A hybrid learning model for efficient classification of Land Use and land change from satellite images. (December 2022)

• Record Type: Journal Article
• Authors: Sengan, Sudhakar; Karn, Arodh Lal; Pustokhin, Denis A.; Pustokhina, Irina V.; Alharbi, Meshal
• Is Part Of: Physics and chemistry of the earth. Volume 128(2022)
• Publication Date: 2022-12
• Subjects: Land use and land cover -- Classification -- Machine learning -- Deep learning -- RAVNet -- Spatial analysis -- Accuracy; Geophysics -- Periodicals; Geochemistry -- Periodicals; Earth sciences -- Periodicals; Geodesy -- Periodicals; Astrophysics -- Periodicals; 550
• DOI: 10.1016/j.pce.2022.103284
• Languages: English
• ISSNs: 1474-7065

Abstract

Abstract: With Deep Learning (DL) outperforming previous Machine Learning (ML) techniques in classifying images, the remote sensing community has recently shown an increased interest in using these algorithms to classify Land Use and Land Cover (LULC) using multispectral and hyperspectral data. Land Use (LU) and Land Cover (LC) are two types of cartographic data that are used to develop smart cities and monitor the environment. LULC classification can benefit greatly from successfully applying remote sensing Image Classification (IC) using high spatial resolution data. The acquisition of spatiotemporal data for LULC classification has been made more accessible because of recent improvements in spatial analysis and Deep Learning (DL) technology. Considering the quality of Deep Neural Networks (DNN) in related Computer Vision (CV) tasks and the enormous volume of remotely sensed data accessible, DL methods appear to be particularly promising for modelling many remote sensing problems. However, there are several issues with ground-truth, resolution, and the nature of data that have a significant impact on categorization performance. We propose a Reversible Residual Network (RAVNet), a hybrid residual attention sensitive segmentation approach, to precisely categorize LULC in this study. The suggested network is based on the VNet model, which extracts relevant information by mixing low-level and high-level Feature Maps (FM). The attention-aware features change adaptively to the integration of residual modules. Our system was tested on the National Agriculture Imagery Program (NAIP) dataset, and the findings demonstrate that our architecture is competitive against other learning models. Highlights: RAVNet, a hybrid residual attention-aware LULC extraction NN inspired by ResNet. A residual VNet architecture allowing for DCNN optimization and performance enhancement. ResNet tested on NAIP and demonstrates that it outperforms existing learning models.