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
Machine Learning and Big Data Analytics in Forestry
share announcement

Machine Learning and Big Data Analytics in Forestry

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 March 2024) | Viewed by 6428

Special Issue Editors

Prof. Dr. Stelian Alexandru Borz

E-Mail Website
Guest Editor
Department of Forest Engineering, Forest Management Planning and Terrestrial Measurements, Faculty of Silviculture and Forest Engineering, Transilvania University of Brasov, Şirul Beethoven 1, 500123 Brasov, Romania
Interests: wood and biomass supply chain optimization; sensor technology; transport optimization; forest planning
Special Issues, Collections and Topics in MDPI journals
Dr. Nopparat Kaakkurivaara

E-Mail Website
Guest Editor
Department of Forest Engineering, Faculty of Forestry, Kasetsart University, 50 Ngamwongwan Rd., Ladyao, Chatuchak, Bangkok 10900, Thailand
Interests: forest harvesting planning; supply chain optimization; operations research in forestry; big data analysis; spatio-temporal analysis

Special Issue Information

Dear Colleagues,

The availability of conventional and new modalities to collect data has brough many opportunities to better document, model and understand forest ecosystems and their management in all the aspects and components of forestry and forest management. Handling big datasets, however, requires advanced tools and methods able to discover and explain complex patterns and inter-relations, while providing gold-standard accurate or improved representations of the underlying behaviors and processes. This Special Issue is focused on collecting high-quality contributions which harness the availability of big data in forestry through the use of conventional and advanced machine learning algorithms and protocols to extract and model useful information with the purpose of better documenting and explaining patterns and relations which are important for the scaled practice and science supporting forestry and forest management.

Contributions are encouraged in all the disciplines supporting forestry and forest management, including but not limited to the following:

  • Remote sensing applications in forest management and forest engineering;
  • Advanced and improved modalities of getting to know the patterns in data and their meaning for forestry and forest management;
  • Prototypes and practice-ready solutions to manage forests at all levels;
  • New approaches to old methods to extend their accuracy and applicability in forestry and forest management;
  • Ground-testing and reliability proving of long-term, near and real-time data collection platforms;
  • Advanced or improved computing protocols, platforms and technologies;
  • Improved management options supported by long-term data;
  • Integrated data handling technologies, autonomous protocols and automation of data analytics.

Prof. Dr. Stelian Alexandru Borz
Dr. Nopparat Kaakkurivaara
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

  • big data
  • analytics
  • machine learning
  • data collection platforms
  • forestry

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

20 pages, 5294 KiB  
Article
FlameTransNet: Advancing Forest Flame Segmentation with Fusion and Augmentation Techniques
by Beiqi Chen, Di Bai, Haifeng Lin and Wanguo Jiao
Forests 2023, 14(9), 1887; https://doi.org/10.3390/f14091887 - 17 Sep 2023
Cited by 3 | Viewed by 1103
Abstract
Forest fires pose severe risks, including habitat loss and air pollution. Accurate forest flame segmentation is vital for effective fire management and protection of ecosystems. It improves detection, response, and understanding of fire behavior. Due to the easy accessibility and rich information content [...] Read more.
Forest fires pose severe risks, including habitat loss and air pollution. Accurate forest flame segmentation is vital for effective fire management and protection of ecosystems. It improves detection, response, and understanding of fire behavior. Due to the easy accessibility and rich information content of forest remote sensing images, remote sensing techniques are frequently applied in forest flame segmentation. With the advancement of deep learning, convolutional neural network (CNN) techniques have been widely adopted for forest flame segmentation and have achieved remarkable results. However, forest remote sensing images often have high resolutions, and relative to the entire image, forest flame regions are relatively small, resulting in class imbalance issues. Additionally, mainstream semantic segmentation methods are limited by the receptive field of CNNs, making it challenging to effectively extract global features from the images and leading to poor segmentation performance when relying solely on labeled datasets. To address these issues, we propose a method based on the deeplabV3+ model, incorporating the following design strategies: (1) an adaptive Copy-Paste data augmentation method is introduced to learn from challenging samples (Images that cannot be adequately learned due to class imbalance and other factors) effectively, (2) transformer modules are concatenated and parallelly integrated into the encoder, while a CBAM attention mechanism is added to the decoder to fully extract image features, and (3) a dice loss is introduced to mitigate the class imbalance problem. By conducting validation on our self-constructed dataset, our approach has demonstrated superior performance across multiple metrics compared to current state-of-the-art semantic segmentation methods. Specifically, in terms of IoU (Intersection over Union), Precision, and Recall metrics for the flame category, our method has exhibited notable enhancements of 4.09%, 3.48%, and 1.49%, respectively, when compared to the best-performing UNet model. Moreover, our approach has achieved advancements of 11.03%, 9.10%, and 4.77% in the same aforementioned metrics as compared to the baseline model. Full article
(This article belongs to the Special Issue Machine Learning and Big Data Analytics in Forestry)
►▼ Show Figures

Figure 1

19 pages, 6717 KiB  
Article
Synergistic Use of Sentinel-1 and Sentinel-2 Based on Different Preprocessing for Predicting Forest Aboveground Biomass
by Gengsheng Fang, Hangyuan Yu, Luming Fang and Xinyu Zheng
Forests 2023, 14(8), 1615; https://doi.org/10.3390/f14081615 - 10 Aug 2023
Viewed by 888
Abstract
Forest aboveground biomass (AGB, Mg/ha) measurement is one of the key indicators for carbon storage evaluation. Remote sensing techniques have been widely employed to predict forest AGB. However, little attention has been paid to the implications involved in the preprocessing of satellite data. [...] Read more.
Forest aboveground biomass (AGB, Mg/ha) measurement is one of the key indicators for carbon storage evaluation. Remote sensing techniques have been widely employed to predict forest AGB. However, little attention has been paid to the implications involved in the preprocessing of satellite data. In this work, considering the areas of low forest AGB in our survey plots, we explored the implications of employing atmospheric correction and speckle filtering with Sentinel-1 (S1) synthetic aperture radar (SAR) and Sentinel-2 (S2) to predict forest AGB using multiple linear regression (MLR) and extreme gradient boosting (XGBoost). In the present study, the types of plots examined included oaks (Quercus spp.), Chinese firs (Cunninghamia lanceolata), and Masson pines (Pinus massoniana), and all of the plots were investigated. Specifically, the feature variables related to S1 (dual polarization and texture measures) and S2 (spectral bands) were modeled individually, and 16 feature sets, including different combinations of S1 and S2 based on different preprocessing measures, were established using MLR and XGBoost. The results show that speckle filtering and atmospheric correction marginally influenced the capacity of the S2 spectral bands, the SAR dual-polarization backscatter, and the SAR-based textural measures in predicting the AGB in our survey plots. The associations between the speckle-filtered and unfiltered SAR images and the S2 Top-of-Atmosphere and Bottom-of-Atmosphere products were considerably strong. Additionally, the texture models generally showed better performances than the raw SAR data. Ultimately, the groups that only encompassed the S2 spectral bands were the best-performing groups among the 16 feature sets, while the groups that included only S1-based data generally performed the worst. Full article
(This article belongs to the Special Issue Machine Learning and Big Data Analytics in Forestry)
►▼ Show Figures

Figure 1

24 pages, 5470 KiB  
Article
Decision-Tree Application to Predict and Spatialize the Wood Productivity Probabilities of Eucalyptus Plantations
by Clayton Alcarde Alvares, Ítalo Ramos Cegatta, Henrique Ferraço Scolforo and Reginaldo Gonçalves Mafia
Forests 2023, 14(7), 1334; https://doi.org/10.3390/f14071334 - 29 Jun 2023
Viewed by 1502
Abstract
Brazil is one of the world’s wood short-fiber producers, cultivating 7.5 million hectares of eucalypt trees. Foresters and resource managers often face difficulties in surveying reliable Eucalyptus productivity levels for the purpose of purchasing and prospecting lands. Spatial data science (DS) and machine [...] Read more.
Brazil is one of the world’s wood short-fiber producers, cultivating 7.5 million hectares of eucalypt trees. Foresters and resource managers often face difficulties in surveying reliable Eucalyptus productivity levels for the purpose of purchasing and prospecting lands. Spatial data science (DS) and machine learning (ML) provide powerful approaches to make the best use of the large datasets available today. Agriculture has made great use of these approaches, and in this paper, we explore how forestry can benefit as well. We hypothesized that both DS and ML techniques can be used to improve Eucalyptus productivity zoning based on multiple operational datasets of tree growth and environment. Based on more than 12,000 permanent forest inventory plots of commercial Eucalyptus plantations and the climate, soil, and altitude variables associated with them, a supervised ML approach was adjusted to model the forest plantation productivity. A multi-tuning of the decision-tree (DT) algorithm hyperparameters was prepared to yield 450 DT models, with a better one delivering an RMSE of 53.5 m3 ha−1, split in 35 terminal nodes, here interpreted as Eucalyptus productivity zones. The DT model showed an optimum performance index of 0.83, a coefficient of determination of 0.91, a root mean squared error of 12.3 m3 ha−1, and a mean absolute percentage error only of 3.1% in predicting the testing dataset throughout the study area. The DT rule set was interpreted in a user-friendly table and was prepared to classify any location within the study area in each one of the 35 productivity zones based on the required environment variables of the DT algorithm. The high quality of the model obtained made it possible to spatialize the DT rules, providing a reliable cartographic visualization of the probability levels of true Eucalyptus productivity for a huge region of forest-based industries in Brazil. These data-science techniques also provided a yield gap analysis using a very down-to-earth approach. We estimated a yield gap by an amount of 4.2 × 107 m3, representing a few more than 113,000 ha, or 15% of the current forest base. This is the amount of avoided area expansion to accumulate the same wood stock in case the productivity is raised to the attainable level in each zone. This present study provided deeper analysis and reproducible tools to manage forest assets sustainably. Full article
(This article belongs to the Special Issue Machine Learning and Big Data Analytics in Forestry)
►▼ Show Figures

Figure 1

15 pages, 784 KiB  
Article
Digital Approach to Successful Business Plans in Forestry and Related Fields
by Eva Abramuszkinová Pavlíková, Jitka Meňházová and Kristaps Lešinskis
Forests 2023, 14(3), 513; https://doi.org/10.3390/f14030513 - 06 Mar 2023
Viewed by 1511
Abstract
This paper introduces the KABADA (Knowledge Alliance of Business Idea Assessment: Digital Approach) tool, together with the opinions of young people about entrepreneurship, their skills, and their experience with this tool. The focus is on non-business students who study natural sciences, engineering, and [...] Read more.
This paper introduces the KABADA (Knowledge Alliance of Business Idea Assessment: Digital Approach) tool, together with the opinions of young people about entrepreneurship, their skills, and their experience with this tool. The focus is on non-business students who study natural sciences, engineering, and other areas at the Faculty of Forestry and Wood Technology at Mendel University in Brno, Czech Republic. The KABADA tool has been developed and tested by a team of international experts. It can be used by a wide audience, including forester management specialists. This structured, web-based platform is based on theoretical research, relevant statistics, and artificial intelligence insights. It guides entrepreneurs through business idea assessment including challenges and opportunities. The research included survey answers from 60 university students before and after using the KABADA tool. The results show that students are interested in entrepreneurship but do not have the knowledge or experience, or support from the curriculum. The majority of the students had no or very low experience with entrepreneurship, no entrepreneurship training, and had not studied entrepreneurship. After using the tool, students declared that they had a higher knowledge of entrepreneurship and the number of students who intended to become an entrepreneur increased. The tool is available online, free of charge. Full article
(This article belongs to the Special Issue Machine Learning and Big Data Analytics in Forestry)
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