Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.5
2.9
Journals
Forests
Special Issues
Remote Sensing Application for Mapping and Monitoring Forest Ecosystems
share announcement

Remote Sensing Application for Mapping and Monitoring Forest Ecosystems

A special issue of Forests (ISSN 1999-4907). This special issue belongs to the section "Forest Inventory, Modeling and Remote Sensing".

Deadline for manuscript submissions: closed (31 January 2024) | Viewed by 7443

Special Issue Editors

Dr. Giovanni D'Amico

E-Mail Website
Guest Editor
Department of Agricultural, Food, Environmental and Forestry Sciences and Technologies, University of Florence, 50145 Florence, Italy
Interests: forestry; remote sensing; forest inventory; airborne laser scanning
Special Issues, Collections and Topics in MDPI journals
Dr. Walter Mattioli

E-Mail Website
Guest Editor
Research Centre for Forestry and Wood, Valle della Quistione, 27, 00166 Rome, Italy
Interests: remote sensing; geomatics; forestry; forest inventory
Prof. Dr. Gherardo Chirici

E-Mail Website
Guest Editor
GeoLAB—Laboratorio di Geomatica Forestale, Dipartimento di Scienze e Tecnologie Agrarie, Alimentari, Ambientali e Forestali, Università degli Studi di Firenze, Via San Bonaventura 13, 50145 Firenze, Italy
Interests: application of geomatics to forestry; remote sensing; forest inventories and monitoring; sustainable forest management; land planning; landscape ecology; biodiversity; forest fires and climate change; bio-geo-chemical models; decision support systems; forest ecology
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Forests are key resources for sustaining life on Earth. They act as carbon sinks, helping to mitigate climate change, achieve the goal of global carbon neutrality and, at the same time, provide numerous valuable ecosystem services. However, forests suffer increasing anthropogenic pressure and natural disturbances (e.g., extreme weather events, floods, droughts, fires, deforestation, insects and diseases, etc.). Therefore, it is crucial to accurately monitor forest ecosystems supporting sustainable forest management.

Large- and medium-scale monitoring of forest environments could be effectively performed through remote sensing data acquired from different sensor platforms and the use of machine learning and deep learning approaches. This Special Issue aims to collect studies on forest ecosystem monitoring using optical data from multispectral or hyperspectral sensors, as well as structural data typically provided by radar and lidar sensors, and integrations between different source data.

Papers focused on remote sensing applications for monitoring forest ecosystems, may address, but are not limited to, the following topics:

  • Tree and vegetation inventory;
  • Vegetation structural characteristics;
  • Classification, detection, and segmentation of vegetation cover;
  • Land cover and landscape change;
  • Early detection of forest disturbances;
  • Forest modelling and climate change adaptation;
  • Forest biotic and abiotic disturbances mapping;
  • Multispectral and hyperspectral image sensors and methods for forest analysis;
  • Lidar and UAV in monitor forest environments;
  • New algorithms and technique for forest monitoring.

Dr. Giovanni D'Amico
Dr. Walter Mattioli
Prof. Dr. Gherardo Chirici
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. Forests is an international peer-reviewed open access monthly 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 2600 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

  • forest inventory
  • forest mapping
  • biodiversity
  • forest disturbance
  • sustainable forest management
  • remote sensing
  • machine learning
  • climate change
  • satellite
  • lidar

Published Papers (6 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

Jump to: Review

14 pages, 1731 KiB  
Article
An Efficient and Light Transformer-Based Segmentation Network for Remote Sensing Images of Landscapes
by Lijia Chen, Honghui Chen, Yanqiu Xie, Tianyou He, Jing Ye and Yushan Zheng
Forests 2023, 14(11), 2271; https://doi.org/10.3390/f14112271 - 20 Nov 2023
Viewed by 830
Abstract
High-resolution image segmentation for landscape applications has garnered significant attention, particularly in the context of ultra-high-resolution (UHR) imagery. Current segmentation methodologies partition UHR images into standard patches for multiscale local segmentation and hierarchical reasoning. This creates a pressing dilemma, where the trade-off between [...] Read more.
High-resolution image segmentation for landscape applications has garnered significant attention, particularly in the context of ultra-high-resolution (UHR) imagery. Current segmentation methodologies partition UHR images into standard patches for multiscale local segmentation and hierarchical reasoning. This creates a pressing dilemma, where the trade-off between memory efficiency and segmentation quality becomes increasingly evident. This paper introduces the Multilevel Contexts Weighted Coupling Transformer (WCTNet) for UHR segmentation. This framework comprises the Mult-level Feature Weighting (MFW) module and Token-based Transformer (TT) designed to weigh and couple multilevel semantic contexts. First, we analyze the multilevel semantics within a local patch without image-level contextual reasoning. It avoids complex image-level contextual associations and eliminates the misleading information carried. Second, MFW is developed to weigh shallow and deep features for enhancing object-related attention at different grain sizes from multilevel semantics. Third, the TT module is introduced to couple multilevel semantic contexts and transform them into semantic tokens using spatial attention. Then, we can capture token interactions and obtain clearer local representations. The suggested contextual weighting and coupling of single-scale patches empower WCTNet to maintain a well-balanced relationship between accuracy and computational overhead. Experimental results show that WCTNet achieves state-of-the-art performance on two UHR datasets of DeepGlobe and Inria Aerial. Full article
(This article belongs to the Special Issue Remote Sensing Application for Mapping and Monitoring Forest Ecosystems)
►▼ Show Figures

Figure 1

13 pages, 4664 KiB  
Article
Robotics in Forest Inventories: SPOT’s First Steps
by Gherardo Chirici, Francesca Giannetti, Giovanni D’Amico, Elia Vangi, Saverio Francini, Costanza Borghi, Piermaria Corona and Davide Travaglini
Forests 2023, 14(11), 2170; https://doi.org/10.3390/f14112170 - 31 Oct 2023
Cited by 2 | Viewed by 1901
Abstract
In the context of the potential future use of unmanned ground vehicles for forest inventories, we present the first experiences with SPOT, a legged robot equipped with a LiDAR instrument and several cameras that have been used with a teleoperation approach for single-tree [...] Read more.
In the context of the potential future use of unmanned ground vehicles for forest inventories, we present the first experiences with SPOT, a legged robot equipped with a LiDAR instrument and several cameras that have been used with a teleoperation approach for single-tree detection and measurements. This first test was carried out using the default LiDAR system (the so-called enhanced autonomy payload-EAP, installed on the board of SPOT to guide autonomous movements) to understand advantages and limitations of this platform to support forest inventory activities. The test was carried out in the Vallombrosa forest (Italy) by assessing different data acquisition methods. The first results showed that EAP LiDAR generated noisy point clouds where only large trees (DBH ≥ 20 cm) could be identified. The results showed that the accuracy in tree identification and DBH measurements were strongly influenced by the path used for data acquisition, with average errors in tree positioning no less than 1.9 m. Despite this, the best methods allowed the correct identification of 97% of large trees. Full article
(This article belongs to the Special Issue Remote Sensing Application for Mapping and Monitoring Forest Ecosystems)
►▼ Show Figures

Figure 1

27 pages, 5125 KiB  
Article
Land Cover Classification of Remote Sensing Images Based on Hierarchical Convolutional Recurrent Neural Network
by Xiangsuo Fan, Lin Chen, Xinggui Xu, Chuan Yan, Jinlong Fan and Xuyang Li
Forests 2023, 14(9), 1881; https://doi.org/10.3390/f14091881 - 15 Sep 2023
Cited by 3 | Viewed by 1297
Abstract
Convolutional neural networks (CNNs) and recurrent neural networks (RNNs) have gained improved results in remote sensing image data classification. Multispectral image classification can benefit from the rich spectral information extracted by these models for land cover classification. This paper proposes a classification model [...] Read more.
Convolutional neural networks (CNNs) and recurrent neural networks (RNNs) have gained improved results in remote sensing image data classification. Multispectral image classification can benefit from the rich spectral information extracted by these models for land cover classification. This paper proposes a classification model called a hierarchical convolutional recurrent neural network (HCRNN) to combine the CNN and RNN modules for pixel-level classification of multispectral remote sensing images. In the HCRNN model, the original 13-band information from Sentinel-2 is transformed into a 1D multispectral sequence using a fully connected layer. It is then reshaped into a 3D multispectral feature matrix. The 2D-CNN features are extracted and used as inputs to the corresponding hierarchical RNN. The feature information at each level is adapted to the same convolution size. This network structure fully leverages the advantages of CNNs and RNNs to extract temporal and spatial features from the spectral data, leading to high-precision pixel-level multispectral remote sensing image classification. The experimental results demonstrate that the overall accuracy of the HCRNN model on the Sentinel-2 dataset reaches 97.62%, which improves the performance by 1.78% compared to the RNN model. Furthermore, this study focused on the changes in forest cover in the study area of Laibin City, Guangxi Zhuang Autonomous Region, which was 7997.1016 km2, 8990.4149 km2, and 8103.0020 km2 in 2017, 2019, and 2021, respectively, with an overall trend of a small increase in the area covered. Full article
(This article belongs to the Special Issue Remote Sensing Application for Mapping and Monitoring Forest Ecosystems)
►▼ Show Figures

Figure 1

19 pages, 9455 KiB  
Article
Mapping Vegetation Types by Different Fully Convolutional Neural Network Structures with Inadequate Training Labels in Complex Landscape Urban Areas
by Shudan Chen, Meng Zhang and Fan Lei
Forests 2023, 14(9), 1788; https://doi.org/10.3390/f14091788 - 01 Sep 2023
Cited by 1 | Viewed by 866
Abstract
Highly accurate urban vegetation extraction is important to supporting ecological and management planning in urban areas. However, achieving high-precision classification of urban vegetation is challenging due to dramatic land changes in cities, the complexity of land cover, and hill shading. Although convolutional neural [...] Read more.
Highly accurate urban vegetation extraction is important to supporting ecological and management planning in urban areas. However, achieving high-precision classification of urban vegetation is challenging due to dramatic land changes in cities, the complexity of land cover, and hill shading. Although convolutional neural networks (CNNs) have unique advantages in remote sensing image classification, they require a large amount of training sample data, making it difficult to adequately train the network to improve classification accuracy. Therefore, this paper proposed an urban vegetation classification method by combining the advantages of transfer learning, deep learning, and ensemble learning. First, three UNet++ networks (UNet++, VGG16-UNet++, and ResNet50-UNet++) were pre-trained using the open sample set of urban land use/land cover (LULC), and the deep features of Sentinel-2 images were extracted using the pre-trained three UNet++ networks. Subsequently, the optimal deep feature set was then selected by Relief-F and input into the Stacking algorithm for urban vegetation classification. The results showed that deeper features extracted by UNet++ networks were able to easily distinguish between different vegetation types compared to Sentinel-2 spectral features. The overall classification accuracy (OA) of UNet++ networks and the Stacking algorithm (UNS) was 92.74%, with a Kappa coefficient of 0.8905. The classification results of UNet++ networks and the Stacking algorithm improved by 2.34%, 1.8%, 2.29%, and 10.74% in OA compared to a single neural network (UNet++, VGG16-UNet++, and ResNet50-UNet++) and the Stacking algorithm, respectively. Furthermore, a comparative analysis of the method with common vegetation classification algorithms (RF, U-Net, and DeepLab V3+) indicated that the results of UNS were 11.31%, 9.38%, and 3.05% better in terms of OA, respectively. Generally, the method developed in this paper could accurately obtain urban vegetation information and provide a reference for research on urban vegetation classification. Full article
(This article belongs to the Special Issue Remote Sensing Application for Mapping and Monitoring Forest Ecosystems)
►▼ Show Figures

Figure 1

20 pages, 8556 KiB  
Article
Forest Tree Species Diversity Mapping Using ICESat-2/ATLAS with GF-1/PMS Imagery
by Zezhi Yang, Qingtai Shu, Liangshi Zhang and Xu Yang
Forests 2023, 14(8), 1537; https://doi.org/10.3390/f14081537 - 28 Jul 2023
Cited by 1 | Viewed by 918
Abstract
Forest ecosystems depend on species of tree variety. Remote sensing for obtaining large-scale spatial distribution information of tree species diversity is a geoscience research hotspot to overcome the limitations of conventional tree species diversity survey approaches. Airborne LiDAR or synergy with airborne optical [...] Read more.
Forest ecosystems depend on species of tree variety. Remote sensing for obtaining large-scale spatial distribution information of tree species diversity is a geoscience research hotspot to overcome the limitations of conventional tree species diversity survey approaches. Airborne LiDAR or synergy with airborne optical imagery has been used to model and estimate tree species diversity for specific forest communities, with many revealing results. However, the data collection for such research is costly, the breadth of monitoring findings is limited, and obtaining information on the geographical pattern is challenging. To this end, we propose a method for mapping forest tree species diversity by synergy satellite optical remote sensing and satellite-based LiDAR based on the spectral heterogeneity hypothesis and structural variation hypothesis to improve the accuracy of the remote sensing monitoring of forest tree species diversity while considering data cost. The method integrates horizontal spectral variation from GF-1/PMS image data with vertical structural variation from ICESat-2 spot data to estimate the species diversity of trees. The findings reveal that synergistic horizontal spectral variation and vertical structural variation overall increase tree species diversity prediction accuracy compared to a single remote sensing variation model. The synergistic approach improved Shannon and Simpson indices prediction accuracy by 0.06 and 0.04, respectively, compared to the single horizontal spectral variation model. The synergistic model, single vertical structural variation model, and single horizontal spectral variation model were the best prediction models for Shannon, Simpson, and richness indices, with R2 of 0.58, 0.62, and 0.64, respectively. This research indicates the potential of synergistic satellite-based LiDAR and optical remote sensing in large-scale forest tree species diversity mapping. Full article
(This article belongs to the Special Issue Remote Sensing Application for Mapping and Monitoring Forest Ecosystems)
►▼ Show Figures

Figure 1

Review

Jump to: Research

14 pages, 3066 KiB  
Review
Remote Sensing Applications in Monitoring Poplars: A Review
by Morena J. Mapuru, Sifiso Xulu and Michael Gebreslasie
Forests 2023, 14(12), 2301; https://doi.org/10.3390/f14122301 - 23 Nov 2023
Viewed by 958
Abstract
Given the ability of remote sensing to detect distinctive plant traits, it has emerged in recent decades as a useful and attractive research tool for forest trees such as poplars. Although poplars have been extensively studied using remote sensing over the past thirty [...] Read more.
Given the ability of remote sensing to detect distinctive plant traits, it has emerged in recent decades as a useful and attractive research tool for forest trees such as poplars. Although poplars have been extensively studied using remote sensing over the past thirty years, no reviews have been conducted to understand the results of multiple applications. Here, we present a review and synthesis of poplar studies in this regard. We searched the Scopus, Google Scholar, and Science Direct databases and found 266 published articles, of which 148 were eligible and analyzed. Our results show a rapid increase in remote sensing-based poplar publications over the period of 1991–2022, with airborne platforms, particularly LiDAR, being predominantly used, followed by satellite and ground-based sensors. Studies are widespread in the Global North, accounting for more than two-thirds of studies. The studies took place mainly in agricultural landscapes, followed by forest areas and riparian areas, with a few in mountain and urban areas. Commonly studied biophysical parameters were mostly obtained from LiDAR data. On the other hand, spectral indicators have been widely used to monitor the health and vitality of poplar trees, integrating various machine learning algorithms. Overall, remote sensing has been widely used in poplar studies, and the increasing use of free satellite data and processing platforms is expected to pave the way for data-poor countries to monitor poplar in the Global South, where resources are mainly limited. Full article
(This article belongs to the Special Issue Remote Sensing Application for Mapping and Monitoring Forest Ecosystems)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-6
Back to TopTop