Land-Use and Land-Cover Classification in Semi-Arid Areas from Medium-Resolution Remote-Sensing Imagery: A Deep Learning Approach

Abstract

Detailed Land-Use and Land-Cover (LULC) information is of pivotal importance in, e.g., urban/rural planning, disaster management, and climate change adaptation. Recently, Deep Learning (DL) has emerged as a paradigm shift for LULC classification. To date, little research has focused on using DL methods for LULC mapping in semi-arid regions, and none that we are aware of have compared the use of different Sentinel-2 image band combinations for mapping LULC in semi-arid landscapes with deep Convolutional Neural Network (CNN) models. Sentinel-2 multispectral image bands have varying spatial resolutions, and there is often high spectral similarity of different LULC features in semi-arid regions; therefore, selection of suitable Sentinel-2 bands could be an important factor for LULC mapping in these areas. Our study contributes to the remote sensing literature by testing different Sentinel-2 bands, as well as the transferability of well-optimized CNNs, for semi-arid LULC classification in semi-arid regions. We first trained a CNN model in one semi-arid study site (Gujranwala city, Gujranwala Saddar and Wazirabadtownships, Pakistan), and then applied the pre-trained model to map LULC in two additional semi-arid study sites (Lahore and Faisalabad city, Pakistan). Two different composite images were compared: (i) a four-band composite with 10 m spatial resolution image bands (Near-Infrared (NIR), green, blue, and red bands), and (ii) a ten-band composite made by adding two Short Wave Infrared (SWIR) bands and four vegetation red-edge bands to the four-band composite. Experimental results corroborate the validity of the proposed CNN architecture. Notably, the four-band CNN model has shown robustness in semi-arid regions, where spatially and spectrally confusing land-covers are present.

Review of Desert Mobility Assessment and Desertification Monitoring Based on Remote Sensing

“…It is very difficult to separate spectrally confused land cover classes in semiarid regions using mediumresolution remotely sensed data, as the spectral response of several classes (e.g., settlements, barren land, and fallow land) are highly similar. Ali et al [132] contributed to the remote sensing literature by testing different Sentinel-2 bands, as well as the transferability of welloptimized CNNs, for semi arid land use and land cover (LULC) classification in semiarid regions. Dang et al [133] used a variety of satellite remote sensing data, such as Landsat, SPOT and GF, and combined them with a variety of machine-learning methods to develop the regional dataset and soil erosion intensity database of the Kubuqi Desert from 1990 to 2020 in the study of land use in the desert.…”

Machine Learning-Based Land Use and Land Cover Mapping Using Multi-Spectral Satellite Imagery: A Case Study in Egypt

“…Ali, K. et al in [21] discuss the use of deep learning methods for LULC classification in semi-arid regions using remote sensing imagery with a medium level of resolution. The authors emphasize the value of comprehensive LULC data for a variety of applications such as urban and rural planning, disaster management, and climate change adaptation.…”

Bare Land Referenced Algorithm from Hyper-Temporal Data (BRAH) for Land Use and Land Cover Age Estimation

“…In this study, a simple reflectance thresholding method was applied to the atmospheric normalized corrected data. While this approach is time-consuming, there are more sophisticated land cover classification methods available that have been proven to be highly accurate [15][16][17]. Some methods can automatically detect land cover types without relying on predefined spectral thresholds [18,19].…”