Search NASA⌕ Search

SEARCH · Search NASA

Results for “ML”

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 217 records · Page 12
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Machine Learning based Aircraft Performance Model Estimation for Trajectory Prediction

The accurate prediction of aircraft trajectory by ground-based decision support tools is a critical component of air traffic management in the US National Airspace System (NAS). Accurate predictions of where the aircraft will be in the future or when they will arrive at specific locations (e.g., fixes) is a key enabler for sequencing and efficient arrival management of flights. Traditional physics based aircraft trajectory prediction relies on a simplified point-mass total energy model whose parameters are referred to as Aircraft Performance Model (APM) parameters. Even though the performance coefficients and weight of an aircraft are a vital part of the aircraft performance model’s predictions and accuracy, these coefficients are proprietary in nature and therefore, unavailable to decision-support tools. Current approaches freeze some coefficients to default base of aircraft data (BADA) values and optimize others. However, the APM parameters are highly coupled by the flight dynamics and prioritizing one parameter over others leads to bias and skewed predictions. To alleviate this problem, we provide a combined optimization framework to predict all the critical (thrust, drag and weight) APM parameters. This paper is focused on training Machine Learning (ML) models that map historical flights to optimized APM parameters that provide the best fit (in terms of prediction error). Our dataset obtained from NASA’s Sherlock data warehouse is comprised of thousands of historical flights and includes weather and track data collected from 2019. Using different subsets of relevant features (e.g., aircraft type), we trained several ML models to estimate the aircraft’s take off weight, drag polar coefficients (both parasitic and lift induced), and thrust settings (multiplier applied to the maximum engine thrust). The chosen flights are from three of the most common aircraft types (B738, B737, and A320) arriving at four airports (LAX, DEN, MSP, and DFW). Our ML approach is comprised of two different solutions: 1- using a subset of features that are known prior to the flight departure and do not change during flight (such as engine type, current temperature at departure & destination airports, aircraft type) and 2 - using a subset of temporal features of the flight trajectory (such as cruise altitude, Mach, airspeed, and rate of climb) in addition to the pre-departure features from the first solution. The labels or target variables are the APM parameters that were obtained by an optimized ordinary differential equations (ODE) fitting process (applied to individual flights). The ODE-fitting is very time intensive and is therefore performed offline. Thus, training an ML model to learn the relationship between the flight features and ODE-generated labels enables faster estimation of the APM parameters and is therefore amenable to real-time prediction. Various ML models including linear regression, random forest, XGBoost, and neural network were trained, and the results are compared. After model validation and hyperparameter-tuning, we observed that the Random Forest model outperformed the other three models by the overall mean square error (MSE) of 2% for the first solution and 1.5% for the second solution. Finally, the ML-derived parameters are compared against default BADA APM parameters using NASA’s Autonomy Development toolkit (ADK) simulation software. The simulation results for one of each aircraft type is shown and discussed.

Aida Sharif Rohani↗
NASA NTRSDate not supplied

Operational Modal Analysis of the Artemis I Dynamic Rollout Test and Wet Dress Rehearsal

NASA has developed an expendable heavy lift launch vehicle capability, the Space Launch System (SLS), to support lunar and deep space exploration. The uncrewed Artemis I was the first flight of this new launch vehicle and tested critical systems for the upcoming crewed Artemis II flight to the moon. Accelerations were recorded at a multitude of locations on Artemis, the Mobile Launcher (ML), and the Crawler Transporter (CT)during the rollout of Artemis I from the Vehicle Assembly Building (VAB) to Launch Pad 39B March 2022 and is referred to as the Artemis I Dynamic Rollout Test (DRT). While Artemis I was at Launch Pad 39B, the Wet Dress Rehearsal (WDR) was performed to demonstrate launch readiness and acceleration measurements were also recorded. Finally, Artemis I rolled back from Launch Pad 39B to the VAB in April 2022, where acceleration measurements were also recorded and is referred to as the rollback portion of DRT. Because the forces during rollout and at the launch pad acting on Artemis I, the ML, and the CT are not directly measurable, Operational Modal Analysis (OMA) techniques, instead of traditional Experimental Modal Analysis (EMA) techniques, were used to identify modal characteristics. The OMA analysis of DRT and WDR directly builds upon the lessons learned from the OMA analysis of an earlier rollout of the ML from the VAB. DRT and WDR dynamic characteristics will be used to support SLS Integrated Modal Test finite element model correlation efforts and Exploration Ground System ML and CT finite element model verification and validation, which are part of the Building Block approach the Space Launch System program has implemented. The dynamic characteristics extracted from DRT as well as the rollout acceleration time histories themselves will be used in the development of generic rollout forcing functions that will provide refined estimates of the Artemis IV rollout forces, which will have the heavier and larger SLS Block 1B launch vehicle and Mobile Launcher 2 (ML-2). This paper briefly describes Artemis I, the ML, and the CT physical characteristics, DRT rollout/rollback and WDR data collection, the challenges in implementing OMA techniques due in part to the CT harmonics, and how these challenges were overcome to obtain the Artemis I DRT configuration and WDR configuration modal characteristics.

Apollo↗
NASA NTRSDate not supplied

Runway Sign Classifier: A DAL C Certifiable Machine Learning System

In recent years, the remarkable progress of Machine Learning (ML) technologies within the domain of Artificial Intelligence (AI) systems has presented unprecedented opportunities for the aviation industry, paving the way for further advancements in automation, including the potential for single pilot or fully autonomous operation of large commercial airplanes. However, ML technology faces major incompatibilities with existing airborne certification standards, such as ML model traceability and explainability issues or the inadequacy of traditional coverage metrics. Certification of ML-based airborne systems using current standards is problematic due to these challenges. This paper presents a case study of an airborne system utilizing a Deep Neural Network (DNN) for airport sign detection and classification. Building upon our previous work, which demonstrates compliance with Design Assurance Level (DAL) ”D”, we upgrade the system to meet the more stringent requirements of Design Assurance Level ”C”. To achieve DAL C, we employ an established architectural mitigation technique involving two redundant and dissimilar Deep Neural Networks. The application of novel ML-specific data management techniques further enhances this approach. This work is intended to illustrate how the certification challenges of ML-based systems can be addressed for medium criticality airborne applications.

Flight Software↗
NASA NTRSDate not supplied

Operational Modal Analysis of the Artemis I Dynamic Rollout Test and Wet Dress Rehearsal

NASA has developed an expendable heavy lift launch vehicle capability, the Space Launch System (SLS), to support lunar and deep space exploration. The uncrewed Artemis I was the first flight of this new launch vehicle and tested critical systems for the upcoming crewed Artemis II flight to the moon. Accelerations were recorded at a multitude of locations on Artemis, the Mobile Launcher (ML), and the Crawler Transporter (CT)during the rollout of Artemis I from the Vehicle Assembly Building (VAB) to Launch Pad 39B March 2022 and is referred to as the Artemis I Dynamic Rollout Test (DRT). While Artemis I was at Launch Pad 39B, the Wet Dress Rehearsal (WDR) was performed to demonstrate launch readiness and acceleration measurements were also recorded. Finally, Artemis I rolled back from Launch Pad 39B to the VAB in April 2022, where acceleration measurements were also recorded and is referred to as the rollback portion of DRT. Because the forces during rollout and at the launch pad acting on Artemis I, the ML, and the CT are not directly measurable, Operational Modal Analysis (OMA) techniques, instead of traditional Experimental Modal Analysis (EMA) techniques, were used to identify modal characteristics. The OMA analysis of DRT and WDR directly builds upon the lessons learned from the OMA analysis of an earlier rollout of the ML from the VAB. DRT and WDR dynamic characteristics will be used to support SLS Integrated Modal Test finite element model correlation efforts and Exploration Ground System ML and CT finite element model verification and validation, which are part of the Building Block approach the Space Launch System program has implemented. The dynamic characteristics extracted from DRT as well as the rollout acceleration time histories themselves will be used in the development of generic rollout forcing functions that will provide refined estimates of the Artemis IV rollout forces, which will have the heavier and larger SLS Block 1B launch vehicle and Mobile Launcher 2 (ML-2). This paper briefly describes Artemis I, the ML, and the CT physical characteristics, DRT rollout/rollback and WDR data collection, the challenges in implementing OMA techniques due in part to the CT harmonics, and how these challenges were overcome to obtain the Artemis I DRT configuration and WDR configuration modal characteristics.

Apollo↗
NASA NTRSDate not supplied

Using Artificial Intelligence and Machine Learning to Enhance Mission Design and Operations of the Habitable Worlds Observatory (HWO)

One key aspect in the development of HWO is the early deployment of artificial intelligence (AI) and machine learning (ML) to enhance mission science and operations. Our subtask group is part of the HWO AI/ML working group and focuses on AI and ML for mission operations. Our task group seeks to educate other HWO working groups about AI and ML capabilities for mission operations, investigate how to bridge technology gaps, and enable new capabilities particularly in the areas of observational scheduling, instrument health monitoring, and downlink operations. We focus on mission tasking / scheduling both for mission analysis in development and operations. AI and ML for mission scheduling includes: tools to support proposal calls and review, ensuring fairness in calls for proposals, community peer reviews and ease workloads, as well as in-flight and ground software development (e.g., using natural language processing (NLP) to support process automation from requirements). AI and ML for the mission’s development and operations include 1) anomaly detection and prediction (from onboard and ground based tools) to monitor the spacecraft’s health, 2) ground-based automated scheduling for mission operations including long-term and short-term planning and maintenance, and 3) flight system flexible execution (as flight proven for Spitzer and JWST) to enable robust execution despite execution variations, and 4) data analysis for prioritization (e.g., real-time data evaluation leading to autonomous actions and adjustments, high-priority identification, onboard data compression, etc.). Incorporation of ML and AI will enable HWO to address the major science questions related to exoplanet characterization, general astrophysics, and solar system exploration and also extend the boundaries of space mission technologies.

Mark Moussa↗
NASA NTRS2021

Social Bias in AI and its Implications

Previous studies have documented many different types of biases that exist in artificial intelligence (AI) and machine learning (ML) systems. We reviewed the literature on AI and ML bias with a focus on social implications and found that bias in AI and ML can potentially have harmful social impacts on individuals and/or groups of people. By affecting people differently according to characteristics such as race, gender, or sexual orientation, AI and ML systems may lead to harm by exacerbating social inequities. We recount examples of issues that have occurred in systems that use technology that might be used at NASA and elsewhere so that similar issues might be identified and mitigated in future systems. We also provide interested parties with a gateway into existing work on social bias in AI and ML systems.

artificial intelligence (AI)↗
DOE OSTI2024

In Silico Chemical Experiments in the Age of AI: From Quantum Chemistry to Machine Learning and Back

Computational chemistry is an indispensable tool for understanding molecules and predicting chemical properties. However, traditional computational methods face significant challenges due to the difficulty of solving the Schrödinger equations and the increasing computational cost with the size of the molecular system. In response, there has been a surge of interest in leveraging artificial intelligence (AI) and machine learning (ML) techniques to in silico experiments. Integrating AI and ML into computational chemistry increases the scalability and speed of the exploration of chemical space. However, challenges remain, particularly regarding the reproducibility and transferability of ML models. This review highlights the evolution of ML in learning from, complementing, or replacing traditional computational chemistry for energy and property predictions. Starting from models trained entirely on numerical data, a journey set forth toward the ideal model incorporating or learning the physical laws of quantum mechanics. This paper also reviews existing computational methods and ML models and their intertwining, outlines a roadmap for future research, and identifies areas for improvement and innovation. Ultimately, the goal is to develop AI architectures capable of predicting accurate and transferable solutions to the Schrödinger equation, thereby revolutionizing in silico experiments within chemistry and materials science.

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

Machine Learning in the Context of Laser-Induced Breakdown Spectroscopy

The integration of machine learning (ML) with Laser-Induced Breakdown Spectroscopy (LIBS) has revolutionized the analytical capabilities of LIBS. The combi-nation of both methods enables more accurate and efficient data analysis. While LIBS itself is a powerful technique for elemental analysis, the vast amount of spectral data it generates can be hard to interpret. Machine learning addresses these challenges by leveraging algorithms that can learn from data, identify patterns, and make predictions without explicit programming for the interpretation of each specific task. In LIBS application, ML techniques are used to enhance various analytical processes. For example, ML algorithms can classify materials based on their spectral fingerprints, predict the concentration of elements in a sample, and identify underlying patterns within complex datasets. Here, this application improves the precision of LIBS analyses while significantly reducing the time required for data processing and interpretation. In this chapter, the fundamental concepts of ML will be discussed first. Following this, the process of data splitting and the importance of feature selection will be examined. Several machine learning methods will then be closely examined, exploring how each can benefit LIBS analysis and highlighting their respective advantages and shortcomings. This structured approach will provide a comprehensive understanding of the integration of ML in the context of LIBS analysis.

47 OTHER INSTRUMENTATION↗
DOE OSTI2024

Constraining Galaxy-Halo connection using machine learning

We investigate the potential of machine learning (ML) methods to model small-scale galaxy clustering for constraining Halo Occupation Distribution (HOD) parameters. Our analysis reveals that while many ML algorithms report good statistical fits, they often yield likelihood contours that are significantly biased in both mean values and variances relative to the true model parameters. This highlights the importance of careful data processing and algorithm selection in ML applications for galaxy clustering, as even seemingly robust methods can lead to biased results if not applied correctly. ML tools offer a promising approach to exploring the HOD parameter space with significantly reduced computational costs compared to traditional brute-force methods if their robustness is established. Using our ANN-based pipeline, we successfully recreate some standard results from recent literature. Properly restricting the HOD parameter space, transforming the training data, and carefully selecting ML algorithms are essential for achieving unbiased and robust predictions. Among the methods tested, artificial neural networks (ANNs) outperform random forests (RF) and ridge regression in predicting clustering statistics, when the HOD prior space is appropriately restricted. We demonstrate these findings using the projected two-point correlation function (w p (r p )), angular multipoles of the correlation function (ξ ℓ (r)), and the void probability function (VPF) of Luminous Red Galaxies from Dark Energy Spectroscopic Instrument mocks. Our results show that while combining w p (r p ) and VPF improves parameter constraints, adding the multipoles ξ 0 , ξ 2 , and ξ 4 to w p (r p ) does not significantly improve the constraints.

cosmology↗
DOE OSTI2026

Generation of random geological models using multi-randomization for machine learning

Generating high-fidelity geological models is essential for advancing machine learning (ML) methods in automated seismic interpretation. For instance, seismic images paired with corresponding fault labels are foundational for ML-based fault detection from seismic migration sections. While several open-access datasets of random geological models exist, open-source tools specifically designed to produce large volumes of such models for ML applications remain scarce. To address this gap, we present RGM (Random Geological Model), an open-source software package for efficiently generating 2D and 3D synthetic geological models tailored for ML workflows. RGM supports the creation of diverse model components, including medium property distributions (P-/S-wave velocities and density), seismic reflectivity images (i.e., synthetic migration sections), relative geological time, and discrete fault attributes such as probability, dip, strike, rake, and displacement. It also accommodates the creation of complex geological features such as salt bodies and unconformities. The model generation algorithm employs a multi-randomization strategy, yielding an effectively infinite-dimensional model space that encompasses a wide range of geological scenarios and associated seismic features. Furthermore, RGM incorporates a method to generate synthetic elastic migration images using analytical elastic reflection coefficients combined with frequency-dependent scaling. This functionality enables the creation of training datasets for ML models that leverage elastic seismic images. RGM is implemented in modern object-oriented Fortran, allowing users to flexibly control statistical parameters governing model variability. We demonstrate the capability, performance, and geological realism of the package through comprehensive 2D and 3D examples.

58 GEOSCIENCES↗
DOE OSTI2024

Machine learning in materials research: Developments over the last decade and challenges for the future

The number of studies that apply machine learning (ML) to materials science has been growing at a rate of approximately 1.67 times per year over the past decade. In this review, I examine this growth in various contexts. First, I present an analysis of the most commonly used tools (software, databases, materials science methods, and ML methods) used within papers that apply ML to materials science. The analysis demonstrates that despite the growth of deep learning techniques, the use of classical machine learning is still dominant as a whole. It also demonstrates how new research can effectively build upon past research, particular in the domain of ML models trained on density functional theory calculation data. Next, I present the progression of best scores as a function of time on the matbench materials science benchmark for formation enthalpy prediction. In particular, a dramatic improvement of 7 times reduction in error is obtained when progressing from feature-based methods that use conventional ML (random forest, support vector regression, etc.) to the use of graph neural network techniques. Finally, I provide views on future challenges and opportunities, focusing on data size and complexity, extrapolation, interpretation, access, and relevance.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Low Activity Waste Glass Optimization with Property Models from Machine Learning, Part 2: Experimental Validation and Active Learning

The United States Department of Energy is responsible for managing legacy nuclear waste stored in underground tanks at the Hanford Site. To treat the waste, it is planned as the current baseline to separately vitrify low-activity waste (LAW) and high-level waste fractions. Previously, machine learning (ML) based glass property models (e.g., chemical durability, viscosity, electrical conductivity and SO3 solubility) were developed with prediction uncertainties. A waste glass optimization approach was then established to enable the capability of using these ML models in LAW glass formulation. In this study, the previous ML models were first experimentally validated, and the results were incorporated back into the database to update the ML models. The updated models and formulations showed increased waste loading while reducing the failure rate, demonstrating improved predictive accuracy, reduced uncertainties, and the effectiveness of active learning in guiding high-dimensional, nonlinear LAW glass design. This represents the first experimental validation of ML based LAW glass formulation, with practical benefits such as higher waste loading, shorter mission duration, and lower operational risk.

Lu, Xiaonan (ORCID:0000000179708148)↗
DOE OSTI2026

OmicsMLMentor: A Web Application for Guided Machine Learning Analysis of Omics Data

Expression-based omics technologies (e.g. proteomics, metabolomics, transcriptomics, etc.) increasingly rely on supervised and unsupervised machine learning (ML) models to find key biomolecules distinguishing conditions, identify natural groupings in biological data, or generate predictions for outcomes of interest. Fitting ML models to omics data presents several challenges, including handling missing data, selecting a normalization method, choosing a valid model, and optimizing hyperparameters, all requiring statistical programming skills to address these challenges. Thus, the open-source web application SLOPE was designed to lower the barrier to ML modeling for omics data. SLOPE supports the fitting of 15 ML models (10 supervised and 5 unsupervised) tailored to omics datasets, such as proteomics, metabolomics, lipidomics, and transcriptomics. SLOPE offers several omics-specific features, including methods for handling missingness (imputation, conversion, removal), normalization tests, ranking of models based on the structure of a user’s data and user input, and optimal hyperparameter selections using cross-validation splits. By streamlining ML workflows for omics analysis, SLOPE address critical gaps in existing online web tools, facilitating a broader adoption of these models for omics research. Here, SLOPE is applied to data from a lignin exposure study to highlight the workflow for fitting both supervised and unsupervised models to data.

lipidomics↗
DOE OSTI2025

Dehydration of Methyl Lactate on Alkali Cation-Exchanged Faujasite: Effects of Metal Cation Identity and Water Pressure

Turnover rates for the catalytic dehydration of methyl lactate (ML) over ion-exchanged faujasite (FAU) catalysts depend on the identity of alkali metal cations (Na + , K + , Cs + ) and local solvation effects. Analysis of rate measurements and in situ infrared spectroscopy gives evidence that the reaction involves kinetically relevant dissociation of adsorbed methyl lactate upon alkali metal cations. This process involves concerted methyl transfer to the surface and dissociation of the alkali metal from the framework, which occurs at cationic active sites that remain predominantly unoccupied under relevant conditions (0.5–10 kPa ML, 0.5–15 kPa H 2 O, 563–583 K). Despite the mechanistic similarities, apparent activation enthalpies (ΔH app ‡ ) decrease linearly (47 kJ mol –1 from Na + to Cs + ) with ionization energy and cationic radius, and apparent activation entropies (ΔS app ‡ ) decrease 74 J mol –1 K –1 . These trends reflect electrostatic interactions that stabilize the cations to the anionic sites on the zeolite: stronger association between these charges leads to increasingly endothermic processes to displace the alkali metal to form a cationic methoxy and an intrapore metal lactate intermediate. Water physisorption measurements suggest alkali metal ions bind superstoichiometric quantities of water within FAU pores, and in situ infrared spectra suggest the concerted adsorption of ML requires reorganization of this water. Consequently, these processes introduce entropic gains that partially offset entropy losses associated with ML adsorption. Hence, turnover rates differ only by a factor of 2 among Na-, K-, and Cs-FAU at 573 K (ΔΔG app ‡ = 5 kJ mol –1 ). These findings demonstrate the interplay of alkali metal ions with zeolite active sites and intrapore water clusters for ML dehydration, indicating that these interactions can be leveraged to deliver optimal performance under different reaction conditions.

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

Prediction of Specificity of α-Conotoxins to Subtypes of Human Nicotinic Acetylcholine Receptors with Semi-supervised Machine Learning

Conotoxins are a family of highly toxic neurotoxins composed of cysteine-rich peptides produced by marine cone snails. The most lethal cone snail species to humans is Conus geographus, with fatality rates of up to ∼65% from a single sting, which is caused mostly by the activity of α-conotoxins against human nicotinic acetylcholine receptors (nAChRs). While sequence-based machine learning (ML) classifiers have been trained to identify targets of conotoxins binding voltage-gated ion channels, no ML model has been built to predict the subtype-specific nAChR targets of α-conotoxins. Here, we trained an ML model in a semi-supervised manner to predict the specificity of α-conotoxin binding toward different human nAChR subtypes to overcome the challenge of limited data in subtype-specific nAChR targets of α-conotoxins and the issue that one α-conotoxin can bind multiple nAChR subtypes with high selectivity. We considered additional features of sequences of α-conotoxins in training our ML model, including the secondary structure propensities and electrostatic properties, which resulted in better prediction capability for the ML model. Notably, we identify that most α-conotoxins bind to α3β2, α1γδ, and α7 subtypes of human nAChRs. Our findings from this study provide a framework for predicting targets of various kinds of toxins.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Design and Validation of a High-Throughput Reductive Catalytic Fractionation Method

Reductive catalytic fractionation (RCF) is a promising method to extract and depolymerize lignin from biomass, and bench-scale studies have enabled considerable progress in the past decade. RCF experiments are typically conducted in pressurized batch reactors with volumes ranging between 50 and 1000 mL, limiting the throughput of these experiments to one to six reactions per day for an individual researcher. Here, we report a high-throughput RCF (HTP-RCF) method in which batch RCF reactions are conducted in 1 mL wells machined directly into Hastelloy reactor plates. The plate reactors can seal high pressures produced by organic solvents by vertically stacking multiple reactor plates, leading to a compact and modular system capable of performing 240 reactions per experiment. Using this setup, we screened solvent mixtures and catalyst loadings for hydrogen-free RCF using 50 mg poplar and 0.5 mL reaction solvent. The system of 1:1 isopropanol/methanol showed optimal monomer yields and selectivity to 4-propyl substituted monomers, and validation reactions using 75 mL batch reactors produced identical monomer yields. To accommodate the low material loadings, we then developed a workup procedure for parallel filtration, washing, and drying of samples and a 1H nuclear magnetic resonance spectroscopy method to measure the RCF oil yield without performing liquid-liquid extraction. As a demonstration of this experimental pipeline, 50 unique switchgrass samples were screened in RCF reactions in the HTP-RCF system, revealing a wide range of monomer yields (21-36%), S/G ratios (0.41-0.93), and oil yields (40-75%). These results were successfully validated by repeating RCF reactions in 75 mL batch reactors for a subset of samples. We anticipate that this approach can be used to rapidly screen substrates, catalysts, and reaction conditions in high-pressure batch reactions with higher throughput than standard batch reactors.

BIOMASS FUELS,INORGANIC, ORGANIC, PHYSICAL, AND AN↗
DOE OSTI2024

Increasing the Reproducibility and Replicability of Supervised AI/ML in the Earth Systems Science by Leveraging Social Science Methods

Artificial intelligence (AI) and machine learning (ML) pose a challenge for achieving science that is both reproducible and replicable. The challenge is compounded in supervised models that depend on manually labeled training data, as they introduce additional decision-making and processes that require thorough documentation and reporting. We address these limitations by providing an approach to hand labeling training data for supervised ML that integrates quantitative content analysis (QCA)—a method from social science research. The QCA approach provides a rigorous and well-documented hand labeling procedure to improve the replicability and reproducibility of supervised ML applications in Earth systems science (ESS), as well as the ability to evaluate them. Specifically, the approach requires (a) the articulation and documentation of the exact decision-making process used for assigning hand labels in a “codebook” and (b) an empirical evaluation of the reliability” of the hand labelers. In this paper, we outline the contributions of QCA to the field, along with an overview of the general approach. We then provide a case study to further demonstrate how this framework has and can be applied when developing supervised ML models for applications in ESS. With this approach, we provide an actionable path forward for addressing ethical considerations and goals outlined by recent AGU work on ML ethics in ESS.

58 GEOSCIENCES↗
DOE OSTI2024

A Machine Learning Bias Correction on Large–Scale Environment of High–Impact Weather Systems in E3SM Atmosphere Model

Large–scale dynamical and thermodynamical processes are common environmental drivers of high–impact weather systems causing extreme weather events. However, such large–scale environmental conditions often display systematic biases in climate simulations, posing challenges to evaluating high–impact weather systems and extreme weather events. In this paper, a machine learning (ML) approach was employed to bias correct the large–scale wind, temperature, and humidity simulated by the atmospheric component of the Energy Exascale Earth System Model (E3SM) at ~1° resolution. The usefulness of the ML approach for extreme weather analysis was demonstrated with a focus on three high–impact weather systems, including tropical cyclones (TCs), extratropical cyclones (ETCs), and atmospheric rivers (ARs). We show that the ML model can effectively reduce climate bias in large–scale wind, temperature, and humidity while preserving their responses to imposed climate change perturbations. The bias correction is found to directly improve water vapor transport associated with ARs, and representations of thermodynamical flows associated with ETCs. When the bias–corrected large–scale winds are used to drive a synthetic TC track forecast model over the Atlantic basin, the resulting TC track density agrees better with that of the TC track model driven by observed winds. In addition, the ML model insignificantly interferes with the mean climate change signals of large–scale storm environments as well as the occurrence and intensity of three weather systems. This study suggests that the proposed ML approach can be used to improve the downscaling of extreme weather events by providing more realistic large–scale storm environments simulated by low–resolution climate models.

54 ENVIRONMENTAL SCIENCES↗