Search NASA⌕ Search

SEARCH · Search NASA

Results for “Explainable machine learning”

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 307 records · Page 17

Using feature importance as an exploratory data analysis tool on Earth system models

Abstract. Machine learning (ML) models are commonly used to generate predictions, but these models can also support the discovery of new science. Generating accurate predictions necessitates that a model captures the structure of the underlying data. If the structure is properly extracted, ML could be a useful exploratory and evidential tool. In this paper, we present a case study that demonstrates the use of ML for exploratory data analysis (EDA) in the climate space. We apply the ML explainability method of spatiotemporal zeroed feature importance (stZFI) to understand how climate-variable associations evolve over space and time. Our analyses focus on data from ensembles of Earth system models (ESMs) which provide data on different climate states and conditions. We elect to work with ESM ensembles since they allow us to compare feature importance across alternative scenarios not available with observed data. The ensembles also account for natural variability so that we can distinguish between signal and noise due to natural climate variability when computing feature importance. The use of perturbed initial condition ensembles introduces variability mimicking the natural variability in the atmosphere; thus the signals emerging using feature importance (FI) can be evaluated against the natural variability in the climate system. For our analyses, we consider the 1991 volcanic eruption of Mount Pinatubo, which was a large stratospheric aerosol injection. We explore the climate pathway associated with the eruption from aerosols to radiation to temperature at both the near-surface and stratospheric levels. In addition to applying the method to data generated from two different ESMs, we apply stZFI to reanalysis data to compare the associations identified by stZFI. We show how stZFI tracks the importance of aerosol optical depth over time on forecasting temperatures. This case study illustrates usefulness of an ML tool (stZFI) for EDA on a well-studied climate exemplar.

Ries, Daniel (ORCID:0000000250294647)↗

Towards Prediction of Non-Radiative Decay Pathways in Organic Compounds I: The Case of Naphthalene Quantum Yields

Many emerging technologies depend on human’s ability to control and manipulate the excited-state properties of molecular systems. These technologies include fluorescent labeling in biomedical imaging, light harvesting in photovoltaics, and electroluminescence in light-emitting devices. All of these systems suffer from non-radiative loss pathways that dissipate electronic energy as heat, which causes the overall system efficiency to be directly linked to quantum yield (Φ) of the molecular excited state. Unfortunately, Φ is very difficult to predict from first principles because the description of a slow non-radiative decay mechanism requires an accurate description of long-timescale excited-state quantum dynamics. In the present study, we introduce an efficient semi-empirical method of calculating the fluorescence quantum yield (Φ fl ) for molecular chromophores, which converts simple electronic energies computed using time-dependent density functional theory (TDDFT) into an estimate of Φ fl . As with all machine learning strategies, the algorithm needs to be trained on fluorescent dyes for which Φ fl ’s are known, so as to provide a black-box method which can later predict Φfl’s for chemically similar chromophores that have not been studied experimentally. Here, as a first illustration of how our proposed algorithm can be trained, we examine a family of 25 naphthalene derivatives. The simplest application of the energy gap law is found to be inadequate to explain the rates of internal conversion (IC) or intersystem crossing (ISC) – the electronic properties of at least one higher-lying electronic state (S n or T n ) or one far-from-equilibrium geometry are typically needed to obtain accurate results. Indeed, the key descriptors turn out to be the transition state between the Franck–Condon minimum and a distorted local minimum near an S 0 /S 1 conical intersection (which governs IC) and the magnitude of the spin-orbit coupling (which governs ISC). The resulting Φ fl ’s are predicted with reasonable accuracy (~ 22%), making our approach a promising ingredient for high-throughput screening and rational design of the molecular excited states with desired Φ fl ’s. We thus conclude that our model, while semi-empirical in nature, does in fact extract sound physical insight into the challenge of describing non-radiative relaxations.

36 MATERIALS SCIENCE↗

Projecting Large Fires in the Western US With an Interpretable and Accurate Hybrid Machine Learning Method

More frequent and widespread large fires are occurring in the western United States (US), yet reliable methods for predicting these fires, particularly with extended lead times and a high spatial resolution, remain challenging. In this study, we proposed an interpretable and accurate hybrid machine learning (ML) model, that explicitly represented the controls of fuel flammability, fuel availability, and human suppression effects on fires. The model demonstrated notable accuracy with a F 1 -score of 0.846 ± 0.012, surpassing process-driven fire danger indices and four commonly used ML models by up to 40% and 9%, respectively. More importantly, the ML model showed remarkably higher interpretability relative to other ML models. Specifically, by demystifying the “black box” of each ML model using the explainable AI techniques, we identified substantial structural differences across ML fire models, even among those with similar accuracy. The relationships between fires and their drivers, identified by our model, were aligned closer with established fire physical principles. The ML structural discrepancy led to diverse fire predictions and our model predictions exhibited greater consistency with actual fire occurrence. With the highly interpretable and accurate model, we revealed the strong compound effects from multiple climate variables related to evaporative demand, energy release component, temperature, and wind speed, on the dynamics of large fires and megafires in the western US. Our findings highlight the importance of assessing the structural integrity of models in addition to their accuracy. They also underscore the critical need to address the rise in compound climate extremes linked to large wildfires.

54 ENVIRONMENTAL SCIENCES↗

Emerging Technologies for Privacy Preservation in Energy Systems

This study explores the intersection of digitalization and privacy within the energy sector, focusing on the emerging challenges and opportunities presented by integrating Distributed Energy Resources (DERs) and advanced metering infrastructure. The need for robust digital privacy measures has become crucial as the energy industry evolves towards a more decentralized, digitalized, and decarbonized future. This study delves into four cutting-edge privacy-preserving technologies—Homomorphic Encryption (HE), Secure Multiparty Computation (SMPC), Differential Privacy (DP), and Federated Learning (FL)—each offering unique solutions to safeguard consumer data by increasing digital connectivity and data exchange. Through a detailed examination of these methods, the study explains how each technology operates, its applications within the energy sector, and the specific privacy challenges it addresses. Homomorphic Encryption allows for secure computations on encrypted data, enabling data analysis without compromising privacy. Secure Multiparty Computation enables collaborative data analysis across different entities while protecting the confidentiality of the inputs. Differential Privacy introduces randomness into the assembled data set, preventing the identification of individual records in statistical databases. Lastly, Federated Learning offers a paradigm shift in data analysis, where machine learning models are trained at the edge, minimizing the centralization of sensitive data. The research underscores the significance of implementing these privacy-enhancing technologies to comply with strict data protection regulations, foster consumer trust, and enhance the security of the energy infrastructure. By providing a comprehensive overview of these methodologies and their practical implications for the energy sector, this study aims to contribute to the ongoing discourse on digital privacy, offering insights into how the energy industry can navigate the complexities of data privacy in the digital age.

Cali, Umit↗

Machine Learning meets Algebraic Combinatorics: A Suite of Benchmark Datasets to Accelerate AI for Mathematics Research

The use of benchmark datasets has become an important engine of progress in machine learning (ML) over the past 15 years. Recently there has been growing interest in utilizing machine learning to drive advances in research-level mathematics. However, off-the-shelf solutions often fail to deliver the types of insights required by mathematicians. This suggests the need for new ML methods specifically designed with mathematics in mind. The question then is: what benchmarks should the community use to evaluate these? On the one hand, toy problems such as learning the multiplicative structure of small finite groups have become popular in the mechanistic interpretability community whose perspective on explainability aligns well with the needs of mathematicians. While toy datasets are a useful benchmark for initial work, they lack the scale, complexity, and sophistication of many of the principal objects of study in modern mathematics. To address this, we introduce a new collection of benchmark datasets, Algebraic Combinatorics Benchmarks (ACBench), representing either classic or open problems in algebraic combinatorics, a subfield of mathematics that studies discrete structures arising from abstract algebra. After describing the datasets, we discuss the challenges involved in constructing “good” mathematics benchmarks, describe baseline model performance, and discuss some of the insights these datasets can provide that may be of interest even to those who are not interested in mathematics research itself.

97 MATHEMATICS AND COMPUTING↗

Explaining Health Risk Behaviors in the U.S. with Social Deprivation at Local and Regional Levels

Health risk behaviors are precursors to many chronic health outcomes, and hence, they pose a challenge to public health. Social deprivation undoubtedly creates circumstances that limit access to healthy habits. Moreover, broad regional effects (weather patterns, political ideology, social norms), and local characteristics (cultural notions and barriers, urban places) also influence lifestyle choices and must be accounted for to truly understand the impact of social deprivation on risky behaviors. This research fills the knowledge gap in epidemiological modeling of health risk behaviors by leveraging machine learning to find associations between social deprivation and health risk behaviors, when adjusted by regional and local effects. Four health risk behaviors, namely, binge drinking, smoking, lack of sleep, and lack of physical activity from the CDC PLACES project are considered in a single framework to understand and compare the interplay between local/regional characteristics and seven measures of social deprivation. Our results indicate that local and/or regional factors rise to the top for three out of four risk behaviors (binge drinking, smoking and lack of sleep) out-competing social deprivation measures. Un-entangling the geographical effects reveals that poverty, educational attainment and non-employment are the three deprivation measures most significantly associated with all four health risk factors. The research thus indicates that public health policies to promote healthy lifestyle behaviors must seek to remedy social deprivation, but using socially and culturally sensitive interventions.

Gokhale, Swapna↗

Maximizing efficiency of dataset compression for machine learning potentials with information theory

Machine learning interatomic potentials (MLIPs) balance high accuracy and lower costs compared to density functional theory calculations, but their performance often depends on the size and diversity of training datasets. Large datasets improve model accuracy and generalization but are computationally expensive to produce and train on, while smaller datasets risk discarding rare but important atomic environments and compromising MLIP accuracy/reliability. Here, we develop an information-theoretical framework to quantify the efficiency of dataset compression methods and propose an algorithm that maximizes this efficiency. By framing atomistic dataset compression as an instance of the minimum set cover (MSC) problem over atom-centered environments, our method identifies the smallest subset of structures that contains as much information as possible from the original dataset while pruning redundant information. The approach is extensively demonstrated on the GAP-20 and TM23 datasets and validated on 64 varied datasets from the ColabFit repository. Across all cases, MSC consistently retains outliers, preserves dataset diversity, and reproduces the long-tail distributions of forces even at high compression rates, outperforming other subsampling methods. Furthermore, MLIPs trained on MSC-compressed datasets exhibit reduced error for out-of-distribution data even in low-data regimes. We explain these results using an outlier analysis and show that such quantitative conclusions could not be achieved with conventional dimensionality reduction methods. The algorithm is implemented in the open-source QUESTS package and can be used for several tasks in atomistic modeling, from data subsampling, outlier detection, and training improved MLIPs at a lower cost.

36 MATERIALS SCIENCE↗

A daily, 250 m and real-time gross primary productivity product (2000–present) covering the contiguous United States

Abstract. Gross primary productivity (GPP) quantifies the amount of carbon dioxide (CO2) fixed by plants through photosynthesis. Although as a key quantity of terrestrial ecosystems, there is a lack of high-spatial-and-temporal-resolution, real-time and observation-based GPP products. To address this critical gap, here we leverage a state-of-the-art vegetation index, near-infrared reflectance of vegetation (NIRV), along with accurate photosynthetically active radiation (PAR), to produce a SatelLite Only Photosynthesis Estimation (SLOPE) GPP product for the contiguous United States (CONUS). Compared to existing GPP products, the proposed SLOPE product is advanced in its spatial resolution (250 m versus >500 m), temporal resolution (daily versus 8 d), instantaneity (latency of 1 d versus >2 weeks) and quantitative uncertainty (on a per-pixel and daily basis versus no uncertainty information available). These characteristics are achieved because of several technical innovations employed in this study: (1) SLOPE couples machine learning models with MODIS atmosphere and land products to accurately estimate PAR. (2) SLOPE couples highly efficient and pragmatic gap-filling and filtering algorithms with surface reflectance acquired by both Terra and Aqua MODIS satellites to derive a soil-adjusted NIRV (SANIRV) dataset. (3) SLOPE couples a temporal pattern recognition approach with a long-term Cropland Data Layer (CDL) product to predict dynamic C4 crop fraction. Through developing a parsimonious model with only two slope parameters, the proposed SLOPE product explains 85 % of the spatial and temporal variations in GPP acquired from 49 AmeriFlux eddy-covariance sites (324 site years), with a root-mean-square error (RMSE) of 1.63 gC m−2 d−1. The median R2 over C3 and C4 crop sites reaches 0.87 and 0.94, respectively, indicating great potentials for monitoring crops, in particular bioenergy crops, at the field level. With such a satisfactory performance and its distinct characteristics in spatiotemporal resolution and instantaneity, the proposed SLOPE GPP product is promising for biological and environmental research, carbon cycle research, and a broad range of real-time applications at the regional scale. The archived dataset is available at https://doi.org/10.3334/ORNLDAAC/1786 (download page: https://daac.ornl.gov/daacdata/cms/SLOPE_GPP_CONUS/data/, last access: 20 January 2021) (Jiang and Guan, 2020), and the real-time dataset is available upon request.

54 ENVIRONMENTAL SCIENCES↗

Application-level benchmarking of quantum computers using nonlocal game strategies

In a nonlocal game, two noncommunicating players cooperate to convince a referee that they possess a strategy that does not violate the rules of the game. Quantum strategies allow players to optimally win some games by performing joint measurements on a shared entangled state, but computing these strategies can be challenging. We present a variational quantum algorithm to compute quantum strategies for nonlocal games by encoding the rules of a nonlocal game into a Hamiltonian. We show how this algorithm can generate a short-depth optimal quantum strategy for a graph coloring game with a quantum advantage. This quantum strategy is then evaluated on fourteen different quantum hardware platforms to demonstrate its utility as a benchmark. Finally, we discuss potential sources of errors that can explain the observed decreased performance of the executed task and derive an expression for the number of samples required to accurately estimate the win rate in the presence of noise.

nonlocal games↗

Deep Learning with Reflection High-Energy Electron Diffraction Images to Predict Cation Ratio in Sr 2 x Ti 2(1– x ) O 3 Thin Films

Machine learning (ML) with in-situ diagnostics offers a transformative approach to accelerate, understand, and control thin film synthesis by uncovering relationships between synthesis conditions and material properties. In this study, we demonstrate the application of deep learning to predict the stoichiometry of Sr 2x Ti 2(1–x) O 3 thin films using reflection high-energy electron diffraction images acquired during pulsed laser deposition. A gated convolutional neural network trained for regression of the Sr atomic fraction achieved accurate predictions with a small dataset of 31 samples. Explainable AI techniques revealed a previously unknown correlation between diffraction streak features and cation stoichiometry in Sr 2x Ti 2(1–x) O 3 thin films. Here, our results demonstrate how ML can be used to transform a ubiquitous in-situ diagnostic tool, that is usually limited to qualitative assessments, into a quantitative surrogate measurement of continuously valued thin film properties. Such methods are critically needed to enable real-time control, autonomous workflows, and accelerate traditional synthesis approaches.

77 NANOSCIENCE AND NANOTECHNOLOGY↗

The Andromeda gamma-ray excess: background systematics of the millisecond pulsars and dark matter interpretations

ABSTRACT Since the discovery of an excess in gamma rays in the direction of M31, its cause has been unclear. Published interpretations focus on dark matter or stellar related origins. Studies of a similar excess in the Milky Way centre motivate a correlation of the spatial morphology of the signal with the distribution of stellar mass in M31. However, a robust determination of the best theory for the observed excess emission is challenging due to uncertainties in the astrophysical gamma-ray foreground model. We perform a spectro-morphological analysis of the M31 gamma-ray excess using state-of-the-art templates for the distribution of stellar mass in M31 and novel astrophysical foreground models for its sky region. We construct maps for the old stellar populations of M31 based on data from the PAndAS survey and carefully remove the foreground stars. We also produce improved astrophysical foreground models via novel image inpainting techniques based on machine learning methods. Our stellar maps, mimicking the location of a population of millisecond pulsars in the bulge of M31, reach a 5.4σ significance, making them as strongly favoured as the simple phenomenological models usually considered in the literature, e.g. disc-like templates. This detection is robust to generous variations of the astrophysical foreground model. Once the stellar templates are included in the astrophysical model, we show that the dark matter annihilation interpretation of the signal is unwarranted. We demonstrate that about one million unresolved millisecond pulsars naturally explain the observed gamma-ray luminosity per stellar mass, energy spectrum, and stellar bulge-to-disc flux ratio.

79 ASTRONOMY AND ASTROPHYSICS↗

Edge ML for CAN bus intrusion detection in AVs

Autonomous Vehicles (AVs) are revolutionizing transportation, but their reliance on interconnected cyber-physical systems exposes them to unprecedented cybersecurity risks. This study addresses the critical challenge of detecting real-time cyber intrusions in self-driving vehicles by leveraging a dataset from the Udacity self-driving car project. We simulate four high-impact attack vectors, Denial of Service (DoS), spoofing, replay, and fuzzy attacks, by injecting noise into spatial features (e.g., bounding box coordinates) to replicate adversarial scenarios. We develop and evaluate two lightweight neural network architectures (NN-1 and NN-2) alongside a logistic regression baseline (LG-1) for intrusion detection. The models achieve exceptional performance, with NN-2 attaining an AUC score of 93.15% and 93.15% accuracy, demonstrating their suitability for edge deployment in AV environments. Through explainable AI techniques, we uncover unique forensic fingerprints of each attack type, such as spatial corruption in fuzzy attacks and temporal anomalies in replay attacks, offering actionable insights for feature engineering and proactive defense. Visual analytics, including confusion matrices, ROC curves, and feature importance plots, validate the models' robustness and interpretability. This research sets a new benchmark for AV cybersecurity, delivering a scalable, field-ready toolkit for Original Equipment Manufacturers (OEMs) and policymakers. By aligning intrusion fingerprints with SAE J3061 automotive security standards, we provide a pathway for integrating machine learning into safety-critical AV systems. Our findings underscore the urgent need for security-by-design AI, ensuring that AVs not only drive autonomously but also defend autonomously. This work bridges the gap between theoretical cybersecurity and life-preserving engineering, offering a leap toward safer, more secure autonomous transportation.

97 MATHEMATICS AND COMPUTING↗

Flow over an espresso cup: inferring 3-D velocity and pressure fields from tomographic background oriented Schlieren via physics-informed neural networks

Tomographic background oriented Schlieren (Tomo-BOS) imaging measures density or temperature fields in three dimensions using multiple camera BOS projections, and is particularly useful for instantaneous flow visualizations of complex fluid dynamics problems. We propose a new method based on physics-informed neural networks (PINNs) to infer the full continuous three-dimensional (3-D) velocity and pressure fields from snapshots of 3-D temperature fields obtained by Tomo-BOS imaging. The PINNs seamlessly integrate the underlying physics of the observed fluid flow and the visualization data, hence enabling the inference of latent quantities using limited experimental data. In this hidden fluid mechanics paradigm, we train the neural network by minimizing a loss function composed of a data mismatch term and residual terms associated with the coupled Navier–Stokes and heat transfer equations. We first quantify the accuracy of the proposed method based on a two-dimensional synthetic data set for buoyancy-driven flow, and subsequently apply it to the Tomo-BOS data set, where we are able to infer the instantaneous velocity and pressure fields of the flow over an espresso cup based only on the temperature field provided by the Tomo-BOS imaging. Moreover, we conduct an independent PIV experiment to validate the PINN inference for the unsteady velocity field at a centre plane. To explain the observed flow physics, we also perform systematic PINN simulations at different Reynolds and Richardson numbers and quantify the variations in velocity and pressure fields. Furthermore, the results in this paper indicate that the proposed deep learning technique can become a promising direction in experimental fluid mechanics.

97 MATHEMATICS AND COMPUTING↗

How Many Elements Matter?

Some studies of stars' multielement abundance distributions suggest at least 5–7 significant dimensions, but others show that many elemental abundances can be predicted to high accuracy from [Fe/H] and [Mg/Fe] (or [Fe/H] and age) alone. We show that both propositions can be, and are, simultaneously true. We adopt a machine-learning technique known as normalizing flow to reconstruct the probability distribution of Milky Way disk stars in the space of 15 elemental abundances measured by APOGEE. Conditioning on T eff and $\mathrm{log}\,g$ minimizes the differential systematics. After further conditioning on [Fe/H] and [Mg/Fe], the residual scatter for most abundances is σ [X/H] ≲ 0.02 dex, consistent with APOGEE's reported statistical uncertainties of ~0.01–0.015 dex and intrinsic scatter of 0.01–0.02 dex. Despite the small scatter, residual abundances display clear correlations between elements, which we show are too large to be explained by measurement uncertainties or by the finite sampling noise. We must condition on at least seven elements to reduce the correlations to a level consistent with the observational uncertainties. Our results demonstrate that cross-element correlations are a much more sensitive probe of a hidden structure than dispersion, and they can be measured precisely in a large sample even if the star-by-star measurement noise is comparable to the intrinsic scatter. We conclude that many elements have an independent story to tell, even for the mundane disk stars and elements produced by the core-collapse and Type Ia supernovae. The only way to learn these lessons is to measure the abundances directly, and not merely infer them.

79 ASTRONOMY AND ASTROPHYSICS↗

Comparison of DeePMD, MTP, GAP, ACE and MACE Machine‐Learned Potentials for Radiation‐Damage Simulations: A User Perspective

Accurate and efficient interatomic potentials are essential for molecular dynamics (MD) simulations of radiation damage, gas diffusion, and phase stability in complex ceramics such as LiAlO 2 , especially under extreme conditions relevant to tritium production. Here, we evaluate the performance of six machine-learned interatomic potentials (MLIPs), moment tensor potential (MTP), Gaussian approximation potential, deep potential (DeePMD), atomic cluster expansion (ACE), message-passing ACE (multilayer atomic cluster expansion (MACE) pretrained) and MACE (trained from-scratch), all trained on the same density functional theory dataset with inclusion of tritium. The MLIPs are benchmarked against traditional Buckingham and ReaxFF potentials in terms of energy accuracy, density predictions, thermal equilibration behavior, threshold displacement energy (E d ), tritium diffusivity, and computational cost. Among the models, MTP shows the best overall balance between efficiency and accuracy, with low force and energy errors and realistic E d values for Li and Al. The ACE and MACE (pretrained and trained from scratch) models exhibit high E d (>200 eV) and unphysical pair interactions. DeePMD underestimates Ed due to overly repulsive behavior even at equilibrium distances. All models over-estimate tritium diffusion but the pretrained MACE model behaves well during tritium-diffusion simulations up to 500 K, maintaining diffusivities in the physically consistent 10 −11 m 2 /s range. Finally, we quantify the computational cost of each potential in large-scale atomic/molecular massively parallel simulator, finding that only MTP is more efficient than traditional empirical potentials, while others are significantly more expensive. These findings explain the trade-offs between accuracy and computational cost in MLIP development and provide essential guidance for use in high-throughput radiation damage and gas diffusion simulations in nuclear ceramics.

74 ATOMIC AND MOLECULAR PHYSICS↗

Budget constrained machine learning for early prediction of adverse outcomes for COVID-19 patients

Abstract The combination of machine learning (ML) and electronic health records (EHR) data may be able to improve outcomes of hospitalized COVID-19 patients through improved risk stratification and patient outcome prediction. However, in resource constrained environments the clinical utility of such data-driven predictive tools may be limited by the cost or unavailability of certain laboratory tests. We leveraged EHR data to develop an ML-based tool for predicting adverse outcomes that optimizes clinical utility under a given cost structure. We further gained insights into the decision-making process of the ML models through an explainable AI tool. This cohort study was performed using deidentified EHR data from COVID-19 patients from ProMedica Health System in northwest Ohio and southeastern Michigan. We tested the performance of various ML approaches for predicting either increasing ventilatory support or mortality. We performed post hoc analysis to obtain optimal feature sets under various budget constraints. We demonstrate that it is possible to achieve a significant reduction in cost at the expense of a small reduction in predictive performance. For example, when predicting ventilation, it is possible to achieve a 43% reduction in cost with only a 3% reduction in performance. Similarly, when predicting mortality, it is possible to achieve a 50% reduction in cost with only a 1% reduction in performance. This study presents a quick, accurate, and cost-effective method to evaluate risk of deterioration for patients with SARS-CoV-2 infection at the time of clinical evaluation.

97 MATHEMATICS AND COMPUTING↗

Geometric Measures of Trustworthiness for Machine Learning Predictions

his report details the findings from the research and investigation of Geometric Measures of Trustworthiness for Machine Learning Predictions. We explored the trustworthiness of machine learning (ML) models’ predictions using geometric measures to quantify the similarity of a query point with the training data. Predictive uncertainty in ML can originate from at least three sources: (1) Model uncertainty, which represents the uncertainty in model form (e.g. decision tree, vs neural network) and estimating the model parameters from the training data, (2) Data uncertainty, which represents the natural complexities of the data such as class overlap and inherent noise, and (3) Distributional uncertainty, which represents the mismatch between the training and operational distributions. The proposed measures focus on measuring and explaining the data and distributional uncertainties by measuring the relationships of operational data with the training data.

97 MATHEMATICS AND COMPUTING↗

Machine Learning of Key Variables Impacting Extreme Precipitation in Various Regions of the Contiguous United States

Abstract Amplification in extreme precipitation intensity and frequency can cause severe flooding and impose significant social and economic consequences. Variations in extreme precipitation intensity, frequencies, and return periods can be attributed to many physical variables across spatial and temporal scales. Here we employ ensemble machine learning (ML) methods, namely random forest (RF), eXtreme Gradient Boosting (XGB), and artificial neural networks (ANN), to explore key contributing variables to monthly extreme precipitation intensity and frequency in six regions over the United States. We further establish emulators for return periods. Results show that the ML models for intensity perform better in regions with obvious seasonality (i.e., Northern Great Plains, Southern Great Plains, and West Coast) than the other three regions (Northeast, Southwest, and Rocky Mountains), while for frequency the models perform well for most regions. The Shapley additive explanation is used to help explain the relationships between extreme precipitation characteristics and identify top variables for RF and XGB. We find that latent heat flux, relative humidity, soil moisture, and large‐scale subsidence are key common variables across the regions for both monthly intensity and frequency, and their compound effects are non‐negligible. The developed ML models capture the probability and return period of extreme precipitation well for all regions and may be used for decision making (e.g., infrastructure planning and design).

54 ENVIRONMENTAL SCIENCES↗