Enrico Soranzo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Enrico Soranzo has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Wei Wu
Institute of Geotechnical Engineering, Boku University, Vienna, Austria
14 shared publications - Carlotta Guardiani
University of Natural Resources and Life Sciences
8 shared publications - Yunteng Wang
Institut für Geotechnik, Universität für Bodenkultur Wien, Vienna, Austria
4 shared publications Carlotta Guardiani
2 shared publicationsWei Wu
2 shared publicationsAhsan Saif
1 shared publication
Latest Publications
- 21 July 2026
- Published by Springer Nature
- p. 31-44
A Hydro-Mechanical Hypoplastic Model for Unsaturated Soils in Isotropic Stress States
- 21 July 2026
- Published by Springer Nature
- p. 31-44
A Hydro-Mechanical Hypoplastic Model for Unsaturated Soils in Isotropic Stress States
- Open Access
- 17 June 2026
- Published by Elsevier in Computers and Geotechnics
- Vol. 199
GRAI3: Generalizable soil particle size distribution from smartphone images
- 17 June 2026
- Published by Elsevier in Computers and Geotechnics
- Vol. 199
Open AccessGRAI3: Generalizable soil particle size distribution from smartphone images
- Open Access
- 6 March 2026
- Published by Elsevier in SSRN Electronic Journal
GRAI3: Generalizable soil particle size distribution from smartphone images
We present GRAI3, a device-agnostic web application for generalizable prediction of soil particle size distribution from standardized smartphone images. GRAI3 couples a streamlined acquisition protocol using a photo-box with a deep learning pipeline based on EfficientNetV2-S, trained on an expanded, diverse dataset. The method models the cumulative particle size distribution with a two-parameter Weibull function, inferring its scale and shape directly from an image. To achieve device-agnostic performance, GRAI3 automatically reads camera EXIF metadata, retrieves per-device pixel density from a calibration table or estimates pixel density when the device is unknown based on the typical angle of view. Images are normalized to a target pixel density and centre-cropped to a fixed resolution before inference, reducing covariate shift across cameras. A lightweight verification model checks whether the uploaded image depicts soil and adheres to photo-box capture requirements. The web application performs real-time inference and provides a one-click PDF report, embedding the original photo, PSD curve and computed parameters. Monte Carlo dropout was implemented to provide a measure of confidence in the model's predictions. Validation on an expanded dataset and cross-device scenarios indicates improved generalizability relative to prior versions, attributable to the upgraded backbone and group cross-validation. GRAI3 thus offers a practical, reproducible workflow for soil granulometry estimation using commodity smartphones, supporting rapid screening, documentation and reporting in geotechnical and environmental applications.
- 6 March 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessGRAI3: Generalizable soil particle size distribution from smartphone images
We present GRAI3, a device-agnostic web application for generalizable prediction of soil particle size distribution from standardized smartphone images. GRAI3 couples a streamlined acquisition protocol using a photo-box with a deep learning pipeline based on EfficientNetV2-S, trained on an expanded, diverse dataset. The method models the cumulative particle size distribution with a two-parameter Weibull function, inferring its scale and shape directly from an image. To achieve device-agnostic performance, GRAI3 automatically reads camera EXIF metadata, retrieves per-device pixel density from a calibration table or estimates pixel density when the device is unknown based on the typical angle of view. Images are normalized to a target pixel density and centre-cropped to a fixed resolution before inference, reducing covariate shift across cameras. A lightweight verification model checks whether the uploaded image depicts soil and adheres to photo-box capture requirements. The web application performs real-time inference and provides a one-click PDF report, embedding the original photo, PSD curve and computed parameters. Monte Carlo dropout was implemented to provide a measure of confidence in the model's predictions. Validation on an expanded dataset and cross-device scenarios indicates improved generalizability relative to prior versions, attributable to the upgraded backbone and group cross-validation. GRAI3 thus offers a practical, reproducible workflow for soil granulometry estimation using commodity smartphones, supporting rapid screening, documentation and reporting in geotechnical and environmental applications.
- Open Access
- 27 February 2026
- Published by Elsevier in Geoscience Frontiers
- Vol. 17 (3)
Strength of a cement-improved clay and a machine learning evaluation of interactions between observed mechanical behaviours
- 27 February 2026
- Published by Elsevier in Geoscience Frontiers
- Vol. 17 (3)
Open AccessStrength of a cement-improved clay and a machine learning evaluation of interactions between observed mechanical behaviours
- Open Access
- 12 May 2025
- Published by Elsevier in Data in Brief
- Vol. 60, 111631
Dataset of close-range soil images and corresponding particle size distributions
- 12 May 2025
- Published by Elsevier in Data in Brief
- Vol. 60, 111631
Open AccessDataset of close-range soil images and corresponding particle size distributions
- Open Access
- 18 March 2025
- Published by Springer Nature in Transportation Infrastructure Geotechnology
- Vol. 12 (4) , 1-34
Three-Dimensional Parametric Analyses of Cross-Passages in Shallow Tunnels Within Noncohesive Soils
Cross-passages are small-diameter tunnels between running tunnels or between a tunnel and a shaft, essential for safety, maintenance, emergency evacuation, and ventilation. The geotechnical design of these cross-passages is complex and not well understood. This paper presents results from a parametric study carried out in a three-dimensional finite element framework using an advanced nonlinear elasto-plastic constitutive model to represent the surrounding soil. Key parameters varied include the aspect ratio of the cross-passage to the parent tunnel, soil strength, and intersection angle. Findings indicate a significant increase in hoop compression at the springlines and longitudinal tension at the crown and invert of the cross-passage. The aspect ratio significantly affects stress distribution, with maximum stress arching occurring at an aspect ratio of 0.5. With the increase in the opening size, stress redistribution is reduced, and opening deformation is increased. The ideal intersection angle between a cross-passage and parent tunnel is found to be 90°, with angles below 70° leading to a large increase in stress concentrations. Extent of stress redistribution due to cross-passage is found to range from 1.5 to 1.2 times its diameter for large openings in loose soils and smaller openings in dense soils, respectively.
- 18 March 2025
- Published by Springer Nature in Transportation Infrastructure Geotechnology
- Vol. 12 (4) , 1-34
Open AccessThree-Dimensional Parametric Analyses of Cross-Passages in Shallow Tunnels Within Noncohesive Soils
Cross-passages are small-diameter tunnels between running tunnels or between a tunnel and a shaft, essential for safety, maintenance, emergency evacuation, and ventilation. The geotechnical design of these cross-passages is complex and not well understood. This paper presents results from a parametric study carried out in a three-dimensional finite element framework using an advanced nonlinear elasto-plastic constitutive model to represent the surrounding soil. Key parameters varied include the aspect ratio of the cross-passage to the parent tunnel, soil strength, and intersection angle. Findings indicate a significant increase in hoop compression at the springlines and longitudinal tension at the crown and invert of the cross-passage. The aspect ratio significantly affects stress distribution, with maximum stress arching occurring at an aspect ratio of 0.5. With the increase in the opening size, stress redistribution is reduced, and opening deformation is increased. The ideal intersection angle between a cross-passage and parent tunnel is found to be 90°, with angles below 70° leading to a large increase in stress concentrations. Extent of stress redistribution due to cross-passage is found to range from 1.5 to 1.2 times its diameter for large openings in loose soils and smaller openings in dense soils, respectively.
- Open Access
- 19 February 2025
- Published by Elsevier in Data in Brief
- Vol. 59, 111391
Comprehensive dataset of dynamic probing heavy test results for subsurface characterization
- 19 February 2025
- Published by Elsevier in Data in Brief
- Vol. 59, 111391
Open AccessComprehensive dataset of dynamic probing heavy test results for subsurface characterization
- 2 July 2024
- Published by Springer Nature
- p. 15-24
Landslide Displacement Prediction with Machine Learning Techniques
- 2 July 2024
- Published by Springer Nature
- p. 15-24
Landslide Displacement Prediction with Machine Learning Techniques