Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
7.9
5.0
Journals
Remote Sensing
Special Issues
Machine Learning Methods Applied to Optical Satellite Images
remotesensing-logo
Submit to Remote Sensing Review for Remote Sensing Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Machine Learning Methods Applied to Optical Satellite Images

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

Deadline for manuscript submissions: closed (31 July 2023) | Viewed by 8709

Special Issue Editors

Prof. Dr. Olena Dubovyk

E-Mail Website
Guest Editor
Department of Geography, University of Bergen, 5020 Bergen, Norway
Interests: remote sensing of land surface dynamics; remote sensing for land degradation and drought monitoring & assessment; remote sensing for agricultural applications; earth observation and geo-information for policy support and international cooperation support (SDGs, Sendai indicators etc.)
Special Issues, Collections and Topics in MDPI journals
Dr. Gohar Ghazaryan

E-Mail Website
Guest Editor
Centre for Agricultural Landscape Research (ZALF), Eberswalder Straße 84, 15374 Müncheberg, Germany
Interests: time series analysis of imagery; landcover/landuse change; cloud computing; data fusion; crop type mapping

Special Issue Information

Dear Colleagues,

In recent years, machine learning algorithms have been remarkably successful. Many data-intensive technical and scientific fields have benefited from these developments, including search engines, speech recognition, and robotics. These applications also include remote sensing tasks. There are many types of remote sensing data available today collected from sensors deployed on different platforms (e.g., aircraft, satellite). Sensors can capture single band images, as well as multi- and hyperspectral data. In remote sensing applications, long time series data are often incorporated into monitoring tasks; therefore, image exploitation has a focus on long time series data with Machine Learning algorithms. Nevertheless, several aspects of the implementation of these methods are still challenging, such as the availability of large reference datasets, spatial autocorrelation and eventually the generalizability and transferability of the models.

 In this special issue we would like to explore the wide-range of Machine learning applications to extract patterns and insights from Remote Sensing data with the main focus on optical imagery.  We invite papers that focus on (i) applications of a variety of methods ranging from basic algorithms such as PCA and K-Means to more sophisticated classification and regression frameworks like SVMs, decision trees, Random Forests, and artificial neural networks; (ii) methodological papers that propose new Machine Learning algorithms or their improvements for Remote Sensing applications, as well as (iii) review papers.

Dr. Olena Dubovyk
Dr. Gohar Ghazaryan
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com 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.

Keywords

  • land cover/land use mapping
  • biophysical parameter retrieval
  • multiscale data fusion
  • anomaly detection

Published Papers (4 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

13 pages, 5845 KiB  
Communication
Imaging Simulation Method for Novel Rotating Synthetic Aperture System Based on Conditional Convolutional Neural Network
by Yu Sun, Xiyang Zhi, Shikai Jiang, Jinnan Gong, Tianjun Shi and Nan Wang
Remote Sens. 2023, 15(3), 688; https://doi.org/10.3390/rs15030688 - 24 Jan 2023
Cited by 6 | Viewed by 1223
Abstract
The novel rotating synthetic aperture (RSA) is a new optical imaging system that uses the method of rotating the rectangular primary mirror for dynamic imaging. It has the advantage of being lightweight, with no need for splicing and real-time surface shape maintenance on [...] Read more.
The novel rotating synthetic aperture (RSA) is a new optical imaging system that uses the method of rotating the rectangular primary mirror for dynamic imaging. It has the advantage of being lightweight, with no need for splicing and real-time surface shape maintenance on orbit. The novel imaging method leads to complex image quality degradation characteristics. Therefore, it is vital to use the image quality improvement method to restore and improve the image quality to meet the application requirements. For the RSA system, a new system that has not been applied in orbit, it is difficult to construct suitable large datasets. Therefore, it is necessary to study and establish the dynamic imaging characteristic model of the RSA system, and on this basis provide data support for the corresponding image super resolution and restoration method through simulation. In this paper, we first analyze the imaging characteristics and mathematically model the rectangular rotary pupil of the RSA system. On this basis, combined with the analysis of the physical interpretation of the blur kernel, we find that the optimal blur kernel is not the point spread function (PSF) of the imaging system. Therefore, the simulation method of convolving the input image directly with the PSF is flawed. Furthermore, the weights of a convolutional neural network (CNN) are the same for each input. This means that the normal convolutional layer is not only difficult to accurately estimate the time-varying blur kernel, but also difficult to adapt to the change in the length–width ratio of the primary mirror. To that end, we propose a blur kernel estimation conditional convolutional neural network (CCNN) that is equivalent to multiple normal CNNs. We extend the CNN to a conditional model by taking an encoding as an additional input and using conditionally parameterized convolutions instead of normal convolutions. The CCNN can simulate the imaging characteristics of the rectangular pupil with different length–width ratios and different rotation angles in a controllable manner. The results of semi-physical experiments show that the proposed simulation method achieves a satisfactory performance, which can provide data and theoretical support for the image restoration and super-resolution method of the RSA system. Full article
(This article belongs to the Special Issue Machine Learning Methods Applied to Optical Satellite Images)
►▼ Show Figures

Figure 1

20 pages, 3456 KiB  
Article
Dynamic Maize Yield Predictions Using Machine Learning on Multi-Source Data
by Michele Croci, Giorgio Impollonia, Michele Meroni and Stefano Amaducci
Remote Sens. 2023, 15(1), 100; https://doi.org/10.3390/rs15010100 - 24 Dec 2022
Cited by 8 | Viewed by 2767
Abstract
Timely yield prediction is crucial for the agri-food supply chain as a whole. However, different stakeholders in the agri-food sector require different levels of accuracy and lead times in which a yield prediction should be available. For the producers, predictions during the growing [...] Read more.
Timely yield prediction is crucial for the agri-food supply chain as a whole. However, different stakeholders in the agri-food sector require different levels of accuracy and lead times in which a yield prediction should be available. For the producers, predictions during the growing season are essential to ensure that information is available early enough for the timely implementation of agronomic decisions, while industries can wait until later in the season to optimize their production process and increase their production traceability. In this study, we used machine learning algorithms, dynamic and static predictors, and a phenology approach to determine the time for issuing the yield prediction. In addition, the effect of data reduction was evaluated by comparing results obtained with and without principal component analysis (PCA). Gaussian process regression (GPR) was the best for predicting maize yield. Its best performance (nRMSE of 13.31%) was obtained late in the season and with the full set of predictors (vegetation indices, meteorological and soil predictors). In contrast, neural network (NNET) and support vector machines linear basis function (SVMl) achieved their best accuracy with only vegetation indices and at the tasseling phenological stage. Only slight differences in performance were observed between the algorithms considered, highlighting that the main factors influencing performance are the timing of the yield prediction and the predictors with which the machine learning algorithms are fed. Interestingly, PCA was instrumental in increasing the performances of NNET after this stage. An additional benefit of the application of PCA was the overall reduction between 12 and 30.20% in the standard deviation of the maize yield prediction performance from the leave one-year outer-loop cross-validation, depending on the feature set. Full article
(This article belongs to the Special Issue Machine Learning Methods Applied to Optical Satellite Images)
►▼ Show Figures

Figure 1

24 pages, 9751 KiB  
Article
Spatio-Temporal Assessment of Olive Orchard Intensification in the Saïss Plain (Morocco) Using k-Means and High-Resolution Satellite Data
by Rebecca Navarro, Lars Wirkus and Olena Dubovyk
Remote Sens. 2023, 15(1), 50; https://doi.org/10.3390/rs15010050 - 22 Dec 2022
Cited by 2 | Viewed by 1888
Abstract
Olive orchard intensification has transformed an originally drought-resilient tree crop into a competing water user in semi-arid regions. In our study, we used remote sensing to evaluate whether intensive olive plantations have increased between 2010 and 2020, contributing to the current risk of [...] Read more.
Olive orchard intensification has transformed an originally drought-resilient tree crop into a competing water user in semi-arid regions. In our study, we used remote sensing to evaluate whether intensive olive plantations have increased between 2010 and 2020, contributing to the current risk of aquifer depletion in the Saïss plain in Morocco. We developed an unsupervised approach based on the principles of hierarchical clustering and used for each year of analysis two images (5 m pixel size) from the PlanetLabs archive. We first calculated area-based accuracy metrics for 2020 with reference data, reaching a user’s accuracy of 0.95 and a producer’s accuracy of 0.89. For 2010, we verified results among different plot size ranges using available 2010 Google Earth Imagery, reaching high accuracy among the 50 largest plots (correct classification rate, CCR, of 0.94 in 2010 and 0.92 in 2020) and lower accuracies among smaller plot sizes. This study allowed us to map super-intensive olive plantations, thereby addressing an important factor in the groundwater economy of many semi-arid regions. Besides the expected increase in plantation size and the emergence of new plantations, our study revealed that some plantations were also given up, despite the political framework encouraging the opposite. Full article
(This article belongs to the Special Issue Machine Learning Methods Applied to Optical Satellite Images)
►▼ Show Figures

Graphical abstract

20 pages, 4216 KiB  
Article
Plant Density Estimation Using UAV Imagery and Deep Learning
by Jinbang Peng, Ehsan Eyshi Rezaei, Wanxue Zhu, Dongliang Wang, He Li, Bin Yang and Zhigang Sun
Remote Sens. 2022, 14(23), 5923; https://doi.org/10.3390/rs14235923 - 23 Nov 2022
Cited by 1 | Viewed by 1932
Abstract
Plant density is a significant variable in crop growth. Plant density estimation by combining unmanned aerial vehicles (UAVs) and deep learning algorithms is a well-established procedure. However, flight companies for wheat density estimation are typically executed at early development stages. Further exploration is [...] Read more.
Plant density is a significant variable in crop growth. Plant density estimation by combining unmanned aerial vehicles (UAVs) and deep learning algorithms is a well-established procedure. However, flight companies for wheat density estimation are typically executed at early development stages. Further exploration is required to estimate the wheat plant density after the tillering stage, which is crucial to the following growth stages. This study proposed a plant density estimation model, DeNet, for highly accurate wheat plant density estimation after tillering. The validation results presented that (1) the DeNet with global-scale attention is superior in plant density estimation, outperforming the typical deep learning models of SegNet and U-Net; (2) the sigma value at 16 is optimal to generate heatmaps for the plant density estimation model; (3) the normalized inverse distance weighted technique is robust to assembling heatmaps. The model test on field-sampled datasets revealed that the model was feasible to estimate the plant density in the field, wherein a higher density level or lower zenith angle would degrade the model performance. This study demonstrates the potential of deep learning algorithms to capture plant density from high-resolution UAV imageries for wheat plants including tillers. Full article
(This article belongs to the Special Issue Machine Learning Methods Applied to Optical Satellite Images)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-4
Back to TopTop