Results for “input data” — Page 66

DOE OSTI2021

Scalable statistical inference of photometric redshift via data subsampling

Handling big data has largely been a major bottleneck in traditional statistical models. Consequently, when accurate point prediction is the primary target, machine learning models are often preferred over their statistical counterparts for bigger problems. But full probabilistic statistical models often outperform other models in quantifying uncertainties associated with model predictions. We develop a data-driven statistical modeling framework that combines the uncertainties from an ensemble of statistical models learned on smaller subsets of data carefully chosen to account for imbalances in the input space. We demonstrate this method on a photometric redshift estimation problem in cosmology, which seeks to infer a distribution of the redshift—the stretching effect in observing the light of far-away galaxies—given multivariate color information observed for an object in the sky. Our proposed method performs balanced partitioning, graph-based data subsampling across the partitions, and training of an ensemble of Gaussian process models.

data subsampling↗

DOE OSTI2023

Understanding the trade-offs of national municipal solid waste estimation methods for circular economy policy

Policies embracing circular economy concepts have taken hold in national legislation around the world. As the number of governments and organizations adopting circular economy policies increases, so does the need for accurate and timely measurement of material resource flows. Since many countries do not have access to centrally reported municipal solid waste (MSW) data, estimation and modeling are critical in evaluating circular economy policy effectiveness. The purpose of this paper is to examine three modeling approaches estimating national MSW data in the United States, including industry-based material flow analysis, waste-extended input-output modeling, and aggregated regional waste reporting. We establish five criteria to guide the analysis through the context of policy monitoring (data quality, flow totality, update frequency, sensitivity to disruption, and product granularity) and use these criteria to analyze and score each model. We then use a literature search to identify five, internationally-implemented options for circular economy policy and determine the data and modeling components that are most helpful in evaluating policy effectiveness. Finally, we provide a crosswalk of the model scores and policy needs to inform the suitability of model selection by policy type. We found that data quality and update frequency are identified as critical components for evaluating circular economy policies within the models evaluated, and can both be fulfilled by aggregated regional waste reporting. Flow totality, sensitivity to disruption, and product granularity requirements vary by both model and policy types. While none of the evaluated models satisfy the combination of requirements for any of the five policies, industry-based material flow analysis offers flow totality for extended producer responsibility, landfill bans, and recycling rate target policies that typically require it. Here, the waste-extended input-output model can provide disruption sensitivity and product granularity as needed for policies like minimum recycled content and market restrictions. Policy developers in areas where strong centralized data collection is not an option should design policy action(s) with modeling tradeoffs in mind, including the potential hybridization of modeling approaches that may provide the most accurate national MSW estimates.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

DOE OSTI2024

High-dimensional and permutation invariant anomaly detection

Methods for anomaly detection of new physics processes are often limited to low-dimensional spaces due to the difficulty of learning high-dimensional probability densities. Particularly at the constituent level, incorporating desirable properties such as permutation invariance and variable-length inputs becomes difficult within popular density estimation methods. In this work, we introduce a permutation-invariant density estimator for particle physics data based on diffusion models, specifically designed to handle variable-length inputs. We demonstrate the efficacy of our methodology by utilizing the learned density as a permutation-invariant anomaly detection score, effectively identifying jets with low likelihood under the background-only hypothesis. To validate our density estimation method, we investigate the ratio of learned densities and compare to those obtained by a supervised classification algorithm.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2022

Data-Driven Probabilistic Voltage Risk Assessment of MiniWECC System with Uncertain PVs and Wind Generations using Realistic Data

Here, it is found from actual data that due to generation dispatch and uncertain renewable generations and loads with complicated correlations, inferring the probabilistic distributions for uncertain inputs is challenging. Many probabilistic power flow approaches have been developed in the literature but their validations using realistic systems and data are lacking. This paper proposes a data-driven probabilistic analysis approach for system risk assessment of the miniWECC system using actual data. The sparse Gaussian process (SGP) is advocated to quantify the impacts of uncertain inputs on voltage security. SGP does not need the probability distribution function of uncertain inputs, can handle correlations and is highly computationally efficient. Results on the miniWECC system using realistic data show that SGP outperforms existing approaches and is able to quantify the voltage violation risks.

17 WIND ENERGY↗

DOE OSTI2025

Semi-supervised permutation invariant particle-level anomaly detection

The development of analysis methods to distinguish potential beyond the Standard Model phenomena in a model-agnostic way can significantly enhance the discovery reach in collider experiments. However, the typical machine learning (ML) algorithms employed for this task require fixed length and ordered inputs that break the natural permutation invariance in collision events. To address this, a semi-supervised anomaly detection tool is presented that takes a variable number of particle-level inputs and leverages a signal model to encode this information into a permutation invariant, event-level representation via supervised training with a Particle Flow Network (PFN). Data events are then encoded into this representation and given as input to an autoencoder for unsupervised ANomaly deTEction on particLe flOw latent sPacE (ANTELOPE), classifying anomalous events based on a low-level and permutation invariant input modeling. Performance of the ANTELOPE architecture is evaluated on simulated samples of hadronic processes in a high energy collider experiment, showing good capability to distinguish disparate models of new physics.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2021

NeuralCubes: Deep Representations for Visual Data Exploration

Visual exploration of large multi-dimensional datasets has seen tremendous progress in recent years, allowing users to express rich data queries that produce informative visual summaries, all in real time. Techniques based on data cubes are some of the most promising approaches. However, these techniques usually require a large memory footprint for large datasets. To tackle this problem, we present NeuralCubes: neural networks that predict results for aggregate queries, similar to data cubes. NeuralCubes learns a function that takes as input a given query, for instance, a geographic region and temporal interval, and outputs the result of the query. The learned function serves as a real-time, low-memory approximator for aggregation queries. Our models are small enough to be sent to the client side (e.g. the web browser for a web-based application) for evaluation, enabling data exploration of large datasets without database/network connection. Here, we demonstrate the effectiveness of NeuralCubes through extensive experiments on a variety of datasets and discuss how NeuralCubes opens up opportunities for new types of visualization and interaction.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2026

Meteoric 10Be Flux Calibration Data for the East River Watershed, Colorado, USA

This data package contains tabular and geospatial data used to quantify and model meteoric beryllium-10 fluxes in the East River watershed, Colorado, USA. The tabular component includes calibration-site data from five glacial moraine sites and includes environmental variables used to evaluate spatial controls on meteoric 10Be delivery, including elevation, mean annual precipitation (MAP), mean snow depth, and mean snow water equivalent (SWE). These site-level data were used to compare observed fluxes with environmental gradients across the watershed and to evaluate the effects of erosion correction on flux estimates. The package also includes supporting slope and curvature values used to assess topographic inputs to the erosion analysis. A second component of the data package contains updated manuscript tables and regression outputs used to summarize the relationships between meteoric 10Be flux and environmental predictors. These tables include meteoric 10Be sample information and AMS results, site-level environmental values, site-level meteoric 10Be inventory and flux values, watershed-averaged predicted fluxes, soil bulk density measurements, fine-fraction values, soil pH measurements, and regression statistics including slope, intercept, coefficient of determination, and p-value. The regression products include both standard linear regressions and regressions in which the intercept is constrained to pass through zero, and they support the analyses presented in the companion manuscript. Together, these tabular files provide the numerical basis for the manuscript tables and the regression-based interpretation of meteoric 10Be flux variability in a snow-dominated mountain watershed. The geospatial component of the package consists of GeoTIFF raster files used to generate the map products presented in Figures 2 and 6 of the companion manuscript. These rasters represent watershed-scale spatial layers for environmental variables and regression-based predictions of meteoric 10Be flux. This dataset contains comma-separated values files (.csv), Microsoft Excel files (.xlsx), GeoTIFF raster files (.tif), and upporting metadata files, including CSV data dictionaries and readme text files (.csv, .txt). The tabular files can be opened with standard spreadsheet software, and the raster files can be viewed and analyzed in GIS software such as ArcGIS Pro or QGIS. Together, these files document the numerical and spatial datasets used to calibrate and predict meteoric 10Be delivery in the East River watershed.

East River↗

DOE OSTI2020

Parameter Sensitivity Analysis of the SparTen High Performance Sparse Tensor Decomposition Software (Extended Analysis)

Tensor decomposition models play an increasingly important role in modern data science applications. One problem of particular interest is fitting a low-rank Canonical Polyadic (CP) tensor decomposition model when the tensor has sparse structure and the tensor elements are nonnegative count data. SparTen is a high-performance C++ library which computes a low-rank decomposition using different solvers: a first-order quasi-Newton or a second-order damped Newton method, along with the appropriate choice of runtime parameters. Since default parameters in SparTen are tuned to experimental results in prior published work on a single real-world dataset conducted using MATLAB implementations of these methods, it remains unclear if the parameter defaults in SparTen are appropriate for general tensor data. Furthermore, it is unknown how sensitive algorithm convergence is to changes in the input parameter values. This report addresses these unresolved issues with large-scale experimentation on three benchmark tensor data sets. Experiments were conducted on several different CPU architectures and replicated with many initial states to establish generalized profiles of algorithm convergence behavior.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2020

Coffea -- Columnar Object Framework For Effective Analysis

The coffea framework provides a new approach to High-Energy Physics analysis, via columnar operations, that improves time-to-insight, scalability, portability, and reproducibility of analysis. It is implemented with the Python programming language, the scientific python package ecosystem, and commodity big data technologies. To achieve this suite of improvements across many use cases, coffea takes a factorized approach, separating the analysis implementation and data delivery scheme. All analysis operations are implemented using the NumPy or awkward-array packages which are wrapped to yield user code whose purpose is quickly intuited. Various data delivery schemes are wrapped into a common front-end which accepts user inputs and code, and returns user defined outputs. We will discuss our experience in implementing analysis of CMS data using the coffea framework along with a discussion of the user experience and future directions.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2024

Is Clean Hydrogen Production a Good Fit for Questa? (Final Economic Impact Results) [Slides]

The Village of Questa, New Mexico is aiming to become a regional clean energy hub with robust and diverse employment opportunities for the local community supported by the energy sector and by other businesses inspired or attracted by abundant clean energy, outdoor recreation, and cultural opportunities. A coalition of stakeholders in the Village of Questa, comprising the Village, Kit Carson Electric Cooperative (KCEC), Questa Economic Development Fund, and Chevron, is exploring options to develop hydrogen production facilities as an opportunity to create jobs, provide reliable clean energy, and utilize former mine resources. Questa is home to a molybdenum mine owned by Chevron that closed in 2014. Several residents in Questa and surrounding communities lost their jobs when the mine closed and transitioned from active operations into environmental remediation. Although remediation efforts have been ongoing since 2014 and are expected to continue for at least 16 more years, the number of jobs with Chevron is much smaller now than it was before the closure. Between available workforce, brownfield land, and water rights formerly supporting mine operations but now in a transition period, there are considerable local resources that could be directed toward clean energy generation. Questa's electricity supply is already 100% solar during daylight hours thanks to Kit Carson Electric Cooperative's (KCEC's) strategic decision-making and partnering over the last decade. Now, Questa, KCEC, and Chevron are exploring the potential costs and benefits of siting an electrolytic hydrogen production facility and additional solar photovoltaic (PV) capacity in Questa to further advance the region's clean energy economy. In this report, we estimated the potential economic impacts (i.e., jobs, value added, gross output, tax revenue) of constructing and operating a combined hydrogen (32 MW polymer electrolyte membrane electrolizer + 7.5 MW fuel cell) and solar facility (22.5 MW) in the Village of Questa, as well as the resulting economic spillovers to Taos County and the state of New Mexico. We employ an input-output model that leverages IMPLAN's economic data for the region complemented by construction and operating expenses estimated by NREL and feedback from the local coalition to evaluate the direct, indirect and induced effects of the project construction (transient impacts) and operation (more permanent impacts). Based on the area's average trade profile, feedback from the coalition and current market conditions, these projects are expected to support 487 full-time equivalent jobs during construction, generating $\$24$ million in income for those workers and $\$82$ million in local economic activity in the state. Of those jobs, 106 are expected to be construction sector jobs. These investments are also estimated to add $\$36.5$ million to New Mexico's gross state product (GSP). In the Village of Questa, we estimate 16 jobs will be supported in construction and transportation industries, generating $\$0.9$ million in earnings. In Taos County, the construction phase is expected to support 285 jobs primarily in construction and professional services, while manufacturing jobs dominate the results for the Rest of New Mexico. The Village is also estimated to receive $\$0.9$ million in tax revenue from the construction phase alone. Once in operation, the project continues to impact the state and Questa. Around 20 jobs (full-time equivalent for each year of operation) are supported across New Mexico, with approximately 11 directly employed in Questa by both facilities. The total annual local economic activity supported by ongoing operations is just over $\$1.3$ million/yr, generating $\$1.6$ million/yr in additional income in the state. Annual operations are estimated to add $\$2.1$ million to the state's GSP. The Village is expected to receive around $\$43,000$/yr in tax revenue. Impacts vary significantly depending on which businesses are supplying materials, equipment and services, and where construction workers reside. Choosing local suppliers will most benefit Questa and the New Mexico economy, adding up to 500 jobs during construction and 13 long-term jobs. Local and state governments may consider ways to incentivize local businesses in order to maximize economic benefits.

08 HYDROGEN↗

DOE OSTI2024

Is Clean Hydrogen Production a Good Fit for Questa? Final Economic Impact Results

The Village of Questa, New Mexico is aiming to become a regional clean energy hub with robust and diverse employment opportunities for the local community supported by the energy sector and by other businesses inspired or attracted by abundant clean energy, outdoor recreation, and cultural opportunities. A coalition of stakeholders in the Village of Questa, comprising the Village, Kit Carson Electric Cooperative (KCEC), Questa Economic Development Fund, and Chevron, is exploring options to develop hydrogen production facilities as an opportunity to create jobs, provide reliable clean energy, and utilize former mine resources. Questa is home to a molybdenum mine owned by Chevron that closed in 2014. Several residents in Questa and surrounding communities lost their jobs when the mine closed and transitioned from active operations into environmental remediation. Although remediation efforts have been ongoing since 2014 and are expected to continue for at least 16 more years, the number of jobs with Chevron is much smaller now than it was before the closure. Between available workforce, brownfield land, and water rights formerly supporting mine operations but now in a transition period, there are considerable local resources that could be directed toward clean energy generation. Questa's electricity supply is already 100% solar during daylight hours thanks to Kit Carson Electric Cooperative's (KCEC's) strategic decision-making and partnering over the last decade. Now, Questa, KCEC, and Chevron are exploring the potential costs and benefits of siting an electrolytic hydrogen production facility and additional solar photovoltaic (PV) capacity in Questa to further advance the region's clean energy economy. In this report, we estimated the potential economic impacts (i.e., jobs, value added, gross output, tax revenue) of constructing and operating a combined hydrogen (32 MW polymer electrolyte membrane electrolizer + 7.5 MW fuel cell) and solar facility (22.5 MW) in the Village of Questa, as well as the resulting economic spillovers to Taos County and the state of New Mexico. We employ an input-output model that leverages IMPLAN's economic data for the region complemented by construction and operating expenses estimated by NREL and feedback from the local coalition to evaluate the direct, indirect and induced effects of the project construction (transient impacts) and operation (more permanent impacts). Based on the area's average trade profile, feedback from the coalition and current market conditions, these projects are expected to support 487 full-time equivalent jobs during construction, generating $\$24$ million in income for those workers and $\$82$ million in local economic activity in the state. Of those jobs, 106 are expected to be construction sector jobs. These investments are also estimated to add $\$36.5$ million to New Mexico's gross state product (GSP). In the Village of Questa, we estimate 16 jobs will be supported in construction and transportation industries, generating $\$0.9$ million in earnings. In Taos County, the construction phase is expected to support 285 jobs primarily in construction and professional services, while manufacturing jobs dominate the results for the Rest of New Mexico. The Village is also estimated to receive $\$0.9$ million in tax revenue from the construction phase alone. Once in operation, the project continues to impact the state and Questa. Around 20 jobs (full-time equivalent for each year of operation) are supported across New Mexico, with approximately 11 directly employed in Questa by both facilities. The total annual local economic activity supported by ongoing operations is just over $\$1.3$ million/yr, generating $\$1.6$ million/yr in additional income in the state. Annual operations are estimated to add $\$2.1$ million to the state's GSP. The Village is expected to receive around $\$43,000$/yr in tax revenue. Impacts vary significantly depending on which businesses are supplying materials, equipment and services, and where construction workers reside. Choosing local suppliers will most benefit Questa and the New Mexico economy, adding up to 500 jobs during construction and 13 long-term jobs. Local and state governments may consider ways to incentivize local businesses in order to maximize economic benefits.

08 HYDROGEN↗

DOE OSTI2025

Uncertainty Quantification for Neutron Shield Using Convolutional Neural Networks

Uncertainty quantification from radiation transport calculations was conducted using a Bayesian inference approach. A surrogate model, using a convolutional neural network, was employed to emulate the neutron fluence, which was simulated with a Monte Carlo radiation transport model. This allowed for a computationally cheap approach to evaluate input parameters and to sample their corresponding posterior probability distributions. Experimental data from the literature were employed to perform uncertainty quantification studies for concrete shields. As a result, the method is a nonintrusive approach that enables studies with multiple input parameters and can be applied to any radiation transport model.

Bayesian inference↗

DOE OSTI2024

Extension of SCALE/Sampler’s sensitivity index for the assessment of cross section, fission yield, and decay data uncertainties

Accurate prediction of nuclide compositions and neutron and gamma sources and spectra for fresh and spent nuclear fuel through computational modeling and simulations is the basis for safeguards instruments design, optimization, and calibration, and for validation of the measured responses. The accuracy of these simulations can be significantly impacted by uncertainties in input parameters to the applied computer code. Input parameters are, for example, dimensions, material compositions, and temperatures of the model. Additionally, important but sometimes neglected input parameters for simulations of nuclear systems are the nuclear data that include nuclear reaction cross sections, fission product yields, and decay data. It has been shown that uncertainties of calculated results are dominated by uncertainties of these nuclear data.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

DOE OSTI2026

F-Hash: Feature-Based Hash Design for Time-Varying Volume Visualization via Multi-Resolution Tesseract Encoding

Interactive time-varying volume visualization is challenging due to its complex spatiotemporal features and sheer size of the dataset. Recent works transform the original discrete time-varying volumetric data into continuous Implicit Neural Representations (INR) to address the issues of compression, rendering, and super-resolution in both spatial and temporal domains. However, training the INR takes a long time to converge, especially when handling large-scale time-varying volumetric datasets. In this work, we proposed F-Hash, a novel feature-based multi-resolution Tesseract encoding architecture to greatly enhance the convergence speed compared with existing input encoding methods for modeling time-varying volumetric data. The proposed design incorporates multi-level collision-free hash functions that map dynamic 4D multi-resolution embedding grids without bucket waste, achieving high encoding capacity with compact encoding parameters. Our encoding method is agnostic to time-varying feature detection methods, making it a unified encoding solution for feature tracking and evolution visualization. Experiments show the F-Hash achieves state-of-the-art convergence speed in training various time-varying volumetric datasets for diverse features. We also proposed an adaptive ray marching algorithm to optimize the sample streaming for faster rendering of the time-varying neural representation.

deep learning↗

DOE OSTI2020

A Novel Modeling Framework for Computationally Efficient and Accurate Real-Time Ensemble Flood Forecasting With Uncertainty Quantification

A novel modeling framework that simultaneously improves accuracy, predictability, and computational efficiency is presented. It embraces the benefits of three modeling techniques integrated together for the first time: surrogate modeling, parameter inference, and data assimilation. The use of polynomial chaos expansion (PCE) surrogates significantly decreases computational time. Parameter inference allows for model faster convergence, reduced uncertainty, and superior accuracy of simulated results. Ensemble Kalman filters assimilate errors that occur during forecasting. To examine the applicability and effectiveness of the integrated framework, we developed 18 approaches according to how surrogate models are constructed, what type of parameter distributions are used as model inputs, and whether model parameters are updated during the data assimilation procedure. We conclude that (1) PCE must be built over various forcing and flow conditions, and in contrast to previous studies, it does not need to be rebuilt at each time step; (2) model parameter specification that relies on constrained, posterior information of parameters (so-called Selected specification) can significantly improve forecasting performance and reduce uncertainty bounds compared to Random specification using prior information of parameters; and (3) no substantial differences in results exist between single and dual ensemble Kalman filters, but the latter better simulates flood peaks. The use of PCE effectively compensates for the computational load added by the parameter inference and data assimilation (up to ~80 times faster). Therefore, the presented approach contributes to a shift in modeling paradigm arguing that complex, high-fidelity hydrologic and hydraulic models should be increasingly adopted for real-time and ensemble flood forecasting.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2020

DEEP CELLULAR RECURRENT NEURAL ARCHITECTURE FOR EFFICIENT MULTIDIMENSIONAL TIME-SERIES DATA PROCESSING

Efficient processing of time series data is a fundamental yet challenging problem in pattern recognition. Though recent developments in machine learning and deep learning have enabled remarkable improvements in processing large scale datasets in many application domains, most are designed and regulated to handle inputs that are static in time. Many real-world data, such as in biomedical, surveillance and security, financial, manufacturing and engineering applications, are rarely static in time, and demand models able to recognize patterns in both space and time. Current machine learning (ML) and deep learning (DL) models adapted for time series processing tend to grow in complexity and size to accommodate the additional dimensionality of time. Specifically, the biologically inspired learning based models known as artificial neural networks that have shown extraordinary success in pattern recognition, tend to grow prohibitively large and cumbersome in the presence of large scale multi-dimensional time series biomedical data such as EEG. Consequently, this work aims to develop representative ML and DL models for robust and efficient large scale time series processing. First, we design a novel ML pipeline with efficient feature engineering to process a large scale multi-channel scalp EEG dataset for automated detection of epileptic seizures. With the use of a sophisticated yet computationally efficient time-frequency analysis technique known as harmonic wavelet packet transform and an efficient self-similarity computation based on fractal dimension, we achieve state-of-the-art performance for automated seizure detection in EEG data. Subsequently, we investigate the development of a novel efficient deep recurrent learning model for large scale time series processing. For this, we first study the functionality and training of a biologically inspired neural network architecture known as cellular simultaneous recurrent neural network (CSRN). We obtain a generalization of this network for multiple topological image processing tasks and investigate the learning efficacy of the complex cellular architecture using several state-of-the?art training methods. Finally, we develop a novel deep cellular recurrent neural network (CDRNN) architecture based on the biologically inspired distributed processing used in CSRN for processing time series data. The proposed DCRNN leverages the cellular recurrent architecture to promote extensive weight sharing and efficient, individualized, synchronous processing of multi-source time series data. Experiments on a large scale multi-channel scalp EEG, and a machine fault detection dataset show that the proposed DCRNN offers state-of-the-art recognition performance while using substantially fewer trainable recurrent units.

Vidyaratne, Lasitha S.↗

DOE OSTI2022

Extrapolating Contaminant Effects from Individuals to Populations: A Case Study on Nanoparticle Toxicity to Daphnia Fed Environmentally Relevant Food Levels

Ecological risk assessment (ERA) is charged with assessing the likelihood a chemical will have adverse environmental or ecological effects. When assessing the risk of a potential contaminant to biological organisms, ecologists are most concerned with the sustainability of populations of organisms, rather than protecting every individual. However, ERA most commonly relies on data on the effect of a potential contaminant on individuals because these experiments are more feasible than costly population-level exposures. In this work, we address the challenge of extrapolating these individual-level results to predict population-level effects. Previous per-capita population growth rate estimates calculated from individual-level exposures of Daphnia pulicaria to silver nanoparticles (AgNPs) at different food rations predict a critical daily food requirement for daphnid populations exposed to 200 μg/L AgNPs to avoid extinction. To test this, we exposed daphnid populations to the same AgNP concentration at three different food inputs, with the lowest ration close to the extinction threshold predicted from data on individuals. The two populations with the higher food inputs persisted, and the population with the lowest food input went extinct after 50 days but did persist through two generations. Further, we demonstrate that we can extrapolate between these levels of biological organization by parameterizing an individual-level biomass model with data on individuals’ response to AgNPs and using these parameters to predict the outcome for control and AgNP-exposed populations. Key to successful extrapolation is careful modeling of temporal changes in resource density, driven by both the experimental protocols and feedback from the consumer. The implication for ecotoxicology is that estimates of extinction thresholds based on studies of individuals may be reliable predictors of population outcomes, but only with careful treatment of resource dynamics.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2023

Machine learning and deep learning for mineralogy interpretation and CO 2 saturation estimation in geological carbon Storage: A case study in the Illinois Basin

Carbon capture and storage (CCS) is a promising approach to simultaneously maintaining energy security and reducing carbon dioxide (CO 2 ) emissions under the current energy portfolio that is dominated by fossil fuel energy. Pre-injection formation characterization and post-injection CO 2 monitoring are two critical tasks to guarantee storage efficiency in CCS. The CCS projects in the Illinois Basin, the first large-scale CO 2 injection into saline aquifers in the United States, employed conventional and the latest pulsed neutron logging (PNL) tools for mineralogy interpretation and CO 2 saturation estimation, which provide valuable references for future CCS projects. Because of the inherent fuzziness of petrophysical measurements and complex subsurface heterogeneity, interpreting well-logging data is time-consuming, and its accuracy can be user-biased. In recent years, data-driven methods have been widely used to capture the non-linear patterns between input features and interpretation results. This work applied and evaluated four commonly used machine learning (ML) models, including ridge regression (RR), random forest (RF), gradient boosting regression (GBR), support vector regression (SVR), and one deep learning (DL) model, the artificial neural network (ANN). We optimized the hyperparameters of the four ML models and the DL model using the simulated annealing algorithm and the grid search strategy, respectively. The input features of the mineralogy interpretation models were eleven conventional well-logging parameters, and the label data (i.e., ground truth) were the porosity and volumetric fractions of six minerals, including quartz, feldspar, dolomite, calcite, clay, and iron minerals. The results demonstrated that the GBR and RF models were superior in predicting volumetric fractions of minerals and porosity; label data with low coefficient of variation (CV) values tended to yield better performance. For CO 2 saturation estimation, the RF was the best-performing model, followed by SVR, ANN, GBR, and RR. Furthermore, we conducted feature importance ranking using the permutation importance algorithm and found that the formation sigma and well pressure were the most important features in this study. In conclusion, the study of CCS projects in the Illinois Basin bridges the gap between the limited knowledge and understanding of geological carbon storage and the increasing demand for reliable, cost-effective, and sustainable energy solutions.

58 GEOSCIENCES↗