Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “inversion methods”

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 991 records · Page 55
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Excited electronic states of Na 2 and K 2 : The potential for long-lived “reservoir” states leading to collision induced population inversions

Potential energy curves (PECs) for the spin-free (ΛS) and spin–orbit (Ω) states associated with the four lowest-lying dissociation channels of Na 2 and K 2 were calculated at the SA-CASSCF/SO-CASPT2/aug-cc-pwCVQZ-DK level. The PECs of Na 2 were consistent with the experimental data and with the FS-CCSD (2,0) calculations, reproducing the double-well and the “shelf” character for some of the potentials of the excited states. For K 2 , the PECs behaved in a similar way and the spectroscopic parameters for the ground and the excited states are in good agreement with the available experimental values. The dissociation energy of K 2 was predicted to be D e = 4454 cm −1 , within an agreement of 5 cm −1 with the experiments. For Na 2 , D e = 5789 cm −1 compared to the experimental value of 6022 cm −1 . The inclusion of spin–orbit coupling effects resulted in avoided crossings, which affect the PECs. Spin–orbit changes the predicted curves for some excited Ω states arising from ΛS states that overlap each other, affecting their associated vibrational frequencies and bond distances. Here, the current studies of the low-lying states in K 2 reveal a similar structure to those of Na 2 , which suggests the accessibility of long-lived energy storing reservoir states and possible population inversions in K 2 following prior experimental work on the reaction of halogen atoms with Na 3 to produce excited states of Na 2 .

Ab-initio methods↗
DOE OSTI2021

Sensitivity of a Subject-specific Ankle Sprain Simulation to Extrinsic Versus Intrinsic Biomechanical Factors

Ankle sprains are the most common musculoskeletal injury in sport and military activity, despite existing prophylactic strategies. The purpose of this report was to develop a probabilistic simulation of lateral ankle sprains during single-limb drop landing, towards accelerating innovation in ankle sprain prevention. A deterministic, subject-specific musculoskeletal model was extended with automation and probabilistic distributions on sprain-related biomechanical factors. Probabilistic simulations were generated using traditional Monte Carlo techniques and the advanced mean value method, a more computationally-efficient approach. Predicted distributions of peak ankle joint rotations, velocities, and moments borne by supporting passive structures agreed favorably with the deterministic model and with reports of real sprain biomechanics. Parameter sensitivities identified that predictions were most strongly influenced by drop height, subtalar joint posture at contact, invertor/evertor co-activation, and passive ankle stiffness. The advanced mean value method predicted confidence bounds comparable to a 1000-trial Monte Carlo simulation, and required only 14 model evaluations and 4-min processing time. The extended probabilistic simulation may be useful to virtually test new prophylactic strategies for ankle sprains, and is made available for open-source use (https://simtk.org/projects/sprain-sim).

60 APPLIED LIFE SCIENCES↗
DOE OSTI2020

Dynamic concurrent learning method to neutralize cyber attacks and faults for industrial asset monitoring nodes

Input signals may be received from monitoring nodes of the industrial asset, each input signal comprising time series data representing current operation. A neutralization engine may transform the input signals into feature vectors in feature space, each feature vector being associated with one of a plurality of overlapping batches of received input signals. A dynamic decision boundary may be generated based on the set of feature vectors, and an abnormal state of the asset may be detected based on the set of feature vectors and a predetermined static decision boundary. An estimated neutralized value for each abnormal feature value may be calculated based on the dynamic decision boundary and the static decision boundary such that a future set of feature vectors will be moved with respect to the static decision boundary. An inverse transform of each estimated neutralized value may be performed to generate neutralized signals comprising time series data that are output.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

A multifrequency characterization of the extragalactic hard X-ray sky

Context: Nowadays, we know that the origin of the cosmic X-ray background (CXB) is mainly due to the integrated emission of active galactic nuclei. Therefore, in order to obtain a precise estimate of the contribution of different source classes to the CXB, it is crucial to achieve full characterization of the hard-X ray sky. Aims: We present a multifrequency analysis of all sources listed in the third release of the Palermo Swift-BAT hard X-ray catalog (3PBC) with the goal of (i) identifying and classifying the largest number of sources adopting multifrequency criteria, with particular emphasis on extragalactic populations and (ii) extracting sources belonging to the class of Seyfert galaxies to present here the release of the second version of the Turin-SyCAT. Methods: We outline a classification scheme based on radio, infrared (IR), and optical criteria that allows us to distinguish between unidentified and unclassified hard X-ray sources, as well as to classify those sources belonging to the Galactic and the extragalactic populations. Results: Our revised version of the 3PBC lists 1176 classified, 820 extragalactic, and 356 Galactic sources, as well as 199 unclassified and 218 unidentified sources. According to our analysis, the hard X-ray sky is mainly populated by Seyfert galaxies and blazars. For the blazar population, we report trends between the hard X-ray and the gamma-ray emissions based on the fact that a large fraction of them also have a counterpart detected by the Fermi satellite. These trends are all in agreement with the expectations of inverse Compton models which are widely adopted to explain the blazar broadband emission. For the Seyfert galaxies, we present the second version of the Turin-SyCAT, including a total of 633 Seyfert galaxies, with 282 new sources corresponding to an increase of ~80% with respect to the previous release. Comparing the hard X-ray and the infrared emissions of Seyfert galaxies, we confirm that there is no clear difference between the flux distribution of the infrared-to-hard X-ray flux ratio of Seyfert galaxies Type 1 and Type 2. However, there is a significant trend between the mid-IR flux and hard X-ray flux, confirming previous statistical results in the literature. Conclusions: We provide two catalog tables. The first is the revised version of the 3PBC catalog based on our multifrequency analyses. The second catalog table is a release of the second version of the Turin-SyCAT catalog. Finally, we highlight that extensive soft X-ray data are already available in the form of the Swift archive which can be used to search for potential counterparts of unidentified hard X-ray sources. All these datasets will be reduced and analyzed in a forthcoming analysis to determine the precise position of low-energy counterparts in the 0.5–10 keV energy range for 3PBC sources that can be targets of future optical spectroscopic campaigns; this is necessary to obtain their precise classification.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

Neutron-unbound states in 31 Ne

Background: The Island of Inversion near the N = 20 shell gap is home to nuclei with reordered single-particle energy levels compared to the spherical shell model. Studies of 31 Ne have revealed that its ground state has a halo component, characterized by a valence neutron orbiting a deformed 30 Ne core. This lightly-bound nucleus with a separation energy of only S n = 170 keV is expected to have excited states that are neutron unbound. Purpose: The purpose of this experiment was to investigate the low-lying excited states in 31 Ne that decay by the emission of a single neutron. Methods: An 89 MeV/u 33 Mg beam impinged on a segmented Be reaction target. Neutron unbound states in 31 Ne were populated via a two-proton knockout reaction. The 30 Ne fragment and associated neutron from the decay of 31 Ne were detected by the MoNA-LISA-Sweeper experimental setup at the National Superconducting Cyclotron Laboratory. Invariant mass spectroscopy was used to reconstruct the two-body decay energy ( 30 Ne + n). Results: The two-body decay energy spectrum exhibits two features: a low-lying peak at 0.30 ± 0.17 MeV and a broad enhancement at 1.50 ± 0.33 MeV, each fit with an energy-dependent asymmetric Breit-Wigner line shape representing a resonance in the continuum. Accompanying shell model calculations using the FSU interaction within NuShellX, combined with cross-section cal culations using the eikonal reaction theory, indicate that these peaks in the decay energy spectrum are caused by multiple resonant states in 31 Ne. Conclusions: In this study, excited states in 31 Ne were observed for the first time. Transitions from calculated shell model final states in 31 Ne to bound states in 30 Ne are in good agreement with the measured decay energy spectrum. Cross-section calculations for the two-proton knockout populating 31 Ne states as well as spectroscopic factors pertaining to the decay of 31 Ne into 30 Ne are used to examine the results within the context of the shell model expectations.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2025

The Principle of Maximum Conformality Correctly Resolves the Renormalization-Scheme-Dependence Problem

In this paper, we clarify a serious misinterpretation and consequent misuse of the Principle of Maximum Conformality (PMC), which also can serve as a mini-review of PMC. In a recently published article, P. M. Stevenson has claimed that “the PMC is ineffective and does nothing to resolve the renormalization-scheme-dependence problem”, concluding incorrectly that the success of PMC predictions is due to the PMC being a “laborious, ad hoc, and back-door” version of the Principle of Minimal Sensitivity (PMS). We show that such conclusions are incorrect, deriving from a misinterpretation of the PMC and an overestimation of the applicability of the PMS. The purpose of the PMC is to achieve precise fixed-order pQCD predictions, free from conventional renormalization schemes and scale ambiguities. We demonstrate that the PMC predictions satisfy all the self-consistency conditions of the renormalization group and standard renormalization-group invariance; the PMC predictions are thus independent of any initial choice of renormalization scheme and scale. The scheme independence of the PMC is also ensured by commensurate scale relations, which relate different observables to each other. Moreover, in the Abelian limit, the PMC dovetails into the well-known Gell-Mann–Low framework, a method universally revered for its precision in QED calculations. Due to the elimination of factorially divergent renormalon terms, the PMC series not only attains a convergence behavior far superior to that of its conventional counterparts but also deftly curtails any residual scale dependence caused by the unknown higher-order terms. This refined convergence, coupled with its robust suppression of residual uncertainties, furnishes a sound and reliable foundation for estimating the contributions from unknown higher-order terms. Anchored in the bedrock of standard renormalization-group invariance, the PMC simultaneously eradicates the factorial divergences and eliminates superfluous systematic errors, which inversely provides a good foundation for achieving high-precision pQCD predictions. Consequently, owing to its rigorous theoretical underpinnings, the PMC is eminently applicable to virtually all high-energy hadronic processes.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2020

Angular scattering of protons through ultrathin graphene foils: Application for time-of-flight instrumentation

Space plasma instruments often rely on ultrathin carbon foils for incident ion detection, time-of-flight (TOF) mass spectrometry, and ionization of energetic neutral atoms. Angular scattering and energy loss of ions or neutral atoms in the foil can degrade instrument performance, including sensitivity and mass resolution; thus, there is an ongoing effort to manufacture thinner foils. Using new 3-layer graphene foils manufactured at the Los Alamos National Laboratory, we demonstrate that these are the thinnest foils reported to date and discuss future testing required for application in space instrumentation. We characterize the angular scattering distribution for 3–30 keV protons through the foils, which is used as a proxy for the foil thickness. We show that these foils are ~2.5–4.5 times thinner than the state-of-the-art carbon foils and ~1.6 times thinner than other graphene foils described in the literature. We find that the inverse relationship between angular scattering and energy no longer holds, reaffirming that this may indicate a new domain of beam–foil interactions for ultrathin (few-layer) graphene foils.

47 OTHER INSTRUMENTATION↗
DOE OSTI2026

Dual Representations and H ∞ -Optimal Control of Partial Differential Equations

We consider H ∞ -optimal state-feedback control of the class of linear Partial Differential Equations (PDEs) which admit a Partial Integral Equation (PIE) representation. While linear matrix inequalities are commonly used for optimal control of Ordinary Differential Equations (ODEs), the absence of a universal state-space representation and suitable dual form prevents such methods from being applied to optimal control of PDEs. Specifically, for ODEs, the controller synthesis problem is defined in state-space, and duality is used to resolve the bilinearity of that synthesis problem. Recently, the PIE representation was proposed as a universal state-space representation for linear PDE systems. In this paper, we show that any PDE system represented by a PIE admits a dual PIE with identical stability and I/O properties. This result allows us to reformulate the stabilizing and optimal state-feedback control problems as convex optimization over the cone of positive Partial Integral (PI) operators. Operator inversion formulae then allow us to construct feedback gains for the original PDE system. The results are verified through application to several canonical problems in optimal control of PDEs and indicate the resulting bounds on H ∞ norm are not conservative.

42 ENGINEERING↗
DOE OSTI2026

Excited-state uncertainties in lattice-QCD calculations of multi-hadron systems

Excited-state effects lead to hard-to-quantify systematic uncertainties in lattice quantum chromodynamics (LQCD) spectroscopy calculations when computationally accessible imaginary times are smaller than inverse excitation gaps, as often arises for multi-hadron systems with signal-to-noise problems. Lanczos residual bounds address this by providing two-sided constraints on energies that do not require assumptions beyond Hermiticity, but often give very conservative systematic uncertainty estimates. Here, a more-constraining set of gap bounds is introduced for hadron spectroscopy. These bounds provide tighter constraints whose validity requires an explicit assumption about an energy gap. Exactly solvable lattice field theory correlators are used to test the utility of residual and gap bounds at finite and infinite statistics. Two-sided bounds and other analysis methods are then applied to a high-statistics LQCD calculation of nucleon-nucleon scattering at $m_π\sim 800$ MeV. Generalized eigenvalue problem (GEVP) and Lanczos energy estimators are compatible when applied to the same correlator data, but analyses including different interpolating operators show statistically significant inconsistencies. However, two-sided bounds from all operators are consistent. Under the assumption that the number of energy levels below $NΔ$ and $ΔΔ$ thresholds is the same as for non-interacting nucleons, gap bounds are sufficient to constrain nucleon-nucleon scattering amplitudes at phenomenologically relevant precision. Lanczos methods further reveal that energy-eigenstate estimates from previously studied asymmetric correlators have not converged over accessible imaginary times. Nevertheless, data-driven examples demonstrate why assumptions are required to draw conclusions about the natures of two-nucleon ground states at these masses.

Detmold, William [MIT, Cambridge, CTP]↗
DOE OSTI2021

A persistent adjoint method with dynamic time-scaling and an application to mass action kinetics

In this article, we consider an optimization problem where the objective function is evaluated at the fixed-point of a contraction mapping parameterized by a control variable, and optimization takes place over this control variable. Since the derivative of the fixed-point with respect to the parameter can usually not be evaluated exactly, an adjoint dynamical system can be used to estimate gradients. Using this estimation procedure, the optimization algorithm alternates between derivative estimation and an approximate gradient descent step. We analyze a variant of this approach involving dynamic time-scaling, where after each parameter update the adjoint system is iterated until a convergence threshold is passed. Here, we prove that, under certain conditions, the algorithm can find approximate stationary points of the objective function. We demonstrate the approach in the settings of an inverse problem in chemical kinetics, and learning in attractor networks.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Characterization of DESI fiber assignment incompleteness effect on 2-point clustering and mitigation methods for DR1 analysis

We present an in-depth analysis of the fiber assignment incompleteness in the Dark Energy Spectroscopic Instrument (DESI) Data Release 1 (DR1). This incompleteness is caused by the restricted mobility of the robotic fiber positioner in the DESI focal plane, which limits the number of galaxies that can be observed at the same time, especially at small angular separations. As a result, the observed clustering amplitude is suppressed in a scale-dependent manner, which, if not addressed, can severely impact the inference of cosmological parameters. We discuss the methods adopted for simulating fiber assignment on mocks and data. In particular, we introduce the fast fiber assignment (FFA) emulator, which was employed to obtain the power spectrum covariance adopted for the DR1 full-shape analysis. We present the mitigation techniques, organised in two classes: measurement stage and model stage. We then use high fidelity mocks as a reference to quantify both the accuracy of the FFA emulator and the effectiveness of the different measurement-stage mitigation techniques. This complements the studies conducted in a parallel paper for the model-stage techniques, namely the θ-cut approach. We find that pairwise inverse probability (PIP) weights with angular upweighting recover the “true” clustering in all the cases considered, in both Fourier and configuration space. Notably, we present the first ever power spectrum measurement with PIP weights from real data.

cosmological simulations↗
DOE OSTI2025

Orbit-averaging and deposition accuracy for runaway electron beams in hybrid kinetic-MHD simulations of the runaway plateau

We develop a new procedure that combines the kinetic orbit runaway electron code (KORC) and the NIMROD extended-magnetohydrodynamic code to simulate runaway electrons (REs) in the post-disruption plateau. KORC integrates guiding-center orbits, with a barycentric-based binary search strategy providing initial guesses for the Newton–Raphson logical-to-physical coordinate inversion, ensuring reliable particle-to-mesh mapping in NIMROD, whose fields remain static for the present study. Samples are drawn in accord with experimental parallel current profiles of RE beams during the plateau phase. Deposition in NIMROD is verified through comparison with a Python-based finite-element code that ensures periodicity in the poloidal direction and continuity at the magnetic axis. Accurate representation of near-axis fields requires finer mesh resolution to prevent under- and overshoots in current density from orbit inaccuracies. Yet, at a fixed particle count, increasing mesh resolution amplifies statistical noise in the deposited fields. An orbit-averaging method accumulates partial current deposits over multiple kinetic steps and reduces the statistical noise with little added computational cost. By coupling kinetic routines from KORC directly into the NIMROD codebase, these developments lay essential groundwork for future self-consistent KORC–NIMROD coupling.

Algorithms and data structure↗
DOE OSTI2022

Case studies in bias reduction and inference for electronic health record data with selection bias and phenotype misclassification

Electronic health records (EHR) are not designed for population‐based research, but they provide easy and quick access to longitudinal health information for a large number of individuals. Many statistical methods have been proposed to account for selection bias, missing data, phenotyping errors, or other problems that arise in EHR data analysis. However, addressing multiple sources of bias simultaneously is challenging. We developed a methodological framework (R package, SAMBA ) for jointly handling both selection bias and phenotype misclassification in the EHR setting that leverages external data sources. These methods assume factors related to selection and misclassification are fully observed, but these factors may be poorly understood and partially observed in practice. As a follow‐up to the methodological work, we demonstrate how to apply these methods for two real‐world case studies, and we evaluate their performance. In both examples, we use individual patient‐level data collected through the University of Michigan Health System and various external population‐based data sources. In case study (a), we explore the impact of these methods on estimated associations between gender and cancer diagnosis. In case study (b), we compare corrected associations between previously identified genetic loci and age‐related macular degeneration with gold standard external summary estimates. These case studies illustrate how to utilize diverse auxiliary information to achieve less biased inference in EHR‐based research.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2020

An Experimental Feasibility Study on Applying Neutron Tomography to Encapsulated Spent Nuclear Fuel - 20050

Visual inspection makes easier to ensure the integrity and safety of spent nuclear fuel (SNF) than any classical techniques. Various classical techniques have been applied but there are no reliable methods to qualitatively and quantitatively verify spent fuel in dry storage. Thus, the present authors have developed the prototype safeguards apparatus for dry storage employing the array of He-4 gas scintillation detectors (S670E, Arktis Radiation Detectors Ltd., Switzerland), newly designed to simultaneously measure thermal and fast neutrons without any moderators. The S670E detector has a cylindrical shape with a diameter of 52 mm and active length of 600 mm (total length: 875 mm). The detector is filled by He-4 gas with an approximate pressure of 180 bar for fast neutron detection, and its inner wall is coated by Li-6 for thermal neutron detection. The scintillation lights generated via Li-6 nuclear reaction and elastic scattering are collected by 24 SiPMs linearly paired at the center of the detector. The detector delivers a TTL (Transistor-Transistor Logic) output for pulse readout and UART (Universal Asynchronous Receiver Transmitter) for device control. In order to assess feasibility of the apparatus, an experimental system has been designed, built, and optimized via computational studies. Cf-252 neutron sources and linearly arrayed detectors, working as a single detector, were occupied for this study due to the difficulties in working with SNF. The laboratory scale cask (diameter: 0.67 m, height: 1.5 m), minimized by a factor of 10 compared to the actual thickness of a commercial TN-32 cask, was also manufactured. The detector array was designed to rotate the lab-scale cask and obtain 36 image profiles at every 10 degrees. All profiles were aligned in single frame image called a sinogram, and the cross-sectional image was then fabricated by the inverse radon transform algorithm. These experiments have been repeated with different configurations and numbers of sources. Some gamma-ray sources were also measured with neutron sources in order to distinguish between neutron and gamma-ray pulses. Basically, a He-4 detector is designed to run on Linux OS so it is difficult to directly apply to Windows-based equipment widely used in S. Korea. Therefore, a new data acquisition board working on Windows OS was designed and built. The board mainly consists of FPGA (Field Programmable Gate Array) and SoC (System on Chip) for TTL pulse readout, sorting measured data, and transferring data to a user interface. In conclusion, the tomographic system at lab-scale has shown considerable potential to detect a partial or gross defect of encapsulated assemblies in dry storage. Next steps of this study will be to 1) repeatedly carry out experiments to demonstrate scientific reliability and validity, and 2) numerically integrate signals with weight factors to enhance the image quality since the suggested system based on passive interrogation method requires longer measurement time. Finally, the system will apply to a commercial dry storage phased out soon in S. Korea. (authors)

07 ISOTOPE AND RADIATION SOURCES↗
DOE OSTI2024

Pioneering Microporous Layers for Proton-Exchange-Membrane Water Electrolyzers via Tape Casting

The imperative shift towards decarbonization necessitates the production of clean hydrogen through water electrolysis, powered by renewable energy sources. Among electrolyzer technologies, proton-exchange-membrane (PEM) systems emerge as a promising option for large-scale hydrogen generation due to their modular design and rapid response, aligning well with the intermittency of renewable energy. In this study, we employ a tape casting method to fabricate microporous layers (MPLs), both as a single layer and as a bilayer over commercial porous transport layers (PTLs), to further enhance performance of water electrolyzers. We demonstrate that microporous layers require adequate pore sizes to facilitate gas removal, preventing gas flooding and preserving electrolyzer performance. Our single layer microporous layers exhibit lower overpotentials compared to commercial sintered Ti PTLs by 142 mV at 4 A·cm ⁻2 . Moreover, we show that having an effective microporous layer enhances electrolyzer performance irrespective of the substrate used, offering avenues for cost reduction. We also investigate novel PTL structures with reduced tortuosity and integrated MPL fabricated via phase inversion tape casting, resulting in a performance enhancement of 92 mV. Our findings unravel the critical role of microporous layer structures and their impact on electrolyzer performance.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Systems and methods for plane-wave and fan-beam ultrasound-waveform tomography

A method for plane-wave or fan-beam ultrasound tomography includes: controlling, by a processor, a multi-channel ultrasound array controller to control a linear ultrasound transducer array to emit plane-wave or fan-beam ultrasound into a biological tissue, the linear ultrasound transducer array including a plurality of transducers; receiving, by the processor, plane-wave or fan-beam ultrasound waveform data from the transducers, the plane-wave or fan-beam ultrasound waveform data including reflections of the plane-wave or fan-beam ultrasound from the biological tissue; computing, by the processor, a synthetic ultrasound-waveform inversion from the received plane-wave or fan-beam ultrasound waveform data; and computing, by the processor, an image of the biological tissue from the synthetic ultrasound-waveform inversion.

Huang, Lianjie↗
DOE OSTI2023

Visualization and efficient generation of constrained high-dimensional theoretical parameter spaces

We describe a set of novel methods for efficiently sampling high-dimensional parameter spaces of physical theories defined at high energies, but constrained by experimental measurements made at lower energies. Often, theoretical models such as supersymmetry are defined by many parameters, $\mathcal{O}$(10 – 100), expressed at high energies, while relevant experimental constraints are often defined at much lower energies, preventing them from directly ruling out portions of the space. Instead, the low-energy constraints define a complex, potentially non-contiguous subspace of the theory parameters. Naive scanning of the theory space for points which satisfy the low-energy constraints is hopelessly inefficient due to the high dimensionality, and the inverse problem is considered intractable. As a result, many theoretical spaces remain under-explored. We introduce a class of modified generative autoencoders, which attack this problem by mapping the high-dimensional parameter space to a structured low-dimensional latent space, allowing for easy visualization and efficient generation of theory points which satisfy experimental constraints. An extension without dimensional compression, which focuses on limiting potential information loss, is also introduced.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

RLMolLM: Reinforcement Learning-Enhanced Language Model Framework for Inverse Molecular Design

Inverse molecular design faces significant challenges due to vast chemical space and complex property requirements. While language models show promise for molecular generation, they struggle with validity, multi-property optimization, and structural constraints. This work presents RLMolLM, a reinforcement learning framework combining Proximal Policy Optimization (PPO) with genetic algorithms to address these limitations. Our approach optimizes multiple user-specified properties including quantitative estimates of drug-likeness (QED), synthetic accessibility (SA), and ADMET (absorption, distribution, metabolism, excretion, and toxicity) endpoints without requiring complete model retraining, while maintaining capability for scaffold-constrained generation where specific substructures must be preserved. We outperform state-of-the-art methods for molecular optimization, achieving best QED scores across GDB13, Moses, and Zinc datasets with up to 31% improvement over previous methods while maintaining excellent validity, uniqueness, and novelty metrics. For simultaneous multi-property optimization, our framework achieves substantial improvements in ADMET properties including 4.5-fold reduction in hERG toxicity and enhanced Caco-2 permeability compared to Moses dataset. Under structural constraints, the framework significantly improves molecular validity while preserving scaffolds and effectively optimizing properties. In conclusion, this versatile solution advances pharmaceutical and materials molecular design through effective integration of reinforcement learning and genetic algorithms with multi-property optimization and scaffold preservation.

Genetic algorithms↗