Improving deep neural network prediction of hydraulic fracturing initiation pressure in hydrate-bearing sediments through feature engineering and architecture search
Abstract
Accurate prediction of hydraulic fracturing initiation pressure ( Pb ) in natural gas hydrate-bearing sediments provides screening-level support for laboratory-scale hydraulic fracturing design in NGH-bearing sediments. This study demonstrates that systematic feature engineering and neural architecture search yield substantial improvements for predicting Pb on a 114-sample published dataset. The framework first expands the feature space from 12 to 208 variables via polynomial transformations, interaction terms, and domain-specific features, followed by deduplication. Multi-method feature selection identifies a 14-feature subset, and extended evaluation identifies a verified 12 × 32 model as the best-performing saved configuration. The reproducible-by-retraining reference is R 2 ≈ 0.87; the verified 12 × 32 saved model achieves R 2 = 0.92 on its original held-out split and is reported as an upper bound on the dataset. The best of 60 retraining runs reaches 0.85—none reproduces 0.92, confirming that 0.92 is a saved-artifact result, not a reproducible target. The verified 12 × 32 model reduces MSE from 19.34 to 8.22 MPa 2 and MAE from 3.16 to 2.14 MPa compared to the best prior reported result (R 2 = 0.81). Feature importance and SHAP analysis show that the model assigns highest importance to stress-composition interactions and stress-derived statistical terms, consistent with known geomechanical controls on fracture initiation. Generalization is modest (CV mean R 2 ≈ 0.50), and simpler models (RandomForest, SVR) are recommended as production-ready baselines; the 12 × 32 DNN is retained as the best verified saved artifact. These findings confirm that the dataset contains untapped predictive capacity, and that methodological refinement through domain-informed feature engineering combined with systematic architecture search provides an effective pathway for improving prediction fidelity in small-sample geomechanical problems.
Related
- Study on the fracture initiation mechanisms of supercritical carbon dioxide and radial branch borehole cooperative fracturing in methane-bearing coal seams
- Architecture Science and Reality Access, Traversal, and Initiation Science: Disciplinary Boundaries, Architectural Foundations, and Scientific Handoff
- Molecular architecture of TE-seeded chromosome-naive initiation networks of protein-protein interactions delineates the Human Protein Map of the assembly of multiprotein complexes
- Pangenome-wide insights into eukaryotic translation initiation factors (eIF) genes uncover targets for sterility mosaic disease resistance engineering in pigeonpea.
- Improving employee performance rating prediction using ANN probability-enhanced ensemble learning
BibTeX
@article{ho2026improving,
title = {{Improving deep neural network prediction of hydraulic fracturing initiation pressure in hydrate-bearing sediments through feature engineering and architecture search}},
author = {Thi H. Ho and Thuat T. Trinh},
journal = {Scientific Reports},
year = {2026},
month = oct,
doi = {10.1038/s41598-026-75431-1},
url = {https://www.nature.com/articles/s41598-026-75431-1},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Improving deep neural network prediction of hydraulic fracturing initiation pressure in hydrate-bearing sediments through feature engineering and architecture search
AU - Thi H. Ho
AU - Thuat T. Trinh
PY - 2026
DA - 2026/10/16
JO - Scientific Reports
DO - 10.1038/s41598-026-75431-1
UR - https://www.nature.com/articles/s41598-026-75431-1
AB - Accurate prediction of hydraulic fracturing initiation pressure ( P_b ) in natural gas hydrate-bearing sediments provides screening-level support for laboratory-scale hydraulic fracturing design in NGH-bearing sediments. This study demonstrates that systematic feature engineering and neural architecture search yield substantial improvements for predicting P_b on a 114-sample published dataset. The framework first expands the feature space from 12 to 208 variables via polynomial transformations, interaction terms, and domain-specific features, followed by deduplication. Multi-method feature selection identifies a 14-feature subset, and extended evaluation identifies a verified 12 × 32 model as the best-performing saved configuration. The reproducible-by-retraining reference is R ^2 ≈ 0.87; the verified 12 × 32 saved model achieves R ^2 = 0.92 on its original held-out split and is reported as an upper bound on the dataset. The best of 60 retraining runs reaches 0.85—none reproduces 0.92, confirming that 0.92 is a saved-artifact result, not a reproducible target. The verified 12 × 32 model reduces MSE from 19.34 to 8.22 MPa ^2 and MAE from 3.16 to 2.14 MPa compared to the best prior reported result (R ^2 = 0.81). Feature importance and SHAP analysis show that the model assigns highest importance to stress-composition interactions and stress-derived statistical terms, consistent with known geomechanical controls on fracture initiation. Generalization is modest (CV mean R ^2 ≈ 0.50), and simpler models (RandomForest, SVR) are recommended as production-ready baselines; the 12 × 32 DNN is retained as the best verified saved artifact. These findings confirm that the dataset contains untapped predictive capacity, and that methodological refinement through domain-informed feature engineering combined with systematic architecture search provides an effective pathway for improving prediction fidelity in small-sample geomechanical problems.
SN - 2045-2322
ER -