The Low-Strain Pile Integrity Test (LSPIT), standardized in ASTM D5882, is widely used as a rapid and economical non-destructive technique for assessing pile continuity in deep foundation systems. However, interpretation of LSPIT reflectograms remains strongly dependent on expert judgment and is influenced by soil–pile interaction effects such as damping and radiation losses, which can alter waveform morphology and confound automated defect screening. This study proposes a soil-aware deep learning framework that combines image-based reflectogram features with categorical geotechnical context describing the dominant soil regime at the measurement site. Reflectogram images are processed with a pretrained ConvNeXt-Large backbone, while soil information derived from Unified Soil Classification System (USCS) logs is represented as a categorical auxiliary input and mapped to a learnable embedding. The resulting multimodal design conditions waveform interpretation based on site context rather than relying on signal morphology alone. The framework is examined on an assembled benchmark of 510 expert-labeled reflectograms (404 intact and 106 defective), including a nine-site subset of 182 field records with explicit soil annotations. On the assembled benchmark, the model yields 99.41% accuracy and a weighted F1-score of 0.9941; on the nine-site subset, the observed accuracy is 99.45% with zero missed defective cases. Balanced accuracy, specificity, missed-detection rate, false-alarm rate, and confidence intervals are additionally reported to better align the evaluation with engineering screening practice. The study also states the current limits of the evidence base, including partial soil annotation, dominant-soil simplification, restricted soil coverage, and the absence of leave-site-out and interpretability-focused validation. Overall, the results support soil-aware multimodal learning as a promising proof-of-concept direction for more context-aware automated LSPIT interpretation, while also identifying the validation steps still required for broad field deployment.

Low-strain pile integrity testing (LSPIT) is widely used for rapid pile screening, but reflectogram interpretation remains difficult because defect morphology, axial extent, signed relative cross-sectional change, attenuation, and wave propagation jointly shape the response. This study reformulates a synthetic archive of 90,900 reflectograms as a physically stratified machine-learning benchmark. Nine benchmark views (A0–A8) isolate neutral cases, axial-domain restrictions, severity thresholds, defect-length regimes, and sign regimes. Four objectives are considered: morphology classification, sign classification, absolute-severity regression, and signed-severity regression. In addition to the representation-specific baseline grid, a controlled five-fold grouped comparison was added in which logistic/ridge models, random forests, and a profile multilayer perceptron used the same 68-dimensional reflectogram-profile vector and identical train/validation/test groups. Under this matched condition, random forests achieved morphology accuracy of 0.810±0.010 and sign accuracy of 0.858±0.002; the corresponding profile-MLP values were 0.756±0.008 and 0.850±0.007. For signed severity, random forest and profile MLP obtained \(R^2\) values of 0.626±0.008 and 0.622±0.014, with mean absolute errors of 10.82±0.10 and 12.22±0.14 percentage points. A sample-size- and target-matched A5–A6 experiment confirmed that short defects consistently facilitate morphology recognition, but showed that severity difficulty is non-monotonic and depends jointly on axial length, morphology, and limited identifiability under the profile representation. A fourfold tail-weighting sensitivity analysis reduced severe-loss miss rates but increased central-range error, indicating both loss-driven and representation-limited causes of tail compression. The study is explicitly limited to synthetic benchmark evaluation; it provides a transparent basis for future, independently grounded field or high-fidelity numerical validation rather than evidence of deployment readiness.

This retrospective offline study examines how dense manual regional annotations can be organized for image-level grapevine disease recognition using pre-acquired HERMOS RGB images. After audit and filtering, 491 source images and 13,765 Pascal VOC regions were retained. A leakage-safe source-image split was used across full-image classification, regional crop classification, crop-to-image aggregation, annotation-guided multiple-instance learning (MIL), and YOLO11 localization. MIL bags in training, validation, and testing were constructed from crops derived from manual boxes; the results therefore describe annotation-assisted aggregation rather than raw-image deployment. The original ConvNeXt-Tiny MIL model achieved macro-F1 0.922 (95% source-image bootstrap CI 0.882–0.956), compared with 0.836 (0.754–0.895) for full-image ConvNeXt-Tiny and 0.869 (0.804–0.917) for the best fixed crop aggregation. Paired macro-F1 differences favored MIL over these baselines by 0.087 (95% CI 0.029–0.163; Holm-adjusted p = 0.013) and 0.053 (0.005–0.114; adjusted p = 0.036), respectively. Downy mildew precision and recall were 1.000 on nine positive test images, but the corresponding exact 95% binomial intervals were 0.664–1.000. Controlled ablations produced lower point estimates without learned attention or the auxiliary instance loss, whereas removing context expansion did not reduce performance; none of the three paired ablation tests was significant after Holm correction. Increasing detector capacity from YOLO11n to YOLO11s did not improve full-image mAP@0.50 (0.175 versus 0.170). These findings support annotation-guided local-evidence aggregation as an offline exploratory benchmark, while not establishing split-to-split stability, computational efficiency, or external-vineyard generalization.

Blast-induced ground vibration is traditionally predicted using empirical scaled-distance equations or numerical simulations driven by simplified analytical loading functions. Although dynamic finite element modeling has significantly advanced the understanding of stress-wave propagation, existing approaches remain unable to reproduce the complete seismic response of actual production blasting because the true blast source is generally unknown and is therefore replaced by simplified pressure–time functions. Consequently, a field-calibrated physics-informed Digital Twin framework for production blasting remains insufficiently established. This study presents a PI-DDT framework for production blasting based on field-derived seismic source reconstruction. The proposed methodology consists of two complementary innovations. First, the three-component near-field pilot-blast record was analyzed through deconvolution-based inverse wave propagation, and the transverse, longitudinal, and vertical components were independently deconvolved to reconstruct three orthogonal equivalent single-hole seismic source histories at the pilot blast hole. Second, the three reconstructed source histories were incorporated into the PLAXIS 3D dynamic finite element model through component-specific dynamic multiplier functions together with the actual production-blast geometry, blast-hole coordinates, electronic initiation sequence, site-specific rock-mass properties, and attenuation characteristics to establish a field-calibrated PI-DDT framework for a full-scale production blast. The proposed framework was applied to a full-scale production blast comprising 83 blast holes in an operating open-pit mine. Model performance was evaluated through a multi-domain performance assessment including PPV, amplitude-envelope development, frequency-spectrum agreement, and cumulative-energy evolution. The simulated responses showed practically meaningful agreement with field measurements across multiple monitoring locations, with a median component PPV error of 11.8%, a mean three-dimensional resultant PPV error of 14.2%, a mean resultant spectral similarity of 84.0%, and a mean three-dimensional cumulative-energy MAE of 4.7%. Unlike conventional blasting simulations that rely on simplified analytical loading functions, the proposed methodology reconstructs a field-derived equivalent seismic source signature and integrates it directly into a physics-based numerical model. The principal scientific contribution of the study lies in the field-calibrated integration of equivalent seismic source reconstruction, actual production-blast geometry and initiation timing, three-dimensional dynamic FEM, and multi-domain model-performance evaluation within a unified physics-informed framework. The developed framework provides a physics-based computational foundation for blast-design evaluation, vibration-control planning, digital mining applications, and future AI-assisted blast-design optimization and adaptive vibration-control workflows.