Results for “Interpretable machine learning” — Page 8

NASA NTRSDate not supplied

A Quantitative Analysis On the Use Of Supervised Machine Learning in Earth Science

Several recent papers have investigated different challenges in applying machine learning (ML) techniques to Earth science problems. The challenges listed range from interpretability of the results to computational demand to data issues. In this paper, we focus on specific challenges listed in the review papers that are centered around training data, as the size of training data is important in applying deep learning (DL) techniques. We are in the process of conducting a literature survey to better understand these challenges as well as to understand any trends. As part of this survey, our review has encompassed Earth science papers from AGU, AMS, IEEE and SPIE journals covering the last ten years and focused on papers that utilize supervised ML techniques.

Katrina S Virts↗

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 OSTI2025

Learning PDFs through interpretable latent representations in Mellin space

Representing the parton distribution functions (PDFs) of the proton and other hadrons through flexible, high-fidelity parametrizations has been a long-standing goal of particle physics phenomenology. This is particularly true since the chosen parametrization methodology can play an influential role in the ultimate PDF uncertainties as extracted in QCD global analyses; these, in turn, are often determinative of the reach of experiments at the LHC and other facilities to nonstandard physics, including at large 𝑥, where parametrization effects can be significant. In this study, we explore a series of encoder-decoder machine-learning (ML) models with various neural-network topologies as efficient means of reconstructing PDFs from meaningful information stored in an interpretable latent space. Given recent effort to pioneer synergies between QCD analyses and lattice-gauge calculations, we formulate a latent representation based on the behavior of PDFs in Mellin space, i.e., their integrated moments, and test the ability of various models to decode PDFs from this information faithfully. We introduce a numerical package, PDFdecoder, which implements several encoder-decoder models to reconstruct PDFs with high fidelity and use this end-to-end tool to explore how such neural-network-based models might connect PDF parametrizations to underlying properties like their Mellin moments. We additionally dissect patterns of learned correlations between encoded Mellin moments and reconstructed PDFs that suggest opportunities for further improvements to ML-based approaches to PDF parametrizations and uncertainty quantification.

Machine learning↗

DOE OSTI2025

Explainable Machine Learning for Functional Data

Black-box machine learning models are recognized as useful tools for prediction applications, but the algorithmic complexity of some models causes interpretation challenges. Explainability methods have been proposed to provide insight into these models, but there is little research focused on supervised modeling with functional data inputs. We argue that, especially in applications of high consequence, it is important to explicitly model the functional dependence in a black-box analysis to not obscure or misrepresent patterns in explanations. As such, we propose the V ariable importance E xplainable E lastic S hape A nalysis (VEESA) pipeline for training supervised machine learning models with functional inputs. The pipeline is an analysis process that includes the data preprocessing, modeling, and post-hoc explanations. The preprocessing is done using elastic functional principal components analysis, which accounts for vertical and horizontal variability in functional data and, ultimately, allows for explanations in the original data space that identify the important functional variability without bias due to correlated variables. Here, we demonstrate the pipeline on two high-consequence applications: explosives classification for national security and inkjet printer identification in forensic science. The applications exhibit the VEESA pipeline’s ability to provide an understanding of the characteristics of the functional data useful for prediction. Code for implementing the pipeline is available in the veesa R package (and supplemental python code).

Elastic Shape Analysis↗

NASA NTRSDate not supplied

Enhancing Neural Network Decision-Making with Variational Autoencoders

Machine intelligence has been used to tackle increasingly complex problems and deep learning solutions are at the forefront of tackling these problems. In general, these architectures have a great number of parameters that are methodically updated in training. The vast number and complexity of deep neural networks makes it very difficult to decipher the inner workings of the neurons and layers that make up the network. This paper posits that trustworthiness and trust in autonomous systems are increased through eXplainable Artificial Intelligence (XAI) and presents a method that enhances the explainability and understanding of a neural network decision. We leverage variational autoencoders to produce human interpretable features from complex data sets. We show that the explainable features can then be used for machine learning applications. This explainability encourages people to be more inclined to justifiably trust machine decision-making.

Loc Tran↗

NASA NTRSDate not supplied

Enhancing Neural Network Explainability with Variational Autoencoders

Machine intelligence has been used to tackle increasingly complex problems and deep learning solutions are at the forefront of tackling these problems. In general, these architectures have a great number of parameters that are methodically updated in training. The vast number and complexity of deep neural networks makes it very difficult to decipher the inner workings of the neurons and layers that make up the network. This paper posits that trustworthiness and trust in autonomous systems are increased through eXplainable Artificial Intelligence (XAI) and presents a method that enhances the explainability and understanding of a neural network decision. We leverage variational autoencoders to produce human interpretable features from complex data sets. We show that the explainable features can then be used for machine learning applications. Explainability inspires trust in autonomous systems that use deep learning, which is necessary for safety critical systems.

Loc Tran↗

DOE OSTI2025

Improving microstructures segmentation via pretraining with synthetic data

Image analysis of material microstructures through microscopy is an integral capability in the field of materials science. The topological and chemical information obtained through microscopy allow us to draw vital connections between material microstructures, properties, and processing. While scanning electron microscopy (SEM) is able to yield a considerable wealth of information interpretable by the intuition of experts, there has been considerable interest in using machine learning, convolutional neural networks (CNNs) in particular, for such image analysis task. Training CNNs for an image analysis task requires a large annotated dataset. However, in many materials science applications, obtaining a large annotated dataset is cost and labor intensive. In this work, we study the use of synthetic data to enlarge the available annotated experimental data of uranium oxide. We utilize a modified Potts model to simulate uranium oxide particles with morphologies similar to those observed experimentally. We then leverage an image-to-image translation model to synthesize the simulated particles as if they are acquired with SEM. Through this process, we obtain pairs of particle images and their corresponding SEM representations, which corresponds to pairs of annotations and images. Unlike previous works, we leverage synthetic data for pretraining a CNN model prior, and finetune that model further with experimental data. We experimentally demonstrate that using synthetic data as incremental learning process benefits the overall performance compared to training a model on combined synthetic and experimental data.

36 MATERIALS SCIENCE↗

DOE OSTI2026

Genesis Data Card Schema, Template and Supporting Tools

Genesis Data Cards provide a standardized template and schema for documenting scientific datasets in support of discovery, access, interoperability, reusability, governed use, and AI usability. This release of the Genesis Data Card repository includes a versioned Markdown template, a LinkML schema with generated Pydantic and JSON artifacts, schema documentation, and example completed data cards. Validation tooling is provided to ensure that completed data cards conform to the schema prior to submission. Accompanying documentation for the structured metadata is provided as a Field Reference Guide. The schema and accompanying template provided in this repository address the call for actionable context that enables humans and AI systems to find, access, interpret, cite, and reuse data, and, when appropriate, integrate it into AI and machine learning workflows. The data card is intended to serve as a common metadata artifact intended to support standardized, cross-program dataset documentation across Department of Energy (DOE)-aligned efforts, including but not limited to Genesis Mission-related implementations, the Office of Science, National Nuclear Security Administration (NNSA), and Advanced Simulation and Computing (ASC) data governance and stewardship initiatives.

data card↗

NASA NTRSDate not supplied

INCREASING THE TRANSPARENCY AND REPRODUCIBILITY OF SPACE RADIATION SCIENCE: THE RADIATION BIOLOGY ONTOLOGY

Among the primary objectives of the Open/Open-Source Science paradigm are making scientific investigation data transparent and results reproducible [1], objectives shared by the FAIR principles [2]. To accomplish this, the conceptual framework that includes all the investigation objects needs to be accurately captured and communicated to all data consumers. A large part of this requires using metadata standards to annotate data collected. These standards should be readily accessible, informed by scientific community consensus and sufficiently specific to encompass all of the important aspects of the investigation. Starting in 2020 we have been co-leading an open consortium to develop a new metadata standard, the Radiation Biology Ontology (RBO), through the Open Biological and Biomedical Ontologies (OBO) Foundry [3]. We began by transforming many of the terms from the National Council on Radiation Protection and Measurement into concepts that can be formally related to existing OBO Foundry classes or attributes. We then identified and imported into the RBO existing OBO Foundry classes that have obvious relevance for radiation biomedicine (for example, concepts from the Environment Ontology that describe radiative processes, and concepts from the Gene Ontology dealing with molecular and cellular responses to radiation). Finally, we scrutinized datasets from investigations of radiation effects held in NASA GeneLab and LSDA repositories and added additional classes, instances, and attributes into the RBO that should be used to annotate these data. We developed the RBO using the open-source tools of GitHub and publish the RBO periodically through the NIH/NCBI BioPortal website, so systems worldwide can leverage the knowledge it contains [4]. This initial phase of concept modeling has yielded an RBO that at present has more than 300 declared concepts, with more than 3500 additional concepts imported from other OBO Foundry ontologies. While this first phase has focused on concepts for annotating samples, environments, exposures, and measurements, the next phase will center on supporting annotation of results and findings, such as concept models of molecular, cellular and tissue effects. The value of the RBO will be determined in part by our ability to engage the community in its development, and we have established a Radiobiology Informatics Consortium with unrestricted membership as the owner of the RBO in order to encourage investigators, system owners and other to join in this effort. Anyone can report issues or request new concept modeling or other features directly on GitHub. By using the BioPortal application programming interface, systems can pose dynamic queries to the latest version of the RBO for information on individual classes or entire hierarchies; this design eliminates the need for systems to be updated in order to use newer versions of the RBO. We hope to contribute to the advancement of open radiobiological science through the continued, open development of the RBO, that will provide more precise, machine-interpretable descriptions of investigations, as well as support data meta-analysis through machine learning or other artificial intelligence methods. REFERENCES [1] Open science in space. Nature Medicine, 2021. 27(9): p. 1485-1485. [2] Wilkinson, M.D., et al., The FAIR Guiding Principles for scientific data management and stewardship. Sci Data, 2016. 3: p. 160018. [3] Smith, B., et al., The OBO Foundry: coordinated evolution of ontologies to support biomedical data integration. Nat Biotechnol, 2007. 25(11): p. 1251-5. [4] Whetzel, P.L., et al., BioPortal: enhanced functionality via new Web services from the National Center for Biomedical Ontology to access and use ontologies in software applications. Nucleic Acids Res, 2011. 39(Web Server issue): p. W541-5.

informatics↗

NASA NTRSDate not supplied

INCREASING THE TRANSPARENCY AND REPRODUCIBILITY OF SPACE RADIATION SCIENCE: THE RADIATION BIOLOGY ONTOLOGY

Among the primary objectives of the Open/Open-Source Science paradigm are making scientific investigation data transparent and results reproducible [1], objectives shared by the FAIR principles [2]. To accomplish this, the conceptual framework that includes all the investigation objects needs to be accurately captured and communicated to all data consumers. A large part of this requires using metadata standards to annotate data collected. These standards should be readily accessible, informed by scientific community consensus and sufficiently specific to encompass all of the important aspects of the investigation. Starting in 2020 we have been co-leading an open consortium to develop a new metadata standard, the Radiation Biology Ontology (RBO), through the Open Biological and Biomedical Ontologies (OBO) Foundry [3]. We began by transforming many of the terms from the National Council on Radiation Protection and Measurement into concepts that can be formally related to existing OBO Foundry classes or attributes. We then identified and imported into the RBO existing OBO Foundry classes that have obvious relevance for radiation biomedicine (for example, concepts from the Environment Ontology that describe radiative processes, and concepts from the Gene Ontology dealing with molecular and cellular responses to radiation). Finally, we scrutinized datasets from investigations of radiation effects held in NASA GeneLab and LSDA repositories and added additional classes, instances, and attributes into the RBO that should be used to annotate these data. We developed the RBO using the open-source tools of GitHub and publish the RBO periodically through the NIH/NCBI BioPortal website, so systems worldwide can leverage the knowledge it contains [4]. This initial phase of concept modeling has yielded an RBO that at present has more than 300 declared concepts, with more than 3500 additional concepts imported from other OBO Foundry ontologies. While this first phase has focused on concepts for annotating samples, environments, exposures, and measurements, the next phase will center on supporting annotation of results and findings, such as concept models of molecular, cellular and tissue effects. The value of the RBO will be determined in part by our ability to engage the community in its development, and we have established a Radiobiology Informatics Consortium with unrestricted membership as the owner of the RBO in order to encourage investigators, system owners and other to join in this effort. Anyone can report issues or request new concept modeling or other features directly on GitHub. By using the BioPortal application programming interface, systems can pose dynamic queries to the latest version of the RBO for information on individual classes or entire hierarchies; this design eliminates the need for systems to be updated in order to use newer versions of the RBO. We hope to contribute to the advancement of open radiobiological science through the continued, open development of the RBO, that will provide more precise, machine-interpretable descriptions of investigations, as well as support data meta-analysis through machine learning or other artificial intelligence methods.

knowledge↗

NASA NTRSDate not supplied

Off-Nominal Event Analysis in Autonomous Flights Based on Explainable Artificial Intelligence

A key objective in the Urban Air Mobility program at NASA is to intelligently perform an autonomous flight in a complex urban environment under all weather conditions with guaranteed levels of safety. To accomplish this, the mission manager (central decision-making module) of the vehicle needs to make informed decisions between various Courses of Action (CoA) based on its' interpretation of the inputs it receives. If an off-nominal event is detected either based on the amalgamation of sensor data or the use of machine learning models, the mission manager may greatly benefit from identification of the input features that most likely contributed to that specific event. Such an understanding is usually not possible to obtain from the classical machine learning models (deep learning) due to the inherent black box like structure. However, this understanding is achieved using eXplainable Artificial Intelligence (XAI) models that provide a human interpretable rationale for the predictions made. This work presents a game theory inspired XAI model for the off-nominal assessment of autonomous flights. The proposed approach based on Shapley values is model agnostic, provides local as well as global explanation and satisfies the four axioms (efficiency, symmetry, dummy, additivity) to achieve fair contribution. The versatility of the approach is first demonstrated on a simulated dataset in which the significance of each input to flight phase prediction is clearly identified. Subsequently, data from simulated flight trajectories are fed into the model which reveal the input features that most likely contributed to a rotor failure event thereby empowering the mission manager to take the appropriate CoA.

autonomy↗

NASA NTRSDate not supplied

Off-Nominal Event Analysis in Autonomous Flights Based on Explainable Artificial Intelligence

A key objective in the Urban Air Mobility program at NASA is to intelligently perform an autonomous flight in a complex urban environment under all weather conditions with guaranteed levels of safety. To accomplish this, the mission manager (central decision-making module) of the vehicle needs to make informed decisions between various Courses of Action (CoA) based on its' interpretation of the inputs it receives. If an off-nominal event is detected either based on the amalgamation of sensor data or the use of machine learning models, the mission manager may greatly benefit from identification of the input features that most likely contributed to that specific event. Such an understanding is usually not possible to obtain from the classical machine learning models (deep learning) due to the inherent black box like structure. However, this understanding is achieved using eXplainable Artificial Intelligence (XAI) models that provide a human interpretable rationale for the predictions made. This work presents a game theory inspired XAI model for the off-nominal assessment of autonomous flights. The proposed approach based on Shapley values is model agnostic, provides local as well as global explanation and satisfies the four axioms (efficiency, symmetry, dummy, additivity) to achieve fair contribution. The versatility of the approach is first demonstrated on a simulated dataset in which the significance of each input to flight phase prediction is clearly identified. Subsequently, data from simulated flight trajectories are fed into the model which reveal the input features that most likely contributed to a rotor failure event thereby empowering the mission manager to take the appropriate CoA.

autonomy↗

DOE OSTI2026

Deployment of Traditional and Hybrid Machine Learning for Critical Heat Flux Prediction in the CTF Thermal-Hydraulics Code

Critical heat flux (CHF) marks the transition from nucleate to film boiling, where heat transfer to the working fluid can rapidly deteriorate. Accurate CHF prediction is essential for efficiency, safety, and preventing equipment damage, particularly in nuclear reactors. Although widely used, empirical correlations frequently exhibit discrepancies when compared to experimental data, limiting their reliability in diverse operational conditions. Traditional machine learning (ML) approaches have demonstrated potential for CHF prediction but often suffer from limited interpretability, data scarcity, and insufficient knowledge of physical principles. Hybrid model approaches, which combine data-driven ML with base models, mitigate these concerns by incorporating prior knowledge of the domain. This study integrates an externally trained purely data-driven ML model and two hybrid models (using the Biasi and Bowring CHF correlations) within the CTF subchannel code via a custom Fortran framework. Performance was evaluated using two validation cases: a subset of the Nuclear Regulatory Commission (NRC) CHF database and the Bennett dryout experiments. In both cases, the hybrid models demonstrated significantly lower error metrics compared to conventional empirical correlations, with the best models often reducing relative error by about 5 percentage points. The pure ML model achieved comparable accuracy, outperforming the hybrid Biasi model in the NRC test case (3.3% versus 5.5% relative error) but exhibiting slightly higher error against the hybrid Bowring model in the Bennett test case (7.7% versus 6.1%). Trend analysis of error parity indicated that ML-based models reduced the tendency for CHF overprediction, improving overall accuracy. These results demonstrate that ML-based CHF models can be effectively integrated into subchannel codes and could potentially increase performance compared to conventional methods.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2026

Data, model inputs, and analysis scripts associated with a manuscript on stream intermittency controls across spatial scales in Pacific Northwest watersheds

NOTE: The manuscript associated with this data package is currently in review. The data may be revised based on reviewer feedback. Upon manuscript acceptance, this data package will be updated with the final dataset and additional metadata. This data package is associated with the manuscript "Hydroclimatic Memory and Watershed Template Shape Stream Intermittency: Multi-scale Attribution Using Process-based Simulation and Explainable ML" by Niroula et al. (2026), submitted to Water Resources Research (WRR). The study investigates the dominant controls on stream intermittency across local, reach, and watershed scales using a coupled process-based simulation and explainable machine-learning framework. Long-term daily simulations from the Advanced Terrestrial Simulator (ATS) were used to generate wetness states and ponded-depth responses over river-corridor cells. These ATS outputs were then aggregated across scales and used to train XGBoost (eXtreme Gradient Boosting) models. SHAP (SHapley Additive exPlanations) was applied to quantify the relative importance of hydroclimatic forcings, watershed template attributes, and antecedent-memory effects in shaping intermittency behavior. The analysis is carried out for three contrasting Pacific Northwest watersheds: Oak Creek (OCW), American River Watershed (ARW), and H.J. Andrews (HJA). Across these testbeds, the package contains ATS-ready watershed inputs, ATS run configuration and selected output files, model-evaluation data products, intermittency-analysis datasets, machine-learning target-feature tables, SHAP outputs, and notebooks used to organize, analyze, and visualize results. At a high level, the package documents a workflow in which ATS provides the physically based simulation backbone and explainable machine learning is used as a post-processing attribution tool. The contents are intended to support interpretation of the manuscript figures and results, provide context for how intermittency metrics were generated at multiple scales, and preserve the key artifacts needed to understand and reuse the analysis workflow. The package contains a high-level directory summary file (`summary.txt`) and four main content folders (1) `evaluation_plots` contains evaluation figures and supporting evaluation datasets; (2) `intermittency_plots` contains intermittency-focused analysis notebook and prepared datasets; (3) `ml-training-and-shap_values_plots` contains ML training inputs, SHAP outputs, and figure-generation notebooks; and (4) `watershed_mesh_and_ats_input` contains ATS model setup materials, forcing inputs, geometry, and selected run files. More specifically, the `evaluation_plots` folder contains the notebook used for ATS evaluation plotting and site-specific evaluation datasets. These include evapotranspiration and water-balance products for three watersheds, as well as an Oak Creek field-measurement discharge file. The `intermittency_plots` folder contains the notebook used for intermittency analysis and the prepared datasets used to analyze intermittent and non-intermittent wetness behavior across the study watersheds. The `ml-training-and-shap_values_plots` folder contains notebooks and outputs for the machine-learning and explainability workflow. This includes the main XGBoost and SHAP notebook(s), a beeswarm plotting notebook, target-feature tables for machine-learning training, SHAP summary tables, and per-sample SHAP value archives. The `watershed_mesh_and_ats_input` folder contains ATS-related watershed inputs and supporting materials. This includes mesh and shape products, ATS-readable LAI and meteorological forcing inputs, selected ATS spinup and transient-run files, and a watershed workflow example notebook. Subdirectories are organized by watershed where applicable.All files are .cpg (codepage files), .csv (comma-separated values), .dbf (database files), .exo (Exodus mesh format), .h5 (HDF5 format), .ipynb (Jupyter notebooks), .pkl (Python pickle), .prj (projection files), .sh (shell scripts), .shp (shapefile geometry), .shx (shapefile index), .txt (text files), or .xml (markup data).

Advanced Terrestrial Simulator↗

DOE OSTI2026

Conformalized-KANs: Uncertainty Quantification with Coverage Guarantees for Kolmogorov-Arnold Networks (KANs) in Scientific Machine Learning

This paper explores uncertainty quantification (UQ) methods in the context of Kolmogorov–Arnold Networks (KANs). We apply an ensemble approach to KANs to obtain a heuristic measure of UQ, enhancing interpretability and robustness in modeling complex functions. Building on this, we introduce Conformalized-KANs, which integrate conformal prediction, a distribution-free UQ technique, with KAN ensembles to generate calibrated prediction intervals with guaranteed coverage.} Extensive numerical experiments are conducted to evaluate the effectiveness of these methods, focusing particularly on the robustness and accuracy of the prediction intervals under various hyperparameter settings. We show that the conformal KAN predictions can be applied to recent extensions of KANs, including Finite Basis KANs (FBKANs) and multifideilty KANs (MFKANs). The results demonstrate the potential of our approaches to significantly improve the reliability and applicability of KANs in scientific machine learning.

• Artificial intelligence (AI) / machine learning ↗

DOE OSTI2024

Machine Learning Accelerates Innovation in Perovskite Manufacturing Scale-up (Final Technical Report (FTR))

We propose to address the challenge of the vast parameter space associated with perovskite manufacturing optimization, by developing a machine learning (ML)-assisted optimization framework for a scalable perovskite PV manufacturing tool. This framework will be interpretable, sequential, and rapidly adaptable to upgraded systems (e.g., via transfer learning). The tool is an open-air rapid spray plasma process (RSPP) of perovskite films, which has already been established at Stanford and is a unique platform to test and deploy the proposed ML-guided framework because the RSPP technique is able to conduct optimization experiments with a high throughput, and easily adjust a wide range of process variables.

14 SOLAR ENERGY↗

DOE OSTI2025

Explainable multi-fidelity Bayesian neural network for distribution system state estimation

Distribution System State Estimation (DSSE) is frequently constrained by limited real-time measurements, the uncertainties introduced by distributed energy resources, and the presence of bad data. To address them, this paper proposes an enhanced Multi-Fidelity Bayesian Neural Network (MFBNN) DSSE approach. A low-fidelity layer based on a Deep Neural Network (DNN) is first pre-trained on pseudo-measurement data to learn fundamental state features. Subsequently, a high-fidelity Bayesian Neural Network (BNN) layer leverages limited but high-quality real-time measurements to refine these features, thereby achieving accurate DSSE. Additionally, the deep SHapley Additive exPlanation (SHAP) is developed to quantify the influence of measurement data on DSSE through dual perspectives of global feature importance and local nodal contributions, establishing a hierarchical explainability framework for machine learning-based DSSE. Comparative studies conducted on the IEEE 13-bus system and a real-world 2135-node system from Dominion Energy demonstrate that the proposed method excels in estimation accuracy, even under situations of high noise levels, bad data, and missing data. Further comparisons with Weighted Least Squares (WLS) and other machine learning-based DSSE approaches verify that the proposed framework offers higher accuracy, improved interpretability, and enhanced robustness.

Bad data↗

NASA NTRS2019

Deep Learning Method for Detecting Precursors to Adverse Events

With the recent advancements in Deep Learning methods, the ability to model large complex heterogeneous data sets are fundamentally changing industry and research. Coupled with hardware improvements, and ease of implementation, a wide variety of deep neural network architectures can quickly be developed to solve a sweeping range of problems such as: object detection in images, automatic healthcare diagnosis using heterogenous data sources, real time language translating and sentence prediction, upscaling low resolution images, and forecasting of multivariate timeseries. Generally, many of these architectures outperform classical machine learning approaches in their respective tasks, however, this typically comes at a cost of interpretability. These black box algorithms generally suffer from lack of transparency in both model complexity as well as the rationale behind the prediction. This lack of comprehension, is driving an emerging area of interest in “Explainable AI”. An algorithm called: “Deep Temporal Multiple Instance Learning”1 was a recently developed to identify precursors to adverse events and has been applied in the aviation domain. The deep learning architecture is designed to capture the evolution of the probability of the outcome over the time preceding the adverse event using a multiple instance learning approach as illustrated in Figure 1. Precursors are defined when the probability of the event has exceeded a threshold at some point in the timeseries, at which point, a sensitivity analysis is performed to determine contributing factors. The contributing factors are used to explain and define the precursor during the periods where the probability score is high. The identified contributing factors are then presented to subject matter experts to provide objective insights into the leading factors associated with the particular adverse event. The algorithm has been tested on flight data from a commercial airline and has the ability to discover precursors to known adverse events that take the form of safety critical operations, such as unstable approach events on final approach. Apart from detecting precursors to adverse events, the converse can also be leveraged to discover corrective actions. These positive actions manifest themselves as periods in the timeseries when the precursor score has been lowered from an elevated state; meaning that if the system had been left uncorrected, it would have eventually reached the adverse event state. Characterizing these state changes can help identify successful interventions that may not have been known before. Policy makers and procedure designers can use this additional knowledge to craft more safety and efficient resilient procedures for future operations and therefore improve the overall performance of the National Airspace.

Matthews, Bryan L.↗