Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Data bias”

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 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Evaluating the Use of Foundational Chemical Language Models in Multimodal Graph Fusion

Rapid and accurate prediction of the physicochemical properties of molecules given their structures remains a key challenge in cheminformatics. Machine learning approaches offer high-throughput options, but the optimality of inductive biases and data representations are up for debate. For example, BERT-based masked language models (MLMs) can be trained in a self-supervised way on hundreds of millions to billions of readily available SMILES strings. Another option is graph neural networks (GNNs), which can operate directly on molecular structures. Yet, generating accurate molecular geometry is computationally expensive, leading to a relative scarcity in data compared to SMILES strings. It is attractive to combine these two paradigms by pre-training an LM on a large corpus of SMILES strings and embedding these representation into a geometric graph neural network. Despite the promise of such an approach, and contrary to previous studies, we find mixed results with the combination of the LMs and GNNs on several molecule datasets. In particular, we found evidence for improvement on the FreeSolv and QM7 benchmarks, but degraded performance on the ESOL, LIPO and QM9 datasets compared to a GNN baseline.

Francel, Collin [University of Alabama]↗
DOE OSTI2020

Sampling Subjective Polygons for Patch-Based Deep Learning Land-Use Classification in Satellite Images

Model generalization remains a key challenge in the analysis of large amounts of heterogeneous satellite image data. One major limiting factor in developing generalizable models, in the context of supervised learning, is the lack of high quality training datasets. A model's capacity to perform well on new data is often inhibited by imbalance and bias in the data that was used for training. This is especially a problem when using convolutional neural networks to classify urban land-use in satellite images. Notable dataset imbalance issues in this application include land-use type imbalance and image scene imbalance. To begin understanding these dataset imbalance problems in more detail, we develop and test a number of sampling methods for generating training image datasets from subjective training polygons for urban land-use classification. We investigate sampling at different point densities as a means to reduce content repetition and therefore content imbalance and bias in the training image dataset.

Arndt, Jacob↗
DOE OSTI2021

Error Characteristics and Scale Dependence of Current Satellite Precipitation Estimates Products in Hydrological Modeling

Satellite precipitation estimates (SPEs) are promising alternatives to gauge observations for hydrological applications (e.g., streamflow simulation), especially in remote areas with sparse observation networks. However, the existing SPEs products are still biased due to imperfections in retrieval algorithms, data sources and post-processing, which makes the effective use of SPEs a challenge, especially at different spatial and temporal scales. In this study, we used a distributed hydrological model to evaluate the simulated discharge from eight quasi-global SPEs at different spatial scales and explored their potential scale effects of SPEs on a cascade of basins ranging from approximately 100 to 130,000 km 2 . The results indicate that, regardless of the difference in the accuracy of various SPEs, there is indeed a scale effect in their application in discharge simulation. Specifically, when the catchment area is larger than 20,000 km2, the overall performance of discharge simulation emerges an ascending trend with the increase of catchment area due to the river routing and spatial averaging. Whereas below 20,000 km 2 , the discharge simulation capability of the SPEs is more randomized and relies heavily on local precipitation accuracy. Our study also highlights the need to evaluate SPEs or other precipitation products (e.g., merge product or reanalysis data) not only at the limited station scale, but also at a finer scale depending on the practical application requirements. Here we have verified that the existing SPEs are scale-dependent in hydrological simulation, and they are not enough to be directly used in very fine scale distributed hydrological simulations (e.g., flash flood). More advanced retrieval algorithms, data sources and bias correction methods are needed to further improve the overall quality of SPEs.

DTVGM↗
DOE OSTI2020

Biases in genome reconstruction from metagenomic data

Background Advances in sequencing, assembly, and assortment of contigs into species-specific bins has enabled the reconstruction of genomes from metagenomic data (MAGs). Though a powerful technique, it is difficult to determine whether assembly and binning techniques are accurate when applied to environmental metagenomes due to a lack of complete reference genome sequences against which to check the resulting MAGs. Methods We compared MAGs derived from an enrichment culture containing ~20 organisms to complete genome sequences of 10 organisms isolated from the enrichment culture. Factors commonly considered in binning software—nucleotide composition and sequence repetitiveness—were calculated for both the correctly binned and not-binned regions. This direct comparison revealed biases in sequence characteristics and gene content in the not-binned regions. Additionally, the composition of three public data sets representing MAGs reconstructed from the Tara Oceans metagenomic data was compared to a set of representative genomes available through NCBI RefSeq to verify that the biases identified were observable in more complex data sets and using three contemporary binning software packages. Results Repeat sequences were frequently not binned in the genome reconstruction processes, as were sequence regions with variant nucleotide composition. Genes encoded on the not-binned regions were strongly biased towards ribosomal RNAs, transfer RNAs, mobile element functions and genes of unknown function. Our results support genome reconstruction as a robust process and suggest that reconstructions determined to be >90% complete are likely to effectively represent organismal function; however, population-level genotypic heterogeneity in natural populations, such as uneven distribution of plasmids, can lead to incorrect inferences.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Implications of Non-Bingham Rheology

One of the key challenges now facing the US Department of Energy (DOE) is the fate of radioactive waste remaining from World War II and the Cold War which is stored underground in tanks some 75 feet in diameter and over 30 feet tall. Over time, the waste has segmented into multiple layers with sludges and slurries at the bottom with salt crust layers often at the top and liquid in between. DOE’s current official baseline plans call for remaining sludges and slurries to be removed from the tanks and converted into a more stable glass waste form. Minimizing worker exposure to radiation drives DOE to use slurry processing techniques to suspend, mobilize, transport, mix, and process the waste. Therefore, a clear and quantitative understanding of Hanford waste rheology is essential for the success of the DOE mission. Historically much of the waste has been characterized using Eugene Bingham’s model more than a century old that provides a straight line fit to higher shear rate data with the intercept suggesting a yield stress and the slope providing the consistency. Yet, Bingham fits overestimate the shear stress at a given shear rate for low to intermediate shear rates, exactly the range of shear rates typically encountered in pipe flow, where shear rates peak along the pipe wall and vanish in the center. This model produces a fictitious yield stress for some of the wastes that do not exhibit yield phenomena. While over estimating the yield stress may be prudent, safe, and conservative for some applications (e.g., pump sizing to ensure that pumps can handle yield stresses), over estimating the rheology may be inaccurate and non-conservative for other applications (e.g., eroding settled particle beds). Therefore, this paper evaluates the slurry rheology of Hanford and Savannah River wastes using a more modern rheological model that fits the full range of experimental data. Although a bias has been recognized and alternative models proposed, the magnitude of this bias and the implications for tank waste have only been qualitatively suggested. The purpose of this paper is to evaluate quantitatively implications of the poor quality of fit between a Bingham model for rheology and experimental data at modest shear rates. We first demonstrate the magnitude of the bias between the data and the Bingham extrapolation. We then evaluate quantitatively the velocity profile under laminar conditions. This analysis shows that the bias may be large (hundreds of percent or more) at modest shear rates and that modest shear rates dominate pipe velocity profiles.

Rheology, Radioactive waste↗
DOE OSTI2024

The PARADIGM Project: Case Study in Balancing Experiment Uncertainty with Design simplicity

Accurate nuclear data are required for simulations of many applications including nuclear criticality safety. Actinide nuclear data at intermediate energies (from 1 to 100s of keV) are imprecise and inaccurate, because of scarce differential data, and an insufficient theory approach to capture the structures expected in the data to yield evaluated nuclear data, and lack of integral data for proper validation. This is a known deficiency but has proved challenging to address. More specifically, only 5% of integral experiments in the International Criticality Safety Benchmark Evaluation Project (ICSBEP) benchmark suite address intermediate energies (Fig. 1). Associated calculated effective multiplication factor, k eff , values for these experiments are far outside the experimental uncertainties and are 25× further from experiment than for fast energies. These differences could either stem from systematic biases in nuclear data, experiments or both. The goal of the PARADIGM (PARallel Approach of Differential and InteGral Measurements) project is to significantly reduce (by more than tens of percent) the uncertainties of intermediate energy actinide nuclear data. The PARADIGM project designed and intends to execute LANSCE (Los Alamos Neutron Science CEnter) and NCERC (National Criticality Experiments Research Center) intermediate experiments in parallel. They will specifically address a high priority nuclear data need—reducing bias and uncertainty in intermediate plutonium nuclear data. The two experiment will achieve that by informing each other and nuclear theory. By doing all these steps in parallel, the timeline to deliver improved nuclear data to users will significantly be reduced. This work will focus on the integral experiment final design and the balance of design and modeling simplicity while minimizing experiment uncertainty.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2023

An empirical approach to model selection: weak lensing and intrinsic alignments

ABSTRACT In cosmology, we routinely choose between models to describe our data, and can incur biases due to insufficient models or lose constraining power with overly complex models. In this paper, we propose an empirical approach to model selection that explicitly balances parameter bias against model complexity. Our method uses synthetic data to calibrate the relation between bias and the χ2 difference between models. This allows us to interpret χ2 values obtained from real data (even if catalogues are blinded) and choose a model accordingly. We apply our method to the problem of intrinsic alignments – one of the most significant weak lensing systematics, and a major contributor to the error budget in modern lensing surveys. Specifically, we consider the example of the Dark Energy Survey Year 3 (DES Y3), and compare the commonly used non-linear alignment (NLA) and tidal alignment and tidal torque (TATT) models. The models are calibrated against bias in the Ωm–S8 plane. Once noise is accounted for, we find that it is possible to set a threshold Δχ2 that guarantees an analysis using NLA is unbiased at some specified level Nσ and confidence level. By contrast, we find that theoretically defined thresholds (based on, e.g. p-values for χ2) tend to be overly optimistic, and do not reliably rule out cosmological biases up to ∼1–2σ. Considering the real DES Y3 cosmic shear results, based on the reported difference in χ2 from NLA and TATT analyses, we find a roughly $30{{\ \rm per\ cent}}$ chance that were NLA to be the fiducial model, the results would be biased (in the Ωm–S8 plane) by more than 0.3σ. More broadly, the method we propose here is simple and general, and requires a relatively low level of resources. We foresee applications to future analyses as a model selection tool in many contexts.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

CovTransformer: A transformer model for SARS-CoV-2 lineage frequency forecasting

With hundreds of SARS-CoV-2 lineages circulating in the global population, there is an ongoing need for predicting and forecasting lineage frequencies and thus identifying rapidly expanding lineages. Accurate prediction would allow for more focused experimental efforts to understand pathogenicity of future dominating lineages and characterize the extent of their immune escape. Here, we first show that the inherent noise and biases in lineage frequency data make a commonly-used regression-based approach unreliable. To address this weakness, we constructed a machine learning model for SARS-CoV-2 lineage frequency forecasting, called CovTransformer, based on the transformer architecture. We designed our model to navigate challenges such as a limited amount of data with high levels of noise and bias. We first trained and tested the model using data from the UK and the USA, and then tested the generalization ability of the model to many other countries and US states. Remarkably, the trained model makes accurate predictions two months into the future with high levels of accuracy both globally (in 31 countries with high levels of sequencing effort) and at the US-state level. Our model performed substantially better than a widely used forecasting tool, the multinomial regression model implemented in Nextstrain, demonstrating its utility in SARS-CoV-2 monitoring. Assuming a newly emerged lineage is identified and assigned, our test using retrospective data shows that our model is able to identify the dominating lineages 7 weeks in advance on average before they became dominant. Overall, our work demonstrates that transformer models represent a promising approach for SARS-CoV-2 forecasting and pandemic monitoring.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

Second-generation downscaled earth system model data using generative machine learning

The second-generation Sup3rCC dataset provides high-resolution meteorological data generated through the downscaling of multiple earth system models (ESMs) from the Coupled Model Intercomparison Project Phase 6 (CMIP6). This downscaling is performed through application of a generative machine learning approach called Super-Resolution for Renewable Resource Data (sup3r). This dataset builds on the first-generation Sup3rCC data by applying improved bias correction methods and adding downscaled precipitation to the output variables. As with the first Sup3rCC version, the data still include temperature, wind speed and direction at multiple heights, pressure, three components of downwelling solar radiation, and relative humidity—all at 4-kilometer (km) hourly resolution over the contiguous United States. This is a 25x spatial enhancement and 24x temporal enhancement of the source 100-km daily-average ESM data. This extension of the Sup3rCC dataset includes data from six ESMs from two shared socioeconomic pathways (SSPs) totaling 400 years of data with multiple future projections of changing meteorological conditions. The scenario selection was based on a structured evaluation of historical ESM skill and comprehensive representation of possible trajectories of future climate change in temperature, humidity, precipitation, solar irradiance, and near-surface wind speeds. The inclusion of multiple future projections is intended to enable users to assess key drivers of un 36 certainty and variability. All data are double-bias corrected, resulting in a product that can be used out-of-the-box for energy system analysis with minimal historical bias. The potential applications of Sup3rCC data extend to various topics in renewable energy resource assessment, energy systems modeling, and grid resilience studies. High-resolution future meteorological projections are critical for evaluating the effects of changing meteorological conditions on renewable energy generation, energy demand, and for optimizing energy storage and grid infrastructure. The 4-km hourly resolution of the downscaled data enables understanding of spatial and temporal variability at the scales necessary for energy system operational planning. In addition, the dataset can support risk assessments by providing detailed information on possible future extreme weather events and long-term meteorological variability at scales relevant to energy infrastructure. By offering an enhanced representation of possible future meteorological conditions, the second-generation Sup3rCC dataset enables more precise modeling of energy resilience and adaptation strategies in response to changing meteorological conditions.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Modeling of the high column density systems in the Lyman-Alpha forest

The Lyman-α forests observed in the spectra of high-redshift quasars can be used as a tracer of the cosmological matter density to study baryon acoustic oscillations (BAO) and the Alcock-Paczynski effect. Extraction of cosmological information from these studies requires modeling of the forest correlations. While the models depend most importantly on the bias parameters of the intergalactic medium (IGM), they also depend on the numbers and characteristics of high-column-density systems (HCDs) ranging from Lyman-limit systems with column densities log N HI /1cm -2 > 17 to damped Lyman-α systems (DLAs) with log N HI /1cm -2 > 20.2. These HCDs introduce broad damped absorption characteristic of a Voigt profile. Consequently they imprint a component on the power spectrum whose modes in the radial direction are suppressed, leading to a scale-dependent bias. Using mock data sets of known HCD content, we test a model that describes this effect in terms of the distribution of column densities of HCDs, the Fourier transforms of their Voigt profiles and the bias of the halos containing the HCDs. Our results show that this physically well-motivated model describes the effects of HCDs with an accuracy comparable to that of the ad-hoc models used in published forest analyses. We also discuss the problems of applying the model to real data, where the HCD content and their bias is uncertain.

Lyman alpha forest↗
DOE OSTI2026

Machine Learning Eliminates Reanalysis Warm Bias and Reveals Weaker Winter Surface Cooling Over Arctic Sea Ice

The surface energy budget governs Arctic sea-ice growth/melt, yet observations are sparse, and reanalysis data sets suffer from systematic biases. Here, we train a neural network with observational data to bias-correct hourly ERA5 fluxes over Arctic ice-covered regions (≥70°N; sea-ice concentration >80%) for 1994–2024. Training data cover two full seasonal cycles and different sea-ice regimes. The neural network reduces RMSE for net shortwave radiation by ∼40%, downward longwave radiation by ∼16% and the total surface energy budget by ∼55%, eliminating the wintertime warm bias of ∼4 K in ERA5. Wintertime surface cooling is reduced by ∼50%, yielding thermodynamic ice-growth estimates of ∼80–120 cm, consistent with SMOS–CryoSat satellite thickness increases and in contrast to the 150–200 cm growth implied by ERA5. Our bias-corrected data capture the observed clear/cloudy states of the winter boundary layer and can be used to study Arctic climatology, evaluate climate models and drive sea-ice-ocean models.

Hossain, Akil [Alfred Wegener Institute for Polar ↗
DOE OSTI2021

Evaluating fine-resolution, regional outputs of a variable resolution global climate model

Climate models have been used to study water resources and regional hydrologic responses to climate change, but climate model outputs must be downscaled to provide relevant regional data. However, the accuracy of this regional data is limited by uncertainties across and within downscaling methods, uncertainty across global outputs, and discontinuities at downscaled boundaries. A new alternative to traditional downscaling is a variable resolution model that incorporates fine-resolution regions directly into a coarse-resolution, global climate simulation in order to capture contiguous dynamics across resolution boundaries. In this study, we used the Variable-Resolution Community Earth System Model (VR-CESM) to generate one-eighth degree (14 km) fine-resolution outputs for the western U.S. and eastern China from 1970-2006. We focus our evaluation on precipitaiton, temperature, snow pack, solar radiation, and wind. We compare the model outputs with remote-sensing-based precipitation data, and both reanalysis and gridded weather station data for precipitation and temperature. VR-CESM generally has a cold bias in winter and a warm bias in summer in the western U.S., which compensate each other to reduce the annual bias. In eastern China, however, the sign of temperature biases are more consistent throughout the year with cold biases in the higher mountains and warm biases throughout most of the rest of the region. Precipitation biases are dependent upon reference data, and show slight overestimation in high mountain regions in both the U.S. and China with respect to gridded weather station data. Simulated snow cover in the western U.S. is reasonable compared to remote sensing data, but snow cover and snow water equivalent have larger biases when compared to reanalysis data. In eastern China there are widespread snow cover biases compared to remote sensing data. VR-CESM underestimates downward shortwave radiation to a greater degree in summer than in winter, and underestimates surface layer windspeed over mountains to a greater degree than in other areas. Comparison between VR-CESM and a coarser simulation (1-degree Beijing Climate Center model) shows reduced precipitation biases in the mountainous regions with finer resolution, indicating the value of variable-resolution modeling for reigonal studies.

Di Vittorio, Alan↗
DOE OSTI2022

MISPR : an open-source package for high-throughput multiscale molecular simulations

Computational tools provide a unique opportunity to study and design optimal materials by enhancing our ability to comprehend the connections between their atomistic structure and functional properties. However, designing materials with tailored functionalities is complicated due to the necessity to integrate various computational-chemistry software (not necessarily compatible with one another), the heterogeneous nature of the generated data, and the need to explore vast chemical and parameter spaces. The latter is especially important to avoid bias in scattered data points-based models and derive statistical trends only accessible by systematic datasets. Here, we introduce a robust high-throughput multi-scale computational infrastructure coined MISPR (Materials Informatics for Structure–Property Relationships) that seamlessly integrates classical molecular dynamics (MD) simulations with density functional theory (DFT). By enabling high-performance data analytics and coupling between different methods and scales, MISPR addresses critical challenges arising from the needs of automated workflow management and data provenance recording. The major features of MISPR include automated DFT and MD simulations, error handling, derivation of molecular and ensemble properties, and creation of output databases that organize results from individual calculations to enable reproducibility and transparency. In this work, we describe fully automated DFT workflows implemented in MISPR to compute various properties such as nuclear magnetic resonance chemical shift, binding energy, bond dissociation energy, and redox potential with support for multiple methods such as electron transfer and proton-coupled electron transfer reactions. The infrastructure also enables the characterization of large-scale ensemble properties by providing MD workflows that calculate a wide range of structural and dynamical properties in liquid solutions. MISPR employs the methodologies of materials informatics to facilitate understanding and prediction of phenomenological structure–property relationships, which are crucial to designing novel optimal materials for numerous scientific applications and engineering technologies.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Lorentz group equivariant autoencoders

Abstract There has been significant work recently in developing machine learning (ML) models in high energy physics (HEP) for tasks such as classification, simulation, and anomaly detection. Often these models are adapted from those designed for datasets in computer vision or natural language processing, which lack inductive biases suited to HEP data, such as equivariance to its inherent symmetries. Such biases have been shown to make models more performant and interpretable, and reduce the amount of training data needed. To that end, we develop the Lorentz group autoencoder (LGAE), an autoencoder model equivariant with respect to the proper, orthochronous Lorentz group $$\textrm{SO}^+(3,1)$$ SO + ( 3 , 1 ) , with a latent space living in the representations of the group. We present our architecture and several experimental results on jets at the LHC and find it outperforms graph and convolutional neural network baseline models on several compression, reconstruction, and anomaly detection metrics. We also demonstrate the advantage of such an equivariant model in analyzing the latent space of the autoencoder, which can improve the explainability of potential anomalies discovered by such ML models.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Regulatory Testing of WTP HL W Glasses for Compliance with Delisting Requirements, VSL-03R3780-1, Rev. 1

(Part of the data collected for this work and discussed in this report was subject to data quality and bias issues. All the affected tests have subsequently been repeated, as directed by the Waste Treatment Plant Project, and new statistical analyses have been performed on the revised data set. A subsequently-issued report supercedes this report and describes the revised data, together with the revised composition-property models (Kot et al. 2004). The reader should refer to the new report for discussion of the revised data set and composition-property (TCLP cadmium release) models. None of the data for the spike glasses, designed for Case 1 and Case 2 COPCs testing, were affected by this issue.)

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

Federated learning for 2D synchrotron x-ray diffractometry: a cross-institutional approach for phase quantification of Ti–6Al–4V alloy

High-energy Two dimensional (2D) synchrotron x-ray diffractometry provides important insights into the atomistic structure and phase evolution of materials, yet traditional analysis methods remain complex, knowledge-intensive, and computationally demanding. Deep-learning models offer a powerful alternative for automating their analysis. Institutions that hold these datasets may be unwilling to share their data due to privacy and security policies, as well as the challenges associated with large-scale data transfer. As a result, models trained on local datasets often perform well only on their own data but exhibit bias and poor generalization across different instruments or facilities. To overcome these limitations, we explore federated learning (FL) for 2D synchrotron diffractograms, enabling collaborative model training without exchanging raw data. In this study, 2D synchrotron diffractograms of Ti–6Al–4V alloy collected from two independent facilities are used to train convolutional neural networks for predicting the β-phase volume fraction. Experimental results show that federated global models significantly outperform locally trained models in terms of generalization and achieve accuracy comparable to centralized trained models. These findings demonstrate the potential of FL to enable secure, cross-institutional collaboration and enhance the scalability of deep-learning-based materials characterization.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Improved Understanding of Coupled Water and Carbon Cycle Processes through Machine Learning Approaches

Focal Area(s): This white paper addresses how explainable machine learning (ML) algorithms can improve insights gained from complex data (Focal Area 3). We will also address how ML approaches related to sensor compression and low energy AI hardware can be used for efficient data acquisition (Focal Area 1). Science Challenge: We will focus on the coupled water cycle and carbon cycle processes in terrestrial ecosystems and terrestrial-aquatic interfaces. Thus, our approaches will be centered around several data-model integration challenges indicated in EESD strategic plans for two science focus areas: Terrestrial Ecosystem Science and Hydrobiogeochemistry. We can use AI to correct systematic model errors due to biases in either data or model structure/processes. Error patterns in model predictions usually vary by region, model, season etc. But there are systematic patterns in them. e.g., soil moisture tends to be overestimated in the arid western continental United States underestimated in wetter eastern USA; some land surface models tend to underestimate moisture in wet seasons and overestimate in dry seasons. Moreover, the consequences of extreme events (e.g., drought, extreme flooding, storm surges associated with tropical storms, hurricanes) on carbon cycle processes are not well represented in ecosystem and Earth system models. Redox-sensitive processes (e.g., rapid oxidation/reduction of iron and other redox-sensitive elements in soil microsites subjected to fluctuated hydrology) in terrestrial-aquatic interfaces further challenge model predictions of hot-spots (and hot-moments) due to poor understanding of underlying mechanisms. Thus, AI/ML approaches can be used to learn patterns in the data and model errors and use them to build model equations and correct process-based model errors.

54 ENVIRONMENTAL SCIENCES↗