Journal Browser

Journal Browser

Deep Learning on the Landsat Archive

A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "Environmental Remote Sensing".

Deadline for manuscript submissions: 30 January 2025 | Viewed by 1158

Special Issue Editors

E-Mail Website
Guest Editor
Department of Environmental Resources Engineering, Intelligent Geocomputing Laboratory, State University of New York College of Environmental Science and Forestry, Syracuse, NY, USA
Interests: environmental monitoring; machine learning; image fusion; accuracy assessment; interdisciplinary land modeling
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Earth Resources Observation and Science (EROS) Center, U.S. Geological Survey, Sioux Falls, SD 57198, USA
Interests: remote sensing; machine learning; computer vision; spatial analysis; uncertainty quantification

E-Mail Website
Guest Editor
Earth Resources Observation and Science (EROS) Center, U.S. Geological Survey, Sioux Falls, SD 57198, USA
Interests: remote sensing; machine learning; artificial intelligence; geoinformatics

Special Issue Information

Dear Colleagues,

Landsat observations offer global, consistent coverage spanning more than fifty years. They have been instrumental in a wide range of studies in land cover and land use, allowing for, in addition, the assessment of natural hazards, urbanization, biodiversity, and climate, among other areas. Landsat’s standing as the workhorse of environmental remote sensing reflects its significant impact. There exists a vast amount of data, freely available and consistently processed, which is ready to offer more discoveries. The application of deep learning (DL) has emerged as a compelling methodology for use to analyze and extract knowledge from this large data archive.  DL has found fruitful ground in a wide range of data-intensive knowledge discovery tasks, e.g., in medical, automotive and security applications.

The goal of this Special Issue is to collect studies that integrate DL methods with the lengthy Landsat observational record. Submissions must use DL methods and be applied on Landsat observations. Non-DL methodologies and non-Landsat observations are also welcome in the context of comparison and calibration/validation, respectively, but not as standalone studies.

We invite manuscripts in:

  • both pixel and patch-based analysis, for example supervised/semi-supervised/unsupervised classification, segmentation, scene labeling and object detection,
  • fusion with other sensors of different spectral and spatial resolutions and/or signal types (e.g., optical, radar, lidar) and super-resolution tasks,
  • the effect and support of reference data types and availability (e.g., sampling strategies, transfer learning),
  • image preprocessing methods, such as sensor calibration/validation and atmospheric correction,
  • time series analysis (e.g., monitoring, forecasting, anomaly detection) and change detection,
  • reviewing collections of validation data appropriate for integration with the Landsat archive.

Prof. Dr. Giorgos Mountrakis
Dr. Pete Doucette
Dr. Neal J. Pastick
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.


  • Landsat classification
  • deep learning
  • time series analysis
  • image fusion
  • image preprocessing
  • classification sampling
  • image segmentation

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:


46 pages, 18613 KiB  
Improved Landsat Operational Land Imager (OLI) Cloud and Shadow Detection with the Learning Attention Network Algorithm (LANA)
by Hankui K. Zhang, Dong Luo and David P. Roy
Remote Sens. 2024, 16(8), 1321; - 9 Apr 2024
Viewed by 820
Landsat cloud and cloud shadow detection has a long heritage based on the application of empirical spectral tests to single image pixels, including the Landsat product Fmask algorithm, which uses spectral tests applied to optical and thermal bands to detect clouds and uses [...] Read more.
Landsat cloud and cloud shadow detection has a long heritage based on the application of empirical spectral tests to single image pixels, including the Landsat product Fmask algorithm, which uses spectral tests applied to optical and thermal bands to detect clouds and uses the sun-sensor-cloud geometry to detect shadows. Since the Fmask was developed, convolutional neural network (CNN) algorithms, and in particular U-Net algorithms (a type of CNN with a U-shaped network structure), have been developed and are applied to pixels in square patches to take advantage of both spatial and spectral information. The purpose of this study was to develop and assess a new U-Net algorithm that classifies Landsat 8/9 Operational Land Imager (OLI) pixels with higher accuracy than the Fmask algorithm. The algorithm, termed the Learning Attention Network Algorithm (LANA), is a form of U-Net but with an additional attention mechanism (a type of network structure) that, unlike conventional U-Net, uses more spatial pixel information across each image patch. The LANA was trained using 16,861 512 × 512 30 m pixel annotated Landsat 8 OLI patches extracted from 27 images and 69 image subsets that are publicly available and have been used by others for cloud mask algorithm development and assessment. The annotated data were manually refined to improve the annotation and were supplemented with another four annotated images selected to include clear, completely cloudy, and developed land images. The LANA classifies image pixels as either clear, thin cloud, cloud, or cloud shadow. To evaluate the classification accuracy, five annotated Landsat 8 OLI images (composed of >205 million 30 m pixels) were classified, and the results compared with the Fmask and a publicly available U-Net model (U-Net Wieland). The LANA had a 78% overall classification accuracy considering cloud, thin cloud, cloud shadow, and clear classes. As the LANA, Fmask, and U-Net Wieland algorithms have different class legends, their classification results were harmonized to the same three common classes: cloud, cloud shadow, and clear. Considering these three classes, the LANA had the highest (89%) overall accuracy, followed by Fmask (86%), and then U-Net Wieland (85%). The LANA had the highest F1-scores for cloud (0.92), cloud shadow (0.57), and clear (0.89), and the other two algorithms had lower F1-scores, particularly for cloud (Fmask 0.90, U-Net Wieland 0.88) and cloud shadow (Fmask 0.45, U-Net Wieland 0.52). In addition, a time-series evaluation was undertaken to examine the prevalence of undetected clouds and cloud shadows (i.e., omission errors). The band-specific temporal smoothness index (TSIλ) was applied to a year of Landsat 8 OLI surface reflectance observations after discarding pixel observations labelled as cloud or cloud shadow. This was undertaken independently at each gridded pixel location in four 5000 × 5000 30 m pixel Landsat analysis-ready data (ARD) tiles. The TSIλ results broadly reflected the classification accuracy results and indicated that the LANA had the smallest cloud and cloud shadow omission errors, whereas the Fmask had the greatest cloud omission error and the second greatest cloud shadow omission error. Detailed visual examination, true color image examples and classification results are included and confirm these findings. The TSIλ results also highlight the need for algorithm developers to undertake product quality assessment in addition to accuracy assessment. The LANA model, training and evaluation data, and application codes are publicly available for other researchers. Full article
(This article belongs to the Special Issue Deep Learning on the Landsat Archive)
Show Figures

Figure 1

Back to TopTop