Treemap Research Articles

Recreating structurally realistic tree maps with airborne laser scanning and ground measurements

The estimation of forest attributes representing aspects of structural biodiversity from vast areas is difficult not only because of the lack of agreement on what constitutes a structurally diverse forest, but also due to difficulties in the detection of small trees. However, a structurally diverse forest should have large variation in tree size (i.e., height and diameter), as well as some clustering of trees, as regular tree pattern is typical for managed forests. In this work we developed a framework for building structurally representative tree maps using airborne laser scanning data and a limited number of ground measurements using data from two locations in Finland. In the proposed method, an individual tree detection algorithm is optimized so that the number of undetected trees and false detections is minimized. The ground measurements are then used to train models for predicting the number and location of undetected trees and false detections by resampling the attributes of undetected trees in the training data. This model can then be applied to other areas in the proximity of the ground measurements to build tree maps, with the location, height, and diameter for each tree. The methodology was shown to reproduce the number of trees, the height distribution, and the spatial pattern of the trees with sufficient accuracy for practical use in large-scale mapping of forest attributes. For example, the individual tree detection could find at best about 54% of the trees with an additional 7% of false detections, resulting in a bias of approximately −30%, while with the new method the bias was reduced to ±10% of the stem density. Further research is needed on how to account for tree species when building tree maps.

Visual displays for communicating scientific uncertainty in influenza forecasts

We offer a general method for testing the usability of visual displays communicating scientific uncertainty, illustrated with publicly available results from CDC's influenza forecasts. The heavy toll of seasonal influenza has prompted major investments in improving these forecasts, making them a focus of machine learning research. However, little research has been devoted to how well users can understand and use these forecasts to inform decisions under uncertainty. Our approach extends psychological theory to experimental tasks posing hypothetical, but realistic decisions using alternative displays based on actual forecasts. Based on Tversky's theory of conceptual-spatial congruence, we predicted actual and perceived usability of four displays (bar chart, tree map, PDF, and 90% confidence interval). Participants (N = 301, recruited on Amazon MTurk) were randomly assigned to use one of four displays for four decision tasks, created to reflect our extension of the theory. We evaluated participants' comprehension, confidence, and judgments of perceived helpfulness, when the display and the decision were congruent or non-congruent. Participants had better comprehension with the most familiar display (bar chart), for all four decisions. However, they did not perceive that display as more helpful or have greater confidence in their responses to it. Participants who reported greater familiarity with a display performed more poorly, despite expressing greater confidence and rating it as more helpful. We discuss the need to evaluate performance, as well as ratings, and the opportunities to extend theoretical frameworks to specific contexts.

A heuristic tomato-bunch harvest manipulator path planning method based on a 3D-CNN-based position posture map and rapidly-exploring random tree

The environment of tomato bunches is complex, and the fruit volume is relatively large, so manipulator picking-harvest motion planning should consider not only how to pick, but also how to avoid obstacles after picking tomato bunches and harvesting them from the complex environment, which puts forward strict requirements for picking-harvest motion performance. However, existing sampling-based algorithms still have problems of blind expansion and low efficiency. To solve these problems, a heuristic tomato-bunch harvest manipulator path planning method based on a 3D-CNN (convolution neural network)-based position posture map (PPM) and rapidly-exploring random tree (RRT) is proposed in this paper. This method comprehensively considers the sampling effectiveness of the whole process of picking and harvesting, search speed, path cost and manipulability of the manipulator, combining a sampling-based path planning algorithm and deep learning framework. The method utilizes CNN and FCN(Fully Connected Neural Networks) for generating a heuristic cost map where each voxel has a cost-to-go value toward the target and an optimal target posture value to guide the expansion tree. In addition, the sampling space of obstacle avoidance planning is reduced by a spatial partition method, and the difficulty caused by the increase in the volume of the end-effector clamping fruit is solved by prioritizing the planning of the fruit harvest path and then planning the picking path. On the basis of the above research, a large number of harvest experiments have verified the effectiveness of the proposed algorithm. Research and experimental results show that, based on the PPM-RRT algorithm, the picking-harvest time of a single tomato bunch is 13 s, and the success rate is close to 100%. Compared with state-of-the-art sampling algorithms, the planning time is reduced by more than 70%, the path length is reduced by more than 24%, and the manipulability of the manipulator is increased by 38.9%. The proposed path planning method is effective in complex environments.

Consumer-grade UAV imagery facilitates semantic segmentation of species-rich savanna tree layers

Conventional forest inventories are labour-intensive. This limits the spatial extent and temporal frequency at which woody vegetation is usually monitored. Remote sensing provides cost-effective solutions that enable extensive spatial coverage and high sampling frequency. Recent studies indicate that convolutional neural networks (CNNs) can classify woody forests, plantations, and urban vegetation at the species level using consumer-grade unmanned aerial vehicle (UAV) imagery. However, whether such an approach is feasible in species-rich savanna ecosystems remains unclear. Here, we tested whether small data sets of high-resolution RGB orthomosaics suffice to train U-Net, FC-DenseNet, and DeepLabv3 + in semantic segmentation of savanna tree species. We trained these models on an 18-ha training area and explored whether models could be transferred across space and time. These models could recognise trees in adjacent (mean F1-Score = 0.68) and distant areas (mean F1-Score = 0.61) alike. Over time, a change in plant morphology resulted in a decrease of model accuracy. Our results show that CNN-based tree mapping using consumer-grade UAV imagery is possible in savanna ecosystems. Still, larger and more heterogeneous data sets can further improve model robustness to capture variation in plant morphology across time and space.

Comparing the Effects of Graphic Organisers and Conventional Method on Students’ Writing Skills

Graphic Organisers help students make valuable connections by cataloguing and patterning ideas in writing. This study aims to investigate whether there is any difference in the overall mean writing scores between two groups: the Experimental Group (using Graphic Organisers) and the Control Group (using the Conventional Method) in the post-test. This study employs a quasi-experimental design, with quantitative data used for data analysis. Bubble maps and tree maps were the Graphic Organisers used by the Experimental Group in learning ESL writing skills. The study consisted of 120 Form Four students (16 years old) from two schools in the District of Hulu Langat, Selangor. The sample consisted of 60 students in each group (Experimental Group and Control Group). The experiment lasted for eight weeks. A pre-test was conducted prior to the intervention, and the post-test was carried out at the end of the experiment. The instruments (pre-test and post-test) consisted of three types of writing tasks: email writing, directed writing, and extended writing. ANCOVA was used to analyse the data obtained from the pre-test and post-test. The results showed that the Experimental Group significantly outperformed the Control Group in their overall writing performance, particularly in the areas of content, communicative achievement, organization, and language. The Control Group had difficulty in their overall and the four areas of writing because the Conventional Method did not help them improve their performance. This study has pivotal pedagogical implications as it demonstrates that Graphic Organisers (Bubble maps and Tree maps) facilitate students in their ESL writing.

The Effects of Bubble Map and Tree Map Method in CEFR Reading Comprehension

The effective method of teaching CEFR reading comprehension makes students to have better exposure and gain confidence in Malaysian secondary schools. The ultimate goal of this study is to investigate whether the use of Bubble Map and Tree Map methods enhances students’ learning of Multiple-Choice Questions (MCQ) in the CEFR reading comprehension. This quantitative study employed a quasi-experimental design. The sample of this study consisted of 105 Form One students (13 years old) from three different schools (school A, B and C) from Petaling Jaya, Selangor. The sample were chosen as intact groups. The Experimental Group 1 (EG1) from school A was taught using Bubble Map, Experimental Group 2 (EG2) from school B was taught using Tree Map and the Control Group (CG) from school C was taught using conventional method. The pre-test and post-test were used as instruments to collect the data for this study. The quantitative data was analyzed using SPSS program for Windows version 26. The MANCOVA test and Tukey HSD were used to analyze the data. The findings demonstrated that EG1 (using Bubble Map) significantly outperformed EG2 and CG in their CEFR reading comprehension. The results also indicated that EG2 (using Tree Map) performed significantly better than CG (using conventional method). This study has essential pedagogical implication because the Bubble Map and Tree Map methods had positive effects in enhancing students’ CEFR reading comprehension. As such, teachers can use Bubble Map and Tree Map methods as an alternative method to teach CEFR reading comprehension in the ESL classroom.

Exploring active LiDAR and very high spatial resolution optical data in tree mapping

Exploring active LiDAR and very high spatial resolution optical data in tree mapping

Mapping tree cover expansion in Montana, U.S.A. rangelands using high‐resolution historical aerial imagery

AbstractWorldwide, trees are colonizing rangelands with high conservation value. The introduction of trees into grasslands and shrublands causes large‐scale changes in ecosystem structure and function, which have cascading impacts on ecosystem services, biodiversity, and agricultural economies. Satellites are increasingly being used to track tree cover at continental to global scales, but these methods can only provide reliable estimates of change over recent decades. Given the slow pace of tree cover expansion, remote sensing techniques that can extend this historical record provide critical insights into the magnitude of environmental change. Here, we estimate conifer expansion in rangelands of the northern Great Plains, United States, North America, using historical aerial imagery from the mid‐20th century and modern aerial imagery. We analyzed 19.3 million hectares of rangelands in Montana, USA, using a convolutional neural network (U‐Net architecture) and cloud computing to detect tree features and tree cover change. Our bias‐corrected results estimate 3.0 ± 0.2 million hectares of conifer tree cover expansion in Montana rangelands, which accounts for 15.4% of the total study area. Overall accuracy was >91%, but the producer's accuracy was lower than the user's accuracy (0.60 vs. 0.88) for areas of tree cover expansion. Nonetheless, the omission errors were not spatially clustered, suggesting that the method is reliable for identifying the regions of Montana where substantial tree expansion has occurred. Using the model results in conjunction with historical and modern imagery allows for effective communication of the scale of tree expansion while overcoming the recency effect caused by shifting environmental baselines.

Mapping tree species diversity of temperate forests using multi-temporal Sentinel-1 and -2 imagery

Accurate information on tree species diversity is critical for forest biodiversity, conservation and management, but mapping forest diversity over large and mixed forest areas using satellite remote sensing data remains a challenge because of scale- and ecosystem-dependent relationships between spectral heterogeneity and tree species diversity. In this study, three different diversity indices (Simpson (λ), Shannon (H’), and Pielou (J’)), were tested to characterize forest tree species diversity using individual monthly and multi-temporal Sentinel-1 and -2 images during 2021. The performance of three different machine learning models, Random Forest (RF), Extreme Gradient Boosting (XGB), and Deep Neural Network (DNN) were tested. A collection of 1,020 plot measurements (comprising 47 tree species and 28,122 trees), randomly collected in a mixed broadleaf-conifer forest area in northeast China, was used to train (n = 816) and validate (n = 204) the models. The models dependent on multi-temporal Sentinel-1/2 imagery were found to outperform the models based on individual monthly data, in predicting forest tree species diversity, with average accuracies of 78% for H’, 77% for λ and 77% for J’. The use of DNN performed marginally better than the XGB and RF models, with accuracies of 81% for H’, 80% for λ and 79% for J’, respectively. Finally, a boosted regression model, involving environmental variable predictors and the DNN-based estimated tree species diversity, showed that on average 63 ± 4% of the spatial variations of tree species diversity was explained by environmental variables, including annual temperature (29.30%), followed by soil fertility (27.03%), snow cover (13.63%) and a digital elevation model (12.33%). Our results highlight that an empirical approach based on machine learning and multi-temporal Sentinel-1/2 data can accurately predict forest tree species diversity and we further show the important roles of air temperature and soil fertility in governing the spatial variability of tree species diversity in a mixed broadleaf-conifer forest setting.

Spectral number of 3-Bernoulli convolutions on and Sierpinski-type measures on

Let be a class of Sierpinski-type measures generated by a pair , where with and and . And let µ b be the 3-Bernoulli convolutions on determined by the pair with . It has been shown that and µ b admit an infinitely many exponential mutually orthogonal system if and only if with , and with respectively. In this paper, we will study the maximal number of exponentials of orthogonal sets of and which we call the spectral number of or µ b . In view of the connection of orthogonality between Sierpinski-type measures on and 3-Bernoulli convolutions µ b on , we study the spectral number of µ b according to the cut-off point . Based on the results for µ b , we give a classification on the spectral number of all Sierpinski-type measures except for the case that at least one and it is not in the form of with . In addition, we provide a structure theorem on the exponential orthogonal sets in for , and at least one and that in for and . To the end, we give an explicit representation on the maximal orthogonal set of exponentials for a class of Moran measures µ w by defining a mixed tree map over a symbol space. As an application, all maximal orthogonal sets of exponentials of with the rational can be explicitly expressed. This result improves the characterization of maximal orthogonal set of exponentials for the integral matrix to that for the rational matrix .

Detection of invasive plants using NAIP imagery and airborne LiDAR in coastal Alabama and Mississippi, USA

Invasive plants have imposed severe threats to native ecosystems worldwide. Triadica sebifera (Tallow tree) and Ligustrum sinense (Chinese privet) are among the most prolific invasive species in the southern United States (US) that needs urgent assessment to protect coastal ecosystems. The lack of spatially explicit assessments of these invasives, coupled with the increasing availability of high-resolution remotely sensed data, represents an opportunity to produce a distribution map for subsequent monitoring. The overall goal of this study was to develop spatially comprehensive maps of Tallow tree and Chinese privet in ecologically sensitive coastal regions, where both invasives have become well established. The study was conducted in three coastal sites within Alabama and Mississippi: (1) Mobile Tensaw River Delta, (2) Bon Secour National Wildlife Refuge, and (3) Mississippi Sandhill Crane National Wildlife Refuge. We implemented three image classification methods, representing unsupervised, supervised, and machine learning techniques, respectively: (1) ISODATA, (2) Maximum Likelihood (ML), and (3) Random Forest (RF). For each classification, a 1 m National Agriculture Imagery Program (NAIP) orthoimage was first examined, then integrated with vegetation structure and topography parameter derived from airborne light detection and ranging (LiDAR). The maximum Overall Accuracy (OA) of 87.5% was obtained using RF model with NAIP stacked image integrated with LiDAR derived variables. Overall, findings highlight the potential for accurately characterizing both Tallow tree and Chinese privet using readily available remote sensing data. Mapped products from this study represent a spatially comprehensive baseline inventory of crucial invasive species and will serve to inform the development of a framework for broader-scale mapping and monitoring efforts.

Molecular epidemiological characteristics of SARS-CoV-2 in imported cases from 2021 to 2022 in Zhejiang Province, China.

The coronavirus disease 2019 (COVID-19) pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has been a global threat since 2020. The emergence of the Omicron variant in 2021, which replaced Delta as the dominant variant of concern, has had a significant adverse impact on the global economy and public health. During this period, Zhejiang Province implemented dynamic zeroing and focused on preventing imported cases. This study aimed to gain clear insight into the characteristics of imported COVID-19 cases in Zhejiang Province. We conducted a systematic molecular epidemiological analysis of 146 imported cases between July 2021 and November 2022 in Zhejiang Province. Virus samples with cycle threshold (Ct) value less than 32 were performed next generation sequencing. Basing the whole genome sequence obtained after quality control and assembly of reads, the whole genome variation map and phylogenetic tree were constructed and further analyzed. Our study identified critical months and populations for surveillance, profiled the variation of various lineages, determined the evolutionary relationships among various lineages of SARS-CoV-2, and compared the results in Zhejiang with those obtained worldwide during this period. The continuous molecular epidemiological surveillance of imported cases of COVID-19 in Zhejiang Province during 2021 to 2022 is consistent with the global epidemic trend.

Injective Split Systems

A split system mathcal S on a finite set X, |X|ge 3, is a set of bipartitions or splits of X which contains all splits of the form {x,X-{x}}, x in X. To any such split system mathcal S we can associate the Buneman graph mathcal B(mathcal S) which is essentially a median graph with leaf-set X that displays the splits in mathcal S. In this paper, we consider properties of injective split systems, that is, split systems mathcal S with the property that {{,textrm{med},}}_{mathcal B(mathcal S)}(Y) ne {{,textrm{med},}}_{mathcal B(mathcal S)}(Y') for any 3-subsets Y,Y' in X, where {{,textrm{med},}}_{mathcal B(mathcal S)}(Y) denotes the median in mathcal B(mathcal S) of the three elements in Y considered as leaves in mathcal B(mathcal S). In particular, we show that for any set X there always exists an injective split system on X, and we also give a characterization for when a split system is injective. We also consider how complex the Buneman graph mathcal B(mathcal S) needs to become in order for a split system mathcal S on X to be injective. We do this by introducing a quantity for |X| which we call the injective dimension for |X|, as well as two related quantities, called the injective 2-split and the rooted-injective dimension. We derive some upper and lower bounds for all three of these dimensions and also prove that some of these bounds are tight. An underlying motivation for studying injective split systems is that they can be used to obtain a natural generalization of symbolic tree maps. An important consequence of our results is that any three-way symbolic map on X can be represented using Buneman graphs.

특허분석을 통한 라틴아메리카지역의 유망 공백물류기술 도출

In recent years, the lack of relevant technological infrastructure for innovation in logistics technology in Latin American nations with significant economic expansion has been a factor impeding economic growth. In this case, even though Latin American nations are actively pursuing policies to revive technical innovation, there is an issue with the absence of objective data for policy formation. We suggests a strategy for revitalizing technical innovation through the utilization of promising vacant technologies predicted by patent data analysis. Using GTM, ARIMA, technology mapping, and decision tree analysis, promising vacant technology groups and technological keywords were identified from 670 logistics-related patents extracted between 2010 and 2020. As a result of the investigation, “Multimodal Transportation” and “Simulation-Based Distribution Optimization” derived based on important technology keywords, is perceived as a required technology to revitalize technological innovation in Latin American nations with large territories. The research results can be used as objective data for policymaking to stimulate technical innovation, contributing to more objective policymaking in Latin American countries.

Robust Scan Registration for Navigation in Forest Environment Using Low-Resolution LiDAR Sensors.

Automated forest machines are becoming important due to human operators' complex and dangerous working conditions, leading to a labor shortage. This study proposes a new method for robust SLAM and tree mapping using low-resolution LiDAR sensors in forestry conditions. Our method relies on tree detection to perform scan registration and pose correction using only low-resolution LiDAR sensors (16Ch, 32Ch) or narrow field of view Solid State LiDARs without additional sensory modalities like GPS or IMU. We evaluate our approach on three datasets, including two private and one public dataset, and demonstrate improved navigation accuracy, scan registration, tree localization, and tree diameter estimation compared to current approaches in forestry machine automation. Our results show that the proposed method yields robust scan registration using detected trees, outperforming generalized feature-based registration algorithms like Fast Point Feature Histogram, with an above 3 m reduction in RMSE for the 16Chanel LiDAR sensor. For Solid-State LiDAR the algorithm achieves a similar RMSE of 3.7 m. Additionally, our adaptive pre-processing and heuristic approach to tree detection increased the number of detected trees by 13% compared to the current approach of using fixed radius search parameters for pre-processing. Our automated tree trunk diameter estimation method yields a mean absolute error of 4.3 cm (RSME = 6.5 cm) for the local map and complete trajectory maps.

The Chemical Space of Marine Antibacterials: Diphenyl Ethers, Benzophenones, Xanthones, and Anthraquinones.

The emergence of multiresistant bacteria and the shortage of antibacterials in the drug pipeline creates the need to search for novel agents. Evolution drives the optimization of the structure of marine natural products to act as antibacterial agents. Polyketides are a vast and structurally diverse family of compounds that have been isolated from different marine microorganisms. Within the different polyketides, benzophenones, diphenyl ethers, anthraquinones, and xanthones have shown promising antibacterial activity. In this work, a dataset of 246 marine polyketides has been identified. In order to characterize the chemical space occupied by these marine polyketides, molecular descriptors and fingerprints were calculated. Molecular descriptors were analyzed according to the scaffold, and principal component analysis was performed to identify the relationships among the different descriptors. Generally, the identified marine polyketides are unsaturated, water-insoluble compounds. Among the different polyketides, diphenyl ethers tend to be more lipophilic and non-polar than the remaining classes. Molecular fingerprints were used to group the polyketides according to their molecular similarity into clusters. A total of 76 clusters were obtained, with a loose threshold for the Butina clustering algorithm, highlighting the large structural diversity of the marine polyketides. The large structural diversity was also evidenced by the visualization trees map assembled using the tree map (TMAP) unsupervised machine-learning method. The available antibacterial activity data were examined in terms of bacterial strains, and the activity data were used to rank the compounds according to their antibacterial potential. This potential ranking was used to identify the most promising compounds (four compounds) which can inspire the development of new structural analogs with better potency and absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties.

Spatial predictions of tree density and tree height across Mexico forests using ensemble learning and forest inventory data.

The National Forestry Commission of Mexico continuously monitors forest structure within the country's continental territory by the implementation of the National Forest and Soils Inventory (INFyS). Due to the challenges involved in collecting data exclusively from field surveys, there are spatial information gaps for important forest attributes. This can produce bias or increase uncertainty when generating estimates required to support forest management decisions. Our objective is to predict the spatial distribution of tree height and tree density in all Mexican forests. We performed wall-to-wall spatial predictions of both attributes in 1-km grids, using ensemble machine learning across each forest type in Mexico. Predictor variables include remote sensing imagery and other geospatial data (e.g., mean precipitation, surface temperature, canopy cover). Training data is from the 2009 to 2014 cycle (n > 26,000 sampling plots). Spatial cross validation suggested that the model had a better performance when predicting tree height r 2 = .35 [.12, .51] (mean [min, max]) than for tree density r 2 = .23 [.05, .42]. The best predictive performance when mapping tree height was for broadleaf and coniferous-broadleaf forests (model explained ~50% of variance). The best predictive performance when mapping tree density was for tropical forest (model explained ~40% of variance). Although most forests had relatively low uncertainty for tree height predictions, e.g., values <60%, arid and semiarid ecosystems had high uncertainty, e.g., values >80%. Uncertainty values for tree density predictions were >80% in most forests. The applied open science approach we present is easily replicable and scalable, thus it is helpful to assist in the decision-making and future of the National Forest and Soils Inventory. This work highlights the need for analytical tools that help us exploit the full potential of the Mexican forest inventory datasets.

Research on reliability of centrifugal compressor unit based on dynamic Bayesian network of fault tree mapping

Research on reliability of centrifugal compressor unit based on dynamic Bayesian network of fault tree mapping

Seeing Trees from Drones: The Role of Leaf Phenology Transition in Mapping Species Distribution in Species-Rich Montane Forests

The complex topography of subtropical montane forests favors the coexistence of diverse plant species, making these species-rich forests a high priority for biodiversity monitoring, prediction, and conservation. Mapping tree species distribution accurately in these areas is an essential basis for biodiversity research and is often challenging due to their complex structure. Remote sensing has widely been used for mapping tree species, but relatively little attention has been paid to species-rich montane forests. In this study, the capability of high-resolution UAV remote sensing imagery for mapping six tree species, standing dead trees, and canopy gaps was tested in a subtropical montane forest at an elevation of 816~1165 m in eastern China. Spectral, spatial geometrical, and textural features in a specific phenological period when obvious color differences among the leaves of different species were extracted, and four object-based classification algorithms (K-nearest neighbor (KNN), classification and regression tree (CART), support vector machine (SVM), and random forest (RF)) were used for tree species classification. We found that: (1) mapping tree species distribution using low-cost UAV RGB imagery in a specific leaf phenological period has great application potential in subtropical montane forests with complex terrain. (2) Plant spectral features in the leaf senescence period contributed significantly to species classification, while the contribution of textural features was limited. The highest classification accuracy was 83% using KNN with the combination of spectral and spatial geometrical features. (3) Topographical complexity had a significant impact on mapping species distribution. The classification accuracy was generally higher in steep areas, especially in the low slope area.

Mapping tree species diversity in temperate montane forests using Sentinel-1 and Sentinel-2 imagery and topography data

Detailed information on spatial patterns of tree species diversity (TSD) is essential for biodiversity assessment, forest disturbance monitoring, and the management and conservation of forest resources. TSD mapping approaches based on the Spectral Variability Hypothesis (SVH) could provide a reliable alternative to image classification methods. However, such methods have not been tested in large-scale TSD mapping using Sentinel-1 and Sentinel-2 images. In this study, we developed a new workflow for large-scale TSD mapping in an approximately 4000 km2 temperate montane forest using Sentinel-1 and Sentinel-2 imagery-based heterogeneity metrics and topographic data. Through a systematic comparison of model performance in 24 prediction scenarios with different combinations of input variables, and a correlation analysis between six image heterogeneity metrics and two in-situ TSD indicators (species richness S and Shannon-Wiener diversity H′), we assessed the effects of vegetation phenology, image heterogeneity metrics, and sensor type on the accuracy of TSD predictions. Our results show that (1) the combination of Sentinel-1 and Sentinel-2 imagery produced higher accuracy of TSD predictions compared to the Sentinel-2 data alone, and that the further inclusion of topographic data yielded the highest accuracy (S: R2 = 0.562, RMSE = 1.502; H′: R2 = 0.628, RMSE = 0.231); (2) both Multi-Temporal and Spectral-Temporal-Metric data capture phenology-related information of tree species and significantly improved the accuracy of TSD predictions; (3) texture metrics outperformed other image heterogeneity metrics (i.e., Coefficient of Variation, Rao's Q, Convex Hull Volume, Spectral Angle Mapper, and the Convex Hull Area), and the enhanced vegetation index (EVI) derived image heterogeneity metrics were most effective in predicting TSD; and (4) the spatial distribution of TSD showed a clear decrease trend along the altitudinal gradient (r = −0.61 for S and − 0.45 for H′) and varied significantly among forest types. Our results suggest a good potential of the SVH-based approaches combined with Sentinel-1 and Sentinel-2 imagery and topographic data for large-scale TSD mapping in temperate montane forests. The TSD maps generated in our study will be valuable for forest biodiversity assessments and for developing management and conservation measures.