Search NASA⌕ Search

SEARCH · Search NASA

Results for “Scientific Applications”

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
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Visualization at exascale: Making it all work with VTK-m

The VTK-m software library enables scientific visualization on exascale-class supercomputers. Exascale machines are particularly challenging for software development in part because they use GPU accelerators to provide the vast majority of their computational throughput. Algorithmic designs for GPUs and GPU-centric computing often deviate from those that worked well on previous generations of high-performance computers that relied on traditional CPUs. Fortunately, VTK-m provides scientific visualization algorithms for GPUs and other accelerators. VTK-m also provides a framework that simplifies the implementation of new algorithms and adds a porting layer to work across multiple processor types. This paper describes the main challenges encountered when making scientific visualization available at exascale. Here, we document the surprises and obstacles faced when moving from pre-exascale platforms to the final exascale designs and the performance on those systems including scaling studies on Frontier, an exascale machine with over 37,000 AMD GPUs. We also report on the integration of VTK-m with other exascale software technologies. Finally, we show how VTK-m helps scientific discovery for applications such as fusion and particle acceleration that leverage an exascale supercomputer.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Equilipy: a python package for calculating phase equilibria

The CALPHAD (CALculation of PHAse Diagram) approach (Nigel Saunders & Miodownik, 1998) provides predictions for thermodynamically stable phases in multicomponent-multiphase materials across a wide range of temperatures. Consequently, the CALPHAD calculations became an essential tool in materials and process design (Luo, 2015). Such design tasks frequently require navigating a high-dimensional space due to multiple components involved in the system. This increasing complexity demands high-throughput CALPHAD calculations, especially in the rapidly evolving field of alloy design. In response to the need, we developed Equilipy an open-source Python package designed for calculating phase equilibria of multicomponent-multiphase systems. Equilipy is specifically tailored for high-throughput CALPHAD calculations, offering parallel computations across multiple processors and nodes with the given NPT input conditions namely elemental compositions (N), pressure (P), and temperature (T). Equilipy utilizes the program structure and Gibbs energy functions from the Fortran-based program, Thermochimica (Piro et al., 2013), with incorporating a new Gibbs energy minimization algorithm. This algorithm, originally developed by Capitani and Brown in 1987 (Capitani & Brown, 1987), has been revised and implemented to enhance the stability and performance of calculations. The Fortran codes are precompiled and interfaced with Python via F2PY, ensuring high computation speed. Benchmark tests shown in Figure 1 demonstrate that Equilipy’s computation speed is comparable to those of established commercial software, TC-Python and PanPython. This result highlights its efficiency and potential applications in various scientific and industrial fields.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Machine learning models for PDE constrained optimization

Partial differential equation (PDE)-constrained optimization problems arise in a variety of scientific and engineering applications, such as topology optimization, electrodynamics, fluid dynamics, and structural dynamics. However, these problems are often challenging and computationally expensive to solve, due to the need to solve the PDEs within the optimization loop. One approach to reducing the computational cost of these methods while providing convergence guarantees is through inexact trust region methods; this method uses lower fidelity solutions of the PDE at early stages of the optimization and adjusts the required accuracy of inexact PDE solvers as the optimization progresses. In this work, we explore the use of machine learning based surrogate models with these inexact trust region methods. We first demonstrate the potential of this approach by using Gaussian processes as the surrogate model and test this on a simple PDE-constrained optimization problem. We then document explorations into improving the computational costs of evolutional deep neural network / neural Galerkin methods, with the eventual goal of using these methods with the inexact trust region algorithms. We are able to speed up these approaches, albeit at the cost of lower accuracy.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

FY 2025 Multidimensional Data Correlation Platform: Unified Software Architecture for Advanced Materials and Manufacturing Technologies Data Management and Processing

The Advanced Materials and Manufacturing Technologies (AMMT) program continues to advance a data-driven approach to demonstrate the utility of additive manufacturing for fabricating components for nuclear applications. A key scientific goal is to leverage data to better understand manufacturing outcomes and thereby improve the performance, reliability, and lifespan of nuclear components. Ultimately, this effort supports the development of standards for certification and qualification of additively manufactured components, enabling broader industry adoption. In support of this objective, the AMMT program is building and deploying a data management platform to record, index, analyze, and make available the manufacturing data generated across the AMMT program. In FY 2023, the team conceptualized the architecture of the platform and, in FY 2024, deployed the first functional version at the Oak Ridge National Laboratory (ORNL) Manufacturing Demonstration Facility (MDF). In FY 2025, the platform was officially opened to all AMMT members. To enable this expansion, core modifications and enhancements were developed, including improvements to the user interface and workflows for data entry and retrieval. Most notably, robust security and access control mechanisms were implemented to protect data and manage information sharing. This effort featured a logging system, protected views, and controlled access mechanisms. This report documents these enhancements and the transition of the platform into program-wide use.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Self-Consistent Relativistic Electron Scattering using the Sherlock Scattering Model for X-ray Diagnostics

We present on a new, self-consistent, arbitrary-temperature Romberg integration scheme for modeling electron scattering in materials in a LANL Lagrangian Shock Hydro (LSH) code. Electron beam-target interactions are fundamental to a wide range of scientific and technological applications. When high-energy electron beams hit their target, they may scatter, deposit energy, or ionize the source. These processes govern the behavior and outcomes in nanotechnology manufacturing, electron microscopy, and modern X-ray diagnostics. Simulating these interactions is essential for interpreting experimental results, predicting material responses, and designing efficient tools and experiments. At Los Alamos, this is done using a LSH code, which is a multi-dimension, multi-material, massively parallel, multi-physics code used to simulate applications from asteroid impacts to electron beam interactions. By effectively and efficiently modeling the way that electrons scatter from the beam we can bolster these simulations and more accurately predict experimental outcomes. The model currently implemented in the LSH of interest is based on work by Papp and does not self-consistently preserve momentum in the slightly relativistic regime; here we adopt a model proposed by Braams and Karney and implement a Romberg integration scheme to compute the diffusion tensor. In this paper we will provide background on the Braams-Karney diffusion tensor as well as the Romberg integration scheme we employed to numerically solve for it. We will show that our integration scheme is accurate in solving for the set of scalar potentials used to re-express the diffusion tensor in differential form, and in solving for the diffusion coefficients in the larger LSH code. By using this diffusion tensor rather than the existing Papp one, and numerically integrating it with a Romberg method, we produce much more accurate, self-consistent results.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2025

Fundamental Research Aimed at Diverting Excess Reducing Power in Photosynthesis to Orthogonal Metabolic Pathways

Photosystems are incredible biological machines that use sunlight to drive the conversion of carbon dioxide to sugar. The amount of sunlight available for photosynthesis sometimes exceeds the amount of energy plants can use. This excess energy has to be safely dissipated through non-productive biological processes. The ultimate goal of this project is to understand whether we can utilize that otherwise unused excess energy. In our previous work, we showed that, in principle, it is possible to attach a catalyst to photosystem I and generate H2 using light. Our current strategy is to genetically fuse parts of the photosystem I complex with a recently discovered oxygen-tolerant [FeFe] hydrogenase. Our rationale is that such chimeric proteins may potentially result in the natural incorporation of the photosystem I-hydrogenase link using the inherent genetic machinery of the cell. In this project, we aim to verify that light-driven hydrogen production in this construction is possible. Throughout the project, we designed nanoconstructs that showcase the plausibility of this technology, at least in vitro. We take advantage of these constructs to investigate details of the coupling between photosystem I and a H2-producing enzyme called [FeFe] hydrogenase. This part of the project reveals details of the electron transfer between photosystem I and the attached hydrogenase, providing information that can lead to new strategies for improved biological photocatalysis. We also researched efficient and robust tethering of the [FeFe] hydrogenase to photosystem I in cyanobacteria. This work will highlight successful design strategies to guide the future development of photosynthetic biohybrids. Uncovering the principles governing the utilization of otherwise unusable energy significantly further our understanding of cyanobacterial photosynthesis. The work proposed establishes the feasibility of diverting excess energy under high light conditions to orthogonal enzymatic pathways and set design rules for efficient utilization of such a strategy for scientific and industrial applications in biosensing, renewable energy, and high-value chemicals production. The work addresses the DOE-BES Photosynthetic Systems program goal to develop a multidimensional understanding of photosystems that would provide specific metrics that instruct strategies for improving biological photosynthesis and for guiding the future development of bioreactors and biomimetic energy systems.

Photosynthetic systems, hydrogenase, cyanobacteria↗
DOE OSTI2026

Studies of whistler propagation along a plasma density gradient that is parallel to the magnetic field

Low frequency plasma wave generation in space is important for both scientific and practical applications. One of the most promising techniques for doing this is to directly inject whistler waves into the space environment from an antenna onboard one or more satellites. This technique has been discussed for years, but there are still open questions about the best way to generate plasma waves. So far, most theoretical [Kondrat92], lab based [Pribyl2010, Stenzel2016] and space-based experiments [DSX] have focused on studying the generation of whistler waves from an electric dipole antenna. However, a dipole antenna is very inefficient because it puts a lot of energy in waves that are not effective for most applications. Theoretical [Kondrat92] and lab experimental [Stenzel2016] results indicate that a loop antenna is much more efficient at generating whistler waves than a dipole antenna. A satellite experiment will need to be developed to demonstrate that whistler waves can be generated from a loop antenna in the space environment. The challenge is that to efficiently transmit whistler modes in the natural plasma environment of space, the loop antenna will have to be very large. For example, at L=2 (one earth radius away from the surface of the earth) a loop antenna would need a radius on the order of ~200 m to radiate efficiently, as shown in fig. 1, left. The antenna size and complexity would require a prohibitively large and expensive satellite mission. Our proposed innovation is to exploit the fact that the characteristic wavelength of whistler waves decreases in more dense plasma, which reduces the size needed for an antenna to radiate efficiently. Fortunately, a technique already exists for enhancing the local plasma density in space, called a plasma contactor [Kovaleski2001]. A plasma contactor can be used to create a local environment where the plasma density is enhanced around the satellite, which in turn reduces the size of an antenna that is needed to radiate efficiently (Fig. 1, right).

42 ENGINEERING↗
DOE OSTI2025

A standards perspective on genomic data reusability and reproducibility

Genomic and metagenomic sequence data provides an unprecedented ability to re-examine findings, offering a transformative potential for advancing research, developing computational tools, enhancing clinical applications, and fostering scientific collaboration. However, effective and ethical reuse of genomics data is hampered by numerous technical and social challenges. The International Microbiome and Multi’Omics Standards Alliance (IMMSA, https://www.microbialstandards.org/) and the Genomic Standards Consortium (GSC, https://gensc.org) hosted a 5-part seminar series “A Year of Data Reuse” in 2024 to explore challenges and opportunities of data reuse and reproducibility across disparate domains of the genomic sciences. Addressing these challenges will require a multifaceted approach, including common metadata reporting, clear communication, standardized protocols, improved data management infrastructure, ethical guidelines, and collaborative policies that prioritize transparency and accessibility. We offer strategies to enable responsible and technically feasible data reuse, recognition of data reproducibility challenges, and emphasizing the importance of cross-disciplinary efforts in the pursuit of open science and data-driven innovation.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Discrete global grid system-based flow routing datasets in the Amazon and Yukon basins

Abstract. Discrete global grid systems (DGGS) are emerging spatial data structures widely used to organize geospatial datasets across scales. While DGGS have found applications in various scientific disciplines, including atmospheric science and ecology, their integration into physically based hydrological models and Earth system models (ESMs) has been hindered by the lack of flow routing datasets based on DGGS. In response to this gap, this study pioneers the development of new flow routing datasets using icosahedral Snyder equal-area (ISEA) DGGS and a novel mesh-independent flow direction model. We present flow routing datasets for two large basins, the tropical Amazon River basin and the Arctic Yukon River basin. These datasets (1) facilitate the adoption of DGGS for hydrological models and (2) provide flow routing inputs for evaluation of DGGS-based flow routing in the Amazon and Yukon river basins. The data are available at https://doi.org/10.5281/zenodo.8377765 (Liao, 2023).

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Development of an immersion fiber optic Raman probe for real-time analysis of molten materials

This study presents an advancement in high-temperature Raman spectroscopy, specifically for analyzing molten materials. It introduces an approach by integrating a fiber-optic Raman probe with a copper block protection system designed to endure extreme thermal conditions. The copper block features an open port designed to accommodate an external telescope with a 3 cm focal length, enabling Raman spectra collection in challenging high-temperature environments. A built-in gas channel ensures a continuous flow of argon gas to prevent flux intrusion. The robust copper block acts as a reliable shield, safeguarding the fiber-optic Raman probe within molten materials. This enhancement maintains the probe's integrity and significantly improves its resilience, making it ideal for rigorous investigations of molten substances. This advancement is particularly relevant in metallurgy, where flux materials impact production quality and efficiency. The ability to acquire Raman signals under elevated thermal conditions offers opportunities for studying molecular dynamics, compositional changes, and chemical interactions within molten substances. This introduced direct immersion probing technique has implications, benefiting both scientific and industrial fields. It holds promise for advancing research and exploration in various contexts, from fundamental scientific inquiries to practical applications in metallurgical processes, where flux materials are critical for optimizing production quality and efficiency. Furthermore, this approach enhances the capabilities of high-temperature Raman spectroscopy, making it a valuable tool for investigating molten materials and their properties in diverse settings.

Argon↗
DOE OSTI2025

32 examples of LLM applications in materials science and chemistry: towards automation, assistants, agents, and accelerated scientific discovery

Abstract Large language models (LLMs) are reshaping many aspects of materials science and chemistry research, enabling advances in molecular property prediction, materials design, scientific automation, knowledge extraction, and more. Recent developments demonstrate that the latest class of models are able to integrate structured and unstructured data, assist in hypothesis generation, and streamline research workflows. To explore the frontier of LLM capabilities across the research lifecycle, we review applications of LLMs through 32 total projects developed during the second annual LLM hackathon for applications in materials science and chemistry, a global hybrid event. These projects spanned seven key research areas: (1) molecular and material property prediction, (2) molecular and material design, (3) automation and novel interfaces, (4) scientific communication and education, (5) research data management and automation, (6) hypothesis generation and evaluation, and (7) knowledge extraction and reasoning from the scientific literature. Collectively, these applications illustrate how LLMs serve as versatile predictive models, platforms for rapid prototyping of domain-specific tools, and much more. In particular, improvements in both open source and proprietary LLM performance through the addition of reasoning, additional training data, and new techniques have expanded effectiveness, particularly in low-data environments and interdisciplinary research. As LLMs continue to improve, their integration into scientific workflows presents both new opportunities and new challenges, requiring ongoing exploration, continued refinement, and further research to address reliability, interpretability, and reproducibility.

Computer Science↗
DOE OSTI2024

Project DarkStar: Vision for LLNL in 2030

DarkStar was a Strategic Initiative (FY2021-FY2024) to investigate applications of Artificial Intelligence (AI) and Machine Learning (ML) to scientific problems of complex hydrodynamics, shockwave physics and energetic materials. The research focused on physics and engineering design as a process that can be tremendously accelerated through merging AI with advanced physics simulation on exascale-class platforms, and to experimentally validate this revolutionary new approach through dynamic materials campaigns. A central thread of scientific inquiry was in the application of AI to enable human understanding of how to control hydrodynamic instability (which has impacts to areas such as inertial confinement fusion) via engineering features and time-dependent sources. Motivated by an unfinished line of research started by Dr. Johnny von Neumann, AI-enabled simulation approaches were developed that allowed DarkStar researchers to uncover several ground-breaking discoveries regarding hydrodynamic instability, including how to completely suppress Richtmyer-Meshkov instability (RMI). These S&T discoveries, along with other advances, have shown the way for an entirely new approach to time-dependent problems known as inverse design – the idea that complex systems can be developed directly from a final state that is to be achieved and resolve the initial design via satisfying several constraints simultaneously via AI/ML. Through experimental campaigns conducted across a wide range of facilities in the NNSA complex (the High Explosive Application Facility at LLNL, the Dynamic Compression Sector/Advanced Photon Source at Argonne National Lab, and Special Technologies Laboratory at MSTS) the radical new AI/ML approach to engineering complex material dynamics was verified, establishing a new field of study within the realm of shock physics. As advanced manufacturing capabilities continue to develop, the great importance of inverse design as a means to apply that technology effectively for NNSA missions will feature prominently over this decade. DarkStar has positioned NNSA as a world-leader in this newly emerging cross-disciplinary area of AI methods for advanced physics simulation and pioneered multiple novel approaches that have enabled the broader scientific community. By allowing us to see past the horizon, to 2030 and beyond, DarkStar has illuminated the vast potential of AI/ML to impact a wide range of new national security missions and, consequently, multiple areas of further research have already emerged across the NNSA and DOD complex.

42 ENGINEERING↗
DOE OSTI2025

Laboratory Testing to Assess the Feasibility of Polyurethane Flat Belts for Marine Energy Applications

Polyurethane flat belts have received limited scientific attention as load-bearing elements in marine energy systems, particularly in applications involving dynamic tensile and bending loads. This study evaluates their potential as a replacement for traditional wire ropes in marine energy applications, with a focus on their ability to be integrated into winch-driven wave energy converters where bending and tensile stresses can make long-term operation difficult. Polyurethane belts are hypothesized to offer enhanced fatigue resistance due to their reduced thickness in the bending plane and therefore lower bending stresses. This research involves a series of tests utilizing the National Renewable Energy Laboratory’s (NREL) Large-Amplitude Motion Platform to replicate the dynamic conditions experienced by mooring lines of winch-based point-absorber-type marine energy converters. The conditions tested include unequal coiling and uncoiling tensions and load cases resulting from the device’s unconstrained movement relative to its anchor, such as twisting and off-axis loading. Results from this study show that polyurethane flat belts can achieve more than 198 percent of the fatigue life of a conventional wire rope under similar load profiles. The stress concentrations resulting from off-axis loading and cumulative twist beyond the system’s allowable limits have been identified as potential failure modes for flat belt mooring lines used in winch-driven wave energy converters deployed in ocean environments. To mitigate these risks, the use of anti-spin systems and fairleads designed to accommodate off-axis loading while limiting twist accumulation is recommended.

13 HYDRO ENERGY↗
DOE OSTI2026

MOD-Amp System Design Spring: Spring 2026 – Georgetown University, SYSM–5620

High-energy lasers (HELs) play an important role in both national defense and scientific research. In defense applications, HELs are used for target detection, tracking, and engagement. In research environments, they support studies of extreme physical conditions relevant to fusion energy and plasma science. These systems depend on the amplification of light through stimulated emission of radiation, allowing optical energy to be increased to the levels required for operation. This amplification occurs when light passes through an energized gain medium that receives energy from an external optical or electrical source. To achieve the desired output, laser systems often use multiple amplification stages, including high-gain preamplifiers and lower-gain power or booster amplifiers. At Lawrence Livermore National Laboratory (LLNL) and other national laboratories, many large-aperture laser amplifier systems are aging and rely on system-specific hardware, obsolete technologies, and incomplete documentation. These legacy systems create challenges for maintenance, supportability, and long-term operation. Their lack of standardization also increases the difficulty of sustaining reliable performance over time. As this infrastructure continues to age, the likelihood of unplanned downtime grows, which can negatively affect both national security missions and scientific research programs that depend on dependable HEL capabilities. The purpose of this document is to demonstrate the application of systems engineering fundamentals and design thinking through the development of a laser amplifier case study. The proposed system concept is intended as an academic exercise and not as a finalized engineering design. As a result, the development presented in this document is incomplete and may contain technical assumptions or errors that would require further investigation before any real-world implementation.

42 ENGINEERING↗
DOE OSTI2026

A Benchmark Suite for Evaluating Scientific AI Workloads on GPUs

AI applications have been steadily increasing in the allocation portfolio among leadership computing facilities. These applications depend on deep learning frameworks with hardware acceleration and underlying software systems. With the rapid development of applications, software stacks, and hardware devices, it is essential to evaluate the performance of core operations in AI workloads for direction of optimizations and procurement of next-generation high-performance computing (HPC) infrastructures. Currently, most benchmarks lack scientific AI workloads. So, we present DeepKernelBench and the experimental results of evaluating the benchmark suite for early observations and performance comparisons on datacenter GPUs using representative workloads for scientific AI, including Attentions, General matrix multiplications, Geometrics and Fourier neural operations.

Jin, Zheming [Advanced Micro Devices (AMD)]↗
DOE OSTI2024

AXI4MLIR: User-Driven Automatic Host Code Generation for Custom AXI-Based Accelerators

Tensor algebra operations represent an important class of algorithms used across many applications, including machine learning, scientific computing, and data analytics. As a result, the efficient generation of custom accelerators for tensor operations has received increased attention. Previous efforts have produced automated tools enabling users to prototype and explore optimized accelerators. However, little effort has been focused on the host-accelerator interaction in these tools. Efficient use of hardware accelerators requires knowledge about the accelerator's capabilities (operations, data formats, and opcode support), the host CPU microarchitecture (e.g., memory hierarchy), the host-accelerator interface, and the application's features (which code regions should be mapped onto an accelerator). Manually rewriting the original applications to facilitate improved custom accelerator mapping is an error-prone and time-consuming endeavor. To cope with this, we propose AXI4MLIR, a new framework to automatically generate and optimize the communication between the host CPU and arbitrary accelerators that implement linear algebra algorithms. AXI4MLIR extends the MLIR compiler framework to automatically generate efficient host-accelerator driver code for accelerators with AXI-based interfaces. Our compiler extensions enable automatic driver code generation while carefully considering the host's memory hierarchy and target accelerator features. To demonstrate the flexibility and utility of AXI4MLIR, we test it with diverse use cases that include different types of accelerators, tiling scenarios, and dataflow schemes. We compare our experimental results to manual implementations of host-accelerator driver code and find that our approach can reduce CPU cache references by 56% and deliver up to a 1.65x speedup.

Bohm Agostini, Nicolas↗
DOE OSTI2024

A Frequency Domain Methodology for Quantitative Evaluation of Diffuse Wavefield With Applications to Seismic Imaging

Abstract Ambient Noise Imaging (ANI) of subsurface structures relies on seismic interferometry of diffuse seismic wavefields. However, the lack of effective methods to quantify and identify highly diffuse waves hampers applications of ANI, particularly in evaluating seismic attenuation and monitoring structural changes with high temporal resolution. Conventional ANI approaches require data normalization, which effectively suppresses the non‐diffuse component with large amplitude but also results in significant loss of amplitude and phase information in the continuous seismic records. In this study, we propose a frequency domain method to quantitatively evaluate the degree of diffuseness of seismic wavefields by analyzing their statistical characteristics of modal amplitudes for stationarity and randomness. Tests on synthetic waveform and field nodal records show that the proposed method can effectively distinguish between diffuse and non‐diffuse waveforms for either single‐ or three‐component data. As an application, we identify a 60‐s‐long diffuse coda of a local M 2.2 earthquake recorded by a dense nodal array on the San Jacinto Fault Zone, and successfully extract high‐quality dispersion curve andQ‐value without performing data normalization. These results are consistent with those obtained by conventional methods that assess the correlation between coherency and the Green's function, and by modeling ballistic waves generated by road traffic. Our proposed method can advance the imaging of subsurface velocity and attenuation structures as well as monitoring temporal changes for scientific studies and engineering applications.

Geochemistry & Geophysics↗
DOE OSTI2026

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

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

• Artificial intelligence (AI) / machine learning ↗