are processed. The validation of the built-up presence index emphasized its robustness against the type of constructions, the sun angles and the seasons of acquisitions. In this paper, we propose an alternative procedure for the calculation of built-up presence index from panchromatic high resolution satellite images. While radiometric descriptors of human settlements are highly variable across the world and with illumination conditions, the shape of settlements often contains right angles. This property being more stable, we propose a built-up index based on the density of corners. The index is obtained in two steps: - corners are detected by multi scale Harris detector based on differential morphological decompositions; - corners are spatially aggregated to form a density of corners, which is the built-up index. The differential morphological decomposition is a scale-space representation of the image, where image elements are separated by their scales. Then, the Harris corner indicator, which is highly dependent on a scale parameter, can be adapted to a set of scales. The output of the corner detection is a set of points associated to a scale, which represents the right angles in the image. The corners associated to a scale in the range of admissible settlements dimensions are selected and spatially aggregated to derive a density of corners.

The proposed index is extracted from various high resolution panchromatic images and it is compared to the PanTex. In the experimental section, the high correlation between both indicators proves the suitability of the proposed method for consistently detecting built-up presence. Moreover, it gives a new interpretation of the PanTex which is close to a density of corners. Such an observation is critical for understanding the variablity of the PanTex index in between dense urban and industrial areas (industrial areas being composed of large buildings mechanically contain less corners).

A new compact representation of differential morphological profile (DMP) vector fields is presented. It is referred to as the CSL model and is conceived to radically reduce the dimensionality of the DMP descriptors. The model maps three characteristic parameters, namely scale, saliency and level, into the RGB space through a HSV transform. The result is a a medium abstraction semantic layer used for visual exploration, image information mining and pattern classification. Fused with the PANTEX built-up presence index, the CSL model converges to an approximate building footprint representation layer in which color represents building class labels. This process is demonstrated on the first high resolution (HR) global human settlement layer (GHSL) computed from multi-modal HR and VHR satellite images. Results of the first massive processing exercise involving several thousands of scenes around the globe are reported along with validation figures.

A procedure for the calculation of a texture-derived built-up presence index (PanTex) from textural characteristics of panchromatic satellite data is presented. The index is based on fuzzy rule-based composition of anisotropic textural co-occurrence measures derived from the satellite data by the gray-level co-occurrence matrix (GLCM). The strength and weakness of the procedure is analyzed and compared with traditional radiometric and textural approaches with the help of specific examples.

A variant of the PanTex is proposed including information on vegetation if available (PanTexG).

The accuracy and robustness of PanTex against seasonal changes, multi-sensor, multi-scene, and data degradation by wavelet-based compression and histogram stretching is discussed with some examples.

Abstract not available