Single Tree Research Articles

Detecting interactions with random forests: a comment on Gries’ words of caution and suggestions for improvement

Abstract Tree-based methods are being both successfully applied and critically discussed in corpus linguistics. In this article, we would like to contribute a few aspects to this discussion from a methodological point of view. These aspects include the interpretation of interaction effects in single trees and random forests, as well as more general aspects like stability and overfitting. In particular, we have conducted a simulation study to investigate an approach suggested by Gries for computing the importance of interactions in random forests more systematically than the previous literature. The evidence of this simulation study shows that, even when interaction predictors are explicitly added, the permutation variable importance is not suited for distinguishing between main effects and interaction effects or between interaction effects of different orders. We also discuss the use of partial dependence (PD) and individual conditional expectation (ICE) plots for illustrating the functional form and potential interaction effects, and other means of interpretable machine learning.

Development of a recommendation engine for university study programme selection: A regression-based approach

This paper is the third in a series focused on bridging the gap between secondary and higher education. Our primary objective is to develop a robust theoretical framework for an innovative e-business model called the Undergraduate Study Programme Search System (USPSS). This system considers multiple criteria to reduce the likelihood of exam failure or the need for multiple retakes, while maximizing the chances of successful program completion. Testing of the proposed algorithm demonstrated that the Stochastic Gradient Boosted Regression Trees method outperforms the current method used in Lithuania for admitting applicants to 47 educational programs. Specifically, it is more accurate than the Probabilistic Neural Network for 25 programs, the Ensemble of Regression Trees for 24 programs, the Single Regression Tree for 18 programs, the Random Forest Regression for 16 programs, the Bayesian Additive Regression Trees for 13 programs, and the Regression by Discretization for 10 programs.

Fish–Seascape Associations Within an Offshore Protected Area in the Arabian Gulf

ABSTRACTCoral reef ecosystems support high fish biodiversity through ecological interactions with structural complexity across multiple spatial scales including coral colony architecture and the surrounding seascape structure. In an era where the complexity of coral reef ecosystems is being diminished, understanding the importance of structural characteristics beyond single focal patches has the potential to better inform actions for protecting, restoring or creating habitat for reef‐associated species. A seascape ecology approach was applied to explore the associations between multiple scales of seascape structure and fish assemblage response variables within a small (49.6 km2) offshore no‐take MPA, Sir Bu Nair Island Protected Area, in Sharjah, United Arab Emirates. Fish–seascape associations were modelled with single regression trees. Both in situ and remote sensing–derived variables produced the best models with highest contributions from coral cover, amount of hard‐bottom habitat type and structural complexity of the seafloor terrain. Fish species richness was significantly higher where coral cover exceeded 35%. The hard‐bottom areas with coral supported diverse assemblages dominated by carnivorous and omnivorous fishes. The Sir Bu Nair Island Protected Area provides a critical refuge for threatened and regionally overexploited species including those with low resilience to fishing. The ecological success of this protected area is key to safeguarding regional marine biodiversity and recovering fish populations to enhance food security.

Street trees: The contribution of latent heat flux to cooling dense urban areas

Trees are the most important natural factor to alleviate the urban heat island effect and the latent heat flux (LE) they release contributes significantly to urban cooling. In this study, the model ENVI-met was used to study the influence of building geometry on the LE exchanged by trees at the block scale in compact urban areas. The building density (BD), building height (BH) and sky view factor (SVF) were used to characterize building geometry. The sensitivity of LE to building geometry was estimated by multi-linear regression analysis. The following conclusions were drawn:(1) the LE of trees is sensitive to building geometry, higher during daytime than night-time in winter and the higher during night-time than daytime in summer; (2) LE changes as expected across the seasons, with LE larger in summer; (3) The shade affects the LE of a tree by influencing the solar irradiance; (4) In winter the average LE of a single tree is larger with 0.06 than 0.12 fractional vegetation cover (FVC). This study can provide useful leads towards further research to explore latent heat exchanges by trees at the street scale.

Heart disease prediction using machine learning models

Abstract. Heart disease remains a global health threat, making rapid identification crucial. Using the Heart Disease Dataset from Kaggle, this research employs a Random Forest model to analyze 13 clinical variables from 1,025 samples. To improve accuracy and address class imbalance, the dataset was split into training and test sets, utilizing methods such as Z-scores, SMOTE, and feature selection. The Random Forest model, which combines multiple decision trees, achieved high performance with an accuracy of 98.54%, identifying key predictors such as chest pain type, maximum heart rate, and thalassemia. Compared to a single decision tree, the Random Forest model reduces overfitting, improves generalization, and increases predictive accuracy. Factors like cholesterol levels, resting blood pressure, and exercise-induced angina were also considered. By averaging results from multiple trees, the model offers reliable and stable predictions, highlighting its potential in clinical settings for early detection and personalized treatment strategies. This study aims to assist healthcare providers in better allocating resources, planning preventive measures, and tailoring treatment plans to individual patients.

Potential Identification of Root System Architecture Using GPR for Tree Translocation as a Sustainable Forestry Task: A Case Study of the Wild Service Tree

Sustainable economic development serves society but requires taking over space, often at the expense of areas occupied by single trees or even parts of forest areas. Techniques for transplanting adult trees used in various conflict situations at the interface of economy and nature work as a tool for sustainable management of urbanized and industrial areas, as well as, in certain circumstances, forest or naturally valuable areas. This study aimed to evaluate the effectiveness of ground-penetrating radar (GPR) in determining the horizontal and vertical extent of tree root systems before transplantation. Employing this non-invasive method to map root system architecture aids in the appropriate equipment selection and helps define the dimensions and depth of trenches to minimize root damage during excavation. This study specifically focused on the root systems of wild service trees (Sorbus torminalis (L.) Crantz) found in a limestone mine area, where some specimens were planned to be transplanted, as the species is protected under law in Poland. The root systems were scanned with a ground-penetrating radar equipped with a 750 MHz antenna. Then, the root balls were dug out, and the root parameters and other dendrometric parameters were measured. The GPR survey and manual root analyses provided rich comparative graphic material. The number of the main roots detected by the GPR was comparable to those inventoried after extracting the stump. The research was carried out in problematic soil, causing non-standard deformations of the root systems. Especially in such conditions, identifying unusually arranged roots using the GPR method is valuable because it helps in a detailed planning of the transplanting process, minimizing root breakage during the activities carried out, which increases the survival chances of the transplanted tree in a new location.

The Meaning and Measure of Concordance Factors in Phylogenomics.

As phylogenomic datasets have grown in size, researchers have developed new ways to measure biological variation and to assess statistical support for specific branches. Larger datasets have more sites and loci and therefore less sampling variance. While we can more accurately measure the mean signal in these datasets, lower sampling variance is often reflected in uniformly high measures of branch support-such as the bootstrap and posterior probability-limiting their utility. Larger datasets have also revealed substantial biological variation in the topologies found across individual loci, such that the single species tree inferred by most phylogenetic methods represents a limited summary of the data for many purposes. In contrast to measures of statistical support, the degree of underlying topological variation among loci should be approximately constant regardless of the size of the dataset. "Concordance factors" (CFs) and similar statistics have therefore become increasingly important tools in phylogenetics. In this review, we explain why CFs should be thought of as descriptors of topological variation rather than as measures of statistical support, and argue that they provide important information about the predictive power of the species tree not contained in measures of support. We review a growing suite of statistics for measuring concordance, compare them in a common framework that reveals their interrelationships, and demonstrate how to calculate them using an example from birds. We also discuss how measures of topological variation might change in the future as we move beyond estimating a single "tree of life" toward estimating the myriad evolutionary histories underlying genomic variation.

On-Tree Mango Fruit Count Using Live Video- Split Image Dataset to Predict Better Yield at Pre-Harvesting Stage

This study introduces a method for fruit counting in agricultural settings using video capture and the YOLOv7 object detection model. By splitting captured videos into frames and strategically selecting representative frames, the approach aims to accurately estimate fruit counts while minimizing the risk of double counting. YOLOv7, known for its efficiency and accuracy in object detection, is employed to analyze selected frames and detect fruits on trees. Demonstrated the method's effectiveness through its ability to provide farmers with precise yield estimations, optimize resource management, and facilitate early detection of orchard issues such as pest infestations or nutrient deficiencies. This technological integration reduces labor costs and supports sustainable agricultural practices by improving productivity and decision-making capabilities. The scalability of the approach makes it suitable for diverse orchard sizes and types, offering a promising tool for enhancing agricultural efficiency and profitability. The researcher compared YOLOv5n, YOLOv5s, YOLOv7, and YOLOv7-tiny with eight-sided imaging techniques around the tree. The experimental results of YOLOv7 with the eight-sided technique performed best and achieved a count accuracy of 97.7% on a single tree in just 17.112 ms of average inference time. On multiple trees, it is 95.48% in just 17 ms of average inference time, with the help of an eight- sided method on tree images.

ALS-Based, Automated, Single-Tree 3D Reconstruction and Parameter Extraction Modeling

The 3D reconstruction of point cloud trees and the acquisition of stand factors are key to supporting forestry regulation and urban planning. However, the two are usually independent modules in existing studies. In this work, we extended the AdTree method for 3D modeling of trees by adding a quantitative analysis capability to acquire stand factors. We used unmanned aircraft LiDAR (ALS) data as the raw data for this study. After denoising the data and segmenting the single trees, we obtained the single-tree samples needed for this study and produced our own single-tree sample dataset. The scanned tree point cloud was reconstructed in three dimensions in terms of geometry and topology, and important stand parameters in forestry were extracted. This improvement in the quantification of model parameters significantly improves the utility of the original point cloud tree reconstruction algorithm and increases its ability for quantitative analysis. The tree parameters obtained by this improved model were validated on 82 camphor pine trees sampled from the Northeast Forestry University forest. In a controlled experiment with the same field-measured parameters, the root mean square errors (RMSEs) and coefficients of determination (R2s) for diameters at breast height (DBHs) and crown widths (CWs) were 4.1 cm and 0.63, and 0.61 m and 0.74, and the RMSEs and coefficients of determination (R2s) for heights at tree height (THs) and crown base heights (CBHs) were 0.55 m and 0.85, and 1.02 m and 0.88, respectively. The overall effect of the canopy volume extracted based on the alpha shape is closest to the original point cloud and best estimated when alpha = 0.3.

Investigating the distribution of a unique crustacean microendemic to tree hollows.

Water-filled tree hollows constitute phytotelmata that harbor specialized organisms. One striking example of extreme adaptation to these microhabitats is the case of the microcrustacean Micromoina arboricola, which has been found inhabiting the hollow of a single tree individual in the Atlantic Forest. We investigated the spatial distribution and influence of microhabitat characteristics such as hollow volume and height from the ground in the occurrence of M. arboricola. We surveyed all the trunks present in ca. 5000 m2 of an Atlantic old-growth forest area. We found M. arboricola individuals in 75% of the hollows, thus expanding the known distribution of the species. Spatial analysis suggested a clustered pattern of population densities across hollows, indicating that the dispersal capacity to new microhabitat patches may vary in space. Although we did not find an effect of hollow volume, population density was negatively related to hollow height. This suggests that more restrictive abiotic conditions at greater heights limit the occurrence of the species, emphasizing its vulnerability to environmental changes. Hollow-mediated ecosystem engineering depends on the occasional formation of cavities that require time and ancient trees. Preserving old forests with hollows under varying conditions tends to maintain ecosystem functionality and the conservation of this unique microendemic species.

A novel method for estimating avian roost sizes using passive acoustic recordings using deep neural network

Abstract Communal bird roosts serve as information centres and a means of thermoregulation for many species. While some communally roosting species are major pests and cause dis‐amenities, others are of conservation concern. Estimating the population of roosting birds can provide a useful proxy of population size and possibly a more reliable estimate than other sampling techniques. However, estimating these populations is challenging as some roosts are large and often occluded in foliage. Previous acoustic methods such as paired sampling, microphone arrays and use of call rate have been used to estimate bird abundances; however, these are less suited for estimating large roost populations where hundreds of individuals are calling in unison. To address this challenge, we explored using machine learning techniques to estimate a roost population of the Javan myna, Acridotheres javanicus, an invasive species in Singapore. While one may expect to use sound intensity to estimate roost sizes, it is affected by various factors such as distance to the recorder, local propagation conditions (e.g. buildings and trees), weather conditions, and noise from other sources. Here, we used a deep neural network to extract higher order statistics from the sound recordings and use those to help estimate roost sizes. Additionally, we validated our method using automated visual analysis with a dual‐camera setup and manual bird counts. Our estimated bird counts over time using our acoustic model matched the automated visual estimates and manual bird counts at a selected Javan myna roost, thus validating our approach. Our acoustic model estimated close to 400 individual mynas roosting in a single tree. Analyses of additional recordings of Javan myna roosts conducted on two separate occasions and at a different roost location using our acoustic model showed that our roost estimates over time also matched our automated visual estimates well. Practical implication: Our novel approach of estimating communal roost sizes can be achieved robustly using a simple portable acoustic recording system. Our method has multiple applications such as testing the efficacy of avian roost population control measures (e.g. roost tree pruning) and monitoring the populations of threatened bird species that roost communally.

Cultural Transmission in Printed Games of Cupid: Tracing Lines of Descent

Abstract The Game of Cupid is a simple dice-based race game derived from the Game of the Goose in about 1600. Twelve different examples, covering the period to about 1850 and drawn from France, the Low Countries and Britain, are analysed according to distinctive markers that include rules, game board configuration and decorative elements, showing that the evolution of the game can be described by a single tree of descent. The forces governing this evolution are discussed. The results may be of interest to those investigating whether different aspects of a complex cultural trait – such as a board game that has rules, a board and decorative elements – follow separate cultural transmission processes.

Plant Species Classification and Biodiversity Estimation from UAV Images with Deep Learning

Biodiversity is a characteristic of ecosystems that plays a crucial role in the study of their evolution, and to estimate it, the species of all plants need to be determined. In this study, we used Unmanned Aerial Vehicles to gather RGB images of mid-to-high-altitude ecosystems in the Zao mountains (Japan). All the data-collection missions took place in autumn so the plants present distinctive seasonal coloration. Patches from single trees and bushes were manually extracted from the collected orthomosaics. Subsequently, Deep Learning image-classification networks were used to automatically determine the species of each tree or bush and estimate biodiversity. Both Convolutional Neural Networks (CNNs) and Transformer-based models were considered (ResNet, RegNet, ConvNeXt, and SwinTransformer). To measure and estimate biodiversity, we relied on the Gini–Simpson Index, the Shannon–Wiener Index, and Species Richness. We present two separate scenarios for evaluating the readiness of the technology for practical use: the first scenario uses a subset of the data with five species and a testing set that has a very similar percentage of each species to those present in the training set. The models studied reach very high performances with over 99 Accuracy and 98 F1 Score (the harmonic mean of Precision and Recall) for image classification and biodiversity estimates under 1% error. The second scenario uses the full dataset with nine species and large variations in class balance between the training and testing datasets, which is often the case in practical use situations. The results in this case remained fairly high for Accuracy at 90.64% but dropped to 51.77% for F1 Score. The relatively low F1 Score value is partly due to a small number of misclassifications having a disproportionate impact in the final measure, but still, the large difference between the Accuracy and F1 Score highlights the complexity of finely evaluating the classification results of Deep Learning Networks. Even in this very challenging scenario, the biodiversity estimation remained with relatively small (6–14%) errors for the most detailed indices, showcasing the readiness of the technology for practical use.

A telomere-to-telomere Eucalyptus regnans genome: unveiling haplotype variance in structure and genes within one of the world’s tallest trees

BackgroundEucalyptus regnans (Mountain Ash) is an Australian native giant tree species which form forests that are among the highest known carbon-dense biomasses in the world. To enhance genomic studies in this ecologically important species, we assembled a high-quality, mostly telomere-to-telomere complete, chromosome-level, haplotype-resolved reference genome. We sampled a single tree, the Centurion, which is currently a contender for the world’s tallest flowering plant.ResultsUsing long-read sequencing data (PacBio HiFi, Oxford Nanopore ultra-long reads) and chromosome conformation capture data (Hi-C), we assembled the most contiguous and complete Eucalyptus reference genome to date. For each haplotype, we observed contig N50s exceeding 36 Mbp, scaffold N50s exceeding 43 Mbp, and genome BUSCO completeness exceeding 99%. The assembled genome revealed extensive structural variations between the two haplotypes, consisting mostly of insertions, deletions, duplications and translocations. Analysis of gene content revealed haplotype-specific genes, which were enriched in functional categories related to transcription, energy production and conservation. Additionally, many genes reside within structurally rearranged regions, particularly duplications, suggesting that haplotype-specific variation may contribute to environmental adaptation in the species.ConclusionsOur study provides a foundation for future research into E. regnans environmental adaptation, and the high-quality genome will be a powerful resource for conservation of carbon-dense giant tree forests.

Four new Geosmithia species from bark beetles infesting indigenous South African trees

Over the past two decades, numerous Geosmithia fungi have been isolated from the bodies and galleries of wood–boring beetles. However, this genus of asexual Sordariomycetes remains taxonomically and ecologically understudied, especially in the Southern Hemisphere. In South Africa, two prior surveys reported Geosmithia species from bark beetles, but neither thoroughly investigated species identities. In this study, we collected bark beetles from native trees in the Western Cape Province of South Africa and isolated, identified and described their associated Geosmithia species. Geosmithia spp. previously collected in South Africa were also re-examined. The ITS sequences of Geosmithia isolates from 13 beetle taxa infesting 10 host species were considered. Additional gene regions, BT, EF1a and RPB2, were sequenced for a subset of isolates. Four previously described species, G. flava, G. langdonii, G. omnicola and G. pumila were identified by phylogenetic analyses. Additionally, four novel taxa were identified and are here described as G. capensis, G. multisociorum, G. oroboidis and G. stellenboschiana. Geosmithia multisociorum appears to be a generalist associated with multiple beetle–host combinations in the Northern and Southern Hemisphere, whereas G. oroboidis is currently known only from a single beetle and tree host in South Africa. South African isolates of G. capensis and G. stellenboschiana appeared to be restricted to Lanurgus spp. and Hypothenemus sp. beetles, respectively, but both species are also known from beetles and hosts in other countries.

Distribution and Density of Common Woodpigeon (Columba palumbus) in Central Northern Bulgaria

The breeding density of the Woodpigeon was determined in square LH75 in the period from March to May 2023. For this purpose, a point counting method was used, and in addition, some characteristics of the habitats were taken into account. The breeding density of Woodpigeon in the present study was 16.42, 12.75 and 14.44 pairs/100ha, in March, April and May 2023 year, respectively. Breeding density decreases from March to May. Anova analysis showed statistically significant differences in the mean number of song pigeons by habitat and cropland types (F=8.11, p=0.005). The number of song Woodpigeons was significantly greater in open habitats with single large trees or small groups of large trees among grassland and meadows than in other breeding habitat types. Their number is relatively high in Silver lime forests, coniferous plantations, and in the fringe strip of all forest habitats. The number of song pigeons is also relatively high in cases where we have a lack of arable land in the fixed radius or in the presence of wheat. Their number in the fixed radius increased with increasing average tree height. The number of singing pigeons is positively correlated with tree height (R=0.49, F=2.132, p<0.0001). The latest data on the breeding density of the Woodpigeon are from the end of the last century in Bulgaria. This study presents first results on the breeding distribution and density of the species in an information-poor area.

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.

UAV or satellites? How to find the balance between efficiency and accuracy in above ground biomass estimation of artificial young coniferous forest?

The accurate estimation of Above Ground Biomass (AGB) is the basis for plantation forest carbon trading. This study focused on Picea crassifolia artificial plantations, extracting individual tree crown diameters and heights using Unmanned Aerial Vehicles (UAV) data and calculating the individual tree biomass using allometric growth equations. These results were then used to train a satellite image AGB prediction model. In additional, satellite images were resampled to different resolutions to assess the impact of satellite image resolution on model the accuracy. Finally, the model with the highest accuracy among the deep learning algorithms was selected to predicts the AGB within the P. crassifolia plantation forest. The results indicated that the accuracy of single tree crown diameters extracted from P. crassifolia point clouds significantly surpassed those extracted from general point clouds and Crown Height Model (CHM), while the accuracy of the heights extracted from all three sources was similar; RepLKNet outperformed GoogLeNet and ResNet in identifying plantation forest; random forest slightly outperformed XGBoost in the capability of AGB prediction, while the accuracy of the AGB prediction models initially increasd and then decreasd with satellite image resolution, reaching the highest accuracy at a resolution of 50 m. This indicates that the optimal satellite image resolution for estimating the AGB in the study area was affected by scale effects of 50 m. Compared with the combination of satellite data and manual field measurements, the concurrent use of UAVs and satellites offers significant advantages in terms of efficiency and accuracy. UAVs can replace manual sampling for carbon sequestration transactions for plantations.

Modelling and Analysing Routing Protocols Diagrammatically with Bigraphs

As more end-user applications depend on Internet of Things (IoT) technology, it is essential the networking protocols underpinning these applications are reliable. Using Formal Methods to reason about protocol specifications is an established technique, but, due to their perceived difficulty and mathematical nature, receive limited use in practice. We propose an approach based on Milner’s bigraphs—a flexible diagrammatic modelling language—that allows developers to “draw” the protocol updates as a way to increase use of formal methods in protocol design. To show bigraphs in action, we model part of the Routing Protocol for low-power and Lossy Networks (RPL), popular in wireless sensor networks, and verify it using model checking. We compare our approach with the more common simulation approach and show that analysing the bigraph model often finds more valid routes than simulation (which usually returns only a single routing tree even with 500 simulations) and that it has comparable performance. The model is open to extension, with less implementation effort than simulation, and we show this through two examples: a security attack and physical link drops. Bigraphs seem a promising approach to protocol design, and this is the first step in promoting their use.

Ecophysiology of Mediterranean Chestnut (Castanea sativa Mill.) Forests: Effects of Pruning Studied through an Advanced IoT System

Chestnut (Castanea sativa Mill.) forests in the Mediterranean region are facing increasing abandonment due to a combination of factors, ranging from climate change to socioeconomic issues. The recovery of chestnut ecosystems and their preservation and valorization are key to ensuring the supply of the wide spectrum of ecosystem services they provide and to preventing detrimental environmental shifts. The study’s objective was to provide evidence on the effects of different management options on the ecophysiology of chestnut forests, with diverse pruning intensities (low, medium, and high intensity versus no pruning) tested in an abandoned chestnut stand in central Italy with the aim of recovering and rehabilitating it for fruit production. Innovative Internet of Things (IoT) ‘Tree Talker’ devices were installed on single trees to continuously monitor and measure ecophysiological (i.e., water transport, net primary productivity, foliage development) and microclimatic parameters. Results show a reduction in water use in trees subjected to medium- and high-intensity pruning treatments, along with a decrease in the carbon sequestration function. However, interestingly, the results highlight that trees regain their usual sap flow and carbon sink activity at the end of the first post-pruning growing season and fully realign during the following year, as also confirmed by the NDVI values. As such, this paper demonstrates the efficacy of recovering and managing abandoned chestnut forests, and the initial setback in carbon sequestration resulting from pruning is rapidly remedied with the advantage of reviving trees for fruit production. Additionally, the reduced water demand induced by pruning could represent a promising adaptation strategy to climate change, bolstering the resilience of chestnut trees to prolonged and intensified drought periods, which are projected to increase under future climate scenarios, particularly in the Mediterranean region.