An official website of the United States government
Abstract The illegal timber trade has significant impact on the survival of endangered tropical hardwood species likeDalbergiaspp. (rosewood), a world‐wide protected genus from the Convention on International Trade in Endangered Species of Wild Fauna and Flora (CITES). Due to increased threat toDalbergiaspp., and lack of action to reduce threats, port of entry analysis methods are required to identifyDalbergiaspp. Handheld laser‐induced breakdown spectroscopy (LIBS) has been shown to be capable of identifying species and establishing provenance ofDalbergiaspp. and other tropical hardwoods, but analysis methods for this work have yet to be investigated in detail. The present work investigates five well‐known algorithms—partial least squares discriminant analysis (PLS‐DA), classification and regression trees (CART),k‐nearest neighbor (k‐NN), random forest (RF), and support vector machine (SVM)—two training/test set sampling regimes, and data collection at two signal‐to‐noise (S/N) ratios to assess the potential for handheld LIBS analyses. Additionally, imbalanced classes are addressed. For this application, SVM and RF yield near identical results (though RF takes nearly 100 longer to compute), while the S/N ratio has a significant effect on model success assuming all else is equal. It was found that forming a training set with replicate low S/N analyses can perform as well as higher precision training sets for true prediction, even if the predicted samples have low signal to noise! This work confirms handheld LIBS analyzers can provide a viable method for classification of hardwood species, even within the same genus.
more »
« less
Multi-Objective Support Vector Regression Reduces Systematic Error in Moderate Resolution Maps of Tree Species Abundance
When forest conditions are mapped from empirical models, uncertainty in remotely sensed predictor variables can cause the systematic overestimation of low values, underestimation of high values, and suppression of variability. This regression dilution or attenuation bias is a well-recognized problem in remote sensing applications, with few practical solutions. Attenuation is of particular concern for applications that are responsive to prediction patterns at the high end of observed data ranges, where systematic error is typically greatest. We addressed attenuation bias in models of tree species relative abundance (percent of total aboveground live biomass) based on multitemporal Landsat and topoclimatic predictor data. We developed a multi-objective support vector regression (MOSVR) algorithm that simultaneously minimizes total prediction error and systematic error caused by attenuation bias. Applied to 13 tree species in the Acadian Forest Region of the northeastern U.S., MOSVR performed well compared to other prediction methods including single-objective SVR (SOSVR) minimizing total error, Random Forest (RF), gradient nearest neighbor (GNN), and Random Forest nearest neighbor (RFNN) algorithms. SOSVR and RF yielded the lowest total prediction error but produced the greatest systematic error, consistent with strong attenuation bias. Underestimation at high relative abundance caused strong deviations between predicted patterns of species dominance/codominance and those observed at field plots. In contrast, GNN and RFNN produced dominance/codominance patterns that deviated little from observed patterns, but predicted species relative abundance with lower accuracy and substantial systematic error. MOSVR produced the least systematic error for all species with total error often comparable to SOSVR or RF. Predicted patterns of dominance/codominance matched observations well, though not quite as well as GNN or RFNN. Overall, MOSVR provides an effective machine learning approach to the reduction of systematic prediction error and should be fully generalizable to other remote sensing applications and prediction problems.
more »
« less
- Award ID(s):
- 1920908
- PAR ID:
- 10211603
- Date Published:
- Journal Name:
- Remote Sensing
- Volume:
- 12
- Issue:
- 11
- ISSN:
- 2072-4292
- Page Range / eLocation ID:
- 1739
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Understanding how environmental adaptations mediate plant and ecosystem responses becomes increasingly important under accelerating global environmental change. Multi-stemmed trees, for example, differ in form and function from single-stemmed trees and may possess physiological advantages that allow for persistence during stressful climatic events such as extended drought. Following the worst drought in Hawaii in a century, we examined patterns of stem abundance and turnover in a Hawaiian lowland dry forest (LDF) and a montane wet forest (MWF) to investigate how multi-stemmed trees might influence site persistence, and how stem abundance and turnover relate to key functional traits. We found stem abundance and multi-stemmed trees to be an important component for climate resilience within the LDF. The LDF had higher relative abundance of multi-stemmed trees, stem abundance, and mean stem abundance compared to a reference MWF. Within the LDF, multi-stemmed trees had higher relative stem abundance (i.e., percent composition of stems to the total number of stems in the LDF) and higher estimated aboveground carbon than single-stemmed trees. Stem abundance varied among species and tree size classes. Stem turnover (i.e., change in stem abundance between five-year censuses) varied among species and tree size classes and species mean stem turnover was correlated with mean species stem abundance per tree. At the plot level, stem abundance per tree is also a predictor of survival, though mortality did not differ between multiple- and single-stemmed trees. Lastly, species with higher mean stem abundance per tree tended to have traits associated with a higher light-saturated photosynthetic rate, suggesting greater productivity in periods with higher water supply. Identifying the traits that allow species and forest communities to persist in dry environments or respond to disturbance is useful for forecasting ecological climate resilience or potential for restoration in tropical dry forests.more » « less
-
Trees in proximity to power lines can cause significant damage to utility infrastructure during storms, leading to substantial economic and societal costs. This study investigated the effectiveness of non-parametric machine learning algorithms in modeling tree-related outage risks to distribution power lines at a finer spatial scale. We used a vegetation risk model (VRM) comprising 15 predictor variables derived from roadside tree data, landscape information, vegetation management records, and utility infrastructure data. We evaluated the VRM’s performance using decision tree (DT), random forest (RF), k-Nearest Neighbor (k-NN), extreme gradient boosting (XGBoost), and support vector machine (SVM) techniques. The RF algorithm demonstrated the highest performance with an accuracy of 0.753, an AUC-ROC of 0.746, precision of 0.671, and an F1-score of 0.693. The SVM achieved the highest recall value of 0.727. Based on the overall performance, the RF emerged as the best machine learning algorithm, whereas the DT was the least suitable. The DT reported the lowest run times for both hyperparameter optimization (3.93 s) and model evaluation (0.41 s). XGBoost and the SVM exhibited the highest run times for hyperparameter tuning (9438.54 s) and model evaluation (112 s), respectively. The findings of this study are valuable for enhancing the resilience and reliability of the electric grid.more » « less
-
null (Ed.)Non-contact home-based sleep monitoring will bring a paradigm shift to diagnosis and treatment of Obstructive Sleep Apnea (OSA) as it can facilitate easier access to specialized care in order to reach a much boarder set of patients. However, current remote unattended sleep studies are mostly contact sensor based and test results are sometimes falsified by sleep-critical job holders (driver, airline pilots) due to fear of potential job loss. In this work, we investigated identity authentication of patients with OSA symptoms based on extracting respiratory features (peak power spectral density, packing density and linear envelop error) from radar captured paradoxical breathing patterns in a small-scale clinical sleep study integrating three different machine learning classifiers (Support Vector Machine (SVM), K-nearest neighbor (KNN), Random forest). The proposed OSA-based authentication method was tested and validated for five OSA patients with 93.75% accuracy using KNN classifier which outperformed other classifiers.more » « less
-
Abstract An intelligent sensing framework using Machine Learning (ML) and Deep Learning (DL) architectures to precisely quantify dielectrophoretic force invoked on microparticles in a textile electrode-based DEP sensing device is reported. The prediction accuracy and generalization ability of the framework was validated using experimental results. Images of pearl chain alignment at varying input voltages were used to build deep regression models using modified ML and CNN architectures that can correlate pearl chain alignment patterns of Saccharomyces cerevisiae(yeast) cells and polystyrene microbeads to DEP force. Various ML models such as K-Nearest Neighbor, Support Vector Machine, Random Forest, Neural Networks, and Linear Regression along with DL models such as Convolutional Neural Network (CNN) architectures of AlexNet, ResNet-50, MobileNetV2, and GoogLeNet have been analyzed in order to build an effective regression framework to estimate the force induced on yeast cells and microbeads. The efficiencies of the models were evaluated using Mean Absolute Error, Mean Absolute Relative, Mean Squared Error, R-squared, and Root Mean Square Error (RMSE) as evaluation metrics. ResNet-50 with RMSPROP gave the best performance, with a validation RMSE of 0.0918 on yeast cells while AlexNet with ADAM optimizer gave the best performance, with a validation RMSE of 0.1745 on microbeads. This provides a baseline for further studies in the application of deep learning in DEP aided Lab-on-Chip devices.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3390/rs12111739
