Search NASA⌕ Search

SEARCH · Search NASA

Results for “sequential decision making”

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 OSTI2020

The Kalai-Smorodinsky solution for many-objective Bayesian optimization

An ongoing aim of research in multiobjective Bayesian optimization is to extend its applicability to a large number of objectives. While coping with a limited budget of evaluations, recovering the set of optimal compromise solutions generally requires numerous observations and is less interpretable since this set tends to grow larger with the number of objectives. We thus propose to focus on a specific solution originating from game theory, the Kalai-Smorodinsky solution, which possesses attractive properties. In particular, it ensures equal marginal gains over all objectives. We further make it insensitive to a monotonic transformation of the objectives by considering the objectives in the copula space. A novel tailored algorithm is proposed to search for the solution, in the form of a Bayesian optimization algorithm: sequential sampling decisions are made based on acquisition functions that derive from an instrumental Gaussian process prior. Our approach is tested on four problems with respectively four, six, eight, and nine objectives. The method is available in the R package GPGame available on CRAN at https://cran.r-project.org/package=GPGame.

Game theory↗
DOE OSTI2020

Calibration and Uncertainty Estimation Using the Ensemble Kalman Filter with a Large Subsurface Flow and Transport Model - 20321

At routinely monitored groundwater contamination sites, periodically measured environmental conditions such as groundwater levels and contaminant concentrations are used to inform and confirm a conceptual site model (CSM) and guide the development and calibration of a numerical groundwater flow and transport model. The calibration of groundwater flow and transport models after each measurement (sampling) event can illuminate deficiencies in a CSM, identify areas where additional monitoring is warranted, and predict the behavior of the system to guide decision making. However, manual and automated (e.g. PEST) model calibration tools can be time-consuming and computationally expensive to implement after each sampling event. Perhaps as a result, such calibration tools generally utilize all available monitoring data simultaneously rather than sequentially assimilating monitoring data one sampling event at a time as the results from sampling become available. A more real-time data assimilation approach may reduce parameter uncertainty, quantify the value of additional monitoring data, and produce a usable model more quickly and with less effort. To mitigate the potential time-consuming aspects of manual and widely applied automated calibration techniques, a data assimilation algorithm called the ensemble Kalman filter (EnKF) was evaluated as a relatively efficient method of model calibration and uncertainty assessment via the sequential integration of monitoring data into a model. The EnKF was able to successfully and efficiently assimilate monitoring and modeling data to calibrate a complex flow and transport model at a real-world site with significant subsurface heterogeneity, uncertainty, and 12 years of monitoring data (over 4,000 individual measurements of groundwater levels and over 2,500 measurements of contaminant concentrations). Starting with an uncalibrated model data from annual sampling events were sequentially assimilated, and the resultant predication errors and estimated parameter uncertainties were tracked. After all monitoring data were assimilated, both flow and transport residuals at the end of the EnKF process were comparable to those produced via a concurrent PEST calibration effort but required fewer model simulations. Both uncertainty and prediction errors decreased over time. In a real-time application, the adequacy of the model could be assessed after each sampling event. The benefits of such a real-time approach to utilizing monitoring data include reduced costs (in the form of model updates or site characterization efforts), early flagging of possible errors in the CSM, and a reduced risk of overfitting and corresponding increased confidence in model predictions. This tool may be particularly useful compared to other calibration techniques (e.g. manual, PEST) when model runtimes are long, calibration parameters are many, or parameter uncertainty is large. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2010

Identification of Low-level Point Radioactive Sources using a sensor network

Identification of a low-level point radioactive source amidst background radiation is achieved by a network of radiation sensors using a two-step approach. Based on measurements from three or more sensors, a geometric difference triangulation method or an N-sensor localization method is used to estimate the location and strength of the source. Then a sequential probability ratio test based on current measurements and estimated parameters is employed to finally decide: (1) the presence of a source with the estimated parameters, or (2) the absence of the source, or (3) the insufficiency of measurements to make a decision. This method achieves specified levels of false alarm and missed detection probabilities, while ensuring a close-to-minimal number of measurements for reaching a decision. This method minimizes the ghost-source problem of current estimation methods, and achieves a lower false alarm rate compared with current detection methods. This method is tested and demonstrated using: (1) simulations, and (2) a test-bed that utilizes the scaling properties of point radioactive sources to emulate high intensity ones that cannot be easily and safely handled in laboratory experiments.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

Targeted materials discovery using Bayesian algorithm execution

Rapid discovery and synthesis of future materials requires intelligent data acquisition strategies to navigate large design spaces. A popular strategy is Bayesian optimization, which aims to find candidates that maximize material properties; however, materials design often requires finding specific subsets of the design space which meet more complex or specialized goals. We present a framework that captures experimental goals through straightforward user-defined filtering algorithms. These algorithms are automatically translated into one of three intelligent, parameter-free, sequential data collection strategies (SwitchBAX, InfoBAX, and MeanBAX), bypassing the time-consuming and difficult process of task-specific acquisition function design. Our framework is tailored for typical discrete search spaces involving multiple measured physical properties and short time-horizon decision making. We demonstrate this approach on datasets for TiO 2 nanoparticle synthesis and magnetic materials characterization, and show that our methods are significantly more efficient than state-of-the-art approaches. Overall, our framework provides a practical solution for navigating the complexities of materials design, and helps lay groundwork for the accelerated development of advanced materials.

42 ENGINEERING↗
DOE OSTI2017

Assessment of mobility and bioavailability of mercury compounds in sewage sludge and composts

Content of heavy metals, including mercury, determines the method of management and disposal of sewage sludge. Excessive concentration of mercury in composts used as organic fertilizer may lead to accumulation of this element in soil and plant material. Fractionation of mercury in sewage sludge and composts provides a better understanding of the extent of mobility and bioavailability of the different mercury species and helps in more informed decision making on the application of sludge for agricultural purposes. The experimental setup comprises the composing process of the sewage sludge containing 13.1 mg kg{sup −1} of the total mercury, performed in static reactors with forced aeration. In order to evaluate the bioavailability of mercury, its fractionation was performed in sewage sludge and composts during the process. An analytical procedure based on four-stage sequential extraction was applied to determine the mercury content in the ion exchange (water soluble and exchangeable Hg), base soluble (Hg bound to humic and fulvic acid), acid soluble (Hg bound to Fe/Mn oxides and carbonates) and oxidizable (Hg bound to organic matter and sulphide) fractions. The results showed that from 50.09% to 64.55% of the total mercury was strongly bound to organo-sulphur and inorganic sulphide; that during composting, increase of concentrations of mercury compounds strongly bound with organic matter and sulphides; and that mercury content in the base soluble and oxidizable fractions was strongly correlated with concentration of dissolved organic carbon in those fractions. - Highlights: • Composting of sewage sludge was conducted in batch mode. • Changes of mercury fractions and organic matter were investigated. • The relationship between Hg fractions and these parameters were discussed.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Blockchain for Fault-Tolerant Grid Operations Version 2.0

This report explores the potential of distributed ledger technology (DLT) as a transformative tool to enhance fault-tolerant operations in electrical distribution systems. Leveraging DLT's core attributes, including an immutable decentralized ledger, distributed consensus mechanisms, and state replication capabilities, this study focuses on three critical use cases. A central aspect of this research centers on the utilization of a consensus-driven ledger, providing actors within the system, such as distributed resources, with access to a reliable data repository. This empowers these actors to collaborate effectively and make informed decisions, all securely recorded on the blockchain. The first use case concentrates on data configuration, utilizing mathematical criteria---particularly, the chi-squared test for gross error detection---to identify trustworthy sensors for advanced decision-making. Building upon this foundation of trust, the second use case, topology identification, accurately determines circuit breaker states, unveiling the distribution network's topology. Ultimately, the third use case leverages this trust to execute switching actions, reconfiguring feeders and restoring power to disconnected customers after fault events. The concept of trust serves as a cornerstone in this approach, marking a departure from traditional fault location, isolation, and service restoration (FLISR) methods. Additionally, the blockchain-based architecture introduces decentralization, empowering disconnected areas to make autonomous decisions, even when communication with a central control center is disrupted. The primary contributions of this report are twofold: (1) a novel approach for evaluating distribution system voltage areas while preserving data ownership and (2) the implementation of interactions between distribution network areas using the actor model. Unlike the previous sequential approach for evaluating the area connection voltages, which required a radial network topology, this study's area model reduction enables a more versatile approach. The area model reduction addresses issues of prolonged data waiting times and multiple points of failure within the previous approach. Notably, the presented evaluation for the reduced network model area connection reveals a significant increase in the differences in voltage magnitudes. Simulation and evaluation of area agents across four distinct cases elucidate the area-level interaction behavior during a fault event. Simulations demonstrate that the proposed distributed FLISR (DFLISR) approach can successfully restore service to an affected area. Varying message delays and message loss probabilities in each simulation case underscore their impacts on restoration times, ranging from 3 min and 32 s to 6 min and 19 s. In contrast, power is not restored in an area in one of our simulation cases.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2017

Calculating Probability Densities with Homotopy and Applications to Particle Filters

In this work, we explore a homotopy sampling procedure and its generalization, loosely based on importance sampling, known as annealed importance sampling. The procedure makes use of a known probability distribution to find, via homotopy, the unknown normalization of a target distribution, as well as samples of the target distribution. We propose a reformulation of the method that leads to a rejection sampling alternative. Estimates of the error as a function of homotopy stages and sample averages are derived for the algorithmic version of the method. These estimates are useful in making computational efficiency decisions on how the calculation should proceed, given a computer architecture. Consideration is given to how the procedure can be adapted to Bayesian stationary and nonstationary estimation problems. The connection between homotopy sampling and thermodynamic integration is made. Emphasis is placed on the non-stationary problems, and in particular, on a sequential estimation technique known as particle filtering. It is shown that a modification of the particle filter framework to include the homotopy process can improve the computational robustness of particle filters.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Enhancing Building Energy Efficiency through Advanced Sizing and Dispatch Methods for Energy Storage

Energy storage and electrification of buildings hold great potential for future decarbonization. However, there are several technical and economic barriers that prevent large-scale adoption and integration of energy storage in buildings. These barriers include integration with building control systems, high capital costs, and the necessity to identify and quantify value streams for different stakeholders. To overcome these obstacles, it is crucial to develop advanced sizing and dispatch methods to assist planning and operational decision-making for integrating energy storage in buildings. This work develops simple and flexible optimal sizing and dispatch framework for thermal energy storage (TES) and battery energy storage (BES) systems in large-scale office building. The optimal sizes of TES, BES, as well as other building assets are determined in a joint manner instead of sequentially to avoid sub-optimal solutions. The interaction between the sizing at the planning stage and hourly or sub-hourly dispatch at the operating stage is explicitly modeled. The solution is determined considering both capital costs in optimal sizing and operational benefits in optimal dispatch. Comprehensive assessments are performed using simulation studies to quantify potential energy, economic, and emission benefits by different utility tariffs and climate locations, to improve our understanding of the techno-economic performance of different TES and BES systems, and to identify barriers for adopting energy storage for buildings. Finally, the proposed framework will provide guidance to a broad range of stakeholders to properly design energy storage in buildings and maximizes potential benefits, thereby advancing affordable building energy storage deployment and helping us accelerating the transition towards a cleaner and more equitable energy economy.

Yu, Mingyung↗
DOE OSTI2022

Development and assessment of prognosis digital twin in a NAMAC system

The nearly autonomous management and control (NAMAC) system is a comprehensive control system to assist plant operations by furnishing control recommendations to operators. Prognosis digital twin (DT-P) is a critical component in NAMAC for predicting action effects and supporting NAMAC decision-making during normal and accident scenarios. To quantifying and reducing uncertainty of machine-learning-based DT-Ps in multi-step predictions, this work investigates and derives insights from the application of three techniques for optimizing the performance of DT-P by long short-term memory recurrent neural networks, including manual search, sequential model-based optimization, and physics-guided machine learning. Finally, sequential model-based optimization and physics-guide machine learning result in smallest errors when the predicting transients are similar to the training data.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2023

Extreme-scale stochastic optimization and simulation via learning-enhanced decomposition and parallelization (Final Technical Report)

Stochastic optimization and simulation models ubiquitously arise in designing and operating complex service/engineering systems. They can be extreme in scale due to high-dimensional data and decisions, and can also involve decisions made sequentially in response to newly revealed data, both causing significant computational challenge. The objective of this research is to explore a unified framework that integrates machine learning with discrete optimization and risk-averse modeling, to improve the efficiency of decomposition paradigms for stochastic optimization and simulations at extreme scale. The models we consider represent a broad class of complex decision-making problems, where 0-1 or continuous decisions are made before and/or after knowing multiple sources of uncertainties that could be correlated. We will employ machine learning methods to dynamically decide and prioritize computational procedures, including cut generation, branching, and bounding of the optimal objective. Furthermore, the research will shed new lights on the traditional decomposition algorithms for extreme-scale computing. Deliverables of the research include new modeling and computational methods for advancing the state-of-the-art research in optimization and simulation, bringing many relevant risk-averse, data-driven optimization problems in practice within the range of tractability. Examples include distributed computing server scheduling and sensor deployment for monitoring critical infrastructures. Success in this effort will enable progress in solving multiple extreme-scale problems in the complex system design and operations arising from DoE missions in energy, environment, and national security.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

Evolution of LIBS technology to mobile instrumentation for expediting firearm-related investigations at the laboratory and the crime scene

Gunshot residue (GSR) is one of the few forensic disciplines that lack accurate screening techniques. This study proposes using a mobile LIBS instrument to detect inorganic GSR and compares performance to a previously validated laboratory instrument. The mobile LIBS is designed with advanced configurations specifically for on-site GSR analysis, including a CMOS detector and a sampling chamber that holds up to six typical GSR collection devices with separate gas flow ports to prevent cross-contamination. A significant novelty of the portable instrument is its image magnification, which allows quick searching and visualization of GSR particle morphology. The single-particle imaging and elemental composition capability is one of a kind and offers superior confirmatory features for GSR. The mobile LIBS performance was evaluated for residues collected from the hands of shooters (100 samples) and non-shooters (200 background samples), analyzed sequentially by the mobile instrument and then the laboratory instrument. Accuracies better than 98.8% were obtained by both instruments, demonstrating their suitability for trace IGSR detection from skin specimens. Implementation of this methodology is anticipated to drastically speed up response times (i.e., from several hours per sample by standard SEM-EDS practice to a few minutes by LIBS). The screening methods can be easily incorporated into workflows to improve decision-making processes at the crime scene and laboratory settings, reduce backlogs, and improve case management.

47 OTHER INSTRUMENTATION↗
DOE OSTI2020

Model Package Report: Central Plateau Vadose Zone Models

This model package report describes concisely the modeling objectives, conceptualization, implementation, uncertainty and sensitivity, configuration control, limitations, data needs, and recommendations for improvement of the Central Plateau Vadose Zone Models. This collection of models is developed to meet the vadose zone simulation needs of the Hanford Site Composite Analysis (CA), the Hanford Site Cumulative Impact Evaluation (CIE), and are expected to find other applications in Hanford Site remedial cleanup decision-making processes. This model package report describes and documents the development of the models themselves to fulfill technical approaches defined for the CA and the CIE. This report does not document any specific calculation using these models: instead, applications of individual vadose models to perform specific calculations will be documented in environmental calculation files, including inputs and results, as appropriate. Configuration management for the Central Plateau Vadose Zone Models is managed through assignment of unique sequential numerical version numbers and archival of the models in the Environmental Modeling Management Archive.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2016

Final Report, DOE Early Career Award: Predictive modeling of complex physical systems: new tools for statistical inference, uncertainty quantification, and experimental design

Predictive simulation of complex physical systems increasingly rests on the interplay of experimental observations with computational models. Key inputs, parameters, or structural aspects of models may be incomplete or unknown, and must be developed from indirect and limited observations. At the same time, quantified uncertainties are needed to qualify computational predictions in the support of design and decision-making. In this context, Bayesian statistics provides a foundation for inference from noisy and limited data, but at prohibitive computional expense. This project intends to make rigorous predictive modeling *feasible* in complex physical systems, via accelerated and scalable tools for uncertainty quantification, Bayesian inference, and experimental design. Specific objectives are as follows: 1. Develop adaptive posterior approximations and dimensionality reduction approaches for Bayesian inference in high-dimensional nonlinear systems. 2. Extend accelerated Bayesian methodologies to large-scale {\em sequential} data assimilation, fully treating nonlinear models and non-Gaussian state and parameter distributions. 3. Devise efficient surrogate-based methods for Bayesian model selection and the learning of model structure. 4. Develop scalable simulation/optimization approaches to nonlinear Bayesian experimental design, for both parameter inference and model selection. 5. Demonstrate these inferential tools on chemical kinetic models in reacting flow, constructing and refining thermochemical and electrochemical models from limited data. Demonstrate Bayesian filtering on canonical stochastic PDEs and in the dynamic estimation of inhomogeneous subsurface properties and flow fields.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2013

Revisiting Statistical Aspects of Nuclear Material Accounting

Nuclear material accounting (NMA) is the only safeguards system whose benefits are routinely quantified. Process monitoring (PM) is another safeguards system that is increasingly used, and one challenge is how to quantify its benefit. This paper considers PM in the role of enabling frequent NMA, which is referred to as near-real-time accounting (NRTA). We quantify NRTA benefits using period-driven and data-driven testing. Period-driven testing makes a decision to alarm or not at fixed periods. Data-driven testing decides as the data arrives whether to alarm or continue testing. The difference between period-driven and datad-riven viewpoints is illustrated by using one-year and two-year periods. For both one-year and two-year periods, period-driven NMA using once-per-year cumulative material unaccounted for (CUMUF) testing is compared to more frequent Shewhart and joint sequential cusum testing using either MUF or standardized, independently transformed MUF (SITMUF) data. We show that the data-driven viewpoint is appropriate for NRTA and that it can be used to compare safeguards effectiveness. In addition to providing period-driven and data-driven viewpoints, new features include assessing the impact of uncertainty in the estimated covariance matrix of the MUF sequence and the impact of both random and systematic measurement errors.

Burr, T.↗
DOE OSTI2024

Practical and Optimal Sequential Bayesian Experimental Design for Complex Systems Incorporating Human Experimenter Preferences (Final Scientific/Technical Report)

Experiments are indispensable for developing models of complex systems. Carefully designed experiments can provide substantial savings for these expensive data-acquisition opportunities. However, designs based on heuristics are often suboptimal for systems with multiphysics, nonlinear dynamics, and uncertain and noisy environments. Optimal experimental design, while leveraging predictive models, seeks to systematically quantify and maximize the value of experiments. In this project, we focused on the design of multiple experiments, where current approaches are largely suboptimal: batch-design does not adapt to new data acquired during the experiment campaign (no feedback), and greedy/myopic design ignores future dynamics and consequences (no lookahead). We developed the mathematical framework and computational methods for sequential optimal experimental design (sOED) for complex systems. We enabled tractable model-based sOED in a rigorous manner through novel algorithms based on reinforcement learning, and investigated the effects of human experimenters on the design process. Our methods are fully Bayesian, able to quantify and update uncertainty in a principled manner. The traits aimed by our approach—mathematical rigor and optimality, human effects and uncertainty quantification, computational practicality—are crucial for elevating the standards of artificial intelligence (AI) to support decision-making in scientific domains, and contribute toward trust and realistic adoption of AI in experimental design practice.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

Transformation of zinc-concentrate in surface and subsurface environments: Implications for assessing zinc mobility/toxicity and choosing an optimal remediation strategy

Zinc contamination in near- and sub-surface environments is a serious threat to many ecosystems and to public health. Sufficient understanding of Zn speciation and transport mechanisms is therefore critical to evaluating its risk to the environment and to developing remediation strategies. The geochemical and mineralogical characteristics of contaminated soils in the vicinity of a Zn ore transportation route were thoroughly investigated using a variety of analytical techniques (sequential extraction, XRF, XRD, SEM, and XAFS). Imported Zn-concentrate (ZnS) was deposited in a receiving facility and dispersed over time to the surrounding roadside areas and rice-paddy soils. Subsequent physical and chemical weathering resulted in dispersal into the subsurface. The species identified in the contaminated areas included Zn-sulfide, Zn-carbonate, other O-coordinated Zn-minerals, and Zn species bound to Fe/Mn oxides or clays, as confirmed by XAFS spectroscopy and sequential extraction. The observed transformation from S-coordinated Zn to O-coordinated Zn associated with minerals suggests that this contaminant can change into more soluble and labile forms as a result of weathering. For the purpose of developing a soil washing remediation process, the contaminated samples were extracted with dilute acids. The extraction efficiency increased with the increase of O-coordinated Zn relative to S-coordinated Zn in the sediment. Furthermore, this study demonstrates that improved understanding of Zn speciation in contaminated soils is essential for well-informed decision making regarding metal mobility and toxicity, as well as for choosing an appropriate remediation strategy using soil washing.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2012

Using a Simple Binomial Model to Assess Improvement in Predictive Capability: Sequential Bayesian Inference, Hypothesis Testing, and Power Analysis

We present a Bayesian statistical methodology for identifying improvement in predictive simulations, including an analysis of the number of (presumably expensive) simulations that will need to be made in order to establish with a given level of confidence that an improvement has been observed. Our analysis assumes the ability to predict (or postdict) the same experiments with legacy and new simulation codes and uses a simple binomial model for the probability, {theta}, that, in an experiment chosen at random, the new code will provide a better prediction than the old. This model makes it possible to do statistical analysis with an absolute minimum of assumptions about the statistics of the quantities involved, at the price of discarding some potentially important information in the data. In particular, the analysis depends only on whether or not the new code predicts better than the old in any given experiment, and not on the magnitude of the improvement. We show how the posterior distribution for {theta} may be used, in a kind of Bayesian hypothesis testing, both to decide if an improvement has been observed and to quantify our confidence in that decision. We quantify the predictive probability that should be assigned, prior to taking any data, to the possibility of achieving a given level of confidence, as a function of sample size. We show how this predictive probability depends on the true value of {theta} and, in particular, how there will always be a region around {theta} = 1/2 where it is highly improbable that we will be able to identify an improvement in predictive capability, although the width of this region will shrink to zero as the sample size goes to infinity. We show how the posterior standard deviation may be used, as a kind of 'plan B metric' in the case that the analysis shows that {theta} is close to 1/2 and argue that such a plan B should generally be part of hypothesis testing. All the analysis presented in the paper is done with a general beta-function prior for {theta}, enabling sequential analysis in which a small number of new simulations may be done and the resulting posterior for {theta} used as a prior to inform the next stage of power analysis.

42 ENGINEERING↗
DOE OSTI2024

Prognostic analysis of high-flow nasal cannula therapy and non-invasive ventilation in mild to moderate hypoxemia patients and construction of a machine learning model for 48-h intubation prediction—a retrospective analysis of the MIMIC database

Background This study aims to investigate the clinical outcome between high-flow nasal cannula (HFNC) and non-invasive ventilation (NIV) therapy in mild to moderate hypoxemic patients on the first ICU day and to develop a predictive model of 48-h intubation. Methods The study included adult patients from the MIMIC III and IV databases who first initiated HFNC or NIV therapy due to mild to moderate hypoxemia (100 < PaO2/FiO2 ≤ 300). The 48-h and 30-day intubation rates were compared using cross-sectional and survival analysis. Nine machine learning and six ensemble algorithms were deployed to construct the 48-h intubation predictive models, of which the optimal model was determined by its prediction accuracy. The top 10 risk and protective factors were identified using the Shapley interpretation algorithm. Result A total of 123,042 patients were screened, of which, 673 were from the MIMIC IV database for ventilation therapy comparison (HFNC n = 363, NIV n = 310) and 48-h intubation predictive model construction (training dataset n = 471, internal validation set n = 202) and 408 were from the MIMIC III database for external validation. The NIV group had a lower intubation rate (23.1% vs. 16.1%, p = 0.001), ICU 28-day mortality (18.5% vs. 11.6%, p = 0.014), and in-hospital mortality (19.6% vs. 11.9%, p = 0.007) compared to the HFNC group. Survival analysis showed that the total and 48-h intubation rates were not significantly different. The ensemble AdaBoost decision tree model (internal and external validation set AUROC 0.878, 0.726) had the best predictive accuracy performance. The model Shapley algorithm showed Sequential Organ Failure Assessment (SOFA), acute physiology scores (APSIII), the minimum and maximum lactate value as risk factors for early failure and age, the maximum PaCO 2 and PH value, Glasgow Coma Scale (GCS), the minimum PaO 2 /FiO 2 ratio, and PaO 2 value as protective factors. Conclusion NIV was associated with lower intubation rate and ICU 28-day and in-hospital mortality. Further survival analysis reinforced that the effect of NIV on the intubation rate might partly be attributed to the other impact factors. The ensemble AdaBoost decision tree model may assist clinicians in making clinical decisions, and early organ function support to improve patients’ SOFA, APSIII, GCS, PaCO 2 , PaO 2 , PH, PaO 2 /FiO 2 ratio, and lactate values can reduce the early failure rate and improve patient prognosis.

Fu, Wei↗