Deep Learning for Land Use and Land Cover Classification Based on Hyperspectral and Multispectral Earth Observation Data: A Review

Abstract

Lately, with deep learning outpacing the other machine learning techniques in classifying images, we have witnessed a growing interest of the remote sensing community in employing these techniques for the land use and land cover classification based on multispectral and hyperspectral images; the number of related publications almost doubling each year since 2015 is an attest to that. The advances in remote sensing technologies, hence the fast-growing volume of timely data available at the global scale, offer new opportunities for a variety of applications. Deep learning being significantly successful in dealing with Big Data, seems to be a great candidate for exploiting the potentials of such complex massive data. However, there are some challenges related to the ground-truth, resolution, and the nature of data that strongly impact the performance of classification. In this paper, we review the use of deep learning in land use and land cover classification based on multispectral and hyperspectral images and we introduce the available data sources and datasets used by literature studies; we provide the readers with a framework to interpret the-state-of-the-art of deep learning in this context and offer a platform to approach methodologies, data, and challenges of the field.

The New Hyperspectral Satellite PRISMA: Imagery for Forest Types Discrimination

“…In vegetation studies, and more specifically in forestry applications, several studies have used such criteria to discriminate different tree species or groups of species on a band-by-band basis. Roberts et al [ 20 ] evaluated pairwise forest species separability at leaf to stand scale, by means of hyperspectral data. Vaiphasa et al [ 21 ] were able to identify and distinguish 16 vegetation types in a mangrove wetland in Thailand, through the JM distance.…”

Nondestructive Phenolic Compounds Measurement and Origin Discrimination of Peated Barley Malt Using Near-Infrared Hyperspectral Imagery and Machine Learning

“…With the concept first derived in [1], HSI aims to identify the surface materials in a form of images. Afterwards, HSI has been successfully applied in many remote sensing tasks, including precision agriculture [4], land-cover analysis [5], military surveillance [6] and mineral exploration [7]. Owing to its additional radiance spectrum information for each pixel, HSI has become an emerging technique for nondestructive inspection and assessment in a wide range of lab-based new applications, e.g.…”

Resolution Enhancement of Remotely Sensed Land Surface Temperature: Current Status and Perspectives

“…In the field of land use and land cover classification of hyperspectral data, several well-validated public datasets, such as Pavia and Indian Pines datasets, have been made available to the scientific community. They, along with annotations to evaluate the model performances, have boosted the model cross-comparison among researchers [107,108]. Such standard datasets could be developed from the existing studies to test the performance of different LST resolution enhancement methods.…”