Remote Sensing and Machine Learning in Vegetation Biophysical Parameters Estimation (Second Edition)

Dear Colleagues,

Vegetation biophysical parameters are important indicators when characterizing the canopy density and structure of vegetation, such as the leaf area index (LAI), fractional vegetation coverage (FVC), biomass, leaf angle distribution (LAD), clumping index (CI), canopy height, etc. The vegetation biophysical parameters estimated through remote-sensing approaches support numerous applications in agriculture, forestry and other vegetation ecosystems.

The current algorithms employed to estimate biophysical parameters of vegetation include statistical regression, radiative transfer models, machine learning and deep learning techniques. Regression models based on a single vegetation spectral index or another spectral feature are simple and easy to use, with relatively stable accuracy; they are therefore the most widely utilized models. In contrast, machine learning has the ability to nonlinearly model the relationships between the biophysical parameters of vegetation and a satellite-derived spectrum. Deep learning, a new machine learning method, was initially used for target recognition and classification, and has gradually become a popular approach for the estimation of the biophysical parameters of vegetation.

Various types of remote sensing data (optical, LiDAR, SAR, etc.) have different advantages for extracting different vegetation biophysical parameters. The synthesis of different remote-sensing data is also important for estimation of certain vegetation parameters. Additionally, the estimation algorithm is closely related to the spatial and temporal resolution of those remote-sensing data.

Due to the complexity of land-surface vegetation, challenges regarding the estimation of vegetation parameters remain in terms of algorithm performance and applications. Advanced remote-sensing techniques and machine learning provide unprecedented opportunities to tackle these challenges. For example, the spectral responses region of different vegetation physical parameters (including biochemical parameters) may overlap, whereby the integration of multi-source remote sensing data offers significant potential in this regard.

This Special Issue aims to address advances and challenges in the remote-sensing estimation of vegetation biophysical variables using various algorithms and satellite data, and to enhance and promote the application of the estimated parameters. Original research articles and reviews are welcome. Research topics may include (but are not limited to) the following:

(1) The applicability of vegetation parameter estimation algorithms (regression, machine learning, deep learning) in various scenarios (regions, vegetation types, etc.);

(2) New methods such as a vegetation spectral index for vegetation biophysical parameter estimation;

(3) The integration and assimilation of multi-source remote sensing data and other data for vegetation biophysical parameter estimation;

(4) A case study of the applications of estimated vegetation parameters in ecosystems such as agriculture, forest and grassland areas (remote sensing of crop growth, vegetation phenology, vegetation degradation and recovery, etc.).

Dr. Quanjun Jiao
Prof. Dr. Wei Su
Dr. Qiaoyun Xie
Dr. Xing Li
Dr. Bo Liu
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.

• vegetation biophysical parameter estimation
• vegetation spectral indices
• multispectral/hyperspectral/LiDAR/SAR
• satellite/airborne/UAV/tower-based/ground observation
• regression/RTM/machine learning/deep learning
• agriculture
• forest
• grassland
• vegetation dynamics monitoring

• Remote Sensing and Machine Learning in Vegetation Biophysical Parameters Estimation in Remote Sensing (12 articles)