Deep Learning Classification of Land Cover and Crop Types Using Remote Sensing Data

By Nataliia Kussul, M. Lavreniuk, S. Skakun, Andrii Shelestov. 2017

1,488 citations recorded by the source corpus.

Subfields: Atmospheric Science, Ecology, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

In Ecology

In Media Technology

Citations in the corpus

Deep Learning for IoT Big Data and Streaming Analytics: A Survey (2017, methodology): “DL also has been used in remote sensing for land and crop detection and classification [135]–[137].”
A review of deep learning methods for semantic segmentation of remote sensing imagery (2021, methodology): “…monitoring (Blaschke, Lang, Lorup, Strobl, & Zeil, 2000; Yuan & Sarma, 2011), crop cover and type analysis (Yang, Chen, Yuan, & Liu, 2016; Kussul, Lavreniuk, Skakun, & Shelestov, 2017; Jadhav & Singh, 2018), tree species in forests (Dechesne, Mallet, Le Bris, & Gouet-Brunet, 2017),…”
Land-cover classification with high-resolution remote sensing images using transferable deep models (2018, methodology): “As an alternative, end-to-end CNN models are adopted to interpret RS images [37–39,66,67].”
Unmanned Aircraft System (UAS) Technology and Applications in Agriculture (2019, background): “Traditionally, aerial images could only be gathered from satellites, such as those from the Landsat program or through aircraft [4,5].”
Temporal Convolutional Neural Network for the Classification of Satellite Image Time Series (2018, methodology): “Regarding the classification of multi-source and multi-temporal data, 1D-CNN and 2D-CNN have been used without taking advantage of the temporal dimension [35,36]: convolutions are applied either in the spectral domain or in the spatial domain, excluding the temporal one.”
Recent Applications of Landsat 8/OLI and Sentinel-2/MSI for Land Use and Land Cover Mapping: A Systematic Review (2020, methodology): “This factor has expanded the handling and analysis of big Earth spatio-temporal datasets of multi-source data with a Landsat-like resolution [19], and the increase in spatial resolution, free access policies, and systematic global coverage have created a new era to improve LULC and LULCC application”
Deep learning in remote sensing: a review (2017, methodology): “In [27], the authors attempted to carry out the classification of crop types using 1-D CNN and 2-D CNN.”
Deep learning in environmental remote sensing: Achievements and challenges (2020, background): “The present paper mainly reviewed the studies in terms of the pixel-level approaches, which are mostly used for pixel-to-pixel land cover classification, and classified each pixel in images by learning endto-end deep models (Kussul et al., 2017; Li et al., 2016).”
Self-Supervised Pretraining of Transformers for Satellite Image Time Series Classification (2020, methodology): “Among these methods, convolutional neural networks (CNNs) [20, 21] and recurrent neural networks (RNNs, including Long Short-Term Memory (LSTM) or Gated Recurrent Units (GRU)) [22, 23] have been”
Plant Disease Detection and Classification by Deep Learning (2019, methodology): “For classification of crop type, [47] used author-modified CNN, [36] applied VGG 16, [34] implemented three unit LSTM, and [33] used CNN and RGB histogram technique.”
Sentinel-2 Data for Land Cover/Use Mapping: A Review (2020, background): “[90] compared the classification results between Landsat OLI-8 which has no red-edge band and Sentinel-2 images.”
In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness (2020, background): “Crop type or cropland prediction is an important intermediate problem for crop yield prediction, which can aid efficient agricultural practices (“precision agriculture”) that are adaptable to different crop regions [5, 23, 28, 38].”