Search NASA⌕ Search

SEARCH · Search NASA

Results for “evaluation datasets”

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 1,099 records · Page 61

Explicit modeling of abiotic and landscape factors reveals precipitation and forests associated with aphid abundance

Abstract Increases in natural or noncrop habitat surrounding agricultural fields have been shown to be correlated with declines in insect crop pests. However, these patterns are highly variable across studies suggesting other important factors, such as abiotic drivers, which are rarely included in landscape models, may also contribute to variability in insect population abundance. The objective of this study was to explicitly account for the contribution of temperature and precipitation, in addition to landscape composition, on the abundance of a widespread insect crop pest, the soybean aphid ( Aphis glycines Matsumura), in Wisconsin soybean fields. We hypothesized that higher soybean aphid abundance would be associated with higher heat accumulation (e.g., growing degree days) and increasing noncrop habitat in the surrounding landscape, due to the presence of the overwintering primary hosts of soybean aphid. To evaluate these hypotheses, we used an ecoinformatics approach that relied on a large dataset collected across Wisconsin over a 9‐year period (2003–2011), for an average of 235 sites per year ( n = 2,110 fields total). We determined surrounding landscape composition (1.5‐km radius) using publicly available satellite‐derived land cover imagery and interpolated daily temperature and precipitation information from the National Weather Service COOP weather station network. We constructed linear mixed models for soybean aphid abundance based on abiotic and landscape explanatory variables and applied model averaging for prediction using an information theoretic framework. Over this broad spatial and temporal extent in Wisconsin, we found that variation in growing season precipitation was positively related to soybean aphid abundance, while higher precipitation during the nongrowing season had a negative effect on aphid populations. Additionally, we found that aphid populations were higher in areas with proportionally more forest but were lower in areas where minor crops, such as small grains, were more prevalent. Thus, our findings support our hypothesis that including abiotic drivers increases our understanding of crop pest abundance and distribution. Moreover, by explicitly modeling abiotic factors, we may be able to explore how variable climate in tandem with land cover patterns may affect current and future insect populations, with potentially critical implications for crop yields and agricultural food webs.

Stack Whitney, Kaitlin↗

Projected changes in extreme rainfall and temperature events and possible implications for Cameroon's socio-economic sectors

Extreme events like flooding, droughts and heatwave are among the factors causing huge socio-economic losses to Cameroonians. Investigating the potential response of rainfall and temperature extremes to global warming is therefore critically needed for tailoring and adjusting the country's policies. Recent datasets have been developed for this purpose within the Coordinated Output for Regional Evaluations (CORDEX-CORE) initiative, at ~25 km grid spacing. These regional climate models were used to dynamically downscaled four global climate models participating in the Coupled Model Intercomparison Project phase 5 (CMIP5), under the optimistic and pessimistic representative concentration pathways (RCPs) 2.6 and 8.5, respectively. These models were employed in this study for characterizing the response of Cameroon's extreme precipitation and temperature events to global warming, using seven indices defined by the Expert Team on Cli mate Change Detection and Indices. Under global warming, the maximum number of consecutive dry (wet) days' is expected to increase (decrease). However, the annual total rainfall amount is expected to increase, mainly due to the intensification of very wet days and daily rainfall intensity. Furthermore, the temperature-based indices reveal an increase (decrease) in the total annual hot (cold) days, and overall, changes intensify with increased radiative forcing. The high-mitigated low-emission pathway RCP2.6 features attenuated changes, and even sometimes adapts to reverse the sign of changes. Designing reliable policies to limit the risks associated with the above changes is required, as their socio-economic consequences are likely to include food insecurity, heat-related illness, population impoverishment, price rises and market instability.

54 ENVIRONMENTAL SCIENCES↗

Assessing anthropogenic impacts on limited water resources under semi-arid conditions: three-dimensional transient regional modelling in Jordan

Both increasing aridity and population growth strongly stress freshwater resources in semi-arid areas such as Jordan. The country’s second largest governorate, Irbid, with over 1 million inhabitants, is already suffering from an annual water deficit of 25 million cubic meters (MCM). The population is expected to double within the next 20 years. Even without the large number of refugees from Syria, the deficit will likely increase to more then 50 MCM per year by 2035 The Governorate’s exclusive resource is groundwater, abstracted by the extensive Al Arab and Kufr Asad well fields. This study presents the first three-dimensional transient regional groundwater flow model of the entire Wadi al Arab to answer important questions regarding the dynamic quality and availability of water within the catchment. Emphasis is given to the calculation and validation of the dynamic groundwater recharge, derived from a multi-proxy approach, including (1) a hydrological model covering a 30-years dataset, (2) groundwater level measurements and (3) information about springs. The model enables evaluation of the impact of abstraction on the flow regime and the groundwater budget of the resource. Sensitivity analyses of controlling parameters indicate that intense abstraction in the southern part of the Wadi al Arab system can result in critical water-level drops of 10 m at a distance of 16 km from the production wells. Moreover, modelling results suggest that observed head fluctuations are strongly controlled by anthropogenic abstraction rather than variable recharge rates due to climate changes.

58 GEOSCIENCES↗

Lessons Learned in Employing Data Analytics to Predict Oxidation Kinetics and Spallation Behavior of High-Temperature NiCr-Based Alloys

Machine learning (ML) can offer many advantages in predicting material properties over traditional materials development methods based solely on limited experimental investigations or physical-based simulations with the capability to reduce development cost, risk, and time. However, so far, limited efforts have been made to predict alloy oxidation kinetics and spallation behavior via ML due to the lack of consistently measured and sufficient experimental data and the inherent complexity in oxidation behavior of multicomponent high-temperature alloys. A previous study reported the ability of ML to predict oxidation kinetics of NiCr-based alloys as a function of alloy composition and operating conditions. Here, the performance of a ML model in predicting rate constants and spallation probability was evaluated in light of the roles of the data distribution of the experimental dataset (data analytics), the alloy composition, the exposure environment and the chosen oxidation approach to extracting kinetic values from the measured mass changes (but using either a simple parabolic law or a statistical cyclic oxidation model). Potential strategies to improve the predictions and enhance the extrapolative capability of the previously trained model will be discussed.

36 MATERIALS SCIENCE↗

Generalizable machine learning potentials for quantum-accurate predictions of non-equilibrium behavior in 2D materials

Machine learning interatomic potentials (ML-IAPs) are emerging as transformative tools in materials modeling, promising quantum-level accuracy at a fraction of the computational cost. However, their ability to generalize beyond equilibrium configurations and to reliably capture defect- and temperature-driven behavior remains underexplored. Here, we develop and benchmark two state-of-the-art ML-IAPs, Spectral Neighbor Analysis Potential (SNAP) and Allegro, on a comprehensive dataset for monolayer MoSe₂. Using density functional theory (DFT) as the reference, we evaluate their performance in capturing stress–strain behavior, phase transition energetics, defect evolution, edge stability, and fracture toughness. Allegro, a deep equivariant neural network potential, surpasses both SNAP and the classical Tersoff potential in accuracy, efficiency, and transferability. Importantly, both ML potentials accurately reproduce experimental fracture measurements and ab initio predictions of inversion domain formation—phenomena well beyond their training sets. Our findings establish ML-IAPs as viable replacements for traditional force fields in the study of non-equilibrium mechanical phenomena, enabling large-scale, high-fidelity simulations in 2D materials and beyond. In conclusion, this work provides a broadly applicable framework for data-driven modeling of structural and functional transformations under extreme conditions.

2D materials↗

Non-destructive measurement and real-time monitoring of apple hardness during ultrasonic contact drying via portable NIR spectroscopy and machine learning

Portable near-infrared spectrometer in the spectral range of 900–1700 nm was evaluated for the first time to assess and monitor apple hardness in real-time during ultrasonic drying. Calibration models were developed using PLS and ANN, and their performances were evaluated by internal leave-one-out cross-validation and an external dataset. Several pre-treatments including standard normal variate (SNV), multiplicative scatter correction (MSC), Savitzky–Golay first and second derivatives were employed to examine the effects of spectral variations in hardness prediction. Seven important wavelengths were selected using weighted regression coefficients to develop a simple MLR model to facilitate the model interpretation and circumvent noise. The models using PLS, MLR, and ANN with selected wavelengths predicted the apple hardness with R 2 p of 0.91, 0.91, 0.95, and RMSEP of 14.78, 14.85, and 12.46 N, respectively. Finally, the results indicate that portable NIR spectrometers are quite promising for real-time monitoring of apple hardness during ultrasonic drying.

47 OTHER INSTRUMENTATION↗

Evaluating direct vessel injection accident-event progression of AP1000 and key figures of merit to support the design and development of water-cooled small modular reactors

The passive safety systems (PSSs) within water-cooled reactors are meticulously engineered to function autonomously, requiring no external power source or manual intervention. They depend exclusively on inherent natural forces and the fundamental principles of reactor physics, such as gravity, natural convection, and phase changes, to manage, alleviate, and avert the release of radioactive materials into the environment during accident scenarios like a loss-of-coolant accident (LOCA). PSSs are already integrated into such operating commercial reactors as the Advanced Pressurized Reactor-1000 MWe (AP1000) and the Water-Water Energetic Reactor-1200 MWe (WWER-1200) are adopted in most of the upcoming small modular reactor (SMR) designs. Examples of water-cooled SMR PSSs are the passive emergency core-cooling system (ECCS), passive containment cooling system (PCCS), and passive decay-heat removal system, the designs of which vary based on reactor system-design requirements. However, understanding the accident-event progression and phases of a LOCA is pivotal for adopting a specific PSS for a new SMR design. This study covers the accident-event progression for direct vessel injection (DVI) small-break loss-of-coolant accident (SB-LOCA), associated physics phenomena, knowledge gaps, and important figures of merit (FOMs) that may need to be evaluated and assessed to validate thermal-hydraulics models with an available experimental dataset to support new SMR design and development.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Active and machine learning-based approaches to rapidly enhance microbial chemical production

In order to make renewable fuels and chemicals from microbes, new methods are required to engineer microbes more intelligently. Computational approaches, to engineer strains for enhanced chemical production typically rely on detailed mechanistic models (e.g., kinetic/stoichiometric models of metabolism)—requiring many experimental datasets for their parameterization—while experimental methods may require screening large mutant libraries to explore the design space for the few mutants with desired behaviors. To address these limitations, we developed an active and machine learning approach (ActiveOpt) to intelligently guide experiments to arrive at an optimal phenotype with minimal measured datasets. In this study, ActiveOpt was applied to two separate case studies to evaluate its potential to increase valine yields and neurosporene productivity in Escherichia coli. In both the cases, ActiveOpt identified the best performing strain in fewer experiments than the case studies used. This work demonstrates that machine and active learning approaches have the potential to greatly facilitate metabolic engineering efforts to rapidly achieve its objectives.

60 APPLIED LIFE SCIENCES↗

Classifying handedness in chiral nanomaterials using label error robust deep learning

Abstract High-throughput scanning electron microscopy (SEM) coupled with classification using neural networks is an ideal method to determine the morphological handedness of large populations of chiral nanoparticles. Automated labeling removes the time-consuming manual labeling of training data, but introduces label error, and subsequently classification error in the trained neural network. Here, we evaluate methods to minimize classification error when training from automated labels of SEM datasets of chiral Tellurium nanoparticles. Using the mirror relationship between images of opposite handed particles, we artificially create populations of varying label error. We analyze the impact of label error rate and training method on the classification error of neural networks on an ideal dataset and on a practical dataset. Of the three training methods considered, we find that a pretraining approach yields the most accurate results across label error rates on ideal datasets, where size and other morphological variables are held constant, but that a co-teaching approach performs the best in practical application.

36 MATERIALS SCIENCE↗

Cloud micro- and macrophysical properties from ground-based remote sensing during the MOSAiC drift experiment

In the framework of the Multidisciplinary drifting Observatory for the Study of Arctic Climate Polarstern expedition, the Leibniz Institute for Tropospheric Research, Leipzig, Germany, operated the shipborne OCEANET-Atmosphere facility for cloud and aerosol observations throughout the whole year. OCEANET-Atmosphere comprises, amongst others, a multiwavelength Raman lidar, a microwave radiometer, and an optical disdrometer. A cloud radar was operated aboard Polarstern by the US Atmospheric Radiation Measurement program. These measurements were processed by applying the so-called Cloudnet methodology to derive cloud properties. To gain a comprehensive view of the clouds, lidar and cloud radar capabilities for low- and high-altitude observations were combined. Cloudnet offers a variety of products with a spatiotemporal resolution of 30 s and 30 m, such as the target classification, and liquid and ice microphysical properties. Additionally, a lidar-based low-level stratus retrieval was applied for cloud detection below the lowest range gate of the cloud radar. Based on the presented dataset, e.g., studies on cloud formation processes and their radiative impact, and model evaluation studies can be conducted.

54 ENVIRONMENTAL SCIENCES↗

A gated graph transformer for protein complex structure quality assessment and its performance in CASP15

Abstract Motivation Proteins interact to form complexes to carry out essential biological functions. Computational methods such as AlphaFold-multimer have been developed to predict the quaternary structures of protein complexes. An important yet largely unsolved challenge in protein complex structure prediction is to accurately estimate the quality of predicted protein complex structures without any knowledge of the corresponding native structures. Such estimations can then be used to select high-quality predicted complex structures to facilitate biomedical research such as protein function analysis and drug discovery. Results In this work, we introduce a new gated neighborhood-modulating graph transformer to predict the quality of 3D protein complex structures. It incorporates node and edge gates within a graph transformer framework to control information flow during graph message passing. We trained, evaluated and tested the method (called DProQA) on newly-curated protein complex datasets before the 15th Critical Assessment of Techniques for Protein Structure Prediction (CASP15) and then blindly tested it in the 2022 CASP15 experiment. The method was ranked 3rd among the single-model quality assessment methods in CASP15 in terms of the ranking loss of TM-score on 36 complex targets. The rigorous internal and external experiments demonstrate that DProQA is effective in ranking protein complex structures. Availability and implementation The source code, data, and pre-trained models are available at https://github.com/jianlin-cheng/DProQA.

59 BASIC BIOLOGICAL SCIENCES↗

FIRMA: a method for detection of alternative splicing from exon array data

Motivation: Analyses of EST data show that alternative splicing is much more widespread than once thought. The advent of exon and tiling microarrays means that researchers now have the capacity to experimentally measure alternative splicing on a genome wide level. New methods are needed to analyze the data from these arrays. Results: We present a method, finding isoforms using robust multichip analysis (FIRMA), for detecting differential alternative splicing in exon array data. FIRMA has been developed for Affymetrix exon arrays, but could in principle be extended to other exon arrays, tiling arrays or splice junction arrays. We have evaluated the method using simulated data, and have also applied it to two datasets: a panel of 11 human tissues and a set of 10 pairs of matched normal and tumor colon tissue. FIRMA is able to detect exons in several genes confirmed by reverse transcriptase PCR.

59 BASIC BIOLOGICAL SCIENCES↗

Measurement of C P asymmetries in Λ b 0 → p h − decays

A search for C P violation in Λ b 0 → p K − and Λ b 0 → p π − decays is presented using the full Run 1 and Run 2 data samples of p p collisions collected with the LHCb detector, corresponding to an integrated luminosity of 9 fb − 1 at center-of-mass energies of 7, 8, and 13 TeV. For the Run 2 data sample, the C P -violating asymmetries are measured to be A C P p K − = ( − 1.4 ± 0.7 ± 0.4 ) % and A C P p π − = ( 0.4 ± 0.9 ± 0.4 ) % , where the first uncertainty is statistical and the second is systematic. Following significant improvements in the evaluation of systematic uncertainties compared to the previous LHCb measurement, the Run 1 dataset is reanalyzed to update the corresponding results. When combining the Run 2 and updated Run 1 measurements, the final results are found to be A C P p K − = ( − 1.1 ± 0.7 ± 0.4 ) % and A C P p π − = ( 0.2 ± 0.8 ± 0.4 ) % , constituting the most precise measurements of these asymmetries to date. © 2025 CERN, for the LHCb Collaboration 2025 CERN

Aaij, R. (ORCID:0000000305331952)↗

SU-E-I-21: Deformation Mapping and Shape Prediction with 3D Tumor Volume Morphing

Purpose: To compare projection-based versus global correction that compensate for deadtime count loss in SPECT/CT images. Methods: SPECT/CT images of an IEC phantom (2.3GBq 99mTc) with ∼10% deadtime loss containing the 37mm (uptake 3), 28 and 22mm (uptake 6) spheres were acquired using a 2 detector SPECT/CT system with 64 projections/detector and 15 s/projection. The deadtime, Ti and the true count rate, Ni at each projection, i was calculated using the monitor-source method. Deadtime corrected SPECT were reconstructed twice: (1) with projections that were individually-corrected for deadtime-losses; and (2) with original projections with losses and then correcting the reconstructed SPECT images using a scaling factor equal to the inverse of the average fractional loss for 5 projections/detector. For both cases, the SPECT images were reconstructed using OSEM with attenuation and scatter corrections. The two SPECT datasets were assessed by comparing line profiles in xyplane and z-axis, evaluating the count recoveries, and comparing ROI statistics. Higher deadtime losses (up to 50%) were also simulated to the individually corrected projections by multiplying each projection i by exp(-a*Ni*Ti), where a is a scalar. Additionally, deadtime corrections in phantoms with different geometries and deadtime losses were also explored. The same two correction methods were carried for all these data sets. Results: Averaging the deadtime losses in 5 projections/detector suffices to recover >99% of the loss counts in most clinical cases. The line profiles (xyplane and z-axis) and the statistics in the ROIs drawn in the SPECT images corrected using both methods showed agreement within the statistical noise. The count-loss recoveries in the two methods also agree within >99%. Conclusion: The projection-based and the global correction yield visually indistinguishable SPECT images. The global correction based on sparse sampling of projections losses allows for accurate SPECT deadtime loss correction while keeping the study duration reasonable.

60 APPLIED LIFE SCIENCES↗

Lung motion estimation using dynamic point shifting: An innovative model based on a robust point matching algorithm

Purpose: Image-guided radiotherapy is an advanced 4D radiotherapy technique that has been developed in recent years. However, respiratory motion causes significant uncertainties in image-guided radiotherapy procedures. To address these issues, an innovative lung motion estimation model based on a robust point matching is proposed in this paper. Methods: An innovative robust point matching algorithm using dynamic point shifting is proposed to estimate patient-specific lung motion during free breathing from 4D computed tomography data. The correspondence of the landmark points is determined from the Euclidean distance between the landmark points and the similarity between the local images that are centered at points at the same time. To ensure that the points in the source image correspond to the points in the target image during other phases, the virtual target points are first created and shifted based on the similarity between the local image centered at the source point and the local image centered at the virtual target point. Second, the target points are shifted by the constrained inverse function mapping the target points to the virtual target points. The source point set and shifted target point set are used to estimate the transformation function between the source image and target image. Results: The performances of the authors’ method are evaluated on two publicly available DIR-lab and POPI-model lung datasets. For computing target registration errors on 750 landmark points in six phases of the DIR-lab dataset and 37 landmark points in ten phases of the POPI-model dataset, the mean and standard deviation by the authors’ method are 1.11 and 1.11 mm, but they are 2.33 and 2.32 mm without considering image intensity, and 1.17 and 1.19 mm with sliding conditions. For the two phases of maximum inhalation and maximum exhalation in the DIR-lab dataset with 300 landmark points of each case, the mean and standard deviation of target registration errors on the 3000 landmark points of ten cases by the authors’ method are 1.21 and 1.04 mm. In the EMPIRE10 lung registration challenge, the authors’ method ranks 24 of 39. According to the index of the maximum shear stretch, the authors’ method is also efficient to describe the discontinuous motion at the lung boundaries. Conclusions: By establishing the correspondence of the landmark points in the source phase and the other target phases combining shape matching and image intensity matching together, the mismatching issue in the robust point matching algorithm is adequately addressed. The target registration errors are statistically reduced by shifting the virtual target points and target points. The authors’ method with consideration of sliding conditions can effectively estimate the discontinuous motion, and the estimated motion is natural. The primary limitation of the proposed method is that the temporal constraints of the trajectories of voxels are not introduced into the motion model. However, the proposed method provides satisfactory motion information, which results in precise tumor coverage by the radiation dose during radiotherapy.

60 APPLIED LIFE SCIENCES↗

Anatomical pulmonary magnetic resonance imaging segmentation for regional structure-function measurements of asthma

Purpose: Pulmonary magnetic-resonance-imaging (MRI) and x-ray computed-tomography have provided strong evidence of spatially and temporally persistent lung structure-function abnormalities in asthmatics. This has generated a shift in their understanding of lung disease and supports the use of imaging biomarkers as intermediate endpoints of asthma severity and control. In particular, pulmonary {sup 1}H MRI can be used to provide quantitative lung structure-function measurements longitudinally and in response to treatment. However, to translate such biomarkers of asthma, robust methods are required to segment the lung from pulmonary {sup 1}H MRI. Therefore, their objective was to develop a pulmonary {sup 1}H MRI segmentation algorithm to provide regional measurements with the precision and speed required to support clinical studies. Methods: The authors developed a method to segment the left and right lung from {sup 1}H MRI acquired in 20 asthmatics including five well-controlled and 15 severe poorly controlled participants who provided written informed consent to a study protocol approved by Health Canada. Same-day spirometry and plethysmography measurements of lung function and volume were acquired as well as {sup 1}H MRI using a whole-body radiofrequency coil and fast spoiled gradient-recalled echo sequence at a fixed lung volume (functional residual capacity + 1 l). We incorporated the left-to-right lung volume proportion prior based on the Potts model and derived a volume-proportion preserved Potts model, which was approximated through convex relaxation and further represented by a dual volume-proportion preserved max-flow model. The max-flow model led to a linear problem with convex and linear equality constraints that implicitly encoded the proportion prior. To implement the algorithm, {sup 1}H MRI was resampled into ∼3 × 3 × 3 mm{sup 3} isotropic voxel space. Two observers placed seeds on each lung and on the background of 20 pulmonary {sup 1}H MR images in a randomized dataset, on five occasions, five consecutive days in a row. Segmentation accuracy was evaluated using the Dice-similarity-coefficient (DSC) of the segmented thoracic cavity with comparison to five-rounds of manual segmentation by an expert observer. The authors also evaluated the root-mean-squared-error (RMSE) of the Euclidean distance between lung surfaces, the absolute, and percent volume error. Reproducibility was measured using the coefficient of variation (CoV) and intraclass correlation coefficient (ICC) for two observers who repeated segmentation measurements five-times. Results: For five well-controlled asthmatics, forced expiratory volume in 1 s (FEV{sub 1})/forced vital capacity (FVC) was 83% ± 7% and FEV{sub 1} was 86 ± 9%{sub pred}. For 15 severe, poorly controlled asthmatics, FEV{sub 1}/FV C = 66% ± 17% and FEV{sub 1} = 72 ± 27%{sub pred}. The DSC for algorithm and manual segmentation was 91% ± 3%, 92% ± 2% and 91% ± 2% for the left, right, and whole lung, respectively. RMSE was 4.0 ± 1.0 mm for each of the left, right, and whole lung. The absolute (percent) volume errors were 0.1 l (∼6%) for each of right and left lung and ∼0.2 l (∼6%) for whole lung. Intra- and inter-CoV (ICC) were <0.5% (>0.91%) for DSC and <4.5% (>0.93%) for RMSE. While segmentation required 10 s including ∼6 s for user interaction, the smallest detectable difference was 0.24 l for algorithm measurements which was similar to manual measurements. Conclusions: This lung segmentation approach provided the necessary and sufficient precision and accuracy required for research and clinical studies.

60 APPLIED LIFE SCIENCES↗

Towards Misregistration-Tolerant Change Detection using Deep Learning Techniques with Object-Based Image Analysis

Co-registrating is a common pre-processing step for existing change detection algorithms, but registering bi-temporal images is nontrivial. The use of image patch as input for deep learning techniques provides a natural avenue to apply them in the OBIA framework, and have shown successful performance in the object-based land cover mapping and change detection applications. Even though attempts of applying deep learning techniques for change detection applications have been made with varying success, its application under OBIA framework for change detection have not been conducted and its tolerance for misregistration among temporal images are neither known. This study performed change detection under OBIA framework using deep learning techniques for the first time, and evaluated its performance regarding their tolerance of image misregistration on training and testing dataset. Our results demonstrate the proposed change detection scheme is surprisingly robust to image misregistration on the testing dataset, while classifiers trained with the training dataset containing image misregistration errors suffer from slight decrease of overall accuracy.

Liu, Tao↗

Lost in OCR Translation? Vision-Based Approaches to Robust Document Retrieval

Code for ‘Lost in OCR Translation?’: robust document retrieval under degradation. Compares OCR-based, vision-only, and hybrid pipelines; includes SambaNova LLaMA Vision OCR, Nougat, and ViDoRe baselines. Provides QA data generation, RAG evaluation, and metrics (Levenshtein, nDCG@k, Recall@k, EM/F1) with reproducible scripts. Includes dataset guides

Bhattarai, Manish [Los Alamos National Labs]↗