Engineering Papers⌕ Search

SEARCH · Engineering Papers

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 325 records · Page 18
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

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↗
DOE OSTI2026

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↗
DOE OSTI2021

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↗
DOE OSTI2025

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↗
NASA NTRS1991

An introduction to autonomous control systems

The functions, characteristics, and benefits of autonomous control are outlined. An autonomous control functional architecture for future space vehicles that incorporates the concepts and characteristics described is presented. The controller is hierarchical, with an execution level (the lowest level), coordination level (middle level), and management and organization level (highest level). The general characteristics of the overall architecture, including those of the three levels, are explained, and an example to illustrate their functions is given. Mathematical models for autonomous systems, including 'logical' discrete event system models, are discussed. An approach to the quantitative, systematic modeling, analysis, and design of autonomous controllers is also discussed. It is a hybrid approach since it uses conventional analysis techniques based on difference and differential equations and new techniques for the analysis of the systems described with a symbolic formalism such as finite automata. Some recent results from the areas of planning and expert systems, machine learning, artificial neural networks, and the area restructurable controls are briefly outlined.

Antsaklis, Panos J.↗
DOE OSTI2025

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↗
DOE OSTI2022

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↗
DOE OSTI2025

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↗
DOE OSTI2021

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↗
DOE OSTI2022

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↗
DOE OSTI2026

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↗
DOE OSTI2021

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↗
DOE OSTI2024

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↗
DOE OSTI2023

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↗
DOE OSTI2025

A unified ensemble soil moisture dataset across the continental United States

Abstract A unified ensemble soil moisture (SM) package has been developed over the Continental United States (CONUS). The data package includes 19 products from land surface models, remote sensing, reanalysis, and machine learning models. All datasets are unified to a 0.25-degree and monthly spatiotemporal resolution, providing a comprehensive view of surface SM dynamics. The statistical analysis of the datasets leverages the Koppen-Geiger Climate Classification to explore surface SM’s spatiotemporal variabilities. The extracted SM characteristics highlight distinct patterns, with the western CONUS showing larger coefficient of variation values and the eastern CONUS exhibiting higher SM values. Remote sensing datasets tend to be drier, while reanalysis products present wetter conditions. In-situ SM observations serve as the basis for wavelet power spectrum analyses to explain discrepancies in temporal scales across datasets facilitating daily SM records. This study provides a comprehensive soil moisture data package and an analysis framework that can be used for Earth system model evaluations and uncertainty quantification, quantifying drought impacts and land–atmosphere interactions and making recommendations for drought response planning.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Benchmarking for AI for Science

AI has been instrumental for recent developments in a number of domains of the sciences. With several hundred machine learning (ML) algorithms and models, and numerous AI-specific hardware platforms, a common quest for all scientists working on AI for Science is around the selection of machine learning algorithm(s) to solve their domain-specific scientific problems. A number of different initiatives around AI Benchmarking have been set up and have been useful in understanding the benefits of different ML algorithms for different tasks.However, with the majority of these AI Benchmarking initiatives focusing on the conventional notions of benchmarking, where the focus is purely runtime performance (such as training time or inference time), their suitability for benchmarking different ML algorithms for solving scientific problems has been viewed as a performance problem even though both are hardly the same. To make reasonable, explainable, and justifiable advancements in science using AI, it is critical to focus on the merits of these algorithms in handling different domain science problems. In other words, more emphasis must be given on Benchmarking for AI for Science than AI Benchmarking. The vision of the former is not only to assess the performance of ML algorithms, but also to assess, and understand the benefits and merits of different ML algorithms in handling scientific problems. Benchmarking for AI for Science, instead of pure performance focused AI Benchmarking, has several benefits: (i) it has the potential to offer advances in the sciences, much more rapidly than through pure performance-based AI methods, (ii) it will encourage the community to focus on developing better domain-specific AI techniques, particularly given the provision for being able to benchmark different techniques, and (iii) it will encourage hardware manufacturers to focus on developing science-specific hardware subsystems.

Thiyagalingam, Jeyan↗
DOE OSTI2023

Data-driven assessment of magnetic charged particle confinement parameter scaling in magnetized liner inertial fusion experiments on Z

In magneto-inertial fusion, the ratio of the characteristic fuel length perpendicular to the applied magnetic field R to the α-particle Larmor radius $ϱ_α$ is a critical parameter setting the scale of electron thermal-conduction loss and charged burn-product confinement. Here, using a previously developed deep-learning-based Bayesian inference tool, we obtain the magnetic-field fuel-radius product BR ∝ R / $ϱ_α$ from an ensemble of 16 magnetized liner inertial fusion (MagLIF) experiments. Observations of the trends in BR are consistent with relative trade-offs between compression and flux loss as well as the impact of mix from 1D resistive radiation magneto-hydrodynamics simulations in all but two experiments, for which 3D effects are hypothesized to play a significant role. Finally, we explain the relationship between BR and the generalized Lawson parameter χ. Our results indicate the ability to improve performance in MagLIF through careful tuning of experimental inputs, while also highlighting key risks from mix and 3D effects that must be mitigated in scaling MagLIF to higher currents with a next-generation driver.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2021

Explaining and predicting human behavior and social dynamics in simulated virtual worlds: reproducibility, generalizability, and robustness of causal discovery methods

Ground Truth program was designed to evaluate social science modeling approaches using simulation test beds with ground truth intentionally and systematically embedded to understand and model complex Human Domain systems and their dynamics Lazer et al. (Science 369:1060–1062, 2020). Our multidisciplinary team of data scientists, statisticians, experts in Artificial Intelligence (AI) and visual analytics had a unique role on the program to investigate accuracy, reproducibility, generalizability, and robustness of the state-of-the-art (SOTA) causal structure learning approaches applied to fully observed and sampled simulated data across virtual worlds. In addition, we analyzed the feasibility of using machine learning models to predict future social behavior with and without causal knowledge explicitly embedded. In this paper, we first present our causal modeling approach to discover the causal structure of four virtual worlds produced by the simulation teams—Urban Life, Financial Governance, Disaster and Geopolitical Conflict. Our approach adapts the state-of-the-art causal discovery (including ensemble models), machine learning, data analytics, and visualization techniques to allow a human-machine team to reverse-engineer the true causal relations from sampled and fully observed data. We next present our reproducibility analysis of two research methods team’s performance using a range of causal discovery models applied to both sampled and fully observed data, and analyze their effectiveness and limitations. We further investigate the generalizability and robustness to sampling of the SOTA causal discovery approaches on additional simulated datasets with known ground truth. Our results reveal the limitations of existing causal modeling approaches when applied to large-scale, noisy, high-dimensional data with unobserved variables and unknown relationships between them. We show that the SOTA causal models explored in our experiments are not designed to take advantage from vasts amounts of data and have difficulty recovering ground truth when latent confounders are present; they do not generalize well across simulation scenarios and are not robust to sampling; they are vulnerable to data and modeling assumptions, and therefore, the results are hard to reproduce. Finally, when we outline lessons learned and provide recommendations to improve models for causal discovery and prediction of human social behavior from observational data, we highlight the importance of learning data to knowledge representations or transformations to improve causal discovery and describe the benefit of causal feature selection for predictive and prescriptive modeling.

97 MATHEMATICS AND COMPUTING↗