Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “classification models”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Explainable AI classification for parton density theory

Quantitatively connecting properties of parton distribution functions (PDFs, or parton densities) to the theoretical assumptions made within the QCD analyses which produce them has been a longstanding problem in HEP phenomenology. To confront this challenge, we introduce an ML-based explainability framework, XAI4PDF, to classify PDFs by parton flavor or underlying theoretical model using ResNet-like neural networks (NNs). By leveraging the differentiable nature of ResNet models, this approach deploys guided backpropagation to dissect relevant features of fitted PDFs, identifying x-dependent signatures of PDFs important to the ML model classifications. By applying our framework, we are able to sort PDFs according to the analysis which produced them while constructing quantitative, human-readable maps locating the x regions most affected by the internal theory assumptions going into each analysis. This technique expands the toolkit available to PDF analysis and adjacent particle phenomenology while pointing to promising generalizations.

Artificial Intelligence↗
DOE OSTI2022

Integrating very-high-resolution UAS data and airborne imaging spectroscopy to map the fractional composition of Arctic plant functional types in Western Alaska

Widespread changes in vegetation cover and composition are driving strong impacts on Arctic ecosystem functioning and global climate feedbacks. An accurate characterization of tundra vegetation composition is required to understand how the Arctic will respond to future climate change. However, quantifying tundra vegetation composition over large areas is challenging as commonly-used satellite observations are too coarse, spatially and spectrally, to differentiate low-lying tundra vegetation types. Recent airborne and spaceborne imaging spectroscopy platforms provide better data to characterize vegetation composition. Yet, our ability to characterize vegetation composition with imaging spectroscopy remains largely unexplored in the Arctic, particularly due to a lack of ground observations needed to train and test classification models. To address this problem, we collected very-high-resolution (VHR, ~5 cm) unoccupied aerial system (UAS) imagery at three low-Arctic tundra sites located on the Seward Peninsula, western Alaska. In this paper, we examine the feasibility of integrating imagery from the UAS and the hyperspectral Airborne Visible/Infrared Imaging Spectrometer, Next Generation (AVIRIS-NG) airborne instrument to map the fractional composition of 12 key Arctic plant functional types (PFTs). To this end, we first mapped the 12 PFTs from our VHR UAS imagery using random forest classification. We then used these UAS-derived PFT maps as ground truth to develop partial least squares regression (PLSR) models to predict the fractional cover (FCover) of each PFT from AVIRIS-NG imagery. Further, we evaluated the performance of our PLSR models using reserved UAS samples, as well as by mapping PFT FCover and dominant PFT for large tundra landscapes. Our results show that 1) Arctic PFTs can be effectively mapped using VHR UAS imagery, with overall accuracy between 86% and 92%, 2) when the UAS mapped PFTs were used to inform PLSR scaling models, the FCover of the 12 PFTs could be effectively estimated from AVIRIS-NG imagery with a mean absolute error (MAE) <0.13, and 3) our PLSR models outperformed traditional, fully constrained least-squares (FCLS) linear mixture analysis and produced high-quality, spatially contiguous PFT FCover and PFT maps that captured vegetation spatial patterns with similar accuracy to those developed from UAS imagery. The developed PLSR models have the potential to be broadly applied for quantifying vegetation composition with AVIRIS-NG images to help monitor tundra vegetation dynamics and improve process-based modeling of tundra ecosystems.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Using Machine Learning for Quantum Annealing Accuracy Prediction

Quantum annealers, such as the device built by D-Wave Systems, Inc., offer a way to compute solutions of NP-hard problems that can be expressed in Ising or quadratic unconstrained binary optimization (QUBO) form. Although such solutions are typically of very high quality, problem instances are usually not solved to optimality due to imperfections of the current generations quantum annealers. In this contribution, we aim to understand some of the factors contributing to the hardness of a problem instance, and to use machine learning models to predict the accuracy of the D-Wave 2000Q annealer for solving specific problems. We focus on the maximum clique problem, a classic NP-hard problem with important applications in network analysis, bioinformatics, and computational chemistry. By training a machine learning classification model on basic problem characteristics such as the number of edges in the graph, or annealing parameters, such as the D-Wave’s chain strength, we are able to rank certain features in the order of their contribution to the solution hardness, and present a simple decision tree which allows to predict whether a problem will be solvable to optimality with the D-Wave 2000Q. We extend these results by training a machine learning regression model that predicts the clique size found by D-Wave.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Transitioning from Simulation to Reality: Applying Chatter Detection Models to Real-World Machining Data

Chatter, a self-excited vibration phenomenon, is a critical challenge in high-speed machining operations, affecting tool life, product surface quality, and overall process efficiency. While machine learning models trained on simulated data have shown promise in detecting chatter, their real-world applicability remains uncertain due to discrepancies between simulated and actual machining environments. The primary goal of this study is to bridge the gap between simulation-based machine learning models and real-world applications by developing and validating a Random Forest-based chatter detection system. This research focuses on improving manufacturing efficiency through reliable chatter detection by integrating Operational Modal Analysis (OMA), Receptance Coupling Substructure Analysis (RCSA), and Transfer Learning (TL). The study applies a Random Forest classification model trained on over 140,000 simulated machining datasets, incorporating techniques like Operational Modal Analysis (OMA), Receptance Coupling Substructure Analysis (RCSA), and Transfer Learning (TL) to adapt the model for real-world operational data. The model is validated against 1600 real-world machining datasets, achieving an accuracy of 86.1%, with strong precision and recall scores. The results demonstrate the model’s robustness and potential for practical implementation in industrial settings, highlighting challenges such as sensor noise and variability in machining conditions. This work advances the use of predictive analytics in machining processes, offering a data-driven solution to improve manufacturing efficiency through more reliable chatter detection.

42 ENGINEERING↗
DOE OSTI2022

ASK: Adversarial Soft k-Nearest Neighbor Attack and Defense

K-Nearest Neighbor (kNN)-based deep learning methods have been applied to many applications due to their simplicity and geometric interpretability. However, the robustness of kNN-based deep classification models has not been thoroughly explored and kNN attack strategies are underdeveloped. In this paper, we first propose an Adversarial Soft kNN (ASK) loss for developing more effective kNN-based deep neural network attack strategies and designing better defense methods against them. Our ASK loss provides a differentiable surrogate of the expected kNN classification error. It is also interpretable as it preserves the mutual information between the perturbed input and the in-class-reference data. We use the ASK loss to design a novel attack method called the ASK-Attack (ASK-Atk), which shows superior attack efficiency and accuracy degradation relative to previous kNN attacks on hidden layers. We then derive an ASK-Defense (ASK-Def) method that optimizes the worst-case ASK training loss. Experiments on CIFAR-10 (ImageNet) show that (i) ASK-Atk achieves ≥13% (≥ 13% ) improvement in attack success rate over previous kNN attacks, and (ii) ASK-Def outperforms the conventional adversarial training method by ≥ 6.9% (≥ 3.5% ) in terms of robustness improvement. Relevant codes are available at https://github.com/wangren09/ASK .

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Trigger Detection for the sPHENIX Experiment via Bipartite Graph Networks with Set Transformer

Trigger (interesting events) detection is crucial to high-energy and nuclear physics experiments because it improves data acquisition efficiency. It also plays a vital role in facilitating the downstream offline data analysis process. The sPHENIX detector, located at the Relativistic Heavy Ion Collider in Brookhaven National Laboratory, is one of the largest nuclear physics experiments on a world scale and is optimized to detect physics processes involving charm and beauty quarks. Furthermore, these particles are produced in collisions involving two proton beams, two gold nuclei beams, or a combination of the two and give critical insights into the formation of the early universe. This paper presents a model architecture for trigger detection with geometric information from two fast silicon detectors. Transverse momentum is introduced as an intermediate feature from physics heuristics. We also prove its importance through our training experiments. Each event consists of tracks and can be viewed as a graph. A bipartite graph neural network is integrated with the attention mechanism to design a binary classification model. Compared with the state-of-the-art algorithm for trigger detection, our model is parsimonious and increases the accuracy and the AUC score by more than 15%.

97 MATHEMATICS AND COMPUTING↗
NASA NTRSDate not supplied

Algorithmic Detection of Elemental Biosignatures

Machine learning models that classify a sample as indicative or non-indicative of life could play an important role in life-detection missions. Their predictions result from agnostic algorithms and thereby add redundancy to judgements resulting from human expertise. Additionally, their important features can reveal the most informative measurements within the operational constraints of a life-detection mission. The Ladder of Life Detection (Neveu 2018) identifies the need for an understanding of how combinations of multiple biosignatures affect overall confidence. The present work provides a starting point to answer this need, and future work will expand the data types to obtain even more predictive combinations of features. Elemental abundance was chosen as a starting set of features due to its availability in diverse sample types, which are needed to train a generalizable model. A standardized dataset was collected, including 35 non-indicative, e.g., lunar rock, basalt; 19 indicative mixed, e.g., seawater, agricultural soil; 46 indicative non-alive, e.g., coal, chalk; and 10 indicative alive, e.g., biofilm, bacteria. This dataset could be valuable for complementary biosignature research. The samples were standardized to the same limit of detection of a simulated mission scenario. Four classification models were used: k-nearest neighbors (KNN), logistic regression (LR), linear support vector machines (SVM), and Gaussian naïve Bayes (GNB). To obtain feature importances, KNN was run on three principal components of the training data and LR and SVM were run with L1 and L2 regularization. The performances and feature importances of the six model variants on 40:60 train to validation ratios were assessed with Monte Carlo simulations. ROC AUC and mean accuracy scores ranged between 82% - 94%, with sensitivity greater than specificity. For indicative of life predictors, all models had C and Ca as strong and Cl as medium; a majority of models had N, K, and P as medium. For non-indicative of life predictors, all models had Si as strong, and a majority of models had Mg, Al, and Ti as medium. Varied elements were Fe (slightly non-indicative), H (slightly indicative), O (widely varied), Na, Mn, and S. These results serve as a proof of concept and suggest important elemental signals beyond merely the CHNOPS of Earth-based life.

Algorithmic↗
NASA NTRS2024

Hawaiʻi Urban Development: Mapping Urban Infrastructure and Linkages to Wastewater Impacts across Hawaiʻi

Coastal ecosystems and human health across the Hawaiʻian islands are under threat from cesspools and other unpermitted wastewater infrastructure. Cesspools, or home sewage systems that hold wastewater effluent in porous concrete containers underground, discharge raw, untreated sewage directly into waterways. In fact, it is estimated that approximately 88,000 cesspools release 55 million gallons of raw sewage into Hawaiʻi’s waterways each day. Our partners, The Nature Conservancy, Hawaiʻi Regional Office (TNC) and University of Hawaiʻi, Mānoa (UHM), are heavily involved with the implementation and impact of Act 125, which was passed in 2017 by Hawaiʻi State Legislature to help combat these effects. This requires the conversion of cesspools to be upgraded and either converted to approved onsite disposal systems or connected to a sewer system so that the wastewater may be treated and to avoid leaching into the groundwater. Thus, identifying and locating cesspool and other unpermitted wastewater infrastructure is key to state and partner goals. Utilizing NASA Earth observations including Landsat 7 Enhanced Thematic Mapper Plus (ETM+), Landsat 8 Operational Land Imager (OLI), and Landsat 9 OLI-2 imagery, as well as pre-classified Sentinel-2 Multispectral Instrument (MSI) imagery in Esri’s Living Atlas, our team showcased the various perspectives that wastewater pollution research can use to assist in identifying and tracking urban development and concrete condition. This process was demonstrated by utilizing supervised object-based classification models, calculating various urban indices, and finding building size estimates to calculate effluent levels. Additionally, providing our partners with a GIS Methodology that can be built on to reach their future needs.

urban classification↗
NASA NTRSDate not supplied

Interpretable Machine Learning Models for Autonomous Characterization of Analogue Ocean World Seawater Chemistry and Biosignature Potential Using Isotope Ratio Data

Background: Future missions to ocean worlds, such as Enceladus and Europa, will attempt to characterize the subsurface seawater chemistry and assess the potential for life. Such missions will be equipped with capabilities to precisely measure volatile isotopes in plumes, atmospheres, and exospheres. Motivation: While large isotopic fractionations can indicate a biological source, there are signatures resulting from abiotic geochemical processes that mimic isotopic biosignatures. While machine learning (ML) has the potential to disentangle competing effects and biotic mimicry, high-dimensional isotope ratio mass spectrometry (IRMS) data is likely to contain noise/irrelevant features and involve complex statistical interactions that make human inference and interpretation difficult. Further, ML predictions with as far-reaching implications as an extraterrestrial biosignature on an ocean world requires the use of interpretable models (i.e., not “black box” models) with physically and mathematically meaningful feature spaces along with false positive diagnostics. Methods: We use volatile CO2 IRMS data of analogue ocean world seawaters to validate an ML approach to provide biogeochemical context for biosignature detection. We employ a feature selection method called nearest-neighbor projected distance regression (NPDR) that detects statistical interactions and helps elucidate the mechanisms of the Random Forest classification models. Results: We train and validate predictive ML models on volatile CO2 IRMS data of analogue ocean world seawaters to predict major salt components (e.g., MgSO4, NaHCO3), pH, ionic strength, and the presence of biosignatures. Features derived from IRMS measurements are augmented with extracted time-series features. Our results show high test accuracy and interpretability, which is increased by interaction network visualization, sample-wise variable importance scores, and single-sample class probability estimates. We demonstrate an ML mission software solution that triggers autonomous data transmission and biogeochemical sample prediction.

geochemistry↗
DOE OSTI2020

Modeling and Detection of Future Cyber-Enabled DSM Data Attacks

Demand-Side Management (DSM) is an essential tool to ensure power system reliability and stability. In future smart grids, certain portions of a customer’s load usage could be under the automatic control of a cyber-enabled DSM program, which selectively schedules loads as a function of electricity prices to improve power balance and grid stability. In this scenario, the security of DSM cyberinfrastructure will be critical as advanced metering infrastructure and communication systems are susceptible to cyber-attacks. Such attacks, in the form of false data injections, can manipulate customer load profiles and cause metering chaos and energy losses in the grid. The feedback mechanism between load management on the consumer side and dynamic price schemes employed by independent system operators can further exacerbate attacks. To study how this feedback mechanism may worsen attacks in future cyber-enabled DSM programs, we propose a novel mathematical framework for (i) modeling the nonlinear relationship between load management and real-time pricing, (ii) simulating residential load data and prices, (iii) creating cyber-attacks, and (iv) detecting said attacks. In this framework, we first develop time-series forecasts to model load demand and use them as inputs to an elasticity model for the price-demand relationship in the DSM loop. This work then investigates the behavior of such a feedback loop under intentional cyber-attacks. We simulate and examine load-price data under different DSM-participation levels with three types of random additive attacks: ramp, sudden, and point attacks. We conduct two investigations for the detection of DSM attacks. The first studies a supervised learning approach, with various classification models, and the second studies the performance of parametric and nonparametric change point detectors. Results conclude that higher amounts of DSM participation can exacerbate ramp and sudden attacks leading to better detection of such attacks, especially with supervised learning classifiers. We also find that nonparametric detection outperforms parametric for smaller user pools, and random point attacks are the hardest to detect with any method.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Dynamics-Based Peptide–MHC Binding Optimization by a Convolutional Variational Autoencoder: A Use-Case Model for CASTELO

An unsolved challenge in the development of antigen-specific immunotherapies is determining the optimal antigens to target. Comprehension of antigen–major histocompatibility complex (MHC) binding is paramount toward achieving this goal. Here, we apply CASTELO, a combined machine learning-molecular dynamics (ML-MD) approach, to identify per-residue antigen binding contributions and then design novel antigens of increased MHC-II binding affinity for a type 1 diabetes-implicated system. We build upon a small-molecule lead optimization algorithm by training a convolutional variational autoencoder (CVAE) on MD trajectories of 48 different systems across four antigens and four HLA serotypes. We develop several new machine learning metrics including a structure-based anchor residue classification model as well as cluster comparison scores. ML-MD predictions agree well with experimental binding results and free energy perturbation-predicted binding affinities. Moreover, ML-MD metrics are independent of traditional MD stability metrics such as contact area and root-mean-square fluctuations (RMSF), which do not reflect binding affinity data. Finally, our work supports the role of structure-based deep learning techniques in antigen-specific immunotherapy design.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Improved Gas Plume Identification Using Nearest Neighbor Methods for Background Estimation

Longwave infrared (LWIR) hyperspectral imaging (HSI) can be used for many tasks in remote sensing, including detecting and identifying effluent gases by LWIR sensors on airborne platforms. Identification is used after detection to increase confidence in weakly detected plumes, reduce false positives from detection, and distinguish between similar and confounding material signatures. Background estimation is an important step used to reveal the unique spectral characteristics of the detected gas, allowing the identification model to determine what the gas is specifically. The importance of proper background estimation increases when dealing with weak signals, large libraries of gases of interest, and uncommon or heterogeneous backgrounds. In this article, we propose two methods for background estimation: a novel k-nearest segments (KNS) algorithm and the standard k-nearest neighbors (KNN) algorithm. We test our methods and three existing background estimation methods for comparison against global background estimation to determine which performs best at estimating the true background radiance under a plume and for increasing identification confidence using a neural network classification model. We compare the different methods using 640 simulated weak plumes in an urban environment. For identification, our KNS algorithm improves median neural network identification confidence by 53.2%. For background radiance estimation, the KNN algorithm provides a median of 49 times less RMSE than global background estimation. Furthermore, KNN is the easiest method to tune for different plumes, making it an excellent “out of the box” background estimator.

47 OTHER INSTRUMENTATION↗
NASA NTRS2013

Modeling Weather Impact on Airport Arrival Miles-in-Trail Restrictions

When the demand for either a region of airspace or an airport approaches or exceeds the available capacity, miles-in-trail (MIT) restrictions are the most frequently issued traffic management initiatives (TMIs) that are used to mitigate these imbalances. Miles-intrail operations require aircraft in a traffic stream to meet a specific inter-aircraft separation in exchange for maintaining a safe and orderly flow within the stream. This stream of aircraft can be departing an airport, over a common fix, through a sector, on a specific route or arriving at an airport. This study begins by providing a high-level overview of the distribution and causes of arrival MIT restrictions for the top ten airports in the United States. This is followed by an in-depth analysis of the frequency, duration and cause of MIT restrictions impacting the Hartsfield-Jackson Atlanta International Airport (ATL) from 2009 through 2011. Then, machine-learning methods for predicting (1) situations in which MIT restrictions for ATL arrivals are implemented under low demand scenarios, and (2) days in which a large number of MIT restrictions are required to properly manage and control ATL arrivals are presented. More specifically, these predictions were accomplished by using an ensemble of decision trees with Bootstrap aggregation (BDT) and supervised machine learning was used to train the BDT binary classification models. The models were subsequently validated using data cross validation methods. When predicting the occurrence of arrival MIT restrictions under low demand situations, the model was able to achieve over all accuracy rates ranging from 84% to 90%, with false alarm ratios ranging from 10% to 15%. In the second set of studies designed to predict days on which a high number of MIT restrictions were required, overall accuracy rates of 80% were achieved with false alarm ratios of 20%. Overall, the predictions proposed by the model give better MIT usage information than what has been currently provided under current day operations. Traffic flow managers can use these predictions to identify potential MIT restrictions to eliminate (e.g., those occurring during low arrival demand periods), and to determine the days in which a significant number of restrictions may be required

Operation↗
NASA NTRS2019

Long-Term Impacts of Selective Logging on Amazon Forest Dynamics from Multi-Temporal Airborne LiDAR

Forest degradation is common in tropical landscapes, but estimates of the extent and duration of degradation impacts are highly uncertain. In particular, selective logging is a form of forest degradation that alters canopy structure and function, with persistent ecological impacts following forest harvest. In this study, we employed airborne laser scanning in 2012 and 2014 to estimate three-dimensional changes in the forest canopy and understory structure and aboveground biomass following reduced-impact selective logging in a site in Eastern Amazon. Also, we developed a binary classification model to distinguish intact versus logged forests. We found that canopy gap frequency was significantly higher in logged versus intact forests even after 8 years (the time span of our study). In contrast, the understory of logged areas could not be distinguished from the understory of intact forests after 6–7 years of logging activities. Measuring new gap formation between LiDAR acquisitions in 2012 and 2014, we showed rates 2 to 7 times higher in logged areas compared to intact forests. New gaps were spatially clumped with 76 to 89% of new gaps within 5 m of prior logging damage. The biomass dynamics in areas logged between the two LiDAR acquisitions was clearly detected with an average estimated loss of -4.14 +/- 0.76 MgC/hay. In areas recovering from logging prior to the first acquisition, we estimated biomass gains close to zero. Together, our findings unravel the magnitude and duration of delayed impacts of selective logging in forest structural attributes, confirm the high potential of airborne LiDAR multitemporal data to characterize forest degradation in the tropics, and present a novel approach to forest classification using LiDAR data.

Pinage, Ekena Rangel↗
DOE OSTI2026

A machine learning pipeline for identifying infiltration managed aquifer recharge locations from satellite imagery in the San Joaquin Valley, California

This study focuses on an agricultural region in California’s Central Valley, USA, where Managed Aquifer Recharge (MAR) is widely implemented to mitigate groundwater depletion under increasing water demand and climate variability. A deep learning and machine learning framework was developed to identify infiltration-MAR locations using satellite imagery and environmental data. The framework integrates surface water detection from Sentinel-2 imagery, geospatial delineation of water bodies, spatiotemporal tracking of water body dynamics, and supervised classification using meteorological, environmental, and topographic variables. The framework was applied to a 2379 km² study area southwest of Fresno, where 765 water bodies were detected, including 139 identified MAR sites based on publicly available datasets and expert knowledge. The classification model achieved an accuracy of 0.94 and an F1 score of 0.85. Feature importance analysis indicates that cropland, normalized difference vegetation index (NDVI), and evaporation are among the most influential predictors for infiltration-MAR. Notably, the framework suggests that engineered water management in infiltration-MAR systems can disrupt or even reverse the expected positive correlation between surface water extent and precipitation. These findings provide physically interpretable insights into the characteristics of existing infiltration-MAR facilities and demonstrate the potential of the proposed framework as a reproducible, interpretable, and potentially transferable tool for data-driven infiltration-MAR identification and inventory development under growing climatic and hydrological uncertainty.

Classification↗
DOE OSTI2022

Measuring binary fluidization of nonspherical and spherical particles using machine learning aided image processing

Abstract The binary fluidization of Geldart D type nonspherical wood particles and spherical low density polyethylene (LDPE) particles was investigated in a laboratory‐scale bed. The experiment was performed for varying static bed height, wood particles count, as well as superficial gas velocity. The LDPE velocity field were quantified using particle image velocimetry (PIV). The wood particles orientation and velocity are measured using particle tracking velocimetry (PTV). A machine learning pixel‐wise classification model was trained and applied to acquire wood and LDPE particle masks for PIV and PTV processing, respectively. The results show significant differences in the fluidization behavior between LDPE only case and binary fluidization case. The effects of wood particles on the slugging frequency, mean, and variation of bed height, and characteristics of the particle velocities/orientations were quantified and compared. This comprehensive experimental dataset serves as a benchmark for validating numerical models.

Li, Cheng↗
DOE OSTI2024

Predictive analytics of selections of russet potatoes

We explore the application of machine learning algorithms specifically to enhance the selection process of Russet potato (Solanum tuberosum L.) clones in breeding trials by predicting their suitability for advancement. This study addresses the challenge of efficiently identifying high-yield, disease-resistant, and climate-resilient potato varieties that meet processing industry standards. Leveraging manually collected data from trials in the state of Oregon, we investigate the potential of a wide variety of state-of-the-art binary classification models. The dataset includes 1086 clones, with data on 38 attributes recorded for each clone, focusing on yield, size, appearance, and frying characteristics, with several control varieties planted consistently across four Oregon regions from 2013 to 2021. We conduct a comprehensive analysis of the dataset that includes preprocessing, feature engineering, and imputation to address missing values. We focus on several key metrics such as accuracy, F1-score, and Matthews correlation coefficient (MCC) for model evaluation. The top-performing models, namely a feedforward neural network classifier (Neural Net), a histogram-based gradient boosting classifier (HGBC), and a support vector machine classifier (SVM), demonstrate consistent and significant results. To further validate our findings, we conducted a simulation study using the aims, data-generating mechanisms, estimands, methods, and performance measures (ADEMP) framework, simulating different data-generating scenarios to assess model robustness and performance through true positive, true negative, false positive, and false negative distributions, area under the receiver operating characteristic curve (AUC-ROC) and MCC. The simulation results highlight that non-linear models like SVM and HGBC consistently show higher AUC-ROC and MCC than logistic regression, thus outperforming the traditional linear model across various distributions, and emphasizing the importance of model selection and tuning in agricultural trials. Variable selection further enhances model performance and identifies influential features in predicting trial outcomes. The findings emphasize the potential of machine learning in streamlining the selection process for potato varieties, offering benefits such as increased efficiency, substantial cost savings, and judicious resource utilization. Our study contributes insights into precision agriculture and showcases the relevance of advanced technologies for informed decision-making in breeding programs.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

Data driven discovery and quantification of hyperspectral leaf reflectance phenotypes across a maize diversity panel

Abstract Estimates of plant traits derived from hyperspectral reflectance data have the potential to efficiently substitute for traits, which are time or labor intensive to manually score. Typical workflows for estimating plant traits from hyperspectral reflectance data employ supervised classification models that can require substantial ground truth datasets for training. We explore the potential of an unsupervised approach, autoencoders, to extract meaningful traits from plant hyperspectral reflectance data using measurements of the reflectance of 2151 individual wavelengths of light from the leaves of maize ( Zea mays ) plants harvested from 1658 field plots in a replicated field trial. A subset of autoencoder‐derived variables exhibited significant repeatability, indicating that a substantial proportion of the total variance in these variables was explained by difference between maize genotypes, while other autoencoder variables appear to capture variation resulting from changes in leaf reflectance between different batches of data collection. Several of the repeatable latent variables were significantly correlated with other traits scored from the same maize field experiment, including one autoencoder‐derived latent variable (LV8) that predicted plant chlorophyll content modestly better than a supervised model trained on the same data. In at least one case, genome‐wide association study hits for variation in autoencoder‐derived variables were proximal to genes with known or plausible links to leaf phenotypes expected to alter hyperspectral reflectance. In aggregate, these results suggest that an unsupervised, autoencoder‐based approach can identify meaningful and genetically controlled variation in high‐dimensional, high‐throughput phenotyping data and link identified variables back to known plant traits of interest.

Tross, Michael C.↗