Search NASA⌕ Search

SEARCH · Search NASA

Results for “Robust artificial intelligence”

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 163 records · Page 9

China’s Bid To Lead Artificial Intelligence Chip Development within the Decade

In 2017, the Chinese government announced an ambitious, broad strategy to become the global leader in artificial intelligence (AI) theories, technologies, and applications by 2030 and indicated that China’s ability to indigenously produce cutting-edge AI chips would be integral to its success. China’s goal to become a dominant producer of AI hardware within a decade is a bold undertaking because China faces domestic chip production challenges and fierce competition from US chip producers. Our review of Chinese AI chip product lines shows various levels where Chinese companies compete with global firms in the production chain. China lacks a robust indigenous AI chip production infrastructure, and the United States and its allies are tightening controls on the supply of advanced semiconductor manufacturing equipment (SME) and electronic design automation (EDA) software to China. In contrast to their Chinese counterparts, US companies operate in all areas of AI chip production and have consistently driven the development of new chip designs. AI chip production is a costly endeavor, and China’s chip producers currently lack the customer base to lead global AI chip development by the 2030 goal. An expanded customer base may help China attract the necessary expertise to bolster its AI chip production chain. This would also help Chinese producers make their investments in the requisite technology economically sustainable. Chinese researchers continue to pursue promising next-generation AI chip designs, such as neuromorphic computing-based architectures, which in the next five to ten years could position Chinese companies to make or contribute to key innovations in the field.

74 ATOMIC AND MOLECULAR PHYSICS↗

Development of Explainable, Knowledge-Guided AI Models to Enhance the E3SM Land Model Development and Uncertainty Quantification

Focal Area(s): (2)Predictive modeling using AI techniques and AI-derived model components; use of AI and other tools to design a prediction system comprising of a hierarchy of models. (3) Insight gleaned from complex data (both observed and simulated) using AI, big data analytics, and other advanced methods, including explainable AI and physics- or knowledge- guided AI. Science Challenge: The Energy Exascale Earth System Model (E3SM) is a fully coupled, state-of-the-science Earth system model that uses code optimized for DOE's advanced computers to address the most critical scientific questions facing our nation and society (Golaz et al., 2019). The E3SM Land model (ELM) is designed to understand how the changes in terrestrial land surfaces will interact with other Earth system components and has been used to understand hydrologic cycles, biogeophysics, and ecosystem dynamics. In spite of great successes, the ELM has several known issues that restrain rapid improvements. For example, the ELM uses equilibrium models to simulate dynamic land-climate interactions and it requires long model spin-up time to identify suitable initial conditions for transient simulations. The ELM lacks built-in uncertainty mechanisms that can improve the robustness of model predictions. The ELM is a holistic, deterministic model system with a rigid design, and in many situations, it is hard to modify the ELM system to incorporate new theory/hypothesis and new data across scales to address emerging science problems (such as predicting the impacts of water cycle extremes). In addition, The ELM is technically optimized for traditional CPU-centric computers and it cannot fully utilize the current and incoming leadership computers for model simulations and uncertainty quantification (UQ). The success of artificial intelligence (AI) has inspired scientists to use AI models to discover intrinsic features from simulation data (Chattopadhyay et al., 2020) and observational data (Reichstein et al., 2019) to gain further process understanding of Earth science problems. However, autonomous AI model training through deep learning usually requires a huge amount of annotated data. To overcome the limitations from the data and computing resources, knowledge-guided AI models are necessary where human-knowledge is ingested in model construction (Banino et al., 2018) and training process (Silver et al., 2016) for efficient learning. Herein, we present a new way that leverages the process understanding from the ELM to guide AI model development for the ELM enhancement and UQ. We hope this study can inspire further Earth and environmental system model developments and transformations.

54 ENVIRONMENTAL SCIENCES↗

Harnessing ML Privacy by Design Through Crossbar Array Non-idealities

Deep Neural Networks (DNNs), handling computeand data-intensive tasks, often utilize accelerators like Resistiveswitching Random-access Memory (RRAM) crossbar for energyefficient in-memory computation. Despite RRAM’s inherent nonidealities causing deviations in DNN output, this study transforms the weakness into strength. By leveraging RRAM non-idealities, the research enhances privacy protection against Membership Inference Attacks (MIAs), which reveal private information from training data. RRAM non-idealities disrupt MIA features, increasing model robustness and revealing a privacy-accuracy tradeoff. Empirical results with four MIAs and DNNs trained on different datasets demonstrate significant privacy leakage reduction with a minor accuracy drop (e.g., up to 2.8% for ResNet-18 with CIFAR-100).

artificial intelligence↗

Entry Abort Determination Using Non-Adaptive Neural Networks for Mars Precision Landers

The 2009 Mars Science Laboratory (MSL) will attempt the first precision landing on Mars using a modified version of the Apollo Earth entry guidance program. The guidance routine, Entry Terminal Point Controller (ETPC), commands the deployment of a supersonic parachute after converging the range to the landing target. For very dispersed cases, ETPC may not converge the range to the target and safely command parachute deployment within Mach number and dynamic pressure constraints. A full-lift up abort can save 85% of these failed trajectories while abandoning the precision landing objective. Though current MSL requirements do not call for an abort capability, an autonomous abort capability may be desired, for this mission or future Mars precision landers, to make the vehicle more robust. The application of artificial neural networks (NNs) as an abort determination technique was evaluated by personnel at the National Aeronautics and Space Administration (NASA) Johnson Space Center (JSC). In order to implement an abort, a failed trajectory needs to be recognized in real time. Abort determination is dependent upon several trajectory parameters whose relationships to vehicle survival are not well understood, and yet the lander must be trained to recognize unsafe situations. Artificial neural networks (NNs) provide a way to model these parameters and can provide MSL with the artificial intelligence necessary to independently declare an abort. Using the 2009 Mars Science Laboratory (MSL) mission as a case study, a non-adaptive NN was designed, trained and tested using Monte Carlo simulations of MSL descent and incorporated into ETPC. Neural network theory, the development history of the MSL NN, and initial testing with severe dust storm entry trajectory cases are discussed in Reference 1 and will not be repeated here. That analysis demonstrated that NNs are capable of recognizing failed descent trajectories and can significantly increase the survivability of MSL for very dispersed cases. NN testing was then broadened to evaluate fully dispersed entry trajectories. The NN correctly classified 99.7% of descent trajectories as abort or nonabort and reduced the probability of an unsafe parachute deployment by 83%. This second, broader testing phase is discussed in this paper.

Graybeal, Sarah R.↗

FAIR AI models in high energy physics

Abstract The findable, accessible, interoperable, and reusable (FAIR) data principles provide a framework for examining, evaluating, and improving how data is shared to facilitate scientific discovery. Generalizing these principles to research software and other digital products is an active area of research. Machine learning models—algorithms that have been trained on data without being explicitly programmed—and more generally, artificial intelligence (AI) models, are an important target for this because of the ever-increasing pace with which AI is transforming scientific domains, such as experimental high energy physics (HEP). In this paper, we propose a practical definition of FAIR principles for AI models in HEP and describe a template for the application of these principles. We demonstrate the template’s use with an example AI model applied to HEP, in which a graph neural network is used to identify Higgs bosons decaying to two bottom quarks. We report on the robustness of this FAIR AI model, its portability across hardware architectures and software frameworks, and its interpretability.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

A Conceptual World Information Library (WIL) and Land Use Information System (LUIS) - 16181

The Organization for Economic Co-operation and Development Nuclear Energy Agency initiative on the Preservation of Records, Knowledge and Memory is addressing the topic of communicating with future generations on the location, specific contents, and potential risks associated with deep geologic nuclear waste repositories. At the Waste Isolation Pilot Plant (WIPP) in the United States, the U.S. Department of Energy (DOE) has committed, prior to the facility closure, to develop a Passive Institutional Controls (PICs) program designed to last as long as practicable. A portion of this PICs program includes development of records packages, selection of data storage materials and methods, and a determination of records retention/storage locations. The approved plan for record retention at WIPP includes the storage of information including hard copies of data, figures and maps in multiple libraries and archive record centers. With this in mind, it is easy to envision reams of various paper documents in a robust physical archive record center similar to one of the museums in Washington D.C., or DOE's Legacy Management facility in Morgantown, West Virginia. While some portion of records for nuclear waste burial sites should be maintained in this fashion for near-term retrieval purposes, it is widely accepted that this is not an efficient way to communicate with future generations even 1,000 years from now. Transmitting large detailed volumes of information to the future should be captured in an electronic format; maintained on computers, translated by computers, and perhaps updated by artificial intelligence as machine and human languages change over the centuries. In addition to a physical records development and storage process for transmittal to future generations, a web-based electronic database system should be developed. A World Electronic Library (WEL) database could be funded from various nations and perhaps sanctioned by the United Nations and/or the IAEA. This WEL could contain information regarding several different subjects with the intent of being a one-stop-information-shop for future generations. This database would require updates and maintenance for as long as there is a recipient. One subset of the WEL would be a spatial database containing all the information available to any set of GPS coordinates, anywhere within the world. This Land Use Information System (LUIS) database would contain information on past and present land use, natural resources, known geology, hydrology and atmospheric conditions, potential warnings, and other pertinent information. The LUIS database is where specific electronic information, a subset of all the records data gathered for a nuclear waste repository, could reside. For not only would LUIS provide the information on a nuclear waste repository when specific GPS coordinates were entered; but a search from the LUIS on 'Nuclear Waste Repositories' could bring up information, including data on location of repositories, radionuclides, operations, D and D, maps, and regulations, plus many other details for locations throughout the world. This tool could be used by future generations for a number of land use or resource exploration decisions. So what can we do now? We can agree to the types of information that should be captured into an electronic database for nuclear waste repositories. We can agree to the levels of detail, the file names and the formats, for ease of combining information sets in the future. Perhaps we can agree to a central electronic data storage site, or sites, where this information will reside for import into a centralized electronic record system, if one is ever developed. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Earth Independent Medical Operations (EIMO) Datascope: Challenges and Potential Solutions

Data flows and storage/retrieval capacity are severely constrained during missions in space and challenges will become even greater during exploration class missions. There is a need for an artificial intelligence (AI)-based clinical decision support system (CDSS) to monitor and analyze data to provide real-time consultative support for crew medical officer (CMO) decision-making. EIMO is defined as the gradual transition of medical care and decision making from terrestrial to space-based assets, enabling support of astronaut health and performance and reducing overall mission risk. While a hallmark of this paradigm shift from low-earth orbit is that on-board care will increasingly become the responsibility of the astronauts for primary management and decision making, terrestrial assets will continue to be paramount in pre-mission screening and planning, as well as prevention, health maintenance and long-term care contingencies. New capabilities and systems that enable progressively more robust and resilient systems and crews will be necessary to reduce risk and increase probability of deep space exploration mission success. An aspiration for EIMO is to develop AI-enhanced solutions for analysis of crew health & performance data and to facilitate clinical decision support for autonomous medical operations. A “system of systems” approach is envisioned whereby EIMO will deploy AI-supported natural language processing and machine learning (ML) techniques to utilize embedded reference databases and real-time data streams [input vectors] from multiple data sources. Constituent input vectors may include environmental controls, countermeasures data, behavioral data, physiologic wearables, point-of-care laboratory tests, personalized medical records, inventory trade space risk assessments, COTS medical databases, and ground support inputs. An ideal AI capability would possess trained fusion algorithms to cross reference input vectors with medical ‘knowledge’ [cultivated database] to stratify relevant data streams for predictive and actionable capabilities. In addition, EIMO will feature mobility, in that it can be accessed and can push/pull data within and between multiple vehicles/habitats. Large amounts and variable sources of data can be leveraged to diagnose, inform treatment strategies, and potentially predict medical events and performance decrements. Inclusion of advanced training tools using extended reality will enable increasingly autonomous medical care to aid a CMO when ground support is unavailable or time-delayed beyond required action window, e.g., emergent medical situations. EIMO CDSS would require very large datasets to train pre-flight and significant amounts of data are needed to support ML via in-flight CDSS operations. An additional challenge will be to find sufficient data to train a model relevant to astronaut demographics. The rapid, accelerating evolution of this field creates a propitious solution space to leverage multi-modal AI through public-private partnership(s). The status of multi-modal AI systems today would preclude their use for long duration missions as they remain unreliable and are subject to “digital hallucinations” and other errors that could pose operational risk. A federated labs structure is being considered to test and optimize data flow from the multiple input vectors leading to field testing in suitable ground/flight analogs. Critical to the success of an EIMO CDSS will be integration and interoperability and success will be defined by a system that can serve as an in-flight medical consult for the CMO providing critical support during medical contingencies. Benefits to terrestrial medicine may be significant as an outflow of the EIMO medical system, particularly for remote areas and communities lacking significant infrastructure, personnel and resources.

Medical Operations↗

Identification and interpretation of patterns in rocket engine data: Artificial intelligence and neural network approaches

This paper describes an expert system which is designed to perform automatic data analysis, identify anomalous events, and determine the characteristic features of these events. We have employed both artificial intelligence and neural net approaches in the design of this expert system. The artificial intelligence approach is useful because it provides (1) the use of human experts' knowledge of sensor behavior and faulty engine conditions in interpreting data; (2) the use of engine design knowledge and physical sensor locations in establishing relationships among the events of multiple sensors; (3) the use of stored analysis of past data of faulty engine conditions; and (4) the use of knowledge-based reasoning in distinguishing sensor failure from actual faults. The neural network approach appears promising because neural nets (1) can be trained on extremely noisy data and produce classifications which are more robust under noisy conditions than other classification techniques; (2) avoid the necessity of noise removal by digital filtering and therefore avoid the need to make assumptions about frequency bands or other signal characteristics of anomalous behavior; (3) can, in effect, generate their own feature detectors based on the characteristics of the sensor data used in training; and (4) are inherently parallel and therefore are potentially implementable in special-purpose parallel hardware.

Ali, Moonis↗

Experimental Verification of Electric Drive Technologies Based on Artificial Intelligence Tools

In this report, a fully integrated prototype of a flight servo control system is successfully developed and implemented using brushless dc motors. The control system is developed by the fuzzy logic theory, and implemented with a multilayer neural network. First, a neural network-based architecture is introduced for fuzzy logic control. The characteristic rules and their membership functions of fuzzy systems are represented as the processing nodes in the neural network structure. The network structure and the parameter learning are performed simultaneously and online in the fuzzy-neural network system. The structure learning is based on the partition of input space. The parameter learning is based on the supervised gradient decent method, using a delta adaptation law. Using experimental setup, the performance of the proposed control system is evaluated under various operating conditions. Test results are presented and discussed in the report. The proposed learning control system has several advantages, namely, simple structure and learning capability, robustness and high tracking performance and few nodes at hidden layers. In comparison with the PI controller, the proposed fuzzy-neural network system can yield a better dynamic performance with shorter settling time, and without overshoot. Experimental results have shown that the proposed control system is adaptive and robust in responding to a wide range of operating conditions. In summary, the goal of this study is to design and implement-advanced servosystems to actuate control surfaces for flight vehicles, namely, aircraft and helicopters, missiles and interceptors, and mini- and micro-air vehicles.

Rubaai, Ahmed↗

Artificial Intelligence for Controlling Robotic Aircraft

A document consisting mostly of lecture slides presents overviews of artificial-intelligence-based control methods now under development for application to robotic aircraft [called Unmanned Aerial Vehicles (UAVs) in the paper] and spacecraft and to the next generation of flight controllers for piloted aircraft. Following brief introductory remarks, the paper presents background information on intelligent control, including basic characteristics defining intelligent systems and intelligent control and the concept of levels of intelligent control. Next, the paper addresses several concepts in intelligent flight control. The document ends with some concluding remarks, including statements to the effect that (1) intelligent control architectures can guarantee stability of inner control loops and (2) for UAVs, intelligent control provides a robust way to accommodate an outer-loop control architecture for planning and/or related purposes.

Krishnakumar, Kalmanje↗

NASA's Implementation of Cloud Services for Human Space Flight

Cloud is a tried-and-true technology used throughout United States government agencies, including the National Aeronautics and Space Administration (NASA). With reliable results and infrequent downtimes, cloud allows for secure remote access, customizability, and streamlined monitoring options, creating an environment for better data integrity and availability. As NASA increasingly migrates functions to the cloud, the Space Communications and Navigation Program (SCaN) program has been investigating how this capability can be leveraged to provide communication services to its users and customers. Currently, missions such as NASA-ISRO Synthetic Aperture Radar (NISAR), Plankton, Aerosol, Cloud, ocean Ecosystem (PACE), and Roman Space Telescope (RST) are planned to incorporate cloud into their data delivery architecture. However, SCaN is looking to expand further. This conversion to using cloud services allows for greater availability of mission data for both robotic and human space flight (HSF)missions. The SCaN program and the Near Space Network (NSN) are working to consolidate resources and create a cloud environment suitable for the entirety of the SCaN program network architecture. SCaN is in the process of finalizing its cloud architecture and soon will be implementing cloud services. The new services used will adhere to federal regulations including Federal Risk and Authorization Management Program (FedRAMP), which is built upon National Institute of Standards and Technology (NIST)documentation. While keeping in mind these security requirements, an auxiliary objective of the cloud integration is to ensure the most cost-efficient solution; providing a scalable, robust and resilient system. Using cloud services, NASA will gain access to better centralized monitoring and management features, along with customizable services on a pay-per-use plan. With the ever-growing NASA mission data volume needs, maintaining ample storage space is another major constraint. Processing and storing such large amounts of data, on the order of terabytes a day, requires dynamic processing capability which is inherently a strength of cloud computing. By routing this data from ground stations through the cloud, there will be greater ease of access for both SCaN and the user community. Artificial intelligence and other built-in cloud functions can also enhance efficiency, improving data processing time. Thereby also allowing for better data availability. As we look to the future of cloud services, NASA will continue to leverage capabilities that will benefit NASA’s ability to provide cost-effective communication services. This paper further outlines the evolution of cloud use by SCaN in the context of Human Space Flight.

cloud storage↗

Multisensor Machine Learning to Retrieve High Spatiotemporal Resolution Land Surface Temperature

Climate change is making heat waves more frequent, long-lasting, and severe. While multiple satellite types provide data to monitor surface temperature, geostationary (GEO) sensors provide near-continuous, continental-scale observations which can better capture the diurnal variability of land surface temperature (LST) than intermittent observations from low-earth orbit (LEO) sensors. However, standard products from GEO satellites are available at coarsened spatial and temporal resolutions compared to the native sensor resolution. Using datasets from the NASA Earth Exchange, we leveraged co-located, co-temporal observations from LEO and GEO satellites to learn a data-driven mapping using a convolutional neural network. The resulting NASA Earth eXchange Artificial Intelligence LST (NEXAI-LST) achieved a mean absolute error of 1.73 K relative to the target LEO product and improves on both spatial and temporal resolution [2 km, 10 minute] compared to the GEO full disk standard product [10 km, hourly]. In validation against measurements from a ground-based sensor network, NEXAI-LST achieves similar or better fit than both LEO and GEO standard products, while depending none of the prior knowledge of land surface and atmospheric states required by physical-statistical models. Further, application of the model to unseen LEO and GEO satellites demonstrates robust generalization of the model across spatial region, time of day, and sensor. In support of NASA’s open-source science initiative, we make our NEXAI-LST product, model, and codes available to facilitate data exploration and further studies.

Kate Marie Duffy↗

Real-time automatic fiducial marker tracking in low contrast cine-MV images

Purpose: To develop a real-time automatic method for tracking implanted radiographic markers in low-contrast cine-MV patient images used in image-guided radiation therapy (IGRT). Methods: Intrafraction motion tracking using radiotherapy beam-line MV images have gained some attention recently in IGRT because no additional imaging dose is introduced. However, MV images have much lower contrast than kV images, therefore a robust and automatic algorithm for marker detection in MV images is a prerequisite. Previous marker detection methods are all based on template matching or its derivatives. Template matching needs to match object shape that changes significantly for different implantation and projection angle. While these methods require a large number of templates to cover various situations, they are often forced to use a smaller number of templates to reduce the computation load because their methods all require exhaustive search in the region of interest. The authors solve this problem by synergetic use of modern but well-tested computer vision and artificial intelligence techniques; specifically the authors detect implanted markers utilizing discriminant analysis for initialization and use mean-shift feature space analysis for sequential tracking. This novel approach avoids exhaustive search by exploiting the temporal correlation between consecutive frames and makes it possible to perform more sophisticated detection at the beginning to improve the accuracy, followed by ultrafast sequential tracking after the initialization. The method was evaluated and validated using 1149 cine-MV images from two prostate IGRT patients and compared with manual marker detection results from six researchers. The average of the manual detection results is considered as the ground truth for comparisons. Results: The average root-mean-square errors of our real-time automatic tracking method from the ground truth are 1.9 and 2.1 pixels for the two patients (0.26 mm/pixel). The standard deviations of the results from the 6 researchers are 2.3 and 2.6 pixels. The proposed framework takes about 128 ms to detect four markers in the first MV images and about 23 ms to track these markers in each of the subsequent images. Conclusions: The unified framework for tracking of multiple markers presented here can achieve marker detection accuracy similar to manual detection even in low-contrast cine-MV images. It can cope with shape deformations of fiducial markers at different gantry angles. The fast processing speed reduces the image processing portion of the system latency, therefore can improve the performance of real-time motion compensation.

60 APPLIED LIFE SCIENCES↗

“Innervated” Pipelines: A New Technology Platform for In-Situ Repair and Embedded Intelligence

The overall vision pursued under the project would ultimately enable capability for real-time operational monitoring of natural gas (and other) pipeline infrastructures through the combination of in-situ repair and rehabilitation methods with embedded fiber optic sensing and associated data analytics methods and platform tools. Benefits to the public include more resilient and robust natural gas pipeline infrastructures with the potential to expand the applications of developed technologies under the program to other important areas of critical energy infrastructure in the future such as H2 pipelines and infrastructure, municipal and other civil infrastructure, as well as subsurface oil, gas, and geothermal infrastructure applications. The program has successfully demonstrated feasibility for all of the critical enabling elements and serves as a foundation for future technology maturation, deployment, and customization for other potential applications and high-priority needs into the future. Several underlying innovations have shown potential for commercial deployment and are the subject of continued development and technology transfer based upon patents submitted during the project duration.

02 PETROLEUM↗

Atikokan Digital Twin: Machine learning in a biomass energy system

The Atikokan Generating Station, operated by Ontario Power Generation, has a 200 MW, biomass-fired tower boiler that operates on a dispatch schedule with a five-minute cycle. The boiler is generally operated in the range of 40–100 MW using two of five burner levels. In order to optimize boiler performance, we propose the implementation of a unique digital twin. Our digital twin abstraction couples Bayesian inference from science-based models and from observations (machine learning) with decision theory to predict operating-variable set points that optimize the physical asset (the boiler) in the presence of uncertainty (artificial intelligence). We focus this paper on the continuous Bayesian machine learning part of the Atikokan Digital Twin; we discuss decision theory in a companion paper. We identify and learn about 12 operational, model, and measured-output parameters and their uncertainties from high-fidelity, science-based simulations of the Atikokan boiler and from the observed measurements at the power plant. Since the goal of the Atikokan Digital Twin is to implement it online in real time, we require fast function evaluations for the quantities of interest extracted from the simulations in the Bayesian analysis. We use Gaussian process regression/interpolation to create accurate, robust surrogate models. We define the Bayesian priors and likelihood function and solve for the posterior distributions of the 12 parameters. Here we then propagate these distributions (i.e., parameters with uncertainty) into the predicted distributions of 790 quantities of interest to learn about the relative importance of various sources of error including experimental, model, and operating-parameter errors.

09 BIOMASS FUELS↗

El Agente: An autonomous agent for quantum chemistry

Computational chemistry tools are widely used to study the behavior of chemical phenomena. Yet, the complexity of these tools can make them inaccessible to non-specialists and challenging even for experts. In this work, we introduce El Agente Q, an LLM-based multi-agent system that dynamically generates and executes quantum chemistry workflows from natural language user prompts. The system is built on a novel cognitive architecture featuring a hierarchical memory framework that enables flexible task decomposition, adaptive tool selection, post-analysis, and autonomous file handling and submission. El Agente Q is benchmarked on six university-level course exercises and two case studies, demonstrating robust problem-solving performance (averaging >87% task success) and adaptive error handling through in situ debugging. It also supports longer-term, multi-step task execution for more complex workflows, while maintaining transparency through detailed action trace logs. Together, these capabilities lay the foundation for increasingly autonomous and accessible quantum chemistry.

agentic systems↗

Comprehensive AI-based System for Control, Sensor Estimation, and Fault Detection of Cascaded Multilevel Inverters

In this paper, an Artificial Intelligence-based (AI) system is proposed for an 11-level cascaded H-bridge multilevel inverter (MLI) with the aims of harmonic suppression and reliability enhancement. The system consists of three seamlessly integrated Neural Networks (NNs). First, a multilayer perceptron is used to generalize the optimal switching angles for selective harmonic elimination under non-equal DC voltages. Next, an autoencoder NN estimates the voltage sensor readings to address potential drifting. Finally, a perceptron NN detects inverter faults based solely on the output voltage of the MLI. Simulation scenarios were evaluated, and the results show that the proposed system provides a comprehensive solution for the robust operation of the MLI. The proposed solution is capable of minimizing the targeted harmonics orders with minimal impact on the fundamental voltage, even when the voltage sensor drifts. Furthermore, the inverter under fault conditions was successfully identified.

Rezende da Costa Reis Kimpara, Renata↗

Temporal Subsampling Diminishes Small Spatial Scales in Recurrent Neural Network Emulators of Geophysical Turbulence

The immense computational cost of traditional numerical weather and climate models has sparked the development of machine learning (ML) based emulators. Because ML methods benefit from long records of training data, it is common to use data sets that are temporally subsampled relative to the time steps required for the numerical integration of differential equations. Here, we investigate how this often overlooked processing step affects the quality of an emulator's predictions. We implement two ML architectures from a class of methods called reservoir computing: (a) a form of Nonlinear Vector Autoregression (NVAR), and (b) an Echo State Network (ESN). Despite their simplicity, it is well documented that these architectures excel at predicting low dimensional chaotic dynamics. We are therefore motivated to test these architectures in an idealized setting of predicting high dimensional geophysical turbulence as represented by Surface Quasi-Geostrophic dynamics. In all cases, subsampling the training data consistently leads to an increased bias at small spatial scales that resembles numerical diffusion. Interestingly, the NVAR architecture becomes unstable when the temporal resolution is increased, indicating that the polynomial based interactions are insufficient at capturing the detailed nonlinearities of the turbulent flow. The ESN architecture is found to be more robust, suggesting a benefit to the more expensive but more general structure. Spectral errors are reduced by including a penalty on the kinetic energy density spectrum during training, although the subsampling related errors persist. Future work is warranted to understand how the temporal resolution of training data affects other ML architectures.

58 GEOSCIENCES↗