Forests

45 pages, 2074 KiB

Open AccessReview

Advancements in Artificial Intelligence Applications for Forest Fire Prediction

by Hui Liu, Lifu Shu, Xiaodong Liu, Pengle Cheng, Mingyu Wang and Ying Huang

Forests 2025, 16(4), 704; https://doi.org/10.3390/f16040704 - 19 Apr 2025

In recent years, the increasingly significant impacts of climate change and human activities on the environment have led to more frequent occurrences of extreme events such as forest fires. The recurrent wildfires pose severe threats to ecological environments and human life safety. Consequently, [...] Read more.

In recent years, the increasingly significant impacts of climate change and human activities on the environment have led to more frequent occurrences of extreme events such as forest fires. The recurrent wildfires pose severe threats to ecological environments and human life safety. Consequently, forest fire prediction has become a current research hotspot, where accurate forecasting technologies are crucial for reducing ecological and economic losses, improving forest fire management efficiency, and ensuring personnel safety and property security. To enhance comprehensive understanding of wildfire prediction research, this paper systematically reviews studies since 2015, focusing on two key aspects: datasets with related tools and prediction algorithms. We categorized the literature into three categories: statistical analysis and physical models, traditional machine learning methods, and deep learning approaches. Additionally, this review summarizes the data types and open-source datasets used in the selected literature. The paper further outlines current challenges and future directions, including exploring wildfire risk data management and multimodal deep learning, investigating self-supervised learning models, improving model interpretability and developing explainable models, integrating physics-informed models with machine learning, and constructing digital twin technology for real-time wildfire simulation and fire scenario analysis. This study aims to provide valuable support for forest natural resource management and enhanced environmental protection through the application of remote sensing technologies and artificial intelligence algorithms. Full article

(This article belongs to the Section Forest Inventory, Modeling and Remote Sensing)

► Show Figures

Figure 1

17 pages, 4807 KiB

Open AccessArticle

Research on the Construction of Health Risk Assessment Model for Ancient Banyan Trees (Ficus microcarpa) in Fuzhou City

by Huibin Liu, Wenjian Xu, Yangbin Yu, Xinrui Wang, Wenhao Liu, Zuxing Wei, Lingyan Chen and Donghui Peng

Forests 2025, 16(4), 703; https://doi.org/10.3390/f16040703 - 19 Apr 2025

Abstract

Constructing a scientific health risk assessment system for ancient trees is crucial for preserving cultural heritage and tree resources. As Fuzhou’s city tree, ancient banyan trees (Ficus microcarpa) with expansive canopies and aerial roots have shaped local ecology and history over [...] Read more.

Constructing a scientific health risk assessment system for ancient trees is crucial for preserving cultural heritage and tree resources. As Fuzhou’s city tree, ancient banyan trees (Ficus microcarpa) with expansive canopies and aerial roots have shaped local ecology and history over millennia. However, urbanization-induced habitat loss and structural vulnerabilities (e.g., root damage and branch injuries) increasingly threaten their health. Current generic tree evaluation standards inadequately address banyan trees’ unique aerial root physiology. This study developed a tailored assessment model using 140 ancient banyan trees from Fuzhou’s urban core and Minhou County. The researchers analyzed 12 tree health indicators (crown, trunk, visible roots, etc.) and two environmental factors through structural equation modeling (SEM) and cluster analysis. Key findings: (1) The SEM demonstrated strong data fit (CMIN/DF = 1.575, RMSEA = 0.064, TLI = 0.927, and CFI = 0.945), validating model reliability. (2) Mechanical damage to the visible root system (weight = 0.135) most significantly impacted health, while canopy closure (0.036) and crown saturation (0.034) showed minimal effects. (3) The site environment strongly correlated with trunk and visible root system health but not crown conditions. (4) In total, 60.71% of the sampled trees were healthy/sub-healthy, while 39.29% exhibited poor health. This methodology provides a replicable framework for ancient tree conservation, emphasizing species-specific evaluation criteria and environmental management strategies. The weighted indicator system enables precise health diagnostics and prioritized protection measures for vulnerable heritage trees. Full article

(This article belongs to the Section Forest Inventory, Modeling and Remote Sensing)

20 pages, 1898 KiB

Open AccessReview

Physicochemical Properties of Forest Wood Biomass for Bioenergy Application: A Review

by Leonardo Bianchini, Andrea Colantoni, Rachele Venanzi, Luca Cozzolino and Rodolfo Picchio

Forests 2025, 16(4), 702; https://doi.org/10.3390/f16040702 - 18 Apr 2025

Abstract

Forest wood biomass is a key renewable resource for advancing energy transition and mitigating climate change. This review analyzes the physicochemical properties of forest biomass from major European tree species to assess their suitability for bioenergy applications. This study encompasses key parameters, such [...] Read more.

Forest wood biomass is a key renewable resource for advancing energy transition and mitigating climate change. This review analyzes the physicochemical properties of forest biomass from major European tree species to assess their suitability for bioenergy applications. This study encompasses key parameters, such as moisture content, ash content, volatile matter, fixed carbon, elemental composition, bulk density, and energy content (HHV and LHV). This review analyzed data from 43 publications and extracted 140 records concerning the physicochemical properties of the most common European forest species used for bioenergy. The most commonly represented species were Quercus robur, Eucalyptus spp., and Fagus sylvatica. Moisture content, referring to fresh matter, ranged from 5% to 65%; ash content, referring to a dry basis, ranged from 0.2% to 3.5%; and higher heating value (HHV), referring to dry matter, ranged from 17 to 21 MJ kg⁻¹. This study highlights variability among species and underscores the importance of standardizing biomass characterization methods and the scarcity of data on bulk density and other key logistical parameters. These findings emphasize the need for consistent methodologies and species-specific selection strategies to optimize sustainability and efficiency in forest biomass utilization for bioenergy. Full article

(This article belongs to the Special Issue Advancements in Forest Engineering Technologies and Sustainable Practices)

► Show Figures

Figure 1

17 pages, 2803 KiB

Open AccessArticle

Allometric Models for Estimating Biomass and Carbon Stocks in Natural and Homestead Highland Bamboo Stands in the Sidama Region, Ethiopia

by Dagnew Yebeyen Burru, Jayaraman Durai, Melaku Anteneh Chinke, Gudeta W. Sileshi, Yashwant S. Rawat, Belachew Gizachew, Selim Reza, Fikremariam Haile Desalegne and Kassa Toshe Worassa

Forests 2025, 16(4), 701; https://doi.org/10.3390/f16040701 - 18 Apr 2025

Abstract

Highland bamboo (Oldeania alpina) plays a vital role in supporting local livelihoods, fostering biodiversity conservation and sustainable land management. Despite these benefits, its significant potential for carbon sequestration remains underutilized within Ethiopia’s climate mitigation strategies. In this study, we developed site-specific [...] Read more.

Highland bamboo (Oldeania alpina) plays a vital role in supporting local livelihoods, fostering biodiversity conservation and sustainable land management. Despite these benefits, its significant potential for carbon sequestration remains underutilized within Ethiopia’s climate mitigation strategies. In this study, we developed site-specific allometric equations to assess the biomass and carbon storage potential of highland bamboo. Data were collected from the Garamba natural bamboo forest and Hula homestead bamboo stands in the Sidama Regional State, Southern Ethiopia. Data on stand density and structure were gathered using systematically laid transects and sample plots, while plant samples were analyzed in the laboratory to determine the dry-to-fresh weight ratios. We developed allometric models to estimate the aboveground biomass (AGB) and carbon stock. The study results indicated that homestead bamboo stands exhibited higher biomass accumulation than natural bamboo stands. The AGB was estimated at 92.3 Mg ha⁻¹ in the natural forest and 118.3 Mg ha⁻¹ in homestead bamboo stands, with total biomass carbon storage of 52.1 Mg ha⁻¹ and 66.7 Mg ha⁻¹, respectively. The findings highlight the significant potential of highland bamboo for carbon sequestration in both natural stands and homesteads. Sustainable management of natural highland bamboo stands and integrating bamboo into farms can contribute to climate change mitigation, support ecosystem restoration, and enhance the socio-economic development of communities. Full article

(This article belongs to the Special Issue Biomass Estimation and Carbon Stocks in Forest Ecosystems: 3rd Edition)

► Show Figures

Figure 1

21 pages, 2924 KiB

Open AccessReview

Green Belts in Africa: A Diagnostic Review of Urban Forestry and Sustainable Management Strategies

by Komna Balagou, Kossi Adjonou, Kossi Novigno Segla, Kossi Komi, Jean-Bosco Benewinde Zoungrana, Coffi Aholou and Kouami Kokou

Forests 2025, 16(4), 700; https://doi.org/10.3390/f16040700 - 18 Apr 2025

Abstract

Green belts, consisting mainly of natural forests, woodlands, and agricultural areas surrounding major cities, play an essential role in regulating urban development and controlling the expansion of metropolitan areas. Although this concept has been extensively studied in the world’s major metropolitan areas, it [...] Read more.

Green belts, consisting mainly of natural forests, woodlands, and agricultural areas surrounding major cities, play an essential role in regulating urban development and controlling the expansion of metropolitan areas. Although this concept has been extensively studied in the world’s major metropolitan areas, it remains relatively unknown in many countries, particularly in Africa. There is a great need for research to better understand urban vegetation cover on the continent. This article proposes a systematic review of African publications on green cover for the period 2010 to 2024. A descriptive and thematic analysis of the selected scientific papers was carried out using a database established to examine the state of existing research and understanding of the management of these plant formations in Africa. The results of these analyses highlight several major challenges facing urban forestry, including increasing anthropogenic pressures, lack of urban planning that integrates urban forestry, and shortcomings in the management of existing forest landscapes. The thematic analysis has also helped to identify the topics addressed by African researchers, identify gaps in research, and suggest directions for future studies. Three priority areas emerge from this analysis: the conservation of natural or artificial green belts around cities, the impact of these forest landscapes on urban heat islands (climate impact), and the sustainability of ecosystem management in the context of sustainable urbanization. These guidelines will enable a better understanding and valorization of green belts in Africa, thus contributing to the construction of more sustainable cities and the efficient management of forest landscapes. Full article

(This article belongs to the Special Issue Ecosystem Services in Urban and Peri-Urban Landscapes)

► Show Figures

Figure 1

18 pages, 10232 KiB

Open AccessArticle

Evaluation of Landscape Soil Quality in Different Types of Pisha Sandstone Areas on Loess Plateau

by Lei Huang and Liangyi Rao

Forests 2025, 16(4), 699; https://doi.org/10.3390/f16040699 - 18 Apr 2025

Abstract

Severe soil erosion and land productivity degradation caused by inadequate vegetation cover pose significant challenges to regional ecological protection and sustainable development. To assess changes and variations in soil quality, three sample areas with different distinct texture characteristics were selected from the Pisha [...] Read more.

Severe soil erosion and land productivity degradation caused by inadequate vegetation cover pose significant challenges to regional ecological protection and sustainable development. To assess changes and variations in soil quality, three sample areas with different distinct texture characteristics were selected from the Pisha sandstone region located northeastern of the Loess Plateau. The total data set (TDS) was determined through sampling experiments, and the minimum data set (MDS) was established using principal component analysis. A Random Forest (RF) machine learning model was applied to predict soil quality distribution. The prediction indices were derived from soil analysis dimensions, mean weight diameter measured via wet sieving, and soil enrichment ratio obtained from slope erosion experiments conducted at the corresponding sampling points. During the RF modeling process, 80% of the total soil quality index (SQI), calculated using TDS and MDS evaluation methods, was allocated for model training. The results indicated that pH, ammonia nitrogen, bulk density, silt content, clay content, soil water content, hygroscopic water content, total phosphorus, soluble calcium, and actinomycetes were identified as the optimal predictors for SQI. Furthermore, the RF model demonstrated superior performance in predicting the regional distribution of SQI, with evaluation metrics including (R² = 0.76–0.78, RMSE = 0.03–0.06, MAE = 0.04–0.09). This study confirms the reliability of RF in simulating SQI within the study area and highlights that, in regions undergoing extensive vegetation restoration and with limited sampling conditions, experimental measurements of soil particles and sediment parameters provide an effective approach for evaluating SQI. Full article

(This article belongs to the Section Forest Soil)

► Show Figures

Figure 1

27 pages, 3039 KiB

Open AccessArticle

FPGA-Accelerated Lightweight CNN in Forest Fire Recognition

by Youming Zha and Xiang Cai

Forests 2025, 16(4), 698; https://doi.org/10.3390/f16040698 - 18 Apr 2025

Abstract

Using convolutional neural networks (CNNs) to recognize forest fires in complex outdoor environments is a hot research direction in the field of intelligent forest fire recognition. Due to the storage-intensive and computing-intensive characteristics of CNN algorithms, it is difficult to implement them at [...] Read more.

Using convolutional neural networks (CNNs) to recognize forest fires in complex outdoor environments is a hot research direction in the field of intelligent forest fire recognition. Due to the storage-intensive and computing-intensive characteristics of CNN algorithms, it is difficult to implement them at edge terminals with limited memory and computing resources. This paper uses a FPGA (Field-Programmable Gate Array) to accelerate CNNs to realize forest fire recognition in the field environment and solves the problem of the difficulty in giving consideration to the accuracy and speed of a forest fire recognition network in the implementation of edge terminal equipment. First, a simple seven-layer lightweight network, LightFireNet, is designed. The network is compressed using a knowledge distillation method and the classical network ResNet50 is used as the teacher network to supervise the learning of LightFireNet so that its accuracy rate reaches 97.60%. Compared with ResNet50, the scale of LightFireNet is significantly reduced. Its model parameter amount is 24 K and its calculation amount is 9.11 M, which are 0.1% and 1.2% of ResNet50, respectively. Secondly, the hardware acceleration circuit of LightFireNet is designed and implemented based on the FPGA development board ZYNQ Z7-Lite 7020. In order to further compress the network and speed up the forest fire recognition circuit, the following three methods are used to optimize the circuit: (1) the network convolution layer adopts a depthwise separable convolution structure; (2) the BN (batch normalization) layer is fused with the upper layer (or full connection layer); (3) half float or ap_fixed<16,6>-type data is used to express feature data and model parameters. After the circuit function is realized, the LightFireNet terminal circuit is obtained through the circuit parallel optimization method of loop tiling, ping-pong operation, and multi-channel data transmission. Finally, it is verified on the test dataset that the accuracy of the forest fire recognition of the FPGA edge terminal of the LightFireNet model is 96.70%, the recognition speed is 64 ms per frame, and the power consumption is 2.23 W. The results show that this paper has realized a low-power-consumption, high-accuracy, and fast forest fire recognition terminal, which can thus be better applied to forest fire monitoring. Full article

(This article belongs to the Special Issue Forest Ecology and Resource Monitoring Based on Sensors, Signal and Image Processing)

10 pages, 1553 KiB

Open AccessArticle

Genus-Specific Molecular Markers for In Vitro Detection of Corinectria Forest Pathogens

by Tania Vásquez, Cristian González and Cristian Montalva

Forests 2025, 16(4), 697; https://doi.org/10.3390/f16040697 - 18 Apr 2025

Abstract

Canker disease caused by Corinectria constricta has resulted in significant losses of Pinus radiata for the Chilean forestry industry in recent years. Accurate and prompt detection and identification of the pathogen is essential in this context. In this study, a set of molecular [...] Read more.

Canker disease caused by Corinectria constricta has resulted in significant losses of Pinus radiata for the Chilean forestry industry in recent years. Accurate and prompt detection and identification of the pathogen is essential in this context. In this study, a set of molecular markers was developed using multiple alignments of the actin-1 (ACT) and β-tubulin (Btub) gene regions to detect the genus Corinectria in vitro. The designed molecular markers were evaluated for specificity and sensitivity using conventional PCR assays, which successfully differentiated Corinectria species from other closely related species and fungal pathogens of P. radiata. The results showed that the molecular markers were able to detect Corinectria genus with high specificity and sensitivity, with Act-31F/Act-543R detecting 0.1 ng/µL of template DNA and Btub/BtubR detecting 0.05 ng/µL. This study represents the first report of specific molecular markers being developed to detect/identify the genus Corinectria in vitro, and the use of these markers is suggested for the timely detection of the pathogen in P. radiata plantations. Full article

(This article belongs to the Special Issue Advances in Detection and Identification of Insect Pests and Pathogens)

► Show Figures

Figure 1

14 pages, 3761 KiB

Open AccessArticle

Different Influences of Soil and Climatic Factors on Shrubs and Herbaceous Plants in the Shrub-Encroached Grasslands of the Mongolian Plateau

by Yue Liu, Lei Dong, Jinrong Li, Shuaizhi Lu, Liqing Yi, Huimin Li, Shaoqi Chai and Jian Wang

Forests 2025, 16(4), 696; https://doi.org/10.3390/f16040696 - 17 Apr 2025

Abstract

Factors such as climate change, fire, and overgrazing have been commonly considered the main causes of the global expansion of shrub invasion in grasslands over the past 160 years. Nevertheless, the influence of soil substrates on the progression of shrub encroachment has been [...] Read more.

Factors such as climate change, fire, and overgrazing have been commonly considered the main causes of the global expansion of shrub invasion in grasslands over the past 160 years. Nevertheless, the influence of soil substrates on the progression of shrub encroachment has been insufficiently examined. This study examines the fundamental characteristics of the shrub-encroached desert steppe communities of Caragana tibetica in the Mongolian Plateau. Combining field surveys (field surveys and drone aerial photography) and laboratory experiments, using Spearman’s rank correlation analysis and structural equation modeling (SEM), this research systematically explores the impact of varying degrees of soil sandification on the survival of shrubs and herbaceous plants within these grassland communities. The findings indicate the following: (1) In the eight shrub-encroached grassland plots, the soil exhibited a significantly higher sand content compared to silt and clay, with the sand content generally exceeding 64%. (2) The coverage of shrub species is predominantly influenced by soil factors, particularly the soil sand content. (The path coefficient is 0.56, with p < 0.01). In contrast, herbaceous plants are more strongly influenced by climatic factors. (The path coefficient is 0.83, with p < 0.001). This study examines the response patterns of Caragana tibetica communities to edaphic and climatic factors, highlighting the pivotal role of soil sandification in the initiation and succession of shrub encroachment. The findings furnish a theoretical framework for forecasting future trends in grassland shrub encroachment and provide empirical evidence for the conservation and sustainable management of shrub-encroached grasslands. Full article

(This article belongs to the Section Forest Ecology and Management)

► Show Figures

Figure 1

23 pages, 8466 KiB

Open AccessArticle

Physiological and Flavonoid Metabolic Responses of Black Locust Leaves to Drought Stress in the Loess Plateau of China

by Yan Wang, Ning Peng, Binbin Liu, Yingbin Yang, Chao Yue, Wenfang Hao and Junhao He

Forests 2025, 16(4), 695; https://doi.org/10.3390/f16040695 - 17 Apr 2025

Abstract

Drought threatens the stability of artificial black locust forests on the Loess Plateau, yet there is limited research on the physiological and metabolic responses of mature black locust to drought stress. This study employed a throughfall exclusion system—i.e., moderate drought (40% throughfall reduction), [...] Read more.

Drought threatens the stability of artificial black locust forests on the Loess Plateau, yet there is limited research on the physiological and metabolic responses of mature black locust to drought stress. This study employed a throughfall exclusion system—i.e., moderate drought (40% throughfall reduction), extreme drought (80% throughfall reduction), and 0% throughfall reduction for control—to analyze leaf microstructure, relative water content (RWC), osmotic adjustment substances, hormone levels, and flavonoid metabolites in black locust under controlled drought stress. The results demonstrated that as drought stress intensified, stomatal aperture and density decreased, while trichome density and length exhibited significant increases. MDA, proline, IAA, and osmotic adjustment substances (soluble protein, reducing sugar, and total sugar) first increased and then decreased as drought stress intensified. A total of 245 flavonoid compounds were identified through metabolomic analysis, among which 91 exhibited differential expression under drought treatments. Notably, 37 flavonoids, including flavonols and glycosylated derivatives, were consistently upregulated. These findings suggest that drought stress can lead to the accumulation of flavonoids. This study explored the physiological and metabolic responses of mature black locust trees to drought stress, offering insights for selecting drought-resistant species in vegetation restoration and informing ecological management practices in arid regions. Full article

(This article belongs to the Section Forest Ecophysiology and Biology)

► Show Figures

Figure 1

13 pages, 4318 KiB

Open AccessArticle

Physical and Mechanical Properties and Microstructure Characterization of Thermally Modified Flattened Bamboo (Phyllostachys edulis) Material

by Yixuan Zheng, Lina Liu, Minzhen Bao, Feng Lin, Xujun Wu, Yanjun Li, Yan Gong, Weijie Gu and Weigang Zhang

Forests 2025, 16(4), 694; https://doi.org/10.3390/f16040694 - 17 Apr 2025

Abstract

This study investigated the effects of thermal modification treatment on flattened bamboo lumber by using temperature (180 °C, 190 °C, 200 °C) and duration (2, 3, 4 h) as experimental variables. The physicochemical properties, crystallinity, bending deformation, chemical composition, and microstructural evolution of [...] Read more.

This study investigated the effects of thermal modification treatment on flattened bamboo lumber by using temperature (180 °C, 190 °C, 200 °C) and duration (2, 3, 4 h) as experimental variables. The physicochemical properties, crystallinity, bending deformation, chemical composition, and microstructural evolution of the material before and after treatment were systematically analyzed using universal mechanical testing, scanning electron microscopy (SEM), X-ray diffraction (XRD), Fourier transform infrared spectroscopy (FTIR), and nanoindentation. This comprehensive approach aimed to achieve high-performance flattened bamboo lumber. The results revealed that thermal modification significantly reduced the flexural modulus of elasticity and hardness of the flattened bamboo lumber, which reached their minimum values of 4479 MPa and 786.71 N, under the treatment at 190 °C/3 h. Conversely, it enhanced the longitudinal compressive strength of flattened bamboo lumber, achieving a maximum value of 57.28 MPa at 180 °C/2 h. At the microscale, the nanomechanical strength decreased under 190–200 °C treatments, accompanied by a tighter cell arrangement and evident shrinkage and deformation of the parenchyma cells. Dimensional stability tests combined with FTIR and crystallinity analyses demonstrated a reduction in the number of hydrophilic groups and improved dimensional stability after thermal modification. Notably, the material treated at 200 °C for 4 h retained its dimensional stability and exhibited no deformation. Full article

(This article belongs to the Section Wood Science and Forest Products)

► Show Figures

Figure 1

23 pages, 2802 KiB

Open AccessArticle

Research on the Impact of Climate Change Perceptions on the Carbon Offset Behavior of Visitors to Wuyi Mountain Forestry Heritage Site

by Sunbowen Zhang, Cuifei Liu, Youcheng Chen, Jingxuan Liang and Yongqiang Ma

Forests 2025, 16(4), 693; https://doi.org/10.3390/f16040693 - 17 Apr 2025

Abstract

Forestry heritage tourism can spread the ecological concept of harmonious coexistence between humans and nature, and it is a nature-based solution to climate change. However, how tourists are guided to form an emotional identity and how their attention to climate change issues can [...] Read more.

Forestry heritage tourism can spread the ecological concept of harmonious coexistence between humans and nature, and it is a nature-based solution to climate change. However, how tourists are guided to form an emotional identity and how their attention to climate change issues can be stimulated continuously remain unclear. Therefore, in this study, we selected the Wuyi Mountain Forestry Heritage Site as our study site and employed PLS-SEM to analyze the responses of 384 tourists, thereby examining the underlying mechanism linking their perceptions of climate change to carbon offset behaviors within forestry heritage sites. The results showed the following: Perceptions of climate change had a positive and significant impact on carbon offset behavior (β = 0.310, p < 0.001), ecological identity had a positive and significant impact on carbon offset behavior (β = 0.375, p < 0.001), and the sense of environmental responsibility had a positive and significant impact on carbon offset behavior (β = 0.226, p < 0.01). At the same time, ecological identity and environmental responsibility play an intermediary role, and the impact of climate change perception on the carbon offset behavior of tourists at forestry heritage sites is moderated by tourists’ health attitudes. In addition, gender, age, and educational background have an impact on the process of carbon-offsetting behavior development at forestry heritage sites. This research further clarifies the internal logic of tourists’ carbon offset behavior in the context of heritage tourism, helps to enrich the theoretical system of Nbs and heritage tourism research, and provides a feasible reference for the realization of the SDGs. Full article

(This article belongs to the Special Issue Forests and Nature Tourism: Navigating Conservation, Recreation, and Change in the Anthropocene)

► Show Figures

Figure 1

23 pages, 25076 KiB

Open AccessArticle

Integrating DEM and Deep Learning for Forested Terrain Analysis: Enhancing Fire Risk Assessment Through Mountain Peak and Water System Extraction in Chongli District

by Yihui Wu, Xueying Sun, Liang Qi, Jiang Xu, Demin Gao and Zhengli Zhu

Forests 2025, 16(4), 692; https://doi.org/10.3390/f16040692 - 16 Apr 2025

Abstract

Accurate fire risk assessment in forested terrain is crucial for effective disaster management and ecological conservation. This study innovatively proposes a novel framework that integrates Digital Elevation Models (DEMs) with deep learning techniques to enhance fire risk assessment in Chongli District. Our framework [...] Read more.

Accurate fire risk assessment in forested terrain is crucial for effective disaster management and ecological conservation. This study innovatively proposes a novel framework that integrates Digital Elevation Models (DEMs) with deep learning techniques to enhance fire risk assessment in Chongli District. Our framework innovatively combines DEM data with Faster Regions with Convolutional Neural Networks (Faster R-CNN) and CNN-based methods, breaking through the limitations of traditional approaches that rely on manual feature extraction. It is capable of automatically identifying critical terrain features, such as mountain peaks and water systems, with higher accuracy and efficiency. DEMs provide high-resolution topographical information, which deep learning models leverage to accurately identify and delineate key geographical features. Our results show that the integration of DEMs and deep learning significantly improves the accuracy of fire risk assessment by offering detailed and precise terrain analysis, thereby providing more reliable inputs for fire behavior prediction. The extracted mountain peaks and water systems, as fundamental inputs for fire behavior prediction, enable more accurate predictions of fire spread and potential impact areas. This study not only highlights the great potential of combining geospatial data with advanced machine learning techniques but also offers a scalable and efficient solution for forest fire risk management in mountainous regions. Future work will focus on expanding the dataset to include more environmental variables and validating the model in different geographical areas to further enhance its robustness and applicability. Full article

(This article belongs to the Special Issue Fire Ecology and Management in Forest—2nd Edition)

► Show Figures

Figure 1

14 pages, 5210 KiB

Open AccessArticle

Integrated Metabolome and Transcriptome Analysis Reveals New Insights into the Walnut Seed Coat Coloration

by Ruiqi Wang, Xin Huang, Xueqin Wan, Shuaiying Zhang, Xiandan Luo, Jianghong Qian, Fang He, Lianghua Chen, Fan Zhang and Hanbo Yang

Forests 2025, 16(4), 691; https://doi.org/10.3390/f16040691 - 16 Apr 2025

Abstract

The color of the walnut seed coat is a critical determinant of its market value; however, research into the mechanisms responsible for seed coat color formation is yet to be determined. Using two walnut clones with contrasting pale-yellow and light purple seed coats, [...] Read more.

The color of the walnut seed coat is a critical determinant of its market value; however, research into the mechanisms responsible for seed coat color formation is yet to be determined. Using two walnut clones with contrasting pale-yellow and light purple seed coats, we characterized pigmentation, particularly anthocyanin content, using spectrophotometry. We then conducted integrated transcriptomic and metabolomic analyses to identify the molecular mechanisms and pathways underlying their formation. The anthocyanin content in the light purple seed coat clone was significantly greater than that in the clone with a white seed coat. The results of comparative metabolomics indicated that four anthocyanins (delphinidin, cyanidin-3-(caffeoylglucoside), pelargonidin-3-(6″-caffeoylglucoside), and delphinidin-3-O-sophoroside) were significantly more abundant in the light purple seed coat clone. These anthocyanins were the key pigments responsible for the light purple coloration of the walnut seed coat. Furthermore, comparative transcriptomics revealed that structural genes in the anthocyanin biosynthesis pathway (e.g., phenylalanine ammonia-lyase, 4-coumarate-CoA ligase, chalcone isomerase, and bronze-1) were significantly upregulated in the purple seed coat clone. Coexpression network analysis revealed that several transcription factors (e.g., ARF, bHLH, and MYB-related) were significantly correlated with the upregulation of these structural genes and the accumulation of four key anthocyanins. These transcription factors may serve as critical regulators influencing seed coat color formation. In conclusion, these findings establish a strong theoretical foundation for walnut breeding aimed at developing diverse seed coat colors. Full article

(This article belongs to the Special Issue Genetic Diversity and Gene Analysis in Forest Tree Breeding)

► Show Figures

Figure 1

18 pages, 5147 KiB

Open AccessArticle

Improvement of 3D Green Volume Estimation Method for Individual Street Trees Based on TLS Data

by Yanghong Zhu, Jianrong Li and Yannan Xu

Forests 2025, 16(4), 690; https://doi.org/10.3390/f16040690 - 16 Apr 2025

Abstract

Vertical structure monitoring of urban vegetation provides data support for urban green space planning and ecological management, playing a significant role in promoting sustainable urban ecological development. Three-dimensional green volume (3DGV) is a comprehensive index used to characterize the ecological benefit of urban [...] Read more.

Vertical structure monitoring of urban vegetation provides data support for urban green space planning and ecological management, playing a significant role in promoting sustainable urban ecological development. Three-dimensional green volume (3DGV) is a comprehensive index used to characterize the ecological benefit of urban vegetation. As a critical component of urban vegetation, street trees play a key role in urban ecological benefits evaluation, and the quantitative estimation of their 3DGV serves as the foundation for this assessment. However, current methods for measuring 3DGV based on point cloud data often suffer from issues of overestimation or underestimation. To improve the accuracy of the 3DGV for urban street trees, this study proposed a novel approach that used convex hull coupling k-means clustering convex hulls. A new method based on terrestrial laser scanning (TLS) data was proposed, referred to as the Convex Hull Coupling Method (CHCM). This method divides the tree crown into two parts in the vertical direction according to the point cloud density, which better adapts to the lower density of the upper layer of TLS data and obtains a more accurate 3DGV of individual trees. To validate the effectiveness of the CHCM method, 30 sycamore (Platanus × acerifolia (Aiton) Willd.) plants were used as research objects. We used the CHCM and five traditional 3DGV calculation methods (frustum method, convex hull method, k-means clustering convex hulls, alpha-shape algorithm, and voxel-based method) to calculate the 3DGV of individual trees. Additionally, the 3DGV was predicted and analyzed using five fitting models. The results show the following: (1) Compared with the traditional methods, the CHCM improves the estimation accuracy of the 3DGV of individual trees and shows a high consistency in the data verification, which indicates that the CHCM method is stable and reliable, and (2) the fitting results R² of the five models were all above 0.75, with the exponential function model showing the best fitting accuracy (R² = 0.89, RMSE = 74.85 m³). These results indicate that for TLS data, the CHCM can achieve more accurate 3DGV estimates for individual trees, outperforming traditional methods in both applicability and accuracy. The research results not only offer a novel technical approach for 3DGV calculation using TLS data but also establish a reliable quantitative foundation for the scientific assessment of the ecological benefits of urban street trees and green space planning. Full article

(This article belongs to the Section Urban Forestry)

► Show Figures

Figure 1

27 pages, 6455 KiB

Open AccessArticle

Tackling the Wildfire Prediction Challenge: An Explainable Artificial Intelligence (XAI) Model Combining Extreme Gradient Boosting (XGBoost) with SHapley Additive exPlanations (SHAP) for Enhanced Interpretability and Accuracy

by Bin Liao, Tao Zhou, Yanping Liu, Min Li and Tao Zhang

Forests 2025, 16(4), 689; https://doi.org/10.3390/f16040689 - 16 Apr 2025

Abstract

The intensification of global climate change, combined with increasing human activities, has significantly increased wildfire frequency and severity, posing a major global environmental challenge. As an illustration, Guizhou Province in China encountered a total of 221 wildfires over a span of 12 days. [...] Read more.

The intensification of global climate change, combined with increasing human activities, has significantly increased wildfire frequency and severity, posing a major global environmental challenge. As an illustration, Guizhou Province in China encountered a total of 221 wildfires over a span of 12 days. Despite significant advancements in wildfire prediction models, challenges related to data imbalance and model interpretability persist, undermining their overall reliability. In response to these challenges, this study proposes an explainable wildfire risk prediction model (EWXS) leveraging Extreme Gradient Boosting (XGBoost), with a focus on Guizhou Province. The methodology involved converting raster and vector data into structured tabular formats, merging, normalizing, and encoding them using the Weight of Evidence (WOE) technique to enhance feature representation. Subsequently, the cleaned data were balanced to establish a robust foundation for the EWXS model. The performance of the EWXS model was evaluated in comparison to established models, such as CatBoost, using a range of performance metrics. The results indicated that the EWXS model achieved an accuracy of 99.22%, precision of 98.48%, recall of 96.82%, an F1 score of 97.64%, and an AUC of 0.983, thereby demonstrating its strong performance. Moreover, the SHAP framework was employed to enhance model interpretability, unveiling key factors influencing wildfire risk, including proximity to villages, meteorological conditions, air humidity, and variations in vegetation temperature. This analysis provides valuable support for decision-making bodies by offering clear, explanatory insights into the factors contributing to wildfire risk. Full article

(This article belongs to the Special Issue Forest Fires Prediction and Detection—2nd Edition)

► Show Figures

Figure 1

21 pages, 7705 KiB

Open AccessArticle

Quantifying Missed Opportunities for Cumulative Forest Road Carbon Storage over the Past 50 Years in the Boreal Forest of Eastern Canada

by Alejandro Vega Escobar, François Girard and Osvaldo Valeria

Forests 2025, 16(4), 688; https://doi.org/10.3390/f16040688 - 16 Apr 2025

Abstract

Forest road networks are essential for forest operations but significantly contribute to carbon loss and landscape fragmentation in boreal ecosystems. This study evaluates the potential of reforesting unused forest roads to enhance carbon storage (CS) in Quebec’s boreal forests. Four reforestation scenarios were [...] Read more.

Forest road networks are essential for forest operations but significantly contribute to carbon loss and landscape fragmentation in boreal ecosystems. This study evaluates the potential of reforesting unused forest roads to enhance carbon storage (CS) in Quebec’s boreal forests. Four reforestation scenarios were simulated using spatial data from AQréseau+ and the Ecoforestry Map of Quebec, combined with the CBM-CFS3 carbon model. These scenarios varied in site preparation conditions and species selection, including the use of fast-growing local species. Random forest (RF) models were applied to analyze the influence of key variables on CS dynamics, focusing on the road area and years to harvest. The study area covered approximately 294,000 km², and the temporal dimension was incorporated by estimating the construction dates of forest roads. Results show that scenarios integrating soil preparation and fast-growing species (S1I1) achieved the highest CS potential, with up to 6.8 million tons (Mt) of additional carbon stored over a 40–100 year period for medium-category roads, compared to 1.15 million tons in scenarios without intervention (S0I0). These findings underscore the role of reforestation in enhancing CS within managed forests. Future work should prioritize road segments for reforestation, considering ecological benefits, operational feasibility, and climate resilience. Full article

(This article belongs to the Section Forest Ecology and Management)

► Show Figures

Figure 1

18 pages, 2005 KiB

Open AccessArticle

Comparison of Growth Strategies and Biomass Allocation in Chinese Fir Provenances from the Subtropical Region of China

by Zhibing Wan, Ning Liu, Chenggong Liu, Meiman Zhang, Chengcheng Gao, Lingyu Yang, Liangjin Yao and Xueli Zhang

Forests 2025, 16(4), 687; https://doi.org/10.3390/f16040687 - 16 Apr 2025

Abstract

This study aims to evaluate the growth characteristics of six Chinese fir (Cunninghamia lanceolata (Lamb.) Hook.) provenances (S1–S6) from different climatic regions in subtropical China in order to select superior provenances with strong adaptability, fast growth, and reasonable biomass allocation. These results [...] Read more.

This study aims to evaluate the growth characteristics of six Chinese fir (Cunninghamia lanceolata (Lamb.) Hook.) provenances (S1–S6) from different climatic regions in subtropical China in order to select superior provenances with strong adaptability, fast growth, and reasonable biomass allocation. These results will provide references for genetic improvement and resource utilization of Chinese fir plantations. A total of 385 trees, aged 26 to 48 years, were selected from the Chinese fir gene bank in Anhui. Wood core sampling was used to obtain tree ring width and early/latewood width data. Growth rate, fast-growth period, and biomass allocation of each provenance were analyzed using methods such as the logistic growth equation, BAI (basal area increment), latewood percentage, and biomass estimation. The fast-growth period of Chinese fir starts from the 2nd to the 4th year, with significant growth occurring around the 14th year and growth stabilizing between 30 and 50 years. Provenance S2 showed clear advantages in growth rate and biomass, while S6 was relatively weak. BAI analysis revealed that the provenances reached their growth peak around 10 years of age, with a gradual decline afterward, but S2 maintained higher growth levels for a longer period. Root-shoot ratio analysis showed that S2 had the most balanced ratio, promoting stable growth and efficient water and nutrient absorption, while S6 had a higher root-shoot ratio, indicating growth limitations. Furthermore, S2 demonstrated continuous biomass increase after 30 years, indicating excellent growth potential. This study provides quantitative analysis of the growth characteristics and adaptability of different Chinese fir provenances, offering scientific support for the construction and breeding of Chinese fir plantations, and contributing to enhancing the productivity and ecological adaptability of Chinese fir plantations for sustainable resource utilization. Full article

(This article belongs to the Special Issue Adaptive Mechanisms of Tree Seedlings to Adapt to Stress—Second Edition)

► Show Figures

Figure 1

15 pages, 2645 KiB

Open AccessArticle

Establishing Models for Predicting Above-Ground Carbon Stock Based on Sentinel-2 Imagery for Evergreen Broadleaf Forests in South Central Coastal Ecoregion, Vietnam

by Nguyen Huu Tam, Nguyen Van Loi and Hoang Huy Tuan

Forests 2025, 16(4), 686; https://doi.org/10.3390/f16040686 - 15 Apr 2025

Abstract

In Vietnam, models for estimating Above-Ground Biomass (AGB) to predict carbon stock are primarily based on diameter at breast height (DBH), tree height (H), and wood density (WD). However, remote sensing has increasingly been recognized as a cost-effective and accurate alternative. Within this [...] Read more.

In Vietnam, models for estimating Above-Ground Biomass (AGB) to predict carbon stock are primarily based on diameter at breast height (DBH), tree height (H), and wood density (WD). However, remote sensing has increasingly been recognized as a cost-effective and accurate alternative. Within this context, the present study aimed to develop correlation equations between Total Above-Ground Carbon (TAGC) and vegetation indices derived from Sentinel-2 imagery to enable direct estimation of carbon stock for assessing emissions and removals. In this study, the remote sensing indices most strongly associated with TAGC were identified using principal component analysis (PCA). TAGC values were calculated based on forest inventory data from 115 sample plots. Regression models were developed using Ordinary Least Squares and Maximum Likelihood methods and were validated through Monte Carlo cross-validation. The results revealed that Normalized Difference Vegetation Index (NDVI), Soil Adjusted Vegetation Index (SAVI), and Near Infrared Reflectance (NIR), as well as three variable combinations—(NDVI, ARVI), (SAVI, SIPI), and (NIR, EVI — Enhanced Vegetation Index)—had strong influences on TAGC. A total of 36 weighted linear and non-linear models were constructed using these selected variables. Among them, the quadratic models incorporating NIR and the (NIR, EVI) combination were identified as optimal, with AIC values of 756.924 and 752.493, R² values of 0.86 and 0.87, and Mean Percentage Standard Errors (MPSEs) of 22.04% and 21.63%, respectively. Consequently, these two models are recommended for predicting carbon stocks in Evergreen Broadleaf (EBL) forests within Vietnam’s South Central Coastal Ecoregion. Full article

(This article belongs to the Special Issue Remote Sensing-Based Methods for Forest Aboveground Biomass Estimation)

► Show Figures

Figure 1

Journal Description

Forests

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI