Classification methods for detecting and evaluating changes in desertification-related features in arid and semiarid environments

Abstract

Land cover, land use, soil salinization, and sand encroachment, which are desertification-indicating features, were integrated in a diachronic assessment, obtaining quantitative and qualitative information on the ecological state of the land, particularly degradation tendencies. In arid and semi-arid study areas of Algeria and Tunisia, sustainable development requires the understanding of these dynamics as it withstands the monitoring of desertification processes. Both visual interpretation and automated classification approaches have been set up for salt and sand features extraction using historical and present Landsat imagery. The automated one includes a decision tree classifier and an unsupervised classification applied to the principal components extracted from Knepper ratios composite. New spectral indices are employed in the decision tree classifier for the extraction of features of interest. The validation of the classification methods showed that the decision tree had an overall accuracy over 85% in both areas. Integrating results with ancillary spatial data, we could identify driving forces and estimate the metrics of desertification processes. In the Biskra area (Algeria), it emerged that the expansion of irrigated farmland in the past three decades has been contributing to an ongoing secondary salinization of soils, with an increase of over 75%. In the Oum Zessar area (Tunisia), there has been substantial change in several landscape components in the last decades related to increased anthropic pressure and settlement, agricultural policies, and national development strategies. One of the most concerning aspects is the expansion of sand-encroached areas over the last three decades of around 27%.

Quantitative Assessment of Desertification in an Arid Oasis Using Remote Sensing Data and Spectral Index Techniques

“…Several remote sensing methods and techniques were developed to map and assess desertification in arid and semiarid areas, which can be classified into: Visual interpretation [7], SMA [29,30], classification algorithms [14,31,32] and spectral indices (NDVI, albedo) [2] and image transformation, such as TCT [33].…”

“…On the basis of surveys and experimental data, specific indices have been developed to monitor and assess desertification in the arid and the semiarid regions. Desertification hazards can be mapped based on remotely sensed images using traditional classification methods [14], spectral mixture analysis (SMA) [15] or spectral indices [2]. Some studies proposed that the normalized difference vegetation index (NDVI)-albedo feature space can be used to extract desertification on the basis of the negative relationship between vegetation coverage and surface albedo [16] or the hybrid method combined with the SMA and spectral indices through the use of vegetation fraction and albedo feature space [15].…”

Assessing and mapping wind erosion-prone areas in northeastern Algeria using additive linear model, AHP, FAHP approaches, GIS, and medium resolution multisource remotely sensed data

“…The data used in this study were collected from multi-source datasets (remote sensing images from satellites), existing digitized data in the form of GIS vector maps, government statistical data, and data from the past studies or field surveys of the study area: (1) Four Landsat 8 OLI images were used to build mosaic image for the year 2014 (path/row 192/35, 192/36, 28/45, 193/35 and 193/36) with a spatial resolution of during summer period (CC< 2%). According to Afrasinei et al (2017), only Landsat image with less than 10% CC can be used in such study. All Landsat images were sourced from the USGS Landsat archive (L1T) available at http:// glovis.usgs.gov; (2) Shuttle Radar Topography Mission (SRTM) data were used to extract the slope, at 1arc-second resolution (30m) (http://gdem.ersdac.jspacesystems.or.jp); (3) total annual precipitation (mm) and mean annual evapotranspiration (mm) at ~5-km-pixel resolution for 10 years (2009-2018) obtained from the FAO Water Productivity Open-access portal (WaPOR version2) available at https://wapor.apps.fao.org;(4) characteristics of the soil, namely, clay percentage silt percentage, sand percentage, organic matter content were acquired from the Soil grid database (http:// soilgrids.org/); (5) mean wind speeds (m/s) for the period 2008-2017 were downloaded from the Global Wind Atlas website (http://globalwindatlas.info); (6) statistical data on population, agriculture, and grazing during the year 2015 were compiled from directorate general for agriculture (DGA), and spatial planning department (SPD) .…”

A data‐mining‐based approach for aeolian desertification susceptibility assessment: A case‐study from Northern China

“…In addition, the DT is suitable for exploratory knowledge discovery (Braun et al, 2015;Chen et al, 2014). Currently, DT algorithms have been successfully used in soil mapping (Moran & Bui, 2002;Qi & Zhu, 2003), mineral prospecting mapping (Chen et al, 2014), landslide susceptibility mapping (Braun et al, 2015;Yeon et al, 2010), land coverage classification (Colstoun & Walthall, 2006), and desertification assessment (Afrasinei et al, 2017).…”