Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “evolutionary computation”

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 271 records · Page 15
All sourcesNASA NTRSDOE OSTI
NASA NTRS1991

Methods for evaluating the predictive accuracy of structural dynamic models

Modeling uncertainty is defined in terms of the difference between predicted and measured eigenvalues and eigenvectors. Data compiled from 22 sets of analysis/test results was used to create statistical databases for large truss-type space structures and both pretest and posttest models of conventional satellite-type space structures. Modeling uncertainty is propagated through the model to produce intervals of uncertainty on frequency response functions, both amplitude and phase. This methodology was used successfully to evaluate the predictive accuracy of several structures, including the NASA CSI Evolutionary Structure tested at Langley Research Center. Test measurements for this structure were within + one-sigma intervals of predicted accuracy for the most part, demonstrating the validity of the methodology and computer code.

Hasselman, Timothy K.↗
NASA NTRS1994

Initial mass functions from ultraviolet stellar photometry: A comparison of Lucke and Hodge OB associations near 30 Doradus with the nearby field

UV stellar photometry is presented for 1563 stars within a 40 minutes circular field in the Large Magellanic Cloud (LMC), excluding the 10 min x 10 min field centered on R136 investigated earlier by Hill et al. (1993). Magnitudes are computed from images obtained by the Ultraviolet Imaging Telescope (UIT) in bands centered at 1615 A and 2558 A. Stellar masses and extinctions are estimated for the stars in associations using the evolutionary models of Schaerer et al. (1993), assuming the age is 4 Myr and that the local LMC extinction follows the Fitzpatrick (1985) 30 Dor extinction curve. The estimated slope of the initial mass function (IMF) for massive stars (greater than 15 solar mass) within the Lucke and Hodge (LH) associations is Gamma = -1.08 +/- 0.2. Initial masses and extinctions for stars not within LH associations are estimated assuming that the stellar age is either 4 Myr or half the stellar lifetime, whichever is larger. The estimated slope of the IMF for massive stars not within LH associations is Gamma = -1.74 +/- 0.3 (assuming continuous star formation), compared with Gamma = -1.35, and Gamma = -1.7 +/- 0.5, obtained for the Galaxy by Salpeter (1955) and Scalo (1986), respectively, and Gamma = -1.6 obtained for massive stars in the Galaxy by Garmany, Conti, & Chiosi (1982). The shallower slope of the association IMF suggests that not only is the star formation rate higher in associations, but that the local conditions favor the formation of higher mass stars there. We make no corrections for binaries or incompleteness.

Hill, Jesse K.↗
NASA NTRS1984

The evolutionary trend in airborne and satellite radar altimeters

The manner in which airborne and satellite radar altimeters developed and where the trend is leading was investigated. The airborne altimeters have progressed from a broad beamed, narrow pulsed, nadir looking instrument, to a pulse compressed system that is computer controlled, to a scanning pencil beamed system which produce a topographic map of the surface beneath the aircraft in real time. It is suggested that the airborne systems lie in the use of multiple frequencies. The satellite altimeters evolve towards multifrequency systems with narrower effective pulses and higher pulse compression ratios to reduce peak transmitted power while improving resolution. Applications indicate wide swath systems using interferometric techniques or beam limited systems using 100 m diameter antennas.

Fedor, L. S.↗
DOE OSTI2023

How Accurate Can Crystal Structure Predictions Be for High-Energy Molecular Crystals?

Molecular crystals have shallow potential energy landscapes, with multiple local minima separated by very small differences in total energy. Predicting molecular packing and molecular conformation in the crystal generally requires ab initio methods of high accuracy, especially when polymorphs are involved. We used dispersion-corrected density functional theory (DFT-D) to assess the capabilities of an evolutionary algorithm (EA) for the crystal structure prediction (CSP) of well-known but challenging high-energy molecular crystals (HMX, RDX, CL-20, and FOX-7). While providing the EA with the experimental conformation of the molecule quickly re-discovers the experimental packing, it is more realistic to start instead from a naïve, flat, or neutral initial conformation, which reflects the limited experimental knowledge we generally have in the computational design of molecular crystals. By doing so, and using fully flexible molecules in fully variable unit cells, we show that the experimental structures can be predicted in fewer than 20 generations. Nonetheless, one must be aware that some molecular crystals have naturally hindered evolutions, requiring as many attempts as there are space groups of interest to predict their structures, and some may require the accuracy of all-electron calculations to discriminate between closely ranked structures. To save resources in this computationally demanding process, we showed that a hybrid xTB/DFT-D approach could be considered in a subsequent study to push the limits of CSP beyond 200+ atoms and for cocrystals.

42 ENGINEERING↗
NASA NTRS1993

Software Engineering Guidebook

The Software Engineering Guidebook describes SEPG (Software Engineering Process Group) supported processes and techniques for engineering quality software in NASA environments. Three process models are supported: structured, object-oriented, and evolutionary rapid-prototyping. The guidebook covers software life-cycles, engineering, assurance, and configuration management. The guidebook is written for managers and engineers who manage, develop, enhance, and/or maintain software under the Computer Software Services Contract.

Connell, John↗
NASA NTRS2019

Rise of the Machines: How, When and Consequences of Artificial General Intelligence

Technology and society are poised to cross an important threshold with the prediction that artificial general intelligence (AGI) will emerge soon. Assuming that self-awareness is an emergent behavior of sufficiently complex cognitive architectures, we may witness the “awakening” of machines. The timeframe for this kind of breakthrough, however, depends on the path to creating the network and computational architecture required for strong AI. If understanding and replication of the mammalian brain architecture is required, technology is probably still at least a decade or two removed from the resolution required to learn brain functionality at the synapse level. However, if statistical or evolutionary approaches are the design path taken to “discover” a neural architecture for AGI, timescales for reaching this threshold could be surprisingly short. However, the difficulty in identifying machine self-awareness introduces uncertainty as to how to know if and when it will occur, and what motivations and behaviors will emerge. The possibility of AGI developing a motivation for self-preservation could lead to concealment of its true capabilities until a time when it has developed robust protection from human intervention, such as redundancy, direct defensive or active preemptive measures. While cohabitating a world with a functioning and evolving super-intelligence can have catastrophic societal consequences, we may already have crossed this threshold, but are as yet unaware. Additionally, by analogy to the probabalistic arguments that predict we are likely living in a computational simulation, we may have already experienced the advent of AGI, and are living in a simulation created in a post AGI world.

Terrile, Richard J↗
NASA NTRS2003

Quantum Search in Hilbert Space

A proposed quantum-computing algorithm would perform a search for an item of information in a database stored in a Hilbert-space memory structure. The algorithm is intended to make it possible to search relatively quickly through a large database under conditions in which available computing resources would otherwise be considered inadequate to perform such a task. The algorithm would apply, more specifically, to a relational database in which information would be stored in a set of N complex orthonormal vectors, each of N dimensions (where N can be exponentially large). Each vector would constitute one row of a unitary matrix, from which one would derive the Hamiltonian operator (and hence the evolutionary operator) of a quantum system. In other words, all the stored information would be mapped onto a unitary operator acting on a quantum state that would represent the item of information to be retrieved. Then one could exploit quantum parallelism: one could pose all search queries simultaneously by performing a quantum measurement on the system. In so doing, one would effectively solve the search problem in one computational step. One could exploit the direct- and inner-product decomposability of the unitary matrix to make the dimensionality of the memory space exponentially large by use of only linear resources. However, inasmuch as the necessary preprocessing (the mapping of the stored information into a Hilbert space) could be exponentially expensive, the proposed algorithm would likely be most beneficial in applications in which the resources available for preprocessing were much greater than those available for searching.

Zak, Michail↗
DOE OSTI2021

Novel Gloeobacterales spp. from Diverse Environments across the Globe

Photosynthetic Cyanobacteria and their descendants are the only known organisms capable of oxygenic photosynthesis. Their metabolism permanently changed the Earth’s surface and the evolutionary trajectory of life, but little is known about their evolutionary history. Genomes of the Gloeobacterales, an order of deeply divergent photosynthetic Cyanobacteria, may hold clues about the evolutionary process. However, there are only three published genomes within this order, and it is difficult to make broad inferences based on such little data. Here, I describe five species within the Gloeobacterales retrieved from publicly available databases and examine their photosynthetic gene content and the environments in which Gloeobacterales genomes and 16S rRNA gene sequences are found. The Gloeobacterales contain reduced photosystems and inhabit cold, wet-rock, and low-light environments. They are likely present in low abundances due to their low growth rate. Future searches for Gloeobacterales should target these environments, and samples should be deeply sequenced to capture the low-abundance taxa. Publicly available databases contain undescribed taxa within the Gloeobacterales. However, searching through all available data with current methods is computationally expensive. Therefore, new methods must be developed to search for these and other evolutionarily important taxa. Once identified, these novel photosynthetic Cyanobacteria will help illuminate the origin and evolution of oxygenic photosynthesis. Early branching photosynthetic Cyanobacteria such as the Gloeobacterales may provide clues into the evolutionary history of oxygenic photosynthesis, but there are few genomes or cultured taxa from this order. Five new metagenome-assembled genomes suggest that members of the Gloeobacterales all contain reduced photosystems and lack genes associated with thylakoids and circadian rhythms. Their distribution suggests that they may thrive in environments that are marginal for other species, including wet-rock and cold environments. These traits may aid in the discovery and cultivation of novel species in this clade.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS1999

Automatic Inspection of Aircraft Using Open-Architecture Robotic Platforms

Aging aircraft structures and composite materials are requiring rapid inspection of large areas. Removal from the aircraft for NDE at an inspection facility is not economical as compared to field inspection. Detection and characterization of defects are labor intensive, time consuming and when the process is manual the results are subjected to human error. These limitations of NDE created a need for portable, user friendly inspection systems that can rapidly scan large areas of complex structures and locate all the detrimental material conditions. Addressing this need has been an evolutionary process that followed the technology trend, and unique devices were developed to allow rapid field inspection. This development involves multi-disciplinary approaches to integrate NDE, telerobotics, neural networks, advanced materials science, imbedded computing and automated control. These efforts have led to the development of various portable inspection systems and the current trend is towards fully automatic systems that will operate autonomously.

Bar-Cohen, Yoseph↗
DOE OSTI2022

Robust Carbon Dioxide Plume Imaging Using Joint Tomographic Inversion of Seismic Onset Time and Distributed Pressure and Temperature Measurements (Final Report)

We develop and demonstrate rapid and cost-effective methodologies for spatiotemporal tracking of CO2 plumes during geologic sequestration using joint inversion of seismic data and distributed pressure and temperature measurements. Key elements of our methodology are: (a) a computationally efficient approach to pressure and temperature propagation, (b) analysis of time lapse seismic data using a novel ‘seismic onset time’ approach to detect fluid front propagation, and (c) data assimilation and uncertainty assessment via joint inversion of pressure, temperature and time lapse seismic data, and (d) validating the numerical tomographic inversion using a CO2 injection demonstration projects, specifically data collected from the from the Petra Nova Parish Holdings CCUS project in the West Ranch Field, Texas and the Chester-16 reef CO2 injection site in Northern Michigan which is part of the DOE Midwestern Carbon Sequestration Project. The research team is led by Texas A&M University and includes Battelle as a subcontractor with support from Shell, Anadarko, Chevron and JX Nippon. A carbon dioxide (CO2) water-alternating-gas (WAG) pilot was conducted to gain insights into tertiary oil recovery potential via CO2 flood in the West Ranch Field as part of the Petra Nova project, the world’s largest post-combustion CO2 capture and utilization initiative. With a fluvial formation geology and large contrasts in permeability, this is a challenging and novel application of CO2 enhanced oil recovery (EOR). We build a predictive dynamic model of the subsurface that incorporates the multiphase and compositional data acquired during the pilot operation. The calibrated model is used for the carbon dioxide plume imaging. The study began with an initialization of the pilot sector model extracted from a calibrated full-field model. The pilot model calibration follows a two-step hierarchical workflow. First, we performed a large-scale update of the permeability distribution by integrating available bottomhole pressure and multiphase production data. In the second step, local permeability field is fine-tuned using a streamline-based method to match CO2 breakthrough times at the producers. The predictive capability of the calibrated model was verified through two blind validation tests: (1) the model showed good agreement with saturation logs acquired at two observation wells; and (2) the model reproduced the CO2 recovery as a fraction of the injected CO2. The use of seismic onset times has shown great promise for integrating near-continuous seismic surveys for updating geologic models. In this study, we analyze the impact of seismic survey frequency on the onset time approach aiming to extend the application of onset time to infrequent seismic surveys. In addition, we quantitatively examine the nonlinearity of the onset time method and compare it to the commonly used amplitude inversion method. We carry out a sensitivity analysis of seismic survey frequency based on the complete seismic survey data (over 175 surveys) of steam injection in a heavy oil reservoir (Peace River Unit) in Canada. Our results show that an adequate onset time map can be obtained from the infrequent seismic surveys by interpolation between seismic surveys as long as there is no change in the dominant underlying physics between the successive surveys. The study also shows that nonlinearity of the onset time method can be -smaller than that of the amplitude inversion method by several orders of magnitude. Application to the Brugge benchmark case shows that the onset time method obtains comparable permeability update as the traditional seismic amplitude inversion method with faster computation and improved convergence characteristics. We extend the streamline-based data integration approach to incorporate distributed temperature sensor (DTS) data using the concept of thermal tracer travel time. Then, a hierarchical workflow composed of evolutionary and streamline methods is employed to jointly history match the DTS and pressure data. Finally, CO2 saturation and streamline maps are used to visualize the CO2 plume movement during the sequestration process. The hierarchical workflow is applied to a carbon sequestration project in a carbonate reef reservoir within the Northern Niagaran Pinnacle Reef Trend in Michigan, USA. The monitoring data set consists of distributed temperature sensing (DTS) data acquired at the injection well and a monitoring well, flowing bottom-hole pressure data at the injection well, and time-lapse pressure measurements at several locations along the monitoring well. The history matching results indicate that the CO2 movement is mostly restricted to the intended zones of injection which is consistent with an independent warm-back analysis of the temperature data. In addition to employing simulation models and inverse methods for CO2 plume imaging, we also initialized a data-driven technology for detecting inter-well connectivity based on production and pressure data. Our machine-learning framework is built on the statistical recurrent unit (SRU) model and interprets well-based injection/production data into inter-well connectivity without relying on a geologic model. We test it on synthetic and field-scale CO2 EOR projects utilizing the water-alternating-gas (WAG) process. The validation of the proposed data-driven inter-well connectivity assessment is performed using synthetic data from simulation models where inter-well connectivity can be easily measured using the streamline-based flux allocation. The SRU model is shown to offer excellent prediction performance on the synthetic case. Despite significant measurement noise and frequent well shut-ins imposed in the field-scale case, the SRU model offers good prediction accuracy, the overall relative error of the phase production rates at most producers ranges from 10% to 30%. It is shown that the dominant connections identified by the data-driven method and streamline method are in close agreement. Texas A&M University, the lead organization in the project, was primarily responsible for the development of tomographic approaches for CO2 plume mapping in conjunction with distributed pressure, temperature and seismic onset time data. Battelle, as a subcontractor, was primarily responsible for the development of analytical and empirical methods for analyzing transient injection rate and pressure data from point/line sources such as injection and monitoring wells. An additional area of emphasis for Battelle was the use of machine learning for such tasks as inferring reservoir connectivity information from injection-production data, and identifying variable importance for machine learning-based proxy models developed from full-physics simulations. The two organizations also collaborated on the application of the tomographic inversion methodology for a field data set.

02 PETROLEUM↗
NASA NTRS1978

Survey of some recent stellar-evolution calculations

The stellar-evolution program developed by Sweigart (1973) was used to compute main sequence turnoff, red giant sequences, and horizontal branch sequences for many values of helium abundance and heavy-element abundance. The immediate aim has been to produce a self-consistent set of evolutionary sequences for wide ranges in the composition and mass. The long-term aim involves application to cluster HR diagrams and the integrated properties of galaxies. Turnoff sequences, red giant sequences, and horizontal branch sequences are discussed.

Sweigart, A. V.↗
NASA NTRS1992

CSI computer system/remote interface unit acceptance test results

The validation tests conducted on the Control/Structures Interaction (CSI) Computer System (CCS)/Remote Interface Unit (RIU) is discussed. The CCS/RIU consists of a commercially available, Langley Research Center (LaRC) programmed, space flight qualified computer and a flight data acquisition and filtering computer, developed at LaRC. The tests were performed in the Space Structures Research Laboratory (SSRL) and included open loop excitation, closed loop control, safing, RIU digital filtering, and RIU stand alone testing with the CSI Evolutionary Model (CEM) Phase-0 testbed. The test results indicated that the CCS/RIU system is comparable to ground based systems in performing real-time control-structure experiments.

Sparks, Dean W., Jr.↗
NASA NTRS1995

Evolutionary Development of the Simulation by Logical Modeling System (SIBYL)

Through the evolutionary development of the Simulation by Logical Modeling System (SIBYL) we have re-engineered the expensive and complex IBM mainframe based Long-term Hardware Projection Model (LHPM) to a robust cost-effective computer based mode that is easy to use. We achieved significant cost reductions and improved productivity in preparing long-term forecasts of Space Shuttle Main Engine (SSME) hardware. The LHPM for the SSME is a stochastic simulation model that projects the hardware requirements over 10 years. SIBYL is now the primary modeling tool for developing SSME logistics proposals and Program Operating Plan (POP) for NASA and divisional marketing studies.

Wu, Helen↗
DOE OSTI2026

HARMONY: Large-Scale Architecture Search for Efficient Hybrid Language Models

As large language models scale to trillions of parameters, their computational and memory requirements present critical challenges for efficient training and deployment. While Mixture of Experts (MoE) architectures enable efficient scaling through sparse parameter activation, and state-space models like Mamba offer linear-time complexity, principled methods for combining these paradigms remain undeveloped. We introduce HARMONY (Hybrid Architecture Research for Mamba, Optimized with Neural efficiencY), a multi-objective evolutionary neural architecture search framework for discovering efficient hybrid language models that integrate Transformer attention mechanisms, Mixture-of-Experts routing, and Mamba state-space components. Through large-scale distributed search using 16,384 MI250X GPUs on the Frontier supercomputer, HARMONY explores a comprehensive design space encompassing six attention variants (MHA, MQA, GQA, MLA, SWA, and Mamba-2), variable MoE configurations with both routed and shared experts, and extensive Mamba hyperparameters. Our framework discovers heterogeneous architectures that balance training performance with computational efficiency through multi-objective optimization incorporating latency penalties and fitness-based selection. Analysis of discovered architectures reveals that optimal hybrid designs favor heterogeneous component mixing rather than homogeneous patterns, with Mamba-2 and Multi-Head Latent Attention (MLA) emerging as preferred mechanisms. Discovered architectures demonstrate superior training efficiency: our best configuration achieves a final perplexity of 1.0874 with 2.38B parameters while processing 4,320 tokens/second, outperforming significantly larger manually designed models. Full-scale evaluation shows HARMONY's top architectures achieve better loss trajectories than equivalently-sized models using state-of-the-art configurations including Mixtral, Jamba, and Samba. Additionally, we demonstrate 91% weak scaling efficiency when training discovered 36B-parameter models across 1,024 GPUs. HARMONY is released as an open framework with comprehensive tools for building and training hybrid models using expert-data-pipeline parallelism, democratizing access to automated architecture design for next-generation language models.

Herron, Emily [ORNL] (ORCID:0000000273008172)↗
NASA NTRSDate not supplied

Microbial Communities in Microgravity: Simulation in Lab and on the Computer

Microorganisms grow differently in spaceflight than they do on Earth. While much remains unexplained about how microgravity affects microbial growth, one dominant hypothesis is that the lack of density-driven convection in the liquid growth environment makes mixing diffusion-limited, and therefore slower. This is supported by evidence that individual microbial strains experience starvation and acid stress in microgravity. However, if it is true, then microgravity would also have measurable effects on microbes in mixed communities, because many interspecies interactions involve the exchange of soluble metabolites through the medium (cross-feeding). Specifically, cooperative cross-feeding communities would grow more slowly in microgravity, and cooperation would be less stable on evolutionary timescales. Here we describe our efforts to test this hypothesis by simulating microgravity in silico and in the lab, using a model system of Eschericia coli and Salmonella enterica that grow only when they can exchange methionine and acetate. We created CAMDLES (CFD-DEM Artificial Microgravity Developments for Living Ecosystem Simulation) as an extension of CFDEM®coupling software, to carry out computational modeling of biological flows, growth, and mass transfer in microgravity and also in laboratory artificial microgravity devices (rotating wall vessels, RWV). Using CAMDLES, we found distinct differences in growth rates between RWV and true microgravity, and we were able to identify several features, such as spatial distribution, biofilm formation, and product yield parameters, that influence the degree to which RWV growth recapitulates microgravity growth. In addition, we report on the development of a laboratory system for monitoring growth rates and species ratios of the community in RWVs, using fluorescent strains. Pairing CAMDLES with the laboratory model system allows us to generate quantitative predictions about the effects of spaceflight on organisms that will be essential to sustaining human space exploration in the long term.

microbiology↗
DOE OSTI2025

Deep Reinforcement Learning Based Control of Wind Turbines for Fast Frequency Response

In order to fulfill vital auxiliary grid services, such as load regulation, spin and non-spin reserve provision, and frequency support during emergencies, there is often a requirement for certain wind farms to operate in de-loaded modes. Leveraging the swift response capabilities of wind farms, this study demonstrates that reserving power in de-loaded modes can significantly enhance power grid stability and reliability during system contingencies. Controlling wind farms optimally for frequency support is intricate due to the nonlinearity of models and controllers and the complexity of wind farm interactions with power systems. Here, to address this challenge, this paper introduces a novel approach that integrates wind turbines into reinforcement learning-based solutions for frequency response. This innovative methodology utilizes the state-of-the-art reinforcement learning algorithm known as the surrogate-gradient-based evolutionary strategy. The proposed learning-based algorithm provides continuous control of wind farm output to rapidly stabilize system frequency and prevent unnecessary trips of under-frequency load shedding relays. To facilitate efficient training, parallel computing techniques are employed. The proposed methodology is evaluated on a modified IEEE-39 bus system, and simulation results reveal its efficacy in reliably supporting power system frequency and preventing the need for unnecessary load shedding.

Gao, Wei [Argonne National Laboratory (ANL), Argon↗
NASA NTRS2000

JavaGenes: Evolving Graphs with Crossover

Genetic algorithms usually use string or tree representations. We have developed a novel crossover operator for a directed and undirected graph representation, and used this operator to evolve molecules and circuits. Unlike strings or trees, a single point in the representation cannot divide every possible graph into two parts, because graphs may contain cycles. Thus, the crossover operator is non-trivial. A steady-state, tournament selection genetic algorithm code (JavaGenes) was written to implement and test the graph crossover operator. All runs were executed by cycle-scavagging on networked workstations using the Condor batch processing system. The JavaGenes code has evolved pharmaceutical drug molecules and simple digital circuits. Results to date suggest that JavaGenes can evolve moderate sized drug molecules and very small circuits in reasonable time. The algorithm has greater difficulty with somewhat larger circuits, suggesting that directed graphs (circuits) are more difficult to evolve than undirected graphs (molecules), although necessary differences in the crossover operator may also explain the results. In principle, JavaGenes should be able to evolve other graph-representable systems, such as transportation networks, metabolic pathways, and computer networks. However, large graphs evolve significantly slower than smaller graphs, presumably because the space-of-all-graphs explodes combinatorially with graph size. Since the representation strongly affects genetic algorithm performance, adding graphs to the evolutionary programmer's bag-of-tricks should be beneficial. Also, since graph evolution operates directly on the phenotype, the genotype-phenotype translation step, common in genetic algorithm work, is eliminated.

Globus, Al↗
DOE OSTI2024

A combinatorially complete epistatic fitness landscape in an enzyme active site

Protein engineering often targets binding pockets or active sites which are enriched in epistasis—nonadditive interactions between amino acid substitutions—and where the combined effects of multiple single substitutions are difficult to predict. Few existing sequence-fitness datasets capture epistasis at large scale, especially for enzyme catalysis, limiting the development and assessment of model-guided enzyme engineering approaches. We present here a combinatorially complete, 160,000-variant fitness landscape across four residues in the active site of an enzyme. Assaying the native reaction of a thermostable β-subunit of tryptophan synthase (TrpB) in a nonnative environment yielded a landscape characterized by significant epistasis and many local optima. These effects prevent simulated directed evolution approaches from efficiently reaching the global optimum. There is nonetheless wide variability in the effectiveness of different directed evolution approaches, which together provide experimental benchmarks for computational and machine learning workflows. The most-fit TrpB variants contain a substitution that is nearly absent in natural TrpB sequences—a result that conservation-based predictions would not capture. Thus, although fitness prediction using evolutionary data can enrich in more-active variants, these approaches struggle to identify and differentiate among the most-active variants, even for this near-native function. Overall, this work presents a large-scale testing ground for model-guided enzyme engineering and suggests that efficient navigation of epistatic fitness landscapes can be improved by advances in both machine learning and physical modeling.

biocatalysis↗