ARXIV:2605.30585 · ML UNCERTAINTY QUANTIFICATION · SUBMITTED 01 JUN · 20:29 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedVerifiedPaperPack: citation fields availablePartialProof: unverified proof status

Benchmarking Machine Learning Uncertainty Quantification Methodologies for Predicting Turbine Gas Temperature Degradation

Jostein Barry-Straume · Changmin Son · Adrian Sandu · Gavan Burke · Rekha Sundararajan · Andrew Rimell · +1 at arXiv

A comparative study of five uncertainty quantification methods for predicting turbine gas temperature degradation provides insights into their trade-offs for engine health management.

Ship in 2-4 weeks›Score4.0Evidence unverified

Opportunity summary

Pain A comparative study of five uncertainty quantification methods for predicting turbine gas temperature degradation provides insights into their trade-offs for engine health management.

Evidence 0 refs | 3 sources | 50% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

A comparative study of five uncertainty quantification methods for predicting turbine gas temperature degradation provides insights into their trade-offs for engine health management. This paper investigates five major approaches for constructing prediction intervals --…

METHOD

Full abstract

Effective prognostics and health management of modern engines relies on accurate turbine gas temperature predictions and robust uncertainty quantification to ensure reliability and safety. This paper investigates five major approaches for constructing prediction intervals -- namely the Delta method, Bayesian Monte Carlo Dropout, Bootstrap method, Lower-Upper Bound Estimation, and Mean-Variance Estimation -- as a means of capturing the uncertainty in neural network predictions of turbine gas temperature. Each approach is implemented within a unified experimental framework that employs cross-validation for hyperparameter selection, repeated train-test splits for performance robustness, and multiple metrics to evaluate both the accuracy and tightness of the intervals. In particular, Coverage Probability, Normalized Mean Prediction Interval Width, and the Coverage Width-based Criterion are measured to comprehensively assess each method's reliability and sharpness. Experiments conducted on a representative turbine gas temperature dataset reveal distinct trade-offs among the five methods in terms of interval coverage, width, and stability. These findings provide a practical guide for selecting and tuning prediction interval methods in engine health management and prognostics, ensuring both interpretability and precision in real-world applications.

RESULT

ScienceToStartup currently rates this 4.0/10 on the public viability pass. These findings provide a practical guide for selecting and tuning prediction interval methods in engine health management and prognostics, ensuring both interpretability and precision…

WHY NOW

ML Uncertainty Quantification moved forward this cycle; last verified June 2026. Public score 4.0/10. Production flags indicate code availability.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score4.0

PainA comparative study of five uncertainty quantification methods for predicting turbine gas temperature degradation provides insights into their trade-offs for engine health management.

Evidence0 refs | 3 sources | 50% coverage

Blockerno shell-level blocker reported

Analysis summary

A comparative study of five uncertainty quantification methods for predicting turbine gas temperature degradation provides insights into their trade-offs for engine health management.

VerifiedSource: PDF linkedVerifiedPaperPack: citation fields availablePartialProof: unverified proof status

Benchmarking Machine Learning Uncertainty Quantification Methodologies for Predicting Turbine Gas Temperature Degradation

Jostein Barry-Straume · Changmin Son · Adrian Sandu · Gavan Burke · Rekha Sundararajan · Andrew Rimell · +1 at arXiv

A comparative study of five uncertainty quantification methods for predicting turbine gas temperature degradation provides insights into their trade-offs for engine health management.

Competitive landscape

A comparative study of five uncertainty quantification methods for predicting turbine gas temperature degradation provides insights into their trade-offs for engine health management.

Segment

ML Uncertainty Quantification

Adoption evidence

No public code link in the paper record yet

Commercial read

4.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

{ "contract_version": "paper-r2", "paper_id": "02015ba4-232d-4c84-86cb-687820e070ee", "arxiv_id": "2605.30585", "canonical_route": "/paper/benchmarking-machine-learning-uncertainty-quantification-methodologies-for-predicting-turbine-gas-temperature-degradatio", "active_tab": "synced from current hash by the drawer client", "selected_artifact": "benchmarking-machine-learning-uncertainty-quantification-methodologies-for-predicting-turbine-gas-temperature-degradatio", "endpoints": { "paper_pack": "/api/v1/paper/benchmarking-machine-learning-uncertainty-quantification-methodologies-for-predicting-turbine-gas-temperature-degradatio/paper-pack", "build_passport": "/api/v1/paper/benchmarking-machine-learning-uncertainty-quantification-methodologies-for-predicting-turbine-gas-temperature-degradatio/build-passport", "mcp_resource": "sciencetostartup://surfaces/paper-workspace" } }

{ "surface": "paper", "mode": "paper", "query": "Benchmarking Machine Learning Uncertainty Quantification Methodologies for Predicting Turbine Gas Temperature Degradation", "normalized_query": "2605.30585", "route": "/paper/benchmarking-machine-learning-uncertainty-quantification-methodologies-for-predicting-turbine-gas-temperature-degradatio", "paper_ref": "benchmarking-machine-learning-uncertainty-quantification-methodologies-for-predicting-turbine-gas-temperature-degradatio", "topic_slug": null, "benchmark_ref": null, "dataset_ref": null }

{ "@context": "https://schema.org", "@graph": [ { "@type": "WebPage", "@id": "https://sciencetostartup.com/paper/benchmarking-machine-learning-uncertainty-quantification-methodologies-for-predicting-turbine-gas-temperature-degradatio#webpage", "url": "https://sciencetostartup.com/paper/benchmarking-machine-learning-uncertainty-quantification-methodologies-for-predicting-turbine-gas-temperature-degradatio", "name": "Benchmarking Machine Learning Uncertainty Quantification Methodologies for Predicting Turbine Gas Temperature Degradation", "description": "A comparative study of five uncertainty quantification methods for predicting turbine gas temperature degradation provides insights into their trade-offs for engine health management.", "isPartOf": { "@id": "https://sciencetostartup.com/#website" } }, { "@type": "ScholarlyArticle", "@id": "https://sciencetostartup.com/paper/benchmarking-machine-learning-uncertainty-quantification-methodologies-for-predicting-turbine-gas-temperature-degradatio#scholarlyArticle", "headline": "Benchmarking Machine Learning Uncertainty Quantification Methodologies for Predicting Turbine Gas Temperature Degradation", "description": "A comparative study of five uncertainty quantification methods for predicting turbine gas temperature degradation provides insights into their trade-offs for engine health management.", "url": "https://sciencetostartup.com/paper/benchmarking-machine-learning-uncertainty-quantification-methodologies-for-predicting-turbine-gas-temperature-degradatio", "sameAs": "https://arxiv.org/abs/2605.30585", "identifier": { "@type": "PropertyValue", "propertyID": "arXiv", "value": "2605.30585" }, "isAccessibleForFree": true, "isPartOf": { "@id": "https://sciencetostartup.com/#website" }, "datePublished": "2026-05-28T21:25:47.000Z", "author": [ { "@type": "Person", "name": "Jostein Barry-Straume" }, { "@type": "Person", "name": "Changmin Son" }, { "@type": "Person", "name": "Adrian Sandu" }, { "@type": "Person", "name": "Gavan Burke" }, { "@type": "Person", "name": "Rekha Sundararajan" }, { "@type": "Person", "name": "Andrew Rimell" }, { "@type": "Person", "name": "James G. Steinrock" } ], "additionalProperty": [ { "@type": "PropertyValue", "propertyID": "viabilityScore", "value": 4 }, { "@type": "PropertyValue", "propertyID": "researchDomain", "value": "ML Uncertainty Quantification" }, { "@type": "PropertyValue", "propertyID": "commercialReadiness", "value": "code" } ] }, { "@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://sciencetostartup.com" }, { "@type": "ListItem", "position": 2, "name": "ML Uncertainty Quantification", "item": "https://sciencetostartup.com/topics" }, { "@type": "ListItem", "position": 3, "name": "Benchmarking Machine Learning Uncertainty Quantification Met", "item": "https://sciencetostartup.com/paper/benchmarking-machine-learning-uncertainty-quantification-methodologies-for-predicting-turbine-gas-temperature-degradatio" } ] } ] }

Competitive landscape

A comparative study of five uncertainty quantification methods for predicting turbine gas temperature degradation provides insights into their trade-offs for engine health management.

Segment

ML Uncertainty Quantification

Adoption evidence

No public code link in the paper record yet

Commercial read

4.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

Benchmarking Machine Learning Uncertainty Quantification Methodologies for Predicting Turbine Gas Temperature Degradation

Benchmarking Machine Learning Uncertainty Quantification Methodologies for Predicting Turbine Gas Temperature Degradation

Claim map

Constellation map

Competitive landscape

Buzz

PDF

REFERENCES

Related Papers

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline

Claim map

Constellation map

Competitive landscape

Buzz

PDF

REFERENCES

Related Papers

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline