An official website of the United States government
Abstract Image‐based machine learning tools are an ascendant ‘big data’ research avenue. Citizen science platforms, like iNaturalist, and museum‐led initiatives provide researchers with an abundance of data and knowledge to extract. These include extraction of metadata, species identification, and phenomic data. Ecological and evolutionary biologists are increasingly using complex, multi‐step processes on data. These processes often include machine learning techniques, often built by others, that are difficult to reuse by other members in a collaboration.We present a conceptual workflow model for machine learning applications using image data to extract biological knowledge in the emerging field of imageomics. We derive an implementation of this conceptual workflow for a specific imageomics application that adheres to FAIR principles as a formal workflow definition that allows fully automated and reproducible execution, and consists of reusable workflow components.We outline technologies and best practices for creating an automated, reusable and modular workflow, and we show how they promote the reuse of machine learning models and their adaptation for new research questions. This conceptual workflow can be adapted: it can be semi‐automated, contain different components than those presented here, or have parallel components for comparative studies.We encourage researchers—both computer scientists and biologists—to build upon this conceptual workflow that combines machine learning tools on image data to answer novel scientific questions in their respective fields.
more »
« less
Large‐scale, image‐based tree species mapping in a tropical forest using artificial perceptual learning
Abstract Information about the spatial distribution of species lies at the heart of many important questions in ecology. Logistical limitations and collection biases, however, limit the availability of such data at ecologically relevant scales. Remotely sensed information can alleviate some of these concerns, but presents challenges associated with accurate species identification and limited availability of field data for validation, especially in high diversity ecosystems such as tropical forests.Recent advances in machine learning offer a promising and cost‐efficient approach for gathering a large amount of species distribution data from aerial photographs. Here, we propose a novel machine learning framework, artificial perceptual learning (APL), to tackle the problem of weakly supervised pixel‐level mapping of tree species in forests. Challenges arise from limited availability of ground labels for tree species, lack of precise segmentation of tree canopies and misalignment between visible canopies in the aerial images and stem locations associated with ground labels. The proposed APL framework addresses these challenges by constructing a workflow using state‐of‐the‐art machine learning algorithms.We develop and illustrate the proposed framework by implementing a fine‐grain mapping of three species, the palmPrestoea acuminataand the tree speciesCecropia schreberianaandManilkara bidentata, over a 5,000‐ha area of El Yunque National Forest in Puerto Rico. These large‐scale maps are based on unlabelled high‐resolution aerial images of unsegmented tree canopies. Misaligned ground‐based labels, available for <1% of these images, serve as the only weak supervision. APL performance is evaluated using ground‐based labels and high‐quality human segmentation using Amazon Mechanical Turk, and compared to a basic workflow that relies solely on labelled images.Receiver operating characteristic (ROC) curves and Intersection over Union (IoU) metrics demonstrate that APL substantially outperforms the basic workflow and attains human‐level cognitive economy, with 50‐fold time savings. For the palm andC. schreberiana, the APL framework has high pixelwise accuracy and IoU with reference to human segmentations. ForM.bidentata, APL predictions are congruent with ground‐based labels. Our approach shows great potential for leveraging existing data from global forest plot networks coupled with aerial imagery to map tree species at ecologically meaningful spatial scales.
more »
« less
- Award ID(s):
- 1831952
- PAR ID:
- 10452932
- Publisher / Repository:
- Wiley-Blackwell
- Date Published:
- Journal Name:
- Methods in Ecology and Evolution
- Volume:
- 12
- Issue:
- 4
- ISSN:
- 2041-210X
- Format(s):
- Medium: X Size: p. 608-618
- Size(s):
- p. 608-618
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Ploidy level in plants may influence ecological functioning, demography and response to climate change. However, measuring ploidy level typically requires intensive cell or molecular methods.We map ploidy level variation in quaking aspen, a dominant North American tree species that can be diploid or triploid and that grows in spatially extensive clones. We identify the predictors and spatial scale of ploidy level variation using a combination of genetic and ground‐based and airborne remote sensing methods.We show that ground‐based leaf spectra and airborne canopy spectra can both classify aspen by ploidy level with a precision‐recall harmonic mean of 0.75–0.95 and Cohen's kappa ofc.0.6–0.9. Ground‐based bark spectra cannot classify ploidy level better than chance. We also found that diploids are more common on higher elevation and steeper sites in a network of forest plots in Colorado, and that ploidy level distribution varies at subkilometer spatial scales.Synthesis. Our proof‐of‐concept study shows that remote sensing of ploidy level could become feasible in this tree species. Mapping ploidy level across landscapes could provide insights into the genetic basis of species' responses to climate change.more » « less
-
Time lapse microscopy is essential for quantifying the dynamics of cells, subcellular organelles and biomolecules. Biologists use different fluorescent tags to label and track the subcellular structures and biomolecules within cells. However, not all of them are compatible with time lapse imaging, and the labeling itself can perturb the cells in undesirable ways. We hypothesized that phase image has the requisite information to identify and track nuclei within cells. By utilizing both traditional blob detection to generate binary mask labels from the stained channel images and the deep learning Mask RCNN model to train a detection and segmentation model, we managed to segment nuclei based only on phase images. The detection average precision is 0.82 when the IoU threshold is to be set 0.5. And the mean IoU for masks generated from phase images and ground truth masks from experts is 0.735. Without any ground truth mask labels during the training time, this is good enough to prove our hypothesis. This result enables the ability to detect nuclei without the need for exogenous labeling.more » « less
-
Abstract We introduce a new “ecosystem‐scale” experiment at the Cedar Creek Ecosystem Science Reserve in central Minnesota, USA to test long‐term ecosystem consequences of tree diversity and composition. The experiment—the largest of its kind in North America—was designed to provide guidance on forest restoration efforts that will advance carbon sequestration goals and contribute to biodiversity conservation and sustainability.The new Forest and Biodiversity (FAB2) experiment uses native tree species in varying levels of species richness, phylogenetic diversity and functional diversity planted in 100 m2and 400 m2plots at 1 m spacing, appropriate for testing long‐term ecosystem consequences. FAB2 was designed and established in conjunction with a prior experiment (FAB1) in which the same set of 12 species was planted in 16 m2plots at 0.5 m spacing. Both are adjacent to the BioDIV prairie‐grassland diversity experiment, enabling comparative investigations of diversity and ecosystem function relationships between experimental grasslands and forests at different planting densities and plot sizes.Within the first 6 years, mortality in 400 m2monoculture plots was higher than in 100 m2plots. The highest mortality occurred inTilia americanaandAcer negundomonocultures, but mortality for both species decreased with increasing plot diversity. These results demonstrate the importance of forest diversity in reducing mortality in some species and point to potential mechanisms, including light and drought stress, that cause tree mortality in vulnerable monocultures. The experiment highlights challenges to maintaining monoculture and low‐diversity treatments in tree mixture experiments of large extent.FAB2 provides a long‐term platform to test the mechanisms and processes that contribute to forest stability and ecosystem productivity in changing environments. Its ecosystem‐scale design, and accompanying R package, are designed to discern species and lineage effects and multiple dimensions of diversity to inform restoration of ecosystem functions and services from forests. It also provides a platform for improving remote sensing approaches, including Uncrewed Aerial Vehicles (UAVs) equipped with LiDAR, multispectral and hyperspectral sensors, to complement ground‐based monitoring. We aim for the experiment to contribute to international efforts to monitor and manage forests in the face of global change.more » « less
-
Summary Trade‐offs among carbon sinks constrain how trees physiologically, ecologically, and evolutionarily respond to their environments. These trade‐offs typically fall along a productive growth to conservative, bet‐hedging continuum. How nonstructural carbohydrates (NSCs) stored in living tree cells (known as carbon stores) fit in this trade‐off framework is not well understood.We examined relationships between growth and storage using both within species genetic variation from a common garden, and across species phenotypic variation from a global database.We demonstrate that storage is actively accumulated, as part of a conservative, bet‐hedging life history strategy. Storage accumulates at the expense of growth both within and across species. Within the speciesPopulus trichocarpa, genetic trade‐offs show that for each additional unit of wood area growth (in cm2 yr−1) that genotypes invest in, they lose 1.2 to 1.7 units (mg g−1NSC) of storage. Across species, for each additional unit of area growth (in cm2 yr−1), trees, on average, reduce their storage by 9.5% in stems and 10.4% in roots.Our findings impact our understanding of basic plant biology, fit storage into a widely used growth‐survival trade‐off spectrum describing life history strategy, and challenges the assumptions of passive storage made in ecosystem models today.more » « less
