Performance Metrics for Intelligent Systems Workshop (PerMIS'08 Workshop Proceedings)
No abstract prepared.
SEARCH · Engineering Papers
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.
No abstract prepared.
The advent of widespread use of artificial intelligence (AI) and machine learning (ML) models in science, coupled with fast data production rates of scientific instruments strain the traditional batch-oriented high-performance computing (HPC) environment. As scientific exploration continues to require more data and faster processing and analysis, new emerging technologies and capabilities to enable cross-facility and time-sensitive workflows are required for seamless integration of HPC and experimental facilities. The Advanced Computing Ecosystem (ACE) is a strategic initiative within the Oak Ridge Leadership Computing Facility (OLCF) established in 2024 to support the development of cutting-edge technologies to advance computational research and infrastructure at OLCF and across the Department of Energy (DOE). Several DOE initiatives are spearheading the evolution of the scientific landscape by blurring facility boundaries and connecting the user facilities to advance scientific capabilities and ensure energy dominance. The DOE Integrated Research Infrastructure (IRI) program is one example that is laying a foundation to support complex cross-facility workflows. The IRI program aims to integrate diverse computational resources, data infrastructures, and scientific instruments to facilitate collaboration and accelerate scientific discovery. The Interconnected Science Ecosystem (INTERSECT) initiative at Oak Ridge National Laboratory (ORNL) is another example that aims to revolutionize scientific research through AI-driven, interconnected autonomous laboratories and research facilities. Finally, the American Science Cloud (AmSC), recently announced in the “One Big Beautiful Bill”, aims to leverage prior infrastructure efforts of the IRI and automation and AI efforts of INTERSECT (and others) to build a federated, AI-augmented AmSC platform to unify the DOE’s computing, experimental, and data resources to catalyze scientific innovation.
The discovery of a new allotropic form of elemental carbon – the fullerenes – and subsequently other novel forms of elemental carbon with pyramidalized surfaces, most notably single-walled and multi-walled carbon nanotubes, introduced a novel structural motif to the polycyclic aromatic hydrocarbons (PAHs) with nonplanar surfaces. Our research program supported by BES DOE grant DE-FG02-04ER15514 has dealt with the synthesis, structural studies, and chemistry of the novel curved-surface PAHs with carbon frameworks structurally related to fullerenes. They are referred to as “buckybowls”. We prepared several new buckybowls and, even more importantly, developed the efficient, gram-scale synthetic methodologies for the preparation of small buckybowls, most notably corannulene (C20H10) and its derivatives. In addition, the employment of the corannulene-based synthons previously developed in our laboratory led to a number of highly nonplanar molecular architectures with two or more corannulene subunits with a potential for the applications as novel materials in separation sciences, nanoelectronics, photovoltaics and catalysis. In collaboration with Professor Angelici (Iowa State) we prepared and characterized several transition metal complexes of corannulene, providing the first structural characterization of η6 metal complexes of buckybowls by a single crystal X-ray diffraction. In addition to the definitive structural characterization of the complexes we demonstrated that the (η6-C6Me6)Ru2+ unit in some relatively stable complexes activate the corannulene ligand to react with proper nucleophiles suggesting that such complexex may be used in catalysis. (Section C). We have explored the efficiency of the dispersion-based interactions of curved-surface conjugated carbon networks by high-level computational models. We showed that the curvature of such networks does not reduce the van der Waals attractions as compared to the planar systems of similar size. We than concentrated on the design, synthesis and testing of the previously unknown molecular receptors with corannulene pincers which are capable of forming the strong ball-and-socket inclusion complexes with fullerenes in solution and in the solid state. Buckycatcher I (a molecular receptor with two corannulene pincers preorganized on a tetrabensocyclooctatetraene tether) inclusion complexes with fullerenes provided the first experimental evidence for the importance of concave-convex π – π interactions in the supramolecular chemistry of fullerene carbon cages with buckybowls. C60@Buckycatcher I has become the prototypical supramolecular system formed by the relatively weak (on the atom-to-atom bases) and has been extensively used by the computational community to test the quality of the theoretical models. In addition, Buckycatcher I shows an exceptional ability to adopt other guest molecules and several its inclusion complexes and/or solvates have been structurally characterized. These unusual structures show the potential of the buckycatchers to be tested as novel organic materials. “Intelligent design” of molecular receptors with corannulene receptors using computational approach allowing for a priori prediction of their binding potentials led to the preparation of other buckycatchers. Both bi- and tridentate corannulene pincers were tested and two of the bidentate receptors (Buckycatchers II and III) exhibited the outstanding affinity toward fullerenes, significantly exciding Buckycatcher I performance. Careful tailoring of the tethers resulted in the optimization of binding energies of the receptors with guest carbon cages and in the reduction of the entropy/solvation penalties. Practical preparation of dicorannulenopentacene opens a new avenue for the synthesis of a pool of bis-corannulene receptors possessing polar groups on their dibenzobarrelene tether. The polar “anchors” can be used to attach these efficient fullerene receptors to solid supports in order to modify their surfaces with the potential applications in separation sciences, catalysis and photovoltaic materials. additionally, the presence of such groups will improve the solubility of the receptors in polar solvents, expanding the scope of their supramolecular chemistry in solutions. Rigorous studies of thermodynamics of host-guest association of molecular clips and tweezers in organic solvents with C60/C70 inclusion complexes with Buckycatcher I as a model system have provided a full set of thermodynamical data including ΔG, ΔH, and –TΔS, for the formation of the inclusion complexes over a range of temperatures and in several solvents. Both 1H NMR and Isothermal Calorimetry (ITC) titrations provide virtually identical association constants, confirming the reliability of the results. WE have shown that thermodynamics of the host-guest complex formation is more complicated than anticipated and proposed by the existing computational models. These data are of premium importance for the testing of the computational solvation models and for a deeper understanding of the supramolecular interactions in organic solvents.
The intelligent Data Delivery Service (iDDS) has been developed to cope with the huge increase of computing and storage resource usage in the coming LHC data taking. iDDS has been designed to intelligently orchestrate workflow and data management systems, decoupling data pre-processing, delivery, and main processing in various workflows. It is an experiment-agnostic service around a workflow-oriented structure to work with existing and emerging use cases in ATLAS and other experiments. Here we will present the motivation for iDDS, its design schema and architecture, use cases and current status, and plans for the future.
The intelligent Data Delivery Service (iDDS) has been developed to cope with the huge increase of computing and storage resource usage in the coming LHC data taking. It has been designed to intelligently orchestrate workflows and data management systems, decoupling data pre-processing, delivery, and primary processing in large scale workflows. It is an experiment-agnostic service that has been deployed to serve data carousel (orchestrating efficient processing of tape-resident data), machine learning hyperparameter optimization, active learning, and other complex multi-stage workflows defined via DAG (Directed Acyclic Graph), CWL (Common Workflow Language) and other descriptions, including a growing number of analysis workflows. We will at first introduce some deployed use cases in a summary. Then we will focus on new improvements and use cases under developments in ATLAS, Rubin Observatory and sPHENIX, together with future efforts.
Neuromorphic Computing is a burgeoning field of research. Many groups are exploring hardware architectures and theoretical ideas about spiking recurrent neural networks. The overarching goal is to exploit the low power promise of these neuromorphic systems. However, it is difficult to train spiking recurrent neural networks (SRNNs) to perform tasks and make efficient use of neuromorphic hardware. Reservoir Computing is an attractive methodology because it requires no tuning of weights for the reservoir itself. Yet, to find optimal reservoirs, manual tuning of hyperparameters such as hidden neurons, synaptic density, and natural structure is still required. Because of this, researchers often have to generate and evaluate many networks, which can result in non-trivial amounts of computation. This paper employs the reservoir computing technique (specifically liquid state machines) and genetic algorithms in order to develop useful networks that can be deployed on neuromorphic hardware. We build on past work in reservoir computing and genetic algorithms to demonstrate the power of combining these two techniques and the advantage it can provide over manually tuning reservoirs for use on classification tasks. We discuss the complexities of determining whether or not to use the genetic algorithms approach for liquid state machine generation.
A building energy management system (BEMS) is a computer-based system designed to monitor and control a building's energy needs. Modern BEMS rely on the sensing and connectivity capabilities of Internet of Things (IoT) technology to intelligently adjust the energy consumption to reduce cost while respecting the consumers' preferences. Increasingly, control decisions are made based on predictions by models trained using supervised machine learning methods, which still requires control policies to be formulated in a rule-based fashion. When using reinforcement learning (RL) instead, control policies are learned by observing the utility in terms of cost and comfort associated with actions such as a change in the heating system's setpoint. The resulting RL-based controllers can capture not only the dynamics of the building and the associated electrical devices, but also fluctuations in electricity prices and user demand, avoiding the need to combine multiple predictive models with tailored control policies. This chapter will provide an overview of RL-based approaches for BEMS. After sketching the taxonomy of general RL methods, we discuss the implications of relying on the individual methods in a BEMS context. Existing work applying RL is presented along the key devices controlled by BEMS systems. Finally, we summarize the state-of-the-art and sketch limitations and open research directions.
In hypothetical severe accident scenarios, nuclear power plant safety is challenged by core degradation and release of fission products. To aid the plant operator and technical support center staff, research has been performed to develop understanding of severe accident phenomenology, assessing their risk and devise measures to mitigate accident consequences (Sehgal, 2011). Nuclear power plant accidents involve highly complex physical and chemical interactions, a large number of safety related systems, and emergency operating procedures (EOP) and severe accident management guidelines (SAMG). Large number of factors with uncertainty and stress can overwhelm the operators. The overall objective of the present research is to develop a methodology and tools that an operator can use to predict severe accident progression and make effective decisions to arrest and manage the accident under large uncertainties. Towards this goal, this study examines a novel approach that brings to bear a combined use of techniques in artificial intelligence (Russel and Norvig, 2010), including Bayesian Network (BN), Answer Set Programming (ASP) and Fuzzy Inference (FI) to achieve faster-than-real-time, yet sufficiently accurate analysis of severe accident progression. Bayesian network (BN) is a type of probabilistic graphical models that can be used to represent knowledge and conditional dependencies about an uncertain realm. It is useful for capturing the causal relationships in a complex system. It also allows prediction via Bayesian inference (Kelly and Smith, 2012). It is composed of nodes and edges, which express random variables and probabilistic relationships between the nodes, respectively. This relationship, given by conditional probability is calculated using stochastic methods. The BN is used in several systems for analysis and management of accident risk; e.g. (Knochenhauer and Frid, 2010). In those systems, the nodes or so-called 'effective factors' are presumably known within the network by system descriptions in SAMGs. There are two steps to configure the BN, namely (i) identifying compositions within the network and (ii) defining conditional dependency between nodes. The first step is performed following the spirit of ASP (Baral, 2003) using Prolog (Wielemaker, 2005). Knowledge representation is used to build databases required for processing by ASP. Knowledge representation is defined as the expression of knowledge in a way that is understandable to both human and computers. Originally knowledge indicates data, information and facts. To focus, knowledge should be formed to achieve a goal. In a severe accident, key physics and safety related components status are defined according to a failure mode. The conditional dependencies between nodes are generated by approximate reasoning using Fuzzy inference (Zadeh, 1995). Fuzzy logic is a multiple-valued logic to treat ambiguous features such as linguistic description. It indicates possibility, which is distinguished from probability. Fuzzy set consists of linguistic variables according to the fixed rule. In other words, even uncertain states could be expressed as not binary logic, but as many-value logic by rule-based technology. Fuzzy control system is comprised of Fuzzy inference engine that is performed based on the 'If-Then Rule'. The 'If-Then Rule' is of the following form. If Y1 is B11 and Y2 is B12 then Z is C1. If Y1 is B21 and Y2 is B22 then Z is C2. Y1 and Y2 are inputs, which indicate conditional variables. Z indicates decision-making and both B and C are linguistic variables. With this rule-based technique, the approximate reasoning can be realized by Fuzzy inference. (authors)
As Artificial Intelligence (AI) becomes more pervasive in our society, it is crucial to develop, deploy, and assess Responsible and Trustworthy AI (RTAI) models, i.e., those that consider not only accuracy but also other aspects, such as explainability, fairness, and energy efficiency. Workflow provenance data have historically enabled critical capabilities towards RTAI. Provenance data derivation paths contribute to responsible workflows through transparency in tracking artifacts and resource consumption. Provenance data are well-known for their trustworthiness helping explainability, reproducibility, and accountability. However, there are complex challenges to achieve RTAI, which are further complicated by the heterogeneous infrastructure in the computing continuum (Edge-Cloud-HPC) used to develop and deploy models. As a result, a significant research and development gap remains between workflow provenance data management and RTAI. In this paper, we present a vision of the pivotal role of workflow provenance in supporting RTAI and discuss related challenges. We present a schematic view between RTAI and provenance, and highlight open research directions.
Edge computing enables “next-to-instrument” control and intelligent data volume reduction and the potential for autonomous, adaptive measurement strategies such as for automated control of scan strategies for Doppler lidar (DL). Instruments with narrow bandwidth connections (e.g., ship and remote sites) can do scene determination and save phenomenon-appropriate data. For example, Doppler spectrum can be saved when clouds are detected by the instrument or automatic moment detection can take place in camera images and only preserve spectrum when non-monomodal spectra are detected. Automated control at the edge involves changing the sampling (temporal or scanning strategy) of an instrument to suit the phenomena both present and being studied (Jackson et al. 2020). Both data processing and instrument control introduces the possibility of a software-defined instrument.
Physics-informed neural networks (PINN) have recently become attractive for solving partial differential equations (PDEs) that describe physics laws. By including PDE-based loss functions, physics laws such as mass balance are enforced softly in PINN. This paper investigates how mass balance constraints are satisfied when PINN is used to solve the resulting PDEs. We investigate PINN’s ability to solve the 1D saturated groundwater flow equations (diffusion equations) for homogeneous and heterogeneous media and evaluate the local and global mass balance errors. We compare the obtained PINN’s solution and associated mass balance errors against a two-point finite volume numerical method and the corresponding analytical solution. We also evaluate the accuracy of PINN in solving the 1D saturated groundwater flow equation with and without incorporating hydraulic heads as training data. We demonstrate that PINN’s local and global mass balance errors are significant compared to the finite volume approach. Tuning the PINN’s hyperparameters, such as the number of collocation points, training data, hidden layers, nodes, epochs, and learning rate, did not improve the solution accuracy or the mass balance errors compared to the finite volume solution. Mass balance errors could considerably challenge the utility of PINN in applications where ensuring compliance with physical and mathematical properties is crucial.
Geologic carbon storage projects are maturing worldwide and the footprint of deployment in the offshore is expanding. At present, there are ten projects in operation or that have been completed, more than 50 in construction and development, and dozens of characterization studies completed or underway. Offshore geologic carbon storage offers potential benefits over onshore geologic carbon storage. These offshore projects are generally remote in location, distant from population centers, and avoid complicated pore space rights while having abundant prospective storage potential. Some offshore fields targeted for carbon storage have comparatively fewer prior borehole penetrations except for areas that have been explored for petroleum production, minimizing potential issues such as pressure interference and infrastructure impacts. Yet offshore geologic carbon storage projects face distinctive technical and economic challenges, such as seafloor geohazards (e.g., seabed instability), expensive maritime transport, and meteorological-oceanographic conditions that can damage infrastructure and impact operations. Analytical capabilities and improved computational speeds have advanced engineering, earth and energy sciences in the wake of the arrival of modern data science over the last decade. These advancements have created an opportunity for integrated, multi-systems modeling approaches utilizing artificial intelligence and machine learning that are no longer limited by computational issues. Analytical tools developed alongside this advancement in data science can be leveraged to calibrate the potential advantages and challenges of carbon storage operations in the offshore. New methods and approaches that incorporate data science to analyze multiple aspects of engineered and natural systems can provide insights that complement the characterization and onsite engineering that traditional commercial and operational software addresses. These new methods and approaches can potentially improve the outcome of energy operations and carbon storage. Providing multi-system, science-driven data analytics enhances the knowledge base that offshore developers, operators, and regulatory bodies may draw from to improve offshore site selection and operational efficiency. Here, we provide a brief synopsis of geologic carbon storage efforts to date, an overview of the engineered and natural systems involved in offshore geologic carbon storage, and a review of publicly available, open-source, offshore and/or carbon storage related data- and science-driven tools developed by 2010 or later that are suitable for screening and assessing regions for offshore geologic carbon storage.
The rapid expansion of generative artificial intelligence (GenAI) has generated excitement regarding its potential benefits and concern over its ethical implications. Governments, corporations, and standards organizations have described ethical principles to direct GenAI's development and use; however, practical guidance for implementing these principles is limited. Addressing this gap is critical, especially considering the array of risks associated with GenAI, such as legal liabilities, privacy concerns, security threats, and potential misuse. Robust policies and procedures are critical to support responsible deployment of GenAI. This report examines Pacific Northwest National Laboratory (PNNL)’s approach to promoting responsible GenAI use. Proposed initiatives include developing policies based on ethical principles, creating a governance process to review projects relative to those principles, and implementing onboarding processes for training staff. The governance framework described in this report adapts the structure and principles of Institutional Review Boards (IRBs), traditionally used in human subjects research, for GenAI ethical review, providing oversight. Ethical principles guiding responsible GenAI usage include transparency and accountability, privacy, fairness, safety, security, and validity and reliability. To operationalize these principles, we propose forming a GenAI Assurance Council (GAC) that mirrors the IRB's structure. The GAC will evaluate GenAI projects across privacy, accountability, transparency, safety, security, fairness, and validity dimensions. Complementing policy and governance is AI literacy training to support staff understanding of GenAI's ethical implications. An initial training effort for AI Incubator Chat—a GenAI tool deployed at PNNL—showed promising results, underscoring the importance of clear guidelines and user accountability. Collaborative efforts and the dissemination of best practices are also discussed. The proposed GAC model and AI literacy training provide a blueprint for establishing ethical GenAI use and governance, offering practical tools to bridge the gap between ethical principles and real-world applications. The responsible integration of GenAI at PNNL entails a multifaceted approach involving policy development, ethical governance, and AI literacy training. The positive initial feedback and collaborative opportunities position PNNL to lead by example in GenAI's responsible use, reflecting a proactive stance in addressing the ethical, legal, and societal challenges associated with this emerging technology. PNNL's systematic and ethical approach to GenAI offers a model for other institutions to emulate, promoting safe and responsible technological advancements in the AI domain.
The INTEGRATE (Inverse Network Transformations for Efficient Generation of Robust Airfoil and Turbine Enhancements) project is developing a new inverse-design capability for the aerodynamic design of wind turbine rotors using invertible neural networks. This AI-based design technology can capture complex non-linear aerodynamic effects while being 100 times faster than design approaches based on computational fluid dynamics. This project enables innovation in wind turbine design by accelerating time to market through higher-accuracy early design iterations to reduce the levelized cost of energy. INVERTIBLE NEURAL NETWORKS Researchers are leveraging a specialized invertible neural network (INN) architecture along with the novel dimension-reduction methods and airfoil/blade shape representations developed by collaborators at the National Institute of Standards and Technology (NIST) learns complex relationships between airfoil or blade shapes and their associated aerodynamic and structural properties. This INN architecture will accelerate designs by providing a cost-effective alternative to current industrial aerodynamic design processes, including: - Blade element momentum (BEM) theory models: limited effectiveness for design of offshore rotors with large, flexible blades where nonlinear aerodynamic effects dominate - Direct design using computational fluid dynamics (CFD): cost-prohibitive - Inverse-design models based on deep neural networks (DNNs): attractive alternative to CFD for 2D design problems, but quickly overwhelmed by the increased number of design variables in 3D problems AUTOMATED COMPUTATIONAL FLUID DYNAMICS FOR TRAINING DATA GENERATION - MERCURY FRAMEWORK The INN is trained on data obtained using the University of Marylands (UMD) Mercury Framework, which has with robust automated mesh generation capabilities and advanced turbulence and transition models validated for wind energy applications. Mercury is a multi-mesh paradigm, heterogeneous CPU-GPU framework. The framework incorporates three flow solvers at UMD, 1) OverTURNS, a structured solver on CPUs, 2) HAMSTR, a line based unstructured solver on CPUs, and 3) GARFIELD, a structured solver on GPUs. The framework is based on Python, that is often used to wrap C or Fortran codes for interoperability with other solvers. Communication between multiple solvers is accomplished with a Topology Independent Overset Grid Assembler (TIOGA). NOVEL AIRFOIL SHAPE REPRESENTATIONS USING GRASSMAN SPACES We developed a novel representation of shapes which decouples affine-style deformations from a rich set of data-driven deformations over a submanifold of the Grassmannian. The Grassmannian representation as an analytic generative model, informed by a database of physically relevant airfoils, offers (i) a rich set of novel 2D airfoil deformations not previously captured in the data , (ii) improved low-dimensional parameter domain for inferential statistics informing design/manufacturing, and (iii) consistent 3D blade representation and perturbation over a sequence of nominal shapes. TECHNOLOGY TRANSFER DEMONSTRATION - COUPLING WITH NREL WISDEM Researchers have integrated the inverse-design tool for 2D airfoils (INN-Airfoil) into WISDEM (Wind Plant Integrated Systems Design and Engineering Model), a multidisciplinary design and optimization framework for assessing the cost of energy, as part of tech-transfer demonstration. The integration of INN-Airfoil into WISDEM allows for the design of airfoils along with the blades that meet the dynamic design constraints on cost of energy, annual energy production, and the capital costs. Through preliminary studies, researchers have shown that the coupled INN-Airfoil + WISDEM approach reduces the cost of energy by around 1% compared to the conventional design approach. This page will serve as a place to easily access all the publications from this work and the repositories for the software developed and released through this pr...
Streaming data generated continuously from sensor networks, mobile devices, social media platforms and other edge devices have posed significant challenges to existing computing platforms for achieving both high throughput and low latency data processing in addition to scalable computing. This entry introduces a real-time computing and programming platform for time-critical GIS (Geographic Information System) applications. In this platform, advanced streaming data processing software, such as Apache Kafka and Spark Streaming, are integrated to enable data analytics in real-time. This computing platform can also be extended to integrate GeoAI (Geospatial Artificial Intelligence) based machine learning models to leverage both historical and streaming data to achieve real-time prediction and intelligent geospatial analytics. Two real-time geospatial applications in terms of flood simulation and climate data visualization are introduced to demonstrate how real-time programming and computing can help tackle real-world problems with important societal impacts.
The emergence of doped hafnium oxide (HfO 2 )-based ferroelectric films has enabled highly scalable and silicon-compatible ferroelectric devices, opening new frontiers in neuromorphic and reservoir computing. Among these, ferroelectric field-effect transistors (FeFETs) are particularly promising due to their analog memory characteristics and unique polarization dynamics. These properties make FeFETs ideal candidates for artificial synapses in neuromorphic architectures, supporting deep neural networks and spiking neural networks based on leaky-integrate-and-fire (LIF) mechanisms. Beyond neuromorphic computing, FeFETs also play a crucial role in physical reservoir computing, leveraging their intrinsic nonlinear and history-dependent behavior for efficient real-time learning. This approach offers significant advantages for time-series processing and edge artificial intelligence (AI) applications, addressing the growing need for energy-efficient computing. As a result, this article explores the principles, key demonstrations, and future potential of FeFET-based neuromorphic and reservoir computing, highlighting their impact on next-generation AI hardware.
Enabling new electrochemical technologies requires systems that can operate under ever-more demanding conditions, and progress in energy storage applications reveals tantalizing opportunities to reimagine electrolyte design for performance at extreme potentials. Here, a common thread among these innovations is the formation of significant populations of contact ion pairs (CIPs) in the electrolyte, regardless of the specific cation chemistry or solvent system. The examples summarized in this review suggest that a set of general electrolyte design rules likely exists, where the purposeful selection of anion chemistry can yield CIP structures with tunable control over reaction thermodynamics, kinetics, and interphase chemistry. Identifying the relevant descriptors for high-performance, anion-derived CIP structures can be achieved utilizing a combined experimental and computational approach, aided by machine learning and artificial intelligence, to more rapidly survey the vast combinatorial space available and to enable a new generation of electrolytes for decarbonized electrochemical processes at scale.
Although inspired by neuronal systems in the brain, artificial neural networks generally employ point-neurons, which offer computational complexity far less than that of their biological counterparts. Neurons have dendritic arbors that connect to different sets of synapses and offer local nonlinear accumulation – playing a pivotal role in processing and learning. Inspired by this, we propose a novel neuron design based on a multigate ferroelectric field-effect transistor that mimics dendrites. It leverages ferroelectric nonlinearity for local computations within dendritic branches while utilizing the transistor action to generate the neuronal output. The branched architecture enables smaller crossbar arrays in hardware integration, improving efficiency. Using an experimentally calibrated device-circuit-algorithm cosimulation framework, we demonstrate that networks incorporating our dendritic neurons achieve superior performance compared to much larger networks without dendrites (∼ 17× fewer trainable weight parameters). These findings suggest that dendritic hardware can significantly improve computational efficiency and learning capacity of neuromorphic systems optimized for edge applications.