Dear Colleagues,

LiDAR technology has played a significant role in forest research for decades, facilitating the retrieval of important forest parameters, including biomass, leaf area index, and individual tree health classification. Nevertheless, LiDAR-derived metrics often exhibit site- or sensor-specific characteristics, which can present a challenge when extending the application of evaluated approaches to diverse geographical areas and/or sensor platforms such as spaceborne, airborne, UAV, MLS, and TLS systems. The acquisition of dense point clouds and their computational processing at a large scale can be exceedingly demanding, in terms of both acquisition time and processing power. Recent studies have further shed light on the carbon emissions associated with the computational and storage requirements of Earth observation data. It is, therefore, important to implement adaptable, scalable, and computationally inexpensive approaches for tackling forest-related problems.

Furthermore, with the advancement of artificial intelligence approaches, there are still questions about the best approaches, including traditional machine learning approaches, deep neural networks and more recent developments because, as the network architecture changes, the estimations significantly change as well, along with computational complexity. It will, therefore, be interesting to see how artificial intelligence has evolved and its applicability to LiDAR and forest-related research.

This Special Issue aims to address these critical challenges. Our objective is to evaluate traditional and emerging AI methodologies through the use of benchmarking LiDAR data for forest variables retrieval. We also welcome comprehensive literature review articles, the release of new benchmarking datasets, and the development of open-source tools. Additionally, we are open to relevant contributions that are not explicitly mentioned here.

• Harmonization of LiDAR Data: We invite research that evaluates LiDAR data harmonization techniques by employing benchmarking datasets to ensure consistency and reliability in parameter retrieval across different geographical regions and forest types.
• Open Source Tools: Contributions focusing on the development and release of new open-source tools for LiDAR data processing and analysis.
• Literature Reviews: Comprehensive literature reviews that trace the historical development of LiDAR technology.
• Fusion with different Earth Observation Data: Exploration of innovative approaches that combine LiDAR data with earth observation datasets to extend spatial coverage.
• Benchmarking Datasets: The release of new benchmarking datasets or use of existing ones as they serve as invaluable resources for method evaluation and advancement.
• Comparison of Artificial Intelligence approaches: evaluation and comparison of various machine learning algorithms and/or deep learning models to determine their effectiveness in forest variables retrieval.
• Evaluation of computational complexity of models for deriving forest variables.

Dr. Milto Miltiadou
Dr. Rorai Pereira Martins-Neto
Dr. Henrik J. Persson
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.

• LiDAR remote sensing
• harmonisation of LiDAR data
• benchmarking datasets
• artificial intelligence
• fusion with earth observation data
• computational complexity
• forest inventory and modelling
• forest ecology