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.

SourceResearch connectionFrom yearThrough year

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

At least 19 records

All sources NASA NTRS DOE OSTI

NASA NTRSDate not supplied

Machine Learning Explainability and Transferability for Path Navigation

Deep neural networks are powerful tools for machine perception. Unfortunately their decisions are difficult to explain due to the complexity and size of the networks. Previously we have alleviated this issue by using the representational portion of a deep neural network and combining it with a k-nearest neighbor (KNN) classifier. Through inspection of the decisions made by the KNN, we can directly see the training data responsible for the decisions, allowing us to determine the quality of the overall decision and the quality of the representational layer of the deep NN. While the technique worked well, it requires tens of thousands of latent vectors to be stored for classification. In addition, it lacks the ability to show how parts of an image influence the classification decision. Here we address these issues by 1) Using a radial basis function network (RBFN) in place of the KNN allowing far fewer images to be used in deployment and 2) Using an auto encoder network for explainability. In addition to these techniques, we examine the effects of transfer learning to determine that results are robust. All results are tested on a domain where an unmanned aerial vehicle (UAV) navigates a forest trail through a single camera.

explainable machine learning↗

NASA NTRS2022

Using an Explainable Machine Learning Approach to Characterize Earth System Model Errors: Application of SHAP Analysis to Modeling Lightning Flash Occurrence

Computational models of the Earth System are critical tools for modern scientific inquiry. Effortstoward evaluating and improving errors in representations of physical and chemical processes inthese large computational systems are commonly stymied by highly nonlinear and complexerror behavior. Recent work has shown that these errors can be effectively predicted usingmodern Artificial Intelligence (A.I.) techniques. In this work, we go beyond these previousstudies to apply an interpretable A.I. technique to not only predict model errors but also movetoward understanding the underlying reasons for successful error prediction. We use XGBoostclassification trees and SHapley Additive exPlanations (SHAP) analysis to explore the errors inthe prediction of lightning occurrence in the NASA GEOS model, a widely used Earth SystemModel. This explainable error prediction system can effectively predict the model error andindicates that the errors are strongly related to convective processes and the characteristics ofthe land surface.

Artificial intelligence↗

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↗

NASA NTRSDate not supplied

NASA Earth Systems Digital Twins (ESDT)

"Similarly to artificial intelligence, which is now revolutionizing many aspects of our daily lives, Earth system digital twin technologies have the potential to revolutionize the way Earth Science research will be conducted in the future, and how results and knowledge from this research will provide information to support decision making and yield impactful societal benefits. An Earth System Digital Twin or ESDT is a dynamic and interactive information system that first provides a digital replica of the past and current states of the Earth or Earth system as accurately and timely as possible; second, allows for computing forecasts of future states under nominal assumptions and based on the current replica; and third, offers the capability to investigate many hypothetical scenarios under varying impact assumptions. In other words, an ESDT provides the integrated What-Now, What-Next, and What-If pictures of the Earth or Earth system, by continuously ingesting newly observed data and by leveraging multiple interconnected models, machine learning as well advanced computing and visualization capabilities. Digital twins have been developed in engineering since 2002, but the interest in digital twins for the Earth domain is more recent and stems from the convergence of several developments: - The huge amount of diverse data that has now been collected continuously for more than 50 years, and that is becoming more and more difficult to access, understand, and utilize. - At the same time, because of climate change and its impacts the information produced by all of this data is becoming of interest to many new non-traditional users for analyzing and predicting various phenomena. - Because of advances in computational and visualization capabilities and the parallel unprecedented development of machine learning (ML), extracting relevant information from these large amounts of data and running complex models faster has become possible. As a result, it is becoming necessary and possible to build intuitive and interactive frameworks that will enable users with various skill levels and/or organizational hierarchy levels to easily access large amounts of targeted information along with the relevant tools and models (Earth system and human activity models), to support them in analyzing and visualizing this information, to help them understand interactions among models, to visualize the potential outcomes of various impacts, and to support decision or policy making. The full power of digital twins is that, through an integrated representation and standardized tools and software technologies, the same digital replica can address the needs of multiple users at various resolutions (spatial and temporal) and for various applications (science, economic, policy, etc.) – “from farmer to scientist”. With all these interests at stake, the challenges of building optimal digital twins are many and complex. The first challenge is to determine if a Digital Twin should be global or local, and multi-domain or thematic. For example, some domains such as Climate or Weather will require a global Digital Twin or Digital Twin capabilities while science areas such as Biodiversity might be more local. We can also envision that multiple thematic ESDTs, e.g., Air Quality, Wildfires, Hydrology could be federated or provide input to other ESDTs, either on a regional level or to a more global ESDT. Overall, we can imagine a future “web” of Digital Twins co-existing in a hierarchy or in a network, and capable of being connected or federated depending on the needs. This last point brings up the very important challenge of interoperability, including standards and protocols that will need to be built into these systems from the beginning. Each individual digital twin would have full flexibility in internal construction but would need standards-based interfaces (input and output) or hooks to make it compatible with others. Another challenge when building digital twins will be to decide how to organize each digital replica. Based on the applications targeted by the DT under implementation, various amounts and types of raw data, Analysis Ready Data (ARD) and information will need to be incorporated. Depending on the required latencies and needs of the users, various solutions can be considered, including Data Cubes, Data Lakes, pointers, or computing information on demand. We envision that each ESDT will choose a solution adapted to its specific objectives. Another important challenge is the type(s) of visualization that will be used, as well as the level of interactivity and refresh rate that will be required. Again, this will depend on the objectives of the ESDT, but also on the various users’ needs. In most cases, several types of visualizations and human interfaces will need to be offered depending on the projected users of that system. In parallel to the challenges highlighted above, there are also many tools and technologies that will need to be developed or improved for all types of digital twins. Among those are improved machine learning technologies, for example providing explainability, but also ML techniques for causality and providing a better integration of physics models. Additionally, reliable uncertainty quantification methods will be needed for all ESDT components, from validating data fusion and assimilation to assessing the accuracy of ML models and weighing the values of decisions supported by those systems. This presentation introduces the ESDT concept, presents several ESDT use cases, and a proposed ESDT architecture framework, as well as various technologies being developed by the Advanced Information Systems Technology (AIST) Program."

Earth Science Remote Sensing; Information Systems↗

NASA NTRS2021

NASA Framework for the Ethical Use of Artificial Intelligence (AI)

The NASA Framework for the Ethical Use of Artificial Intelligence (AI) provides six key principles to guide NASA's use of AI. The principles are NASA's AI must be 1. Fair, 2., Explainable and transparent, 3. Accountable, 4. Secure and safe, 5. Human-centric and societally beneficial, and 6. Scientifically and technically robust. The framework describes each ethical AI principle, and then applies that principle to NASA work. The framework also includes a list of questions practitioners should use to guide their AI work. Finally, the framework focuses on concrete, practical considerations for the next five - ten years, while also beginning to lay the foundation for longer-term disruptive change as human-level (or beyond) AI is created.

Artificial Intelligence↗

NASA NTRSDate not supplied

Multi-Class Anomaly Detection in Flight Data using Semi-Supervised Explainable Deep Learning Model

Identifying precursor for safety incidents in aviation data is a crucial task, yet extremely challenging. The main approach, in practice, leverages domain expertise to define expected tolerances in system’s behavior and alarm exceedance from such safety margins. However, this approach is incapable of identifying unknown risk and vulnerabilities. Machine learning has been long studied and deployed to identify precursors for such anomalies, with the great challenge of the need for sufficient labelled set of data to achieve a reliable and accurate performance. In this article, we develop an explainable deep semi-supervised model for anomaly detection in aviation, building upon recent advancements in the machine learning literature. The proposed model combines feature engineering and classification in the feature space, while leveraging all available data (labelled and unlabeled). Validating on two case studies of anomaly detection in take-off and landing phases of commercial aircraft, we show that our model is able to outperform state-of-the-art supervised anomaly detection model and reach significantly high accuracy and low false alarm with minimum amount of available labelled data.

Anomaly Detection↗

NASA NTRS1980

Decision making and problem solving with computer assistance

In modern guidance and control systems, the human as manager, supervisor, decision maker, problem solver and trouble shooter, often has to cope with a marginal mental workload. To improve this situation, computers should be used to reduce the operator from mental stress. This should not solely be done by increased automation, but by a reasonable sharing of tasks in a human-computer team, where the computer supports the human intelligence. Recent developments in this area are summarized. It is shown that interactive support of operator by intelligent computer is feasible during information evaluation, decision making and problem solving. The applied artificial intelligence algorithms comprehend pattern recognition and classification, adaptation and machine learning as well as dynamic and heuristic programming. Elementary examples are presented to explain basic principles.

Kraiss, F.↗

NASA NTRS1995

Introduction to Concepts in Artificial Neural Networks

This introduction to artificial neural networks summarizes some basic concepts of computational neuroscience and the resulting models of artificial neurons. The terminology of biological and artificial neurons, biological and machine learning and neural processing is introduced. The concepts of supervised and unsupervised learning are explained with examples from the power system area. Finally, a taxonomy of different types of neurons and different classes of artificial neural networks is presented.

Artificial Neural↗

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

autonomy↗

NASA NTRS2019

Overcoming the Challenges of Data Integration and Automation

Artificial Intelligence (AI) and machine learning (ML) are gaining increased attention as a way to leverage the world's data to solve problems. Although AI and ML offer much potential, there are often misconceptions about the application of such techniques. This panel discussion includes speakers from airlines and the research community who will present machine learning approaches they have developed on a variety of aviation data including digital flight data, safety reporting data, and traffic flow data. They will explain the purpose of the application, the data used, and the lessons learned in the development and deployment of their solutions. The panel discussion will focus on common pitfalls in developing and AI solution, the dangers of the current hype around AI, tips for gaining value from a machine learning solution, how to determine whether a machine learning approach is appropriate for a problem, and more.

Matthews, Bryan L.↗

NASA NTRS2023

Ceramic Capacitor Grain Size Analysis Using Electron Backscatter Diffraction (EBSD)

The overall scope of this NESC study was to identify (or develop) a tool, methodology, or process that can inspect a ceramic capacitor and consistently return repeatable grain size distribution results. It is important to note that the development of a machine learning technique was considered as an option for this study, but only if an existing automated tool was not available. This report explains why the Electron Backscatter Diffraction analysis method for grain structure and size distribution was deemed a suitable candidate for this work.

Electron Backscatter Diffraction↗

NASA NTRSDate not supplied

Linking OH Variability to Observable Variables, Meteorology and Transport

The hydroxyl radical (OH) plays a vital role in tropospheric chemistry, as it provides the dominant sink for a multitude of pollutants and climate-relevant gases such as methane. Observational constraints on the global distribution and temporal variability of OH are limited, and models simulate a wide range of OH distributions. While OH itself has a short atmospheric lifetime, OH is photochemically coupled to longer-lived species that undergo atmospheric transport. Here, we investigate how much of the OH variability within and between models can be explained by differences in observable species to develop diagnostics for OH differences. We find that NO 2 and water vapor together explain much of the spatial and temporal variability in simulated OH, and we use satellite observations to identify biases in these variables. The OH response to ENSO also differs between models, and we investigate potential causes of these differences such as differences in convection or lightning NOx. We also explore the potential of idealized tracers to represent the OH distribution. Within a single model, meteorological variables such as humidity and idealized tracers of transport can explain a significant portion of the OH spatial variability. We use a Gradient Boosted Regression Trees, a type of machine learning, to account for non-linear relationships between OH and the input variables.

Meteorology↗

NASA NTRSDate not supplied

Development of Machine Learning-Derived Microbiological and Immune Signatures: Applications in Adaptive Risk Assessment of Infectious Disease During Spaceflight

Infectious diseases represent an urgent risk for spaceflight with consequences ranging from loss in crew performance to crew incapacitation or loss of life should an outbreak occur. The resident environmental microbiome on the International Space Station has been monitored through routine surveillance over almost twenty years, beginning with culture-based microbial detection which has advanced to molecular methods in recent years. This has created a wealth of data that we have begun mining to define the microbial ecology of the ISS. Summarized here is our analysis of data from the historical microbial population defined by culture-based monitoring from the past two decades, organized by their likelihood to cause disease into clinical categories. As expected, many residents of the normal microflora in environments where people work and live were detected. However, some known pathogens were also detected. As the spaceflight environment can predispose humans to infection, crew health records were used to source additional data for the set to uncover clinical relevance. Data mining was performed on crew health records to capture adverse health events that may be related to infectious disease. Machine learning, specifically Random Forest analysis, was used to analyze the microbial and crew health datasets. The symptom categories were not explained by the ranked bacteria, due to lack of sufficient data for some categories and due to poor ranking of the pathogens for others. Poor ranking of the bacteria could be due to the clinical symptoms being linked to other disease-causing factors, such as allergy or viral infection. These findings suggest a lack of relationship between bacteria detected on surfaces in the ISS and historical health events experienced by astronauts.

Kristyn Hoffman↗

NASA NTRSDate not supplied

Machine Learning for the Validation of Expert-Elicited Causal Risk Diagrams

Exposure to spaceflight poses risk to human health in complex ways. To help manage this risk, the Human Systems Risk Board (HSRB) at the National Aeronautics and Space Administration (NASA) maintains a set of causal diagrams that attempt to explain how spaceflight hazards generate health risks and lead to adverse outcomes both in-mission, immediately post-mission, and over the long term. These causal risk diagrams are formulated as directed acyclic graphs (DAGs) and can function as knowledge graphs of connected risks and outcomes. These DAGs have proven useful for communication, and, through network analysis, have allowed for the identification of structurally important factors in the risk network. However, the utility these DAGs provide is directly proportional to their verisimilitude, making assessment of this trait using empirical data – whether from actual human spaceflight or various spaceflight analogue exposures and model organisms – a high priority. In this research we explore the use of machine learning algorithms to learn DAG structure from empirical data as a means of evaluating human-elicited DAG structures. To do so, we test several different graph structure-learning algorithms on data concerning changes in the bones of rats and mice after exposure to either spaceflight or a spaceflight analogue. We explore potential methods for indexing the similarity between each algorithm’s output DAG with all the others and with that of the expert-elicited DAG. We discuss next steps in this ongoing line of research and open science initiatives underway to complete them.

directed acyclic graphs↗

NASA NTRS2006

Measuring Constraint-Set Utility for Partitional Clustering Algorithms

Clustering with constraints is an active area of machine learning and data mining research. Previous empirical work has convincingly shown that adding constraints to clustering improves the performance of a variety of algorithms. However, in most of these experiments, results are averaged over different randomly chosen constraint sets from a given set of labels, thereby masking interesting properties of individual sets. We demonstrate that constraint sets vary significantly in how useful they are for constrained clustering; some constraint sets can actually decrease algorithm performance. We create two quantitative measures, informativeness and coherence, that can be used to identify useful constraint sets. We show that these measures can also help explain differences in performance for four particular constrained clustering algorithms.

constraints↗

NASA NTRS2018

Serious Gaming for Building a Basis of Certification via Trust and Trustworthiness of Autonomous Systems

Autonomous systems governed by a variety of adaptive and nondeterministic algorithms are being planned for inclusion into safety-critical environments, such as unmanned aircraft and space systems in both civilian and military applications. However, until autonomous systems are proven and perceived to be capable and resilient in the face of unanticipated conditions, humans will be reluctant or unable to delegate authority, remaining in control aided by machine-based information and decision support. Proving capability, or trustworthiness, is a necessary component of certification. Perceived capability is a component of trust. Trustworthiness is an attribute of a cyber-physical system that requires context-driven metrics to prove and certify. Trust is an attribute of the agents participating in the system and is gained over time and multiple interactions through trustworthy behavior and transparency. Historically, artificial intelligence and machine learning systems provide answers without explanation - without a rationale or insight into the machine “thinking”. In order to function as trusted teammates, machines must be able to explain their decisions and actions. This transparency is a product of both content and communication. NASA’s Autonomy Teaming & TRAjectories for Complex Trusted Operational Reliability (ATTRACTOR) project seeks to build a basis for certification of autonomous systems via establishing metrics for trustworthiness and trust in multi-agent team interactions, using AI (Artificial Intelligence) explainability and persistent modeling and simulation, in the context of mission planning and execution, with analyzable trajectories. Inspired by Massively Multiplayer Online Role Playing Games (MMORPG) and Serious Gaming, the proposed ATTRACTOR modeling and simulation environment is similar to online gaming environments in which player (aka agent) participants interact with each other, affect their environment, and expect the simulation to persist and change regardless of any individual agent’s active participation. This persistent simulation environment will accommodate individual agents, groups of self-organizing agents, and large-scale infrastructure behavior. The effects of the emerging adaptation and coevolution can be observed and measured to building a basis of measurable trustworthiness and trust, toward certification of safety-critical autonomous systems.

Allen, B. Danette↗