Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “data predictive control”

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 541 records · Page 30
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Artificial Intelligence and Machine Learning Applications in Modern Power Systems

Machine learning (ML) and artificial intelligence (AI) algorithms offer valuable tools for the analysis and interpretation of large datasets. These tools have the capability to uncover insights that may not be readily apparent within these datasets. In recent years, the integration of ML and AI has become increasingly prevalent in various applications within the power system domain. One of the earliest instances of machine learning in power systems can be traced back to demand forecasting, where artificial neural networks were employed for short-term load forecasting. In contemporary power systems, an abundance of high-resolution geospatial and temporal data is generated at various time intervals, ranging from sub-seconds (Phasor Measurement Units or PMUs) to seconds (Supervisory Control and Data Acquisition or SCADA), minutes (Process Information or PI), and extending to days, months, and years. These datasets contain valuable information concerning system reliability and performance. This information holds the potential to offer critical insights into system operations, as well as solutions for predicting and mitigating contingencies to prevent cascading outages. Despite the immense power of machine learning tools, system operators, planners, and utilities often exhibit hesitancy in fully embracing AI-enabled system operations and planning. This cautious approach persists, even as numerous diverse applications of machine learning continue to emerge in the realm of power systems. In this chapter, our focus will delve deep into ML and AI applications tailored for power systems. These applications aim to furnish system operators with enhanced situational awareness and augment their decision-making capabilities, especially during challenging operating conditions. Specific areas of interest encompass root cause analyses of electricity market datasets and the strategic selection of representative samples from vast power system databases for training ML/AI models. Finally, the chapter will conclude with a short discussion on the future of ML/AI in power systems and possible directions that the industry is moving towards.

power system applications, machine learning (ML), ↗
DOE OSTI2021

A Physics-Constrained Deep Learning Model for Simulating Multiphase Flow in 3D Heterogeneous Porous Media

Physics-based simulators for multiphase flow in porous media emulate nonlinear processes with coupled physics, and usually require extensive computational resources for software development, maintenance and simulation execution. As a result, a huge demand exists for fast modeling of coupled processes in a wide range of subsurface applications including geological sequestration, hydrocarbon recovery and geothermal energy extraction. In this work, an efficient physics-constrained deep learning model is developed for solving multiphase flow in 3-Dimensional (3D) heterogeneous porous media. The model fully leverages the spatial topology predictive capability of convolutional neural networks, specifically U-Net with successive contracting and expansive steps, and is coupled with an efficient continuity-based smoother to predict flow responses that need spatial continuity. Furthermore, the transient regions are penalized to steer the training process such that the model can accurately capture flow in these regions. The model takes inputs including properties of porous media, fluid properties and well controls, and predicts the temporal-spatial evolution of the state variables (pressure and saturation). While maintaining the continuity of fluid flow, the 3D spatial domain is decomposed into 2D images for reducing training cost, and the decomposition results in an increased number of training data samples and better training efficiency. Additionally, a surrogate model is separately constructed as a postprocessor to calculate well flow rate based on the predictions of state variables from the deep learning model. We use the example of CO 2 injection into saline aquifers, and apply the physics-constrained deep learning model that is trained from physics-based simulation data and emulates the physics process. The model performs prediction with a speedup of ~ 1400 times compared to physics-based simulations, and the average temporal errors of predicted pressure and saturation plumes are 0.27% and 0.099% respectively. Furthermore, water production rate is efficiently predicted by a surrogate model for well flow rate, with a mean error less than 5%. Therefore, with its unique scheme to cope with the fidelity in fluid flow in porous media, the physics-constrained deep learning model can become an efficient predictive model for computationally demanding inverse problems or other coupled processes.

58 GEOSCIENCES↗
DOE OSTI2021

Post-remediation geophysical assessment: Investigating long-term electrical geophysical signatures resulting from bioremediation at a chlorinated solvent contaminated site

There is a growing need to assess long-term impacts of active remediation strategies on treated aquifers. A variety of biogeochemical alterations can result from interactions of the amendment with the aquifer, conceivably leading to a geophysical footprint of the long-term alteration of an aquifer. This concept of post-remediation geophysical assessment was investigated in a shallow, chlorinated solvent-contaminated aquifer six to eight years after amendment delivery. Surface resistivity imaging and cross-borehole resistivity and induced polarization (IP) imaging were performed on a transect that spanned treated and untreated zones of the aquifer. Established relationships between IP parameters and surface electrical conductivity were used to predict vertical profiles of electrolytic conductivity and surface conductivity from the inverted cross-borehole images. Aqueous geochemistry data, along with natural gamma and magnetic susceptibility logs, were used to constrain the interpretation. The electrical conductivity structure determined from surface and borehole imaging was foremost controlled by the electrolytic conductivity of the interconnected pore space, being linearly related to fluid specific conductance. The electrolytic conductivity (and thus the conductivity images alone) did not discriminate between treated and untreated zones of the aquifer. In contrast, inverted phase angles and surface conductivities did discriminate between treated and untreated zones of the aquifer, with the treated zone being up to an order of magnitude more polarizable in places. Supporting aqueous chemistry and borehole logging datasets indicate that this geophysical footprint of the long-term impact of the remediation on the aquifer is most likely associated with the formation of polarizable, dispersed iron sulfide minerals. The study opens the door to the possibility of employing time-lapse electrical geophysical measurements to assist with long-term environmental stewardship of legacy sites undergoing active remediation.

bioremediation↗
DOE OSTI2022

High-throughput screening of tribological properties of monolayer films using molecular dynamics and machine learning

Monolayer films have shown promise as a lubricating layer to reduce friction and wear of mechanical devices with separations on the nanoscale. These films have a vast design space with many tunable properties that can affect their tribological effectiveness. For example, terminal group chemistry, film composition, and backbone chemistry can all lead to films with significantly different tribological properties. This design space, however, is very difficult to explore without a combinatorial approach and an automatable, reproducible, and extensible workflow to screen for promising candidate films. Here, using the Molecular Simulation Design Framework (MoSDeF), a combinatorial screening study was performed to explore 9747 unique monolayer films (116 964 total simulations) and a machine learning (ML) model using a random forest regressor, an ensemble learning technique, to explore the role of terminal group chemistry and its effect on tribological effectiveness. The most promising films were found to contain small terminal groups such as cyano and ethylene. The ML model was subsequently applied to screen terminal group candidates identified from the ChEMBL small molecule library. Approximately 193 131 unique film candidates were screened with approximately a five order of magnitude speed-up in analysis compared to simulation alone. The ML model was thus able to be used as a predictive tool to greatly speed up the initial screening of promising candidate films for future simulation studies, suggesting that computational screening in combination with ML can greatly increase the throughput in combinatorial approaches to generate in silico data and then train ML models in a controlled, self-consistent fashion.

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

Neural net modeling of equilibria in NSTX-U

Neural networks (NNs) offer a path towards synthesizing and interpreting data on faster timescales than traditional physics-informed computational models. In this work we develop two NNs relevant to equilibrium and shape control modeling, which are part of a suite of tools being developed for the National Spherical Torus Experiment-Upgrade for fast prediction, optimization, and visualization of plasma scenarios. The networks include Eqnet, a free-boundary equilibrium solver trained on the EFIT01 (Equilibrium FITtting 01) reconstruction algorithm, and Pertnet, which is trained on the Gspert code and predicts the non-rigid plasma response, a nonlinear term that arises in shape control modeling. The NNs are trained with different combinations of inputs and outputs in order to offer flexibility in use cases. In particular, Eqnet can use magnetic diagnostics as inputs and act as an EFIT-like reconstruction algorithm, or, by using pressure and current profile information the NN can act as a forward Grad–Shafranov equilibrium solver. This forward-mode version is envisioned to be implemented in the suite of tools for simulation of plasma scenarios. The reconstruction-mode version gives some performance improvements compared to the online reconstruction code real-time EFIT, especially when vessel eddy currents are significant. Here, we report strong performance for all NNs indicating that the models could reliably be used within closed-loop simulations or other applications. Some limitations are discussed.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2026

Autoregressive long-horizon prediction of plasma edge dynamics *

Accurate modeling of scrape-off layer (SOL) and divertor-edge dynamics is vital for designing plasma-facing components in fusion devices. High-fidelity edge fluid/neutral codes such as SOLPS-ITER capture SOL physics with high accuracy, but their computational cost limits broad parameter scans and long transient studies. We present transformer-based, autoregressive surrogates for efficient prediction of 2D, time-dependent plasma edge state fields. Trained on SOLPS-ITER spatiotemporal data for the KSTAR tokamak, the surrogates forecast electron temperature, electron density, and radiated power over extended horizons. We evaluate model variants trained with increasing autoregressive horizons (1–100 steps) on short- and long-horizon prediction tasks. Longer-horizon training systematically improves rollout stability and mitigates error accumulation, enabling stable predictions over hundreds to thousands of steps and reproducing key dynamical features such as the motion of high-radiation regions. Measured end-to-end wall-clock times show the surrogate is orders of magnitude faster than SOLPS-ITER, enabling rapid parameter exploration. Prediction accuracy degrades when the surrogate enters physical regimes not represented in the training dataset, motivating future work on data enrichment and physics-informed constraints. Overall, this approach provides a fast, accurate surrogate for computationally intensive plasma edge simulations, supporting rapid scenario exploration, control-oriented studies, and progress toward real-time applications in fusion devices.

autoregressive deep learning↗
DOE OSTI2023

Modeling strategies and data needs for representing coastal wetland vegetation in land surface models

Vegetated coastal ecosystems sequester carbon rapidly relative to terrestrial ecosystems. Coastal wetlands are poorly represented in land surface models, but work is underway to improve process-based, predictive modeling of these ecosystems. Here, in this work, we identify guiding questions, potential simulations, and data needs to make progress in improving representation of vegetation in terrestrial–aquatic interfaces, with a focus on coastal and estuarine ecosystems. We synthesize relevant plant traits and environmental controls on vegetation that influence carbon cycling in coastal ecosystems. We propose that models include separate plant functional types (PFTs) for mangroves, graminoid salt marshes, and succulent salt marshes to adequately represent the variation in aboveground and belowground productivity between common coastal wetland vegetation types. We also discuss the drivers and carbon storage consequences of shifts in dominant PFTs. We suggest several potential approaches to represent the diversity in vegetation tolerance and adaptations to fluctuations in salinity and water level, which drive key gradients in coastal wetland ecosystems. Finally, we discuss data needs for parameterizing and evaluating model implementations of coastal wetland vegetation types and function.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Autonomous Closed-Loop Experimental Characterization and Dynamic Model Validation of a Scaled Underwater Kite

This paper presents the closed-loop experimental framework and dynamic model validation for a 1/12-scale underwater kite design. The pool-based tow testing framework described herein, which involves a fully actuated, closed-loop controlled kite and flexible tether, significantly expands upon the capabilities of any previously developed open-source framework for experimental underwater kite characterization. Specifically, the framework has allowed for the validation of three closed-loop flight control strategies, along with a critical comparison between dynamic model predictions and experimental results. In this paper, we provide a detailed presentation of the experimental tow system and kite setup, describe the control algorithms implemented and tested, and quantify the level of agreement between our multi-degree-of-freedom kite dynamic model and experimental data. Finally, we also present a sensitivity analysis that helps to identify the most influential parameters to kite performance and further explain the remaining mismatches between the model and data.

42 ENGINEERING↗
DOE OSTI2024

Search for ${\text {Z}{}{}} {\text {Z}{}{}} $ and ${\text {Z}{}{}} {\text {H}{}{}} $ production in the ${\text {b}{}{}} {\bar{{\text {b}{}{}}}{}{}} {\text {b}{}{}} {\bar{{\text {b}{}{}}}{}{}} $ final state using proton-proton collisions at $\sqrt{s}=13\,\text {Te}\hspace{-.08em}\text {V} $

A search for ${\text {Z}{}{}} {\text {Z}{}{}} $ and ${\text {Z}{}{}} {\text {H}{}{}} $ production in the ${\text {b}{}{}} {\bar{{\text {b}{}{}}}{}{}} {\text {b}{}{}} {\bar{{\text {b}{}{}}}{}{}} $ final state is presented, where H is the standard model (SM) Higgs boson. The search uses an event sample of proton-proton collisions corresponding to an integrated luminosity of 133$\,\text {fb}^{-1}$ collected at a center-of-mass energy of 13$\,\text {Te}\hspace{-.08em}\text {V}$ with the CMS detector at the CERN LHC. The analysis introduces several novel techniques for deriving and validating a multi-dimensional background model based on control samples in data. A multiclass multivariate classifier customized for the ${\text {b}{}{}} {\bar{{\text {b}{}{}}}{}{}} {\text {b}{}{}} {\bar{{\text {b}{}{}}}{}{}} $ final state is developed to derive the background model and extract the signal. The data are found to be consistent, within uncertainties, with the SM predictions. The observed (expected) upper limits at 95% confidence level are found to be 3.8 (3.8) and 5.0 (2.9) times the SM prediction for the ${\text {Z}{}{}} {\text {Z}{}{}} $ and ${\text {Z}{}{}} {\text {H}{}{}} $ production cross sections, respectively.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

Improving the prediction of daily reservoir releases over the CONUS using conditioned LSTM

Reservoirs play a vital role in regulating streamflow timing and variability for hydroelectricity, flood control, water supply, irrigation, and recreation. Despite their importance, many reservoirs lack comprehensive operational guidelines, making their management complex due to conflicting operational objectives. Hence traditional policy-based reservoir models often fail to capture real-world conditions accurately and they depend on perfect streamflow predictions, which are not always available. In contrast, data-driven models like Long Short-Term Memory (LSTM) networks offer a robust alternative. This study introduces an approach that integrates reservoir characteristics—such as main use, climate, and maximum capacity—into the LSTM model to enhance reservoir release predictions. Using data from nearly 200 reservoirs in the contiguous United States (CONUS), our conditioned LSTM model (LSTM_cond) was compared with both the vanila LSTM and a traditional policy-based approach. Furthermore, our results show that while both LSTM_cond and LSTM perfoms better than the policy-based approach, LSTM_cond consistently outperforms LSTM for hydroelectric, water supply, irrigation, and recreation reservoirs. The KGE median values for LSTM_cond for out-sample reservoirs are 0.764, 0.565, 0.821, and 0.779, respectively, for the aforementioned reservoir types, which are consistently higher that the corresponding KGE values of 0.737, 0.413, 0.775, and 0.713 of LSTM, demonstrating its advantages in improving generalizability.

CONUS↗
DOE OSTI2025

COMPASS-FME Synoptic Site Tree Greenhouse Gas Concentrations

These data are tree stem greenhouse gas concentrations collected from tree gas wells at some of the COMPASS-FME (Coastal Observations, Mechanisms, and Predictions Across Systems and Scales; see https://compass.pnnl.gov/) 'synoptic' sites in the Chesapeake Bay region: Moneystump (MSM), Goodwin Islands (GWI), and GCReW (GCW). The sap flow monitoring trees at these sites in the Upland (UP) and Transition (TR) zones were cored and had gas wells installed at breast height. There were also some dead standing trees cored, gas well installed, and sampled at MSM and GWI. The GCW UP samples overlap with the TEMPEST experiment control plot, so the GCW UP data was pulled from the TEMPEST page and included here. These data provide crucial information about possible pathways for the greenhouse gas (carbon dioxide and methane, CO2 and CH4 respectively) production and emission (or in the case of CH4, perhaps taken up from) the atmosphere.All data are plain text CSV (comma separated value) files and require no special software to read.Updated 2025-10-09 to fix two missing dates (lines 77 and 78 in the data file).

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Using Best Basis Inventory Data to Direct Strategies for Real-Time Monitoring of Hanford High Level Waste

The proposed Direct Feed High Level Waste (DFHLW) approach for processing high-level tank waste at Hanford is intended to reduce processing time by bypassing the Pretreatment Facility and transferring waste directly from the tank farm to the WTP HLW vitrification facility. This processing strategy could reduce or eliminate the washing and leaching steps that would have occurred in the Pretreatment facility. Operation of the vitrification facility is subject to chemical and radiological limits protecting safety (e.g. Waste Acceptance Criteria, or WACs) and process quality (e.g. Process Control Limits, or PCLs). Without washing and leaching, there is a greater risk of exceeding the WACs and PCLs. Hanford process engineers have devised blending strategies based on known chemical and radiological composition, volumes, and solids loadings of individual layers within each waste tank. These blending campaigns succeed in predicting a processing strategy that does not exceed the WACs and PCLs. However, the calculations do not ascribe uncertainties to the tank analysis data, quantities of material taken from the tanks to make the blend, or potential for mixing of layers within tanks. In order to confirm that a process strategy is working, it would be advantageous to have inline or at-line analytical instrumentation installed in the processing facilities that deliver measurement results in real time.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2023

Limits on the Range and Rate of Change in Power Take-Off Load in Ocean Wave Energy Conversion: A Study Using Model Predictive Control

Previous work comparing power take-off (PTO) architectures for ocean wave-powered reverse osmosis suggests that variable displacement in the wave energy converter (WEC)-driven pump does not offer a significant performance advantage. A limitation of that study is that the WEC was subject to a constant load within a given sea state (“Coulomb damping”) and did not account for controlled, moment-to-moment variation of the PTO load enabled by a variable displacement pump. This study explores the potential performance advantage of a variable PTO load over Coulomb damping. Model predictive control is used to provide optimal load control with constraints on the PTO load. The constraints include minimum and maximum loads and a limit on the rate of load adjustment. Parameter studies on these constraints enable conclusions about PTO design requirements in addition to providing an estimated performance advantage over Coulomb damping. Numerical simulation of the Oyster 1 WEC is carried out with performance weighted by historical sea state data from Humboldt Bay, CA. The results show a performance advantage of up to 20% higher yearly-average power absorption over Coulomb damping. Additionally, the parameter studies suggest that the PTO load should be adjustable down to at least 25% of the maximum load and should be adjustable between the minimum and maximum loads within a few seconds.

16 TIDAL AND WAVE POWER↗
DOE OSTI2021

Machine learning-enabled prediction of chemical durability of A 2 B 2 O 7 pyrochlore and fluorite

Pyrochlore-structure type and its derivative in a general formula A 2 B 2 O 7 (A = rare earth elements and actinides; B = Ti, Sn, Zr, Hf, Pb, Si, etc.) display excellent structural flexibility and rich crystal chemistry as promising nuclear waste form materials capable of immobilizing actinides and fission products. It is essential to understand these materials’ chemical durability and element release of radionuclides in order to evaluate their performance in near-field environment. However, it is a formidable grand technological challenge to experimentally perform durability testing across hundreds of thousands of possibilities resulting from their extreme compositional complexities due to cation substitutions at both A and B-sites. In this work, we demonstrate a machine learning approach to determine the key materials parameters and structural characteristics governing the leaching behaviors from a small set of selected compositions as model systems, enabling a science-based prediction of their chemical durability that can be extended to a wide range of chemical compositions. The combination of four key structural characteristics and materials parameters, including ionic radius size difference , ionic potential difference , electronegativity difference , and lattice parameter , creates features an optimized prediction of the chemical durability. Two machine learning models, linear regression and Kernel ridge regression models, are trained on the randomly-split training dataset derived from the experimentally-determined elemental release rates, and subsequently tested on the testing dataset. The predicted leaching rates from both machine learning models show an excellent agreement with the experimental data, demonstrating the feasibility of rapidly evaluating the material properties of new compositions. These results highlight the immense potential of synergizing informatics through machine learning-based models and well-controlled experiments of selected model systems to accelerate materials design and discovery with optimized compositions and performance of promising materials for effective nuclear waste management.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2026

Reduced methane emissions in transgenic rice genotypes are associated with altered rhizosphere microbial hydrogen cycling

Rice paddies significantly contribute to atmospheric methane (CH 4 ). Here, we show that two independent rice genotypes overexpressing genes for PLANT PEPTIDES CONTAINING SULFATED TYROSINE (PSY) reduce cumulative CH 4 emissions by 38% (PSY1) and 58% (PSY2) over 70 days of growth compared with controls. Genome-resolved metatranscriptomic data from PSY rhizosphere soils reveal lower ratios of gene activities for (mostly hydrogenotrophic) CH 4 production versus consumption, decreased activity of H 2 -producing genes, and increased activity of bacterial H 2 oxidation pathways. Metabolic modeling using metagenomic and metabolomic data predicts elevated H 2 oxidation and suppressed H 2 production in the PSY rhizosphere. Assembled genomes of rhizosphere H 2 -oxidizing bacteria are enriched in genes utilizing gluconeogenic acids compared with H 2 -producing counterparts, and their activities are likely stimulated by elevated levels of gluconeogenic acids, primarily amino acids, in PSY root exudates. Overall, our study indicates that decreased CH 4 emissions are due to a lower amount of H 2 available for hydrogenotrophic methanogenesis and provides a powerful strategy to mitigate CH 4 emissions from increasingly widespread rice cultivation.

Biological and medical sciences↗
DOE OSTI2024

Physics-Guided Machine Learning (PGML) for Improved Aerostructure Manufacturing

The Physics-Guided Machine Learning (PGML) for Improved Aerostructure Manufacturing project objective is to automatically tune machining parameter predictions from physics-based models using process data and Bayesian machine learning. The intent is to enable a step change in aerospace manufacturing by combining machine learning, physics-based process models, and sensors/data in a comprehensive digital environment that simultaneously considers the computer numerically controlled (CNC) machining center capabilities, the workpiece material and geometry, and the workpiece support (fixturing). The project hypothesis is that this combination will enable improved performance in machining operations.

42 ENGINEERING↗
DOE OSTI2022

Deep Learning for In-Situ Layer Quality Monitoring during Laser-Based Directed Energy Deposition (LB-DED) Additive Manufacturing Process

Defects are a leading issue for the rejection of parts manufactured through the Directed Energy Deposition (DED) Additive Manufacturing (AM) process. In an attempt to illuminate and advance in situ quality monitoring and control of workpieces, we present an innovative data-driven method that synchronously collects sensing data and AM process parameters with a low sampling rate during the DED process. The proposed data-driven technique determines the important influences that individual printing parameters and sensing features have on prediction at the inter-layer qualification to perform feature selection. Three Machine Learning (ML) algorithms including Random Forest (RF), Support Vector Machine (SVM), and Convolutional Neural Network (CNN) are used. During post-production, a threshold is applied to detect low-density occurrences such as porosity sizes and quantities from CT scans that render individual layers acceptable or unacceptable. This information is fed to the ML models for training. Training/testing are completed offline on samples deemed “high-quality” and “low-quality”, utilizing only features recorded from the build process. CNN results show that the classification of acceptable/unacceptable layers can reach between 90% accuracy while training/testing on a “high-quality” sample and dip to 65% accuracy when trained/tested on “low-quality”/“high-quality” (respectively), indicating over-fitting but showing CNN as a promising inter-layer classifier.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Neural Network Analysis of Nuclear Magnetic Resonance and Infrared Spectra

Nuclear magnetic resonance (NMR) spectroscopy and infrared (IR) spectroscopy are powerful chemical characterization techniques with broad general usage. However, the manual evaluation of the resulting spectra is time-consuming and requires significant expertise, preventing insights from being used in real-time applications. With recent advances in computation and artificial intelligence (AI), new tools are available for automating spectral interpretation. In this work, machine learning (ML) algorithms using 1-dimensional convolutional neural networks (CNNs) were applied to identify common functional groups from spectral information. Raw spectra were collected virtually from the Human Metabolome Database (HMDB) and National Institute of Standards and Technology (NIST) Chemistry WebBook and processed into a suitable standard. Algorithm design was tailored to best fit the nature of the problem, with built-in flexibility to accommodate relevant parameters beyond the raw spectral input, specifically solvent identity and magnetic frequency for NMR. The predictive capability of the algorithm in identifying functional groups is displayed in several examples. This methodology has been compiled into a code repository and could easily be modified to adapt alternative data sources, including other spectrum types. To mitigate overfitting, a common problem in mathematical modeling where overfamiliarity with training data produces trends that are not representative of the general data, a novel metric was developed, referred to as Accufit. Accufit includes a parameter that penalizes substantial differences in the training accuracy and the accuracy of an independent validation set. Examples are presented showing the effectiveness of Accufit in maintaining the model’s predictive capability while controlling the overfitting when used as a custom metric for hyperparameter tuning.

Sturgill, James↗