Special Issue "Proximal/Remote Sensing Coupled with Chemometrics in Vegetation and Soil Sciences"

A special issue of Remote Sensing (ISSN 2072-4292).

Deadline for manuscript submissions: 31 December 2021.

Special Issue Editors

Dr. Asa Gholizadeh
Website
Guest Editor
Department of Soil Science and Soil Protection, Czech University of Life Sciences Prague, 16500, Prague, Czech Republic
Interests: soil spectroscopy; proximal and remote sensing in soil morning; Earth observation; soil contamination; chemometrics; machine learning in soil parameters analysis and monitoring
Special Issues and Collections in MDPI journals
Dr. Mohammadmehdi Saberioon
Website SciProfiles
Guest Editor
German Research Centre for Geosciences, 14473, Potsdam, Germany
Interests: applied remote sensing in different discipline of agriculture and environment studies; field and imaging spectroscopy; image and signal processing; machine learning and deep learning
Special Issues and Collections in MDPI journals
Dr. Fabio Castaldi
Website
Guest Editor
ILVO- Flanders research institute for agriculture, fisheries and food, technology and food science, agricultural engineering. Burg. Van Gansberghelaan 115 bus 1 - 9820 Merelbeke, Belgium
Interests: soil imaging spectroscopy; multi- and hyperspectral remote sensing; precision agriculture; Earth observation; geostatistics; sustainable agriculture; soil mapping; soil organic carbon; data fusion

Special Issue Information

Dear Colleagues,

Proximal and remote sensing as well as their data fusion allow many measurements to be made for environmental (e.g., soil and vegetation) monitoring at depth and in time; however, the derived data from these technologies may include weak, wide, and overlapping absorption bands. The hidden information therefore needs to be extracted to establish a proxy approach to detect vegetation and soil parameters. Chemometrics, the science of extracting information from different databases, including signal and image data by data-driven means, has the potential to address this issue using methods frequently employed in core data-analytic disciplines such as multivariate statistics, applied mathematics, and computer science. Some machine learning algorithms have frequently tried to link proximal/remote sensing data in vegetation and soil variables. However, with the development of large spectral libraries, we need to seize more possibilities to utilize big data analytics to process the spectral data. More advanced machine learning methods as well as deep learning algorithms with higher capability of large-scale processing data might be a solution that supports more sophisticated modeling and permits the easy use of large amounts of computational resources for training such models. The proximal/remote sensing data coupled with chemometrics (e.g., advanced machine learning and especially deep learning methods) therefore offer tremendous but not fully exploited opportunities to monitor and map vegetation and soil variables across various disciplines and on vast spatial scales.

This Special Issue aims i) to report the up-to-date advancements and trends regarding the combination of chemometrics and proximal/remote sensing information by data fusion techniques and ii) to advance the application of chemometrics techniques for proximal/remote sensing-based vegetation and soil monitoring. We welcome contributions in terms of chemometrics methods, including but not limited to novel machine learning and deep learning technique application, potential, and challenges in proximal/remote sensing of vegetation and soil.

Dr. Asa Gholizadeh
Dr. Mohammadmehdi Saberioon
Dr. Fabio Castaldi
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 papers will be 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 2200 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

  • Chemometrics
  • Machine learning
  • Deep learning
  • Remote sensing of soil and vegetation
  • Proximal sensing of soil and vegetation
  • Soil monitoring and mapping
  • Data fusion

Published Papers (1 paper)

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

Research

Open AccessArticle
Estimation of Organic Carbon in Anthropogenic Soil by VIS-NIR Spectroscopy: Effect of Variable Selection
Remote Sens. 2020, 12(20), 3394; https://doi.org/10.3390/rs12203394 - 16 Oct 2020
Abstract
Visible and near-infrared reflectance (VIS-NIR) spectroscopy is widely applied to estimate soil organic carbon (SOC). Intense and diverse human activities increase the heterogeneity in the relationships between SOC and VIS-NIR spectra in anthropogenic soil. This fact results in poor performance of SOC estimation [...] Read more.
Visible and near-infrared reflectance (VIS-NIR) spectroscopy is widely applied to estimate soil organic carbon (SOC). Intense and diverse human activities increase the heterogeneity in the relationships between SOC and VIS-NIR spectra in anthropogenic soil. This fact results in poor performance of SOC estimation models. To improve model accuracy and parsimony, we investigated the performance of two variable selection algorithms, namely competitive adaptive reweighted sampling (CARS) and random frog (RF), coupled with five spectral pretreatments. A total of 108 samples were collected from Jianghan Plain, China, with the SOC content and VIS-NIR spectra measured in the laboratory. Results showed that both CARS and RF coupled with partial least squares regression (PLSR) outperformed PLSR alone in terms of higher model accuracy and less spectral variables. It revealed that spectral variable selection could identify important spectral variables that account for the relationships between SOC and VIS-NIR spectra, thereby improving the accuracy and parsimony of PLSR models in anthropogenic soil. Our findings are of significant practical value to the SOC estimation in anthropogenic soil by VIS-NIR spectroscopy. Full article
Show Figures

Graphical abstract

Back to TopTop