Toward an operational framework for fine-scale urban land-cover mapping in Wallonia using submeter remote sensing and ancillary vector data

Abstract

Eléonore Wolff, "Toward an operational framework for fine-scale urban land-cover mapping in Wallonia using submeter remote sensing and ancillary vector data," J. Appl. Remote Sens. 11(3), 036011 (2017), doi: 10.1117/1.JRS.11.036011. Abstract. Encouraged by the EU INSPIRE directive requirements and recommendations, the Walloon authorities, similar to other EU regional or national authorities, want to develop operational land-cover (LC) and land-use (LU) mapping methods using existing geodata. Urban planners and environmental monitoring stakeholders of Wallonia have to rely on outdated, mixed, and incomplete LC and LU information. The current reference map is 10-years old. The two object-based classification methods, i.e., a rule-and a classifier-based method, for detailed regional urban LC mapping are compared. The added value of using the different existing geospatial datasets in the process is assessed. This includes the comparison between satellite and aerial optical data in terms of mapping accuracies, visual quality of the map, costs, processing, data availability, and property rights. The combination of spectral, tridimensional, and vector data provides accuracy values close to 0.90 for mapping the LC into nine categories with a minimum mapping unit of 15 m 2 . Such a detailed LC map offers opportunities for fine-scale environmental and spatial planning activities. Still, the regional application poses challenges regarding automation, big data handling, and processing time, which are discussed. © The Authors. Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

An innovative use of orthophotos – possibilities to assess plant productivity from colour infrared aerial orthophotos

“…Consequently, colour infrared aerial photos are conventionally regarded as unfit for image transformation and index calculation and we have not found that they have been used to assess primary productivity before. Still, colour infrared aerial orthophotos are increasingly used to automatically separate vegetation from non-vegetation (Banzhaf and Hofer 2008;Grafius et al 2016;Beaumont et al 2017). If it would be possible to use the information contained in the colour infrared aerial photos to obtain some assessment of primary productivity it could provide a fruitful way to investigate vegetation over regional areas of several square km with a high spatial resolution, especially in areas with low-satellite coverage.…”

“…; Beaumont et al. ). If it would be possible to use the information contained in the colour infrared aerial photos to obtain some assessment of primary productivity it could provide a fruitful way to investigate vegetation over regional areas of several square km with a high spatial resolution, especially in areas with low‐satellite coverage.…”

Mapping slums and model population density using earth observation data and open source solutions

“…It could be used on a highperformance computing system to distribute the work on hundreds of different nodes. In this regard, a comparison with eCognition® rule-based classification highlighted the flexibility of the open-source framework in terms of perspective for further developments [13].…”

Use of Sentinel-2 and LUCAS Database for the Inventory of Land Use, Land Use Change, and Forestry in Wallonia, Belgium

“…Such inventory reports have to provide information regarding land identification for estimating change in carbon stock. According to [2] definitions, GHG emissions are estimated through the classification of the land into six LU categories: (1) forest land, (2) cropland, (3) grassland, (4) wetlands, (5) settlements, and (6) other land. Only broad and nonprescriptive definitions are provided for these LU categories: Countries may use their own definitions, which may or may not refer to internationally accepted definitions.…”

“…The current LULC map of Wallonia (Carte d'Occupation des sols de Wallonie (COSW)) dates from 2007 and is based on a combination of several data sources such as a cadastral plan and agricultural census. According to Reference [4], the LULC map of Wallonia relies on outdated, mixed, and incomplete LC and LU information. For this study, we were looking for an approach that would integrate data available at the European scale (i.e., not regional datasets) and be updatable on an annual basis.…”