Biology subjects

Marconi, S.

Publications and source records attributed to Marconi, S..

12 recordsLinked to original sources

bioRxiv2023

Individual tree crown maps for the National Ecological Observatory Network

The ecology of forest ecosystems depends on the composition of trees. Capturing fine-grained information on individual trees at broad scales provides a unique perspective on forest ecosystems, forest restoration and responses to disturbance. Individual tree data at wide extents promises to increase the scale of forest analysis, biogeographic research, and ecosystem monitoring without losing details on individual species composition and abundance. Computer vision using deep neural networks can convert raw sensor data into predictions of individual canopy tree species through labeled data collected by field researchers. Using over 40,000 individual tree stems as training data, we create landscape-level species predictions for over 100 million individual trees across 24 sites in the National Ecological Observatory Network. Using hierarchical multi-temporal models fine-tuned for each geographic area, we produce open-source data available as 1 km2 shapefiles with individual tree species prediction, as well as crown location, crown area and height of 81 canopy tree species. Site-specific models had an average performance of 79% accuracy covering an average of six species per site, ranging from 3 to 15 species per site. All predictions are openly archived and have been uploaded to Google Earth Engine to benefit the ecology community and overlay with other remote sensing assets. We outline the potential utility and limitations of these data in ecology and computer vision research, as well as strategies for improving predictions using targeted data sampling.

ecology↗

bioRxiv2022

Capturing long-tailed individual tree diversity using an airborne multi-temporal hierarchical model

Measuring forest biodiversity using terrestrial surveys is expensive and can only capture common species abundance in large heterogeneous landscapes. In contrast, combining airborne imagery with computer vision can generate individual tree data at the scales of hundreds of thousands of trees. To train computer vision models, ground-based species labels are combined with airborne reflectance data. Due to the difficulty of finding rare species in a large landscape, the majority of classification models only include the most abundant species, leading to biased predictions at broad scales. Extending classification models to include rare species requires targeted data collection and algorithmic improvements to overcome large data imbalances between dominant and rare taxa. In addition, large landscapes often require multiple acquisition events, leading to significant within-species variation in reflectance spectra. Using a multi-temporal hierarchical model, we demonstrate the ability to include species predicted at less than 1% frequency in landscape without losing performance on the dominant species. The final model has over 75% accuracy for 14 species with improved rare species classification compared to a baseline deep learning model. After filtering out dead trees, we generate landscape species maps of individual crowns for over 670,000 individual trees at the Ordway Swisher Biological Station within the National Ecological Observatory Network. We estimate the relative abundance of the species within the landscape and provide three measures of uncertainty to generate a range of counts for each species. These maps provide the first estimates of canopy tree diversity within NEON sites to include rare species and provide a blueprint for capturing tree diversity using airborne computer vision at broad scales.

ecology↗

bioRxiv2022

Quantitative Assessment of 3D Printed Blood Vessels Produced with J750™ Digital Anatomy™ for Suture Simulation

Blood vessels anastomosis is one of the most challenging and delicate tasks to learn in many surgical specialties, especially for vascular and abdominal surgeons. Such a critical skill implies a learning curve that goes beyond technical execution. The surgeon needs to gain proficiency in adapting gestures and the amount of force expressed according to the type of tissue he/she is dealing with. In this context, surgical simulation is gaining a pivotal role in the training of surgeons, but currently available simulators can provide only standard or simplified anatomies, without the chance of presenting specific pathological conditions and rare cases. 3D printing technology, allowing the manufacturing of extremely complex geometries, find a perfect application in the production of realistic replica of patient-specific anatomies. According to available technologies and materials, morphological aspects can be easily handled, while the reproduction of tissues mechanical properties still poses major problems, especially when dealing with soft tissues. The present work focuses on blood vessels, with the aim of identifying - by means of both qualitative and quantitative tests - materials combinations able to best mimic the behavior of the biological tissue during anastomoses, by means of J750 Digital Anatomy technology and commercial photopolymers from Stratasys. Puncture tests and stitch traction tests are used to quantify the performance of the various formulations. Surgical simulations involving anastomoses are performed on selected clinical cases by surgeons to validate the results. A total of 37 experimental materials were tested and 2 formulations were identified as the most promising solutions to be used for anastomoses simulation. Clinical applicative tests, specifically selected to challenge the new materials, raised additional issues on the performance of the materials to be considered for future developments.

bioengineering↗

bioRxiv2021

Continental-scale Hyperspectral tree species classification in the National Ecological Observatory Network

Advances in remote sensing imagery and machine learning applications unlock the potential for developing algorithms for species classification at the level of individual tree crowns at unprecedented scales. However, most approaches to date focus on site-specific applications and a small number of taxonomic groups. Little is known about how well these approaches generalize across broader geographic areas and ecosystems. Leveraging field surveys and hyperspectral remote sensing data from the National Ecological Observatory Network (NEON), we developed a continental-extent model for tree species classification that can be applied to the network, including a wide range of US terrestrial ecosystems. We compared the performance of a model trained with data from 27 NEON sites to models trained with data from each individual site, evaluating advantages and challenges posed by training species classifiers at the US scale. We evaluated the effect of geographic location, topography, and ecological conditions on the accuracy and precision of species predictions (72 out of 77 species). On average, the general model resulted in good overall classification accuracy (micro-F1 score), with better accuracy than site-specific classifiers (average individual tree level accuracy of 0.77 for the general model and 0.70 for site-specific models). Aggregating species to the genus-level increased accuracy to 0.83. Regions with more species exhibited lower classification accuracy. Predicted species were more likely to be confused with congeneric and co-occurring species and confusion was highest for trees with structural damage and in complex closed-canopy forests. The model produced accurate estimates of uncertainty, correctly identifying trees where confusion was likely. Using only data from NEON, this single integrated classifier can make predictions for 20% of all tree species found in forest ecosystems across the entire US, which make up to roughly 90% of the upper canopy of the studied ecosystems. This suggests the potential for integrating information from multiple datasets and locations to develop broad scale general models for species classification from hyperspectral imaging.

ecology↗

bioRxiv2021

Data science competition for cross-site delineation and classification of individual trees from airborne remote sensing data

Delineating and classifying individual trees in remote sensing data is challenging. Many tree crown delineation methods have difficulty in closed-canopy forests and do not leverage multiple datasets. Methods to classify individual species are often accurate for common species, but perform poorly for less common species and when applied to new sites. We ran a data science competition to help identify effective methods for delineation of individual crowns and classification to determine species identity. This competition included data from multiple sites to assess the methods ability to generalize learning across multiple sites simultaneously, and transfer learning to novel sites where the methods were not trained. Six teams, representing 4 countries and 9 individual participants, submitted predictions. Methods from a previous competition were also applied and used as the baseline to understand whether the methods are changing and improving over time. The best delineation method was based on an instance segmentation pipeline, closely followed by a Faster R-CNN pipeline, both of which outperformed the baseline method. However, the baseline (based on a growing region algorithm) still performed well as did the Faster R-CNN. All delineation methods generalized well and transferred to novel forests effectively. The best species classification method was based on a two-stage fully connected neural network, which significantly outperformed the baseline (a random forest and Gradient boosting ensemble). The classification methods generalized well, with all teams training their models using multiple sites simultaneously, but the predictions from these trained models generally failed to transfer effectively to a novel site. Classification performance was strongly influenced by the number of field-based species IDs available for training the models, with most methods predicting common species well at the training sites. Classification errors (i.e., species misidentification) were most common between similar species in the same genus and different species that occur in the same habitat. The best methods handled class imbalance well and learned unique spectral features even with limited data. Most methods performed better than baseline in detecting new (untrained) species, especially in the site with no training data. Our experience further shows that data science competitions are useful for comparing different methods through the use of a standardized dataset and set of evaluation criteria, which highlights promising approaches and common challenges, and therefore advances the ecological and remote sensing field as a whole.

ecology↗

bioRxiv2021

Disentangling the roles of inter and intraspecific variation on leaf trait distributions across the eastern United States

Functional traits are influenced by phylogenetic constraints and environmental conditions, but previous large-scale studies modeled traits either as species weighted averages or directly from the environment, precluding analyses of the relative contributions of inter- and intraspecific variation across regions. We developed a joint model integrating phylogenetic and environmental information to understand and predict the distribution of eight leaf traits across the eastern USA. This model explained 68% of trait variation, outperforming both species-only and environment-only models, with variance attributable to species alone (23%), the environment alone (13%), and their combined effects (25%). The importance of the two drivers varied by trait. Predictions for the eastern USA produced accurate estimates of intraspecific variation and deviated from both species-only and environment-only models. Predictions revealed that intraspecific variation holds information across scales, affects relationships in the leaf economic spectrum and is key for interpreting trait distributions and ecosystem processes within and across ecoregions.

ecology↗

bioRxiv2020

A benchmark dataset for individual tree crown delineation in co-registered airborne RGB, LiDAR and hyperspectral imagery from the National Ecological Observation Network

Broad scale remote sensing promises to build forest inventories at unprecedented scales. A crucial step in this process is designing individual tree segmentation algorithms to associate pixels into delineated tree crowns. While dozens of tree delineation algorithms have been proposed, their performance is typically not compared based on standard data or evaluation metrics, making it difficult to understand which algorithms perform best under what circumstances. There is a need for an open evaluation benchmark to minimize differences in reported results due to data quality, forest type and evaluation metrics, and to support evaluation of algorithms across a broad range of forest types. Combining RGB, LiDAR and hyperspectral sensor data from the National Ecological Observatory Networks Airborne Observation Platform with multiple types of evaluation data, we created a novel benchmark dataset to assess individual tree delineation methods. This benchmark dataset includes an R package to standardize evaluation metrics and simplify comparisons between methods. The benchmark dataset contains over 6,000 image-annotated crowns, 424 field-annotated crowns, and 3,777 overstory stem points from a wide range of forest types. In addition, we include over 10,000 training crowns for optional use. We discuss the different evaluation sources and assess the accuracy of the image-annotated crowns by comparing annotations among multiple annotators as well as to overlapping field-annotated crowns. We provide an example submission and score for an open-source baseline for future methods.

ecology↗

bioRxiv2020

NEON Crowns: a remote sensing derived dataset of 100 million individual tree crowns

Forests provide essential biodiversity, ecosystem and economic services. Information on individual trees is important for understanding the state of forest ecosystems but obtaining individual-level data at broad scales is challenging due to the costs and logistics of data collection. While advances in remote sensing techniques allow surveys of individual trees at unprecedented extents, there remain significant technical and computational challenges in turning sensor data into tangible information. Using deep learning methods, we produced an open-source dataset of individual-level crown estimates for 100 million trees at 37 sites across the United States surveyed by the National Ecological Observatory Networks Airborne Observation Platform. Each canopy tree crown is represented by a rectangular bounding box and includes information on the height, crown area, and spatial location of the tree. Tree crowns identified using this technique correspond well with hand-labeled crowns, exhibiting both high levels of overlap and good correspondence in height estimates. These data have the potential to drive significant expansion of individual-level research on trees by facilitating both regional analyses at scales of ~10,000 ha and cross-region comparisons encompassing forest types from most of the United States.

ecology↗

bioRxiv2019

Geographic Generalization in Airborne RGB Deep Learning Tree Detection

Tree detection is a fundamental task in remote sensing for forestry and ecosystem ecology applications. While many individual tree segmentation algorithms have been proposed, the development and testing of these algorithms is typically site specific, with few methods evaluated against data from multiple forest types simultaneously. This makes it difficult to determine the generalization of proposed approaches, and limits tree detection at broad scales. Using data from the National Ecological Observatory Network we extend a recently developed semi-supervised deep learning algorithm to include data from a range of forest types, determine whether information from one forest can be used for tree detection in other forests, and explore the potential for building a universal tree detection algorithm. We find that the deep learning approach works well for overstory tree detection across forest conditions, outperforming conventional LIDAR-only methods in all forest types. Performance was best in open oak woodlands and worst in alpine forests. When models were fit to one forest type and used to predict another, performance generally decreased, with better performance when forests were more similar in structure. However, when models were pretrained on data from other sites and then fine-tuned using a small amount of hand-labeled data from the evaluation site, they performed similarly to local site models. Most importantly, a universal model fit to data from all sites simultaneously performed as well or better than individual models trained for each local site. This result suggests that RGB tree detection models that can be applied to a wide array of forest types at broad scales should be possible.

ecology↗

bioRxiv2019

Rethinking global carbon storage potential of trees. A comment on Bastin et. al 2019

Key MessageBastin et al. 2019 used flawed assumptions in calculating the carbon storage of restored forests worldwide, resulting in a gross overestimate. ContextBastin et al. 2019 use two flawed assumptions: 1) that the area suitable for restoration does not contain any carbon currently, and 2) that soil organic carbon (SOC) from increased canopy cover will accumulate quickly enough to mitigate anthropogenic carbon emissions. AimsWe re-evaluated the potential carbon storage worldwide using empirical relationships of tree cover and carbon. Methods and ResultsWe use global datasets of tree cover, soil organic carbon, and above ground biomass to estimate the empirical relationships of tree cover and carbon stock storage. A more realistic range of global carbon storage potential is between 71.7 and 75.7 GtC globally, with a large uncertainty associated with SOC. This is less than half of the original 205 GtC estimate. ConclusionThe potential global carbon storage of restored forests is much less than that estimated by Bastin et al. 2019. While we agree on the value of assessing global reforestation potential, we suggest caution in considering it the most effective strategy to mitigate anthropogenic emissions.

ecology↗

bioRxiv2019

Rethinking the fundamental unit of ecological remote sensing: Estimating individual level plant traits at scale

Functional ecology has increasingly focused on describing ecological communities based on their traits (measurable features affecting individuals fitness and performance). Analyzing trait distributions within and among forests could significantly improve understanding of community composition and ecosystem function. Historically, data on trait distributions are generated by (1) collecting a small number of leaves from a small number of trees, which suffers from limited sampling but produces information at the fundamental ecological unit (the individual); or (2) using remote sensing images to infer traits, producing information continuously across large regions, but as plots (containing multiple trees of different species) or pixels, not individuals. Remote sensing methods that identify individual trees and estimate their traits would provide the benefits of both approaches, producing continuous large-scale data linked to biological individuals. We used data from the National Ecological Observatory Network (NEON) to develop a method to scale up functional traits from 160 trees to the millions of trees within the spatial extent of two NEON sites. The pipeline consists of three stages: 1) image segmentation, to identify individual trees and estimate structural traits; 2) ensemble of models to infer leaf mass area (LMA), nitrogen, carbon, and phosphorus content using hyperspectral signatures, and DBH from allometry; and 3) predictions for segmented crowns for the full remote sensing footprint at the NEON sites. The R2 values on held out test data ranged from 0.41 to 0.75 on held out test data. The ensemble approach performed better than single partial least squares models. Carbon performed poorly compared to other traits (R2 of 0.41). The crown segmentation step contributed the most uncertainty in the pipeline, due to over-segmentation. The pipeline produced good estimates of DBH (R2 of 0.62 on held out data). Trait predictions for crowns performed significantly better than comparable predictions on pixels, resulting in improvement of R2 on test data of between to 0.26. We used the pipeline to produce individual level trait data for [~]5 million individual crowns, covering a total extent of [~]360 km2. This large dataset allows testing ecological questions on landscape scales, revealing that foliar traits are correlated with structural traits and environmental conditions.

ecology↗

bioRxiv2019

Individual tree-crown detection in RGB imagery using self-supervised deep learning neural networks

Remote sensing can transform the speed, scale, and cost of biodiversity and forestry surveys. Data acquisition currently outpaces the ability to identify individual organisms in high resolution imagery. We outline an approach for identifying tree-crowns in RGB imagery while using a semi-supervised deep learning detection network. Individual crown delineation has been a long-standing challenge in remote sensing and available algorithms produce mixed results. We show that deep learning models can leverage existing Light Detection and Ranging (LIDAR)-based unsupervised delineation to generate trees that are used for training an initial RGB crown detection model. Despite limitations in the original unsupervised detection approach, this noisy training data may contain information from which the neural network can learn initial tree features. We then refine the initial model using a small number of higher-quality hand-annotated RGB images. We validate our proposed approach while using an open-canopy site in the National Ecological Observation Network. Our results show that a model using 434,551 self-generated trees with the addition of 2848 hand-annotated trees yields accurate predictions in natural landscapes. Using an intersection-over-union threshold of 0.5, the full model had an average tree crown recall of 0.69, with a precision of 0.61 for the visually-annotated data. The model had an average tree detection rate of 0.82 for the field collected stems. The addition of a small number of hand-annotated trees improved the performance over the initial self-supervised model. This semi-supervised deep learning approach demonstrates that remote sensing can overcome a lack of labeled training data by generating noisy data for initial training using unsupervised methods and retraining the resulting models with high quality labeled data.

ecology↗