Forestry Applications Research Articles

Improved Cylinder-Based Tree Trunk Detection in LiDAR Point Clouds for Forestry Applications

The application of LiDAR technology in extracting individual trees and stand parameters plays a crucial role in forest surveys. Accurate identification of individual tree trunks is a critical foundation for subsequent parameter extraction. For LiDAR-acquired forest point cloud data, existing two-dimensional (2D) plane-based algorithms for tree trunk detection often suffer from spatial information loss, resulting in reduced accuracy, particularly for tilted trees. While cylinder fitting algorithms provide a three-dimensional (3D) solution for trunk detection, their performance in complex forest environments remains limited due to sensitivity to parameters like distance thresholds. To address these challenges, this study proposes an improved individual tree trunk detection algorithm, Random Sample Consensus Cylinder Fitting (RANSAC-CyF), specifically optimized for detecting cylindrical tree trunks. Validated in three forest plots with varying complexities in Tianhe District, Guangzhou, the algorithm demonstrated significant advantages in the inlier rate, detection success rate, and robustness for tilted trees. The study showed the following results: (1) The average difference between the inlier rates of tree trunks and non-tree points for the three sample plots using RANSAC-CyF were 0.59, 0.63, and 0.52, respectively, which were significantly higher than those using the Least Squares Circle Fitting (LSCF) algorithm and the Random Sample Consensus Circle Fitting (RANSAC-CF) algorithm (p < 0.05). (2) RANSAC-CyF required only 2 and 8 clusters to achieve a 100% detection success rate in Plot 1 and Plot 2, while the other algorithms needed 26 and 40 clusters. (3) The effective distance threshold range of RANSAC-CyF was more than twice that of the comparison algorithms, maintaining stable inlier rates above 0.9 across all tilt angles. (4) The RANSAC-CyF algorithm still achieved good detection performance in the challenging Plot 3. Together, the other two algorithms failed to detect. The findings highlight the RANSAC-CyF algorithm’s superior accuracy, robustness, and adaptability in complex forest environments, significantly improving the efficiency and precision of individual tree trunk detection for forestry surveys and ecological research.

A Multi-Drone System Proof of Concept for Forestry Applications

This study presents a multi-drone proof of concept for efficient forest mapping and autonomous operation, framed within the context of the OPENSWARM EU Project. The approach leverages state-of-the-art open-source simultaneous localisation and mapping (SLAM) frameworks, like LiDAR (Light Detection And Ranging) Inertial Odometry via Smoothing and Mapping (LIO-SAM), and Distributed Collaborative LiDAR SLAM Framework for a Robotic Swarm (DCL-SLAM), seamlessly integrated within the MRS UAV System and Swarm Formation packages. This integration is achieved through a series of procedures compliant with Robot Operating System middleware (ROS), including an auto-tuning particle swarm optimisation method for enhanced flight control and stabilisation, which is crucial for autonomous operation in challenging environments. Field experiments conducted in a forest with multiple drones demonstrate the system’s ability to navigate complex terrains as a coordinated swarm, accurately and collaboratively mapping forest areas. Results highlight the potential of this proof of concept, contributing to the development of scalable autonomous solutions for forestry management. The findings emphasise the significance of integrating multiple open-source technologies to advance sustainable forestry practices using swarms of drones.

Web-based Timber Logs Information System Using the YOLOv8 Model: IstifTakip

This study introduces İstifTakip, a web-based information system developed for the automated detection and measurement of stacked timber logs using the YOLOv8 deep learning model. The system aims to overcome the limitations of manual timber measurement methods by providing a more accurate and efficient alternative. Data were collected through smartphone images of timber stacks at the Ulucak Forest Depot in İzmir, Türkiye. The YOLOv8 model, optimized using the Optuna library, was trained on this dataset to detect logs and calculate key attributes such as diameter and volume. Hyperparameter optimization with Optuna resulted in a significant improvement in model performance, achieving an mAP@0.5 score of 0.8569, precision of 0.8513, and recall of 0.8827. These results demonstrate the model’s robustness and accuracy in detecting logs across varied image conditions. İstifTakip was developed using the Django framework and offers a user-friendly interface where users can upload images, annotate reference lines, and obtain log measurements. The system is specifically designed for Turkish forestry, supporting local language and practices, which sets it apart from other global solutions. Its scalability and potential for integration with mobile devices make it a valuable tool for future forestry applications. This research highlights the advantages of combining deep learning and smart forestry technologies to enhance operational efficiency and data accuracy in timber stack management.

Applications of CRISPR Technologies in Forestry and Molecular Wood Biotechnology.

Forests worldwide are under increasing pressure from climate change and emerging diseases, threatening their vital ecological and economic roles. Traditional breeding approaches, while valuable, are inherently slow and limited by the long generation times and existing genetic variation of trees. CRISPR technologies offer a transformative solution, enabling precise and efficient genome editing to accelerate the development of climate-resilient and productive forests. This review provides a comprehensive overview of CRISPR applications in forestry, exploring its potential for enhancing disease resistance, improving abiotic stress tolerance, modifying wood properties, and accelerating growth. We discuss the mechanisms and applications of various CRISPR systems, including base editing, prime editing, and multiplexing strategies. Additionally, we highlight recent advances in overcoming key challenges such as reagent delivery and plant regeneration, which are crucial for successful implementation of CRISPR in trees. We also delve into the potential and ethical considerations of using CRISPR gene drive for population-level genetic alterations, as well as the importance of genetic containment strategies for mitigating risks. This review emphasizes the need for continued research, technological advancements, extensive long-term field trials, public engagement, and responsible innovation to fully harness the power of CRISPR for shaping a sustainable future for forests.

A Review of Semantic Segmentation and Instance Segmentation Techniques in Forestry Using LiDAR and Imagery Data

The objective of this review is to conduct a critical analysis of the current literature pertaining to segmentation techniques and provide a methodical summary of their impact on forestry-related activities, emphasizing their applications using LiDAR and imagery data. This review covers the challenges, progress, and application of these strategies in ecological monitoring, forest inventory, and tree species classification. Through the process of synthesizing pivotal discoveries from multiple studies, this comprehensive analysis provides valuable perspectives on the present status of research and highlights prospective areas for further exploration. The primary topics addressed encompass the approach employed for executing the examination, the fundamental discoveries associated with semantic segmentation and instance segmentation in the domain of forestry, and the ramifications of these discoveries for the discipline. This review highlights the effectiveness of semantic and instance segmentation techniques in forestry applications, such as precise tree species identification and individual tree monitoring. However, challenges such as occlusions, overlapping branches, and varying data quality remain. Future research should focus on overcoming these obstacles to enhance the precision and applicability of these segmentation methodologies.

Sodium alginate-g-polyacrylamide hydrogel for water retention and plant growth promotion in water-deficient soils

Natural polymer-based hydrogels are preferred as soil water retention agents due to their inherent biocompatibility and biodegradability. Generally, these natural polymers are chemically modified by graft polymerization of vinyl monomers to improve their water absorption and retention properties. Among the polysaccharides used to prepare natural hydrogels, those based on sodium alginate (Alg) stand out for their high-water absorption and retention capacity, as well as for their ability to promote plant growth. The main objective of this study was to develop a biodegradable alginate-based hydrogel as a water retainer to promote plant growth under water deficit conditions. The synthesis was achieved by grafting poly(acrylamide) (PAM) onto Alg backbone, using bisacrylamide as chemical crosslinker and different ratios of alginate:acrylamide (Ac). In addition, Eucalyptus nitens seedlings were used as a model plant to evaluate the effect of alginate-g-polyacrylamide (Alg:PAM) hydrogel application to the growing medium on plant survival, growth, and physiological responses under both well-watered and water-deficient soil conditions. The maximum degree of swelling (65 g/g) was obtained for the hydrogel prepared. The pseudo-second order model described the water uptake kinetics of the hydrogel. The degradability of Alg:PAM hydrogel reached up to 85 % in 5 weeks in soil and occurs by breaking the glycosidic bonds of the alginate. The E. nitens seedlings cultivated with different doses of Alg:PAM hydrogel (4:1 Alg:Ac) showed higher values of height and root diameter relative growth, survival and photosynthetic responses in comparison to non-treated plants. The results indicate that Alg:PAM hydrogel (4:1 Alg:Ac) has promising applications in forestry as a water retention and seedling growth promoter under water deficient conditions.

Economic valuation of carbon sequestration in Quito’s Metropolitan Park using Sentinel-2 and neural networks

This study introduces an innovative method for assessing the economic value of carbon stored by the urban park forest in Quito, Ecuador. The method uses Sentinel-2 remote sensing data and advanced deep learning techniques. A large forest study area was chosen, and detailed field measurements were taken to gather biomass and carbon data. Sentinel-2 satellite images were processed to correct for radiation and atmospheric conditions, and vegetation indices such as NDVI and EVI were calculated. To model forest biomass, a convolutional neural network (CNN) was created and trained using Sentinel-2 spectral bands and vegetation indices. The model was validated with independent field data and demonstrated high accuracy in estimating biomass and carbon, as indicated by evaluation metrics like RMSE and R². The findings include detailed maps showing the spatial distribution of biomass and carbon in the study area, which can be a valuable tool for forest management and the implementation of policies for valuing stored carbon. This approach combines the high resolution of Sentinel-2 data with the predictive power of neural networks, providing a robust and scalable method for estimating carbon across large forest areas. The study's conclusions emphasize the feasibility and accuracy of this approach and its potential for application in various forestry and geographical contexts.

Mobile Devices in Forest Mensuration: A Review of Technologies and Methods in Single Tree Measurements

Mobile devices such as smartphones, tablets or similar devices are becoming increasingly important as measurement devices in forestry due to their advanced sensors, including RGB cameras and LiDAR systems. This review examines the current state of applications of mobile devices for measuring biometric characteristics of individual trees and presents technologies, applications, measurement accuracy and implementation barriers. Passive sensors, such as RGB cameras have proven their potential for 3D reconstruction and analysing point clouds that improve single tree-level information collection. Active sensors with LiDAR-equipped smartphones provide precise quantitative measurements but are limited by specific hardware requirements. The combination of passive and active sensing techniques has shown significant potential for comprehensive data collection. The methods of data collection, both physical and digital, significantly affect the accuracy and reproducibility of measurements. Applications such as ForestScanner and TRESTIMATM have automated the measurement of tree characteristics and simplified data collection. However, environmental conditions and sensor limitations pose a challenge. There are also computational obstacles, as many methods require significant post-processing. The review highlights the advances in mobile device-based forestry applications and emphasizes the need for standardized protocols and cross-device benchmarking. Future research should focus on developing robust algorithms and cost-effective solutions to improve measurement accuracy and accessibility. While mobile devices offer significant potential for forest surveying, overcoming the above-mentioned challenges is critical to optimizing their application in forest management and protection.

Dual-Wavelength LiDAR with a Single-Pixel Detector Based on the Time-Stretched Method.

In the fields of agriculture and forestry, the Normalized Difference Vegetation Index (NDVI) is a critical indicator for assessing the physiological state of plants. Traditional imaging sensors can only collect two-dimensional vegetation distribution data, while dual-wavelength LiDAR technology offers the capability to capture vertical distribution information, which is essential for forest structure recovery and precision agriculture management. However, existing LiDAR systems face challenges in detecting echoes at two wavelengths, typically relying on multiple detectors or array sensors, leading to high costs, bulky systems, and slow detection rates. This study introduces a time-stretched method to separate two laser wavelengths in the time dimension, enabling a more cost-effective and efficient dual-spectral (600 nm and 800 nm) LiDAR system. Utilizing a supercontinuum laser and a single-pixel detector, the system incorporates specifically designed time-stretched transmission optics, enhancing the efficiency of NDVI data collection. We validated the ranging performance of the system, achieving an accuracy of approximately 3 mm by collecting data with a high sampling rate oscilloscope. Furthermore, by detecting branches, soil, and leaves in various health conditions, we evaluated the system's performance. The dual-wavelength LiDAR can detect variations in NDVI due to differences in chlorophyll concentration and water content. Additionally, we used the radar equation to analyze the actual scene, clarifying the impact of the incidence angle on reflectance and NDVI. Scanning the Red Sumach, we obtained its NDVI distribution, demonstrating its physical characteristics. In conclusion, the proposed dual-wavelength LiDAR based on the time-stretched method has proven effective in agricultural and forestry applications, offering a new technological approach for future precision agriculture and forest management.

Boronic ester bonds hydrogel with temperature and pH responsiveness for controlled release fertilizer

The growth of plants can be severely restricted by insufficient water and fertilizers in pure soil. There exists a significant demand for developing a hydrogel to enhance water retention and enable control release fertilizer. In this study, we synthesized the boronic ester bonds hydrogel with temperature and pH responsiveness using sodium alginate, borax pentahydrate and carboxymethyl chitosan (CMCS) via a one-pot method. Urea was loaded in the hydrogel as a model fertilizer. The dual responsive hydrogel exhibited a rapid release behavior of fertilizer due to the dissociation of boronic ester bonds at 40 °C and pH 5.5. The incorporation of CMCS improved the non-covalent interaction within the hydrogel, accompanied by a reduction in the pore size and swelling ratio to 74 μm and 11.3 g/g, respectively. The hydrogel exhibited desirable water retention capacity in soil with a weight loss of only 41.9 % at day 15, while the degradation rate of hydrogel was 49.0 %. Additionally, the hydrogel displayed good antibacterial activity against both Rhizobium and Bacillus cereus strains while being non-toxic to plants. The dual responsive hydrogel holds promising applications in agriculture, forestry, and horticulture.

Uncertainty talk for bio-digital technologies: Expert conceptions of uncertainties in genomic selection for forestry

The burgeoning literature on uncertainty analysis shows the need for accessible and transparent information about the limitations of knowledge associated with predictive models for environmental decision-making. Using qualitative analysis, we examine how experts involved in the development of genomic selection (GS) for Canadian public forestry conifer breeding assess and communicate uncertainty. GS is a bio-digital technology characterized by big data compilation, sophisticated statistical analysis, and high-throughput genome sequencing. While GS applications in forestry have the potential to increase yields, reduce errors, and improve the selection of resilient trees in the face of climate change, our data revealed barriers that impede more comprehensive discussions about uncertainty, including assumptions that uncertainty can (and should) be eliminated through the availability of more data, tacit commitments to the application of GS in commercial forestry operations, deterministic assumptions about linear gene-to-trait outcomes, and difficulties discussing uncertainty in collective settings. Uncertainty talk is uncomfortable as it can be perceived as a threat to applied research goals, but uncertainty talk is also a necessary, productive, and generative way to encourage transdisciplinary and inclusive discussions at early stages of predictive model deployment for environmental applications.

Automatic Classification of Submerged Macrophytes at Lake Constance Using Laser Bathymetry Point Clouds

Submerged aquatic vegetation, also referred to as submerged macrophytes, provides important habitats and serves as a significant ecological indicator for assessing the condition of water bodies and for gaining insights into the impacts of climate change. In this study, we introduce a novel approach for the classification of submerged vegetation captured with bathymetric LiDAR (Light Detection And Ranging) as a basis for monitoring their state and change, and we validated the results against established monitoring techniques. Employing full-waveform airborne laser scanning, which is routinely used for topographic mapping and forestry applications on dry land, we extended its application to the detection of underwater vegetation in Lake Constance. The primary focus of this research lies in the automatic classification of bathymetric 3D LiDAR point clouds using a decision-based approach, distinguishing the three vegetation classes, (i) Low Vegetation, (ii) High Vegetation, and (iii) Vegetation Canopy, based on their height and other properties like local point density. The results reveal detailed 3D representations of submerged vegetation, enabling the identification of vegetation structures and the inference of vegetation types with reference to pre-existing knowledge. While the results within the training areas demonstrate high precision and alignment with the comparison data, the findings in independent test areas exhibit certain deficiencies that are likely addressable through corrective measures in the future.

Using the full potential of Airborne Laser Scanning (aerial LiDAR) in wildlife research

AbstractSpecies' habitats are strongly influenced by the 3‐dimensional (3D) structure of ecosystems. The dominant technique used to measure 3D structure is Airborne Laser Scanning (ALS), a type of LiDAR (Light Detection and Ranging) technology. Airborne Laser Scanning captures fine‐scale structural information over large spatial extents and provides useful environmental predictors for habitat modeling. However, due to technical complexities of processing ALS data, the full potential of ALS is not yet realized in wildlife research, with most studies relying on a limited set of 3D predictors, such as vegetation metrics developed principally for forestry applications. Here, we highlight the full potential of ALS data for wildlife research and provide insight into how it can be best used to capture the environmental conditions, resources, and risks that directly determine a species' habitat. We provide a nontechnical overview of ALS data, covering data considerations and the modern options available for creating custom, ecologically relevant, ALS predictors. Options included the following: i) direct point cloud approaches that measure structure using grid, voxel, and point metrics, ii) object‐based approaches that identify user‐defined features in the point cloud, and iii) modeled environmental predictors that use additional modeling to infer a range of habitat characteristics, including the extrapolation of field acquired measurements over ALS data. By using custom ALS predictors that capture species‐specific resources, risks, and environmental conditions, wildlife practitioners can produce models that are tailored to a species' ecology, have greater biological realism, test a wider range of species‐environment relationships across scales, and provide more meaningful insights to inform wildlife conservation and management.

Forest Fire Prediction: A Spatial Machine Learning and Neural Network Approach

The study of forest fire prediction holds significant environmental and scientific importance, particularly in regions like South Carolina (SC) with a high incidence rate of forest fires. Despite the limited existing research on forest fires in this area, the application of machine learning and neural network techniques presents an opportunity to enhance forest fire prevention and control efforts. Utilizing data of forest fire from the SC Forestry Commission for the year 2023, prediction models were developed incorporating various factors such as meteorology, terrain, vegetation, and infrastructure—key drivers of forest fires in SC. Feature importance analysis was employed to construct the final fire prediction model using different machine learning and neural network approaches including Decision Tree (DT), Random Forest (RF), Logistic Regression (LR), Artificial Neural Network (ANN), Support Vector Machine (SVM), and Convolutional Neural Network (CNN). Correlation coefficients analysis was employed to construct the final fire hazard map using a correlation test. The evaluation of predictive performance based on accuracy scores revealed that the DT model achieved the highest accuracy of 90.58%, surpassing other models. However, based on the kernel density map of the fire data from 2000 to 2023, the correlation test gave the better fire hazard map compared to any other machine learning or neural network approach that utilized feature importance. Nonetheless, all models achieved prediction accuracies exceeding 80%. This finding directed us to the approach based on the correlation coefficients rather than to those just based on feature importance. The overlap between fire locations and carbon hotspots provided the immediate need to mitigate the carbon loss due to fire in those locations. These results serve as a valuable resource for forest fire prediction in SC, demonstrating the efficacy of the correlation test, providing a theoretical foundation and data support for future forestry applications in the region, and showing the outperforming capability of this method compared to other approaches based on feature importance and the importance to prioritize areas to mitigate the climate change impact based upon fire prediction.

The role of the plant microbiome for forestry, agriculture and urban greenspace in times of environmental change.

This Lilliput article provides a literature overview on ecological effects of the plant microbiome with a focus on practical application in forestry, agriculture and urban greenspace under the spectre of climate change. After an overview of the mostly bacterial microbiome of the model plant Arabidopsis thaliana, worldwide data from forests reveal ecological differentiation with respect to major guilds of predominantly fungal plant root symbionts. The plant-microbiome association forms a new holobiont, an integrated unit for ecological adaptation and evolutionary selection. Researchers explored the impact of the microbiome on the capacity of plants to adapt to changing climate conditions. They investigated the impact of the microbiome in reforestation programs, after wildfire, drought, salination and pollution events in forestry, grasslands and agriculture. With increasing temperatures plant populations migrate to higher latitudes and higher altitudes. Ecological studies compared the dispersal capacity of plant seeds with that of soil microbes and the response of soil and root microbes to experimental heating of soils. These studies described a succession of microbiome associations and the kinetics of a release of stored soil carbon into the atmosphere enhancing global warming. Scientists explored the impact of synthetic microbial communities (SynComs) on rice productivity or tea quality; of whole soil addition in grassland restoration; or single fungal inoculation in maize fields. Meta-analyses of fungal inoculation showed overall a positive effect, but also a wide variation in effect sizes. Climate change will be particularly prominent in urban areas ("urban heat islands") where more than half of the world population is living. Urban landscape architecture will thus have an important impact on human health and studies started to explore the contribution of the microbiome from urban greenspace to ecosystem services.

AI-Driven Strategies for Reducing Deforestation

Recent advancements in data science, coupled with the revolution in digital and satellite technology, have catalyzed the potential for artificial intelligence (AI) applications in forestry and wildlife sectors. Recognizing the critical importance of addressing land degradation and promoting regeneration for climate regulation, ecosystem services, and population well-being, there is a pressing need for effective land use planning and interventions. Traditional regression approaches often fail to capture underlying drivers' complexity and nonlinearity. In response, this research investigates the efficacy of AI in monitoring, predicting, and managing deforestation and forest degradation compared to conventional methods, with a goal to bolster global forest conservation endeavors. Employing a fusion of satellite imagery analysis and machine learning algorithms, such as convolutional neural networks and predictive modelling, the study focuses on key forest regions, including the Amazon Basin, Central Africa, and Southeast Asia. Through the utilization of these AI-driven strategies, critical deforestation hotspots have been successfully identified with an accuracy surpassing 85%, markedly higher than traditional methods. This breakthrough underscores the transformative potential of AI in enhancing the precision and efficiency of forest conservation measures, offering a formidable tool for combating deforestation and degradation on a global scale.

Effects of Illumination Conditions on Individual Tree Height Extraction Using UAV LiDAR: Pilot Study of a Planted Coniferous Stand

Tree height is one of the key dendrometric parameters for indirectly estimating the timber volume or aboveground biomass of a forest. Field measurement is time-consuming and labor-intensive, while unmanned aerial vehicle (UAV)-borne LiDAR is a more efficient tool for acquiring tree heights of large-area forests. Although individual tree heights extracted from point cloud data are of high accuracy, they are still affected by some weather and environment factors. In this study, taking a planted M. glyptostroboides (Metasequoia glyptostroboides Hu & W.C. Cheng) stand as the study object, we preliminarily assessed the effects of various illumination conditions (solar altitude angle and cloud cover) on tree height extraction using UAV LiDAR. The eight point clouds of the target stand were scanned at four time points (sunrise, noon, sunset, and night) in two consecutive days (sunny and overcast), respectively. The point clouds were first classified into ground points and aboveground vegetation points, which accordingly produced digital elevation model (DEM) and digital surface model (DSM). Then, the canopy height model (CHM) was obtained by subtracting DEM from DSM. Subsequently, individual trees were segmented based on the seed points identified by local maxima filtering. Finally, the individual tree heights of sample trees were separately extracted and assessed against the in situ measured values. As results, the R2 and RMSEs of tree heights obtained in the overcast daytime were commonly better than those in the sunny daytime; the R2 and RMSEs at night were superior among all time points, while those at noon were poorest. These indicated that the accuracy of individual tree height extraction had an inverse correlation with the intensity of illumination. To obtain more accurate tree heights for forestry applications, it is best to acquire point cloud data using UAV LiDAR at night, or at least not at noon when the illumination is generally strongest.

Research on Efficient Feature Generation and Spatial Aggregation for Remote Sensing Semantic Segmentation

Semantic segmentation algorithms leveraging deep convolutional neural networks often encounter challenges due to their extensive parameters, high computational complexity, and slow execution. To address these issues, we introduce a semantic segmentation network model emphasizing the rapid generation of redundant features and multi-level spatial aggregation. This model applies cost-efficient linear transformations instead of standard convolution operations during feature map generation, effectively managing memory usage and reducing computational complexity. To enhance the feature maps’ representation ability post-linear transformation, a specifically designed dual-attention mechanism is implemented, enhancing the model’s capacity for semantic understanding of both local and global image information. Moreover, the model integrates sparse self-attention with multi-scale contextual strategies, effectively combining features across different scales and spatial extents. This approach optimizes computational efficiency and retains crucial information, enabling precise and quick image segmentation. To assess the model’s segmentation performance, we conducted experiments in Changge City, Henan Province, using datasets such as LoveDA, PASCAL VOC, LandCoverNet, and DroneDeploy. These experiments demonstrated the model’s outstanding performance on public remote sensing datasets, significantly reducing the parameter count and computational complexity while maintaining high accuracy in segmentation tasks. This advancement offers substantial technical benefits for applications in agriculture and forestry, including land cover classification and crop health monitoring, thereby underscoring the model’s potential to support these critical sectors effectively.

Evaluating spatially enabled machine learning approaches to depth to bedrock mapping, Alberta, Canada.

Maps showing the thickness of sediments above the bedrock (depth to bedrock, or DTB) are important for many geoscience studies and are necessary for many hydrogeological, engineering, mining, and forestry applications. However, it can be difficult to accurately estimate DTB in areas with varied topography, like lowland and mountainous terrain, because traditional methods of predicting bedrock elevation often underestimate or overestimate the elevation in rugged or incised terrain. Here, we describe a machine learning spatial prediction approach that uses information from traditional digital elevation model derived estimates of terrain morphometry and satellite imagery, augmented with spatial feature engineering techniques to predict DTB across Alberta, Canada. First, compiled measurements of DTB from borehole lithologs were used to train a natural language model to predict bedrock depth across all available lithologs, significantly increasing the dataset size. The combined data were then used for DTB modelling employing several algorithms (XGBoost, Random forests, and Cubist) and spatial feature engineering techniques, using a combination of geographic coordinates, proximity measures, neighbouring points, and spatially lagged DTB estimates. Finally, the results were contrasted with DTB predictions based on modelled relationships with the auxiliary variables, as well as conventional spatial interpolations using inverse-distance weighting and ordinary kriging methods. The results show that the use of spatially lagged variables to incorporate information from the spatial structure of the training data significantly improves predictive performance compared to using auxiliary predictors and/or geographic coordinates alone. Furthermore, unlike some of the other tested methods such as using neighbouring point locations directly as features, spatially lagged variables did not generate spurious spatial artifacts in the predicted raster maps. The proposed method is demonstrated to produce reliable results in several distinct physiographic sub-regions with contrasting terrain types, as well as at the provincial scale, indicating its broad suitability for DTB mapping in general.

Stochastic modelling of development and biomass allocation: Computation applied to architecture of young mahogany trees (Khaya senegalensis Desr. A. Juss), a native African savannah emblematic agroforestry species

The architectural plasticity forms observed in trees is a result of meristem functioning, which generates new organs and branches, and adjusts growth processes in response to heterogeneous climatic adaptations that affect biomass allocation. Analyzing this plasticity should enable the selection of adapted individuals for optimizing successful cropping systems. Mahogany tree (Khaya senegalensis) is a rhythmically growing indigenous agroforestry tree that is heavily exploited for its multiple uses. Understanding its growth characteristics, as well as the complexity of its structure (randomness, rhythmicity, etc. of Mahogany tree), could facilitate its conservation and sustainable management. This study aims to model the architecture and physiology of young mahogany trees based on field data using an organ-level structural–functional model called 'GreenLab', which is founded on source-sink relationships. Ninety trees aged 6, 12, and 24 months were measured in the field. Development was calculated using a dual-scale automaton based on the Monte Carlo process, while biomass production and its distribution to different plant organs (source and sink) were calibrated using Pressler's law using Markov chains. Meristematic activity laws, combined with organ sinks (D: Demand), photosynthesis (Q: Supply), and organic series (Q/D: Trophic pressure), were employed to simulate individual architecture. The results demonstrate that the model realistically and flexibly describes topological development and replicates biomass production and allocation processes for rhythmically growing trees. This model will enable the identification of mahogany ideotypes suited for enhancing agroforestry cropping systems based on this species and several other threatened species. These findings introduce and thus lay the groundwork for a computational plant model tailored to the needs of agroforestry from a novel perspective, offering new avenues for agronomic and forestry applications in West Africa and Côte d'Ivoire.