Next Article in Journal
Analysis of Olive Detachment Force to Improve Olive Shaker Efficiency Through Branch Modeling
Previous Article in Journal
Treatment of Ferruginous Water in the Performance of Drip Irrigation Systems
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
AgriEngineering
Volume 7
Issue 2
10.3390/agriengineering7020027
agriengineering-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Soil Structure Analysis with Attention: A Deep Deep-Learning-Based Method for 3D Pore Segmentation and Characterization

by
Italo Francyles Santos da Silva
1,*,†,
Alan de Carvalho Araújo
1,†,
João Dallyson Sousa de Almeida
1,*,†,
Anselmo Cardoso de Paiva
1,†,
Aristófanes Corrêa Silva
1,† and
Deane Roehl
2,†
1
Applied Computing Group (NCA), Federal University of Maranhão, Maranhão 65085-580, Brazil
2
Tecgraf Institute, Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro 22453-900, Brazil
*
Authors to whom correspondence should be addressed.
†
These authors contributed equally to this work.
AgriEngineering 2025, 7(2), 27; https://doi.org/10.3390/agriengineering7020027
Submission received: 16 December 2024 / Revised: 15 January 2025 / Accepted: 16 January 2025 / Published: 27 January 2025
Versions Notes

Abstract

The pore structure plays a crucial role in soil systems. It affects a range of processes essential for soil ecological functions, such as the transport and retention of water and nutrients, as well as gas exchanges. The mechanical and hydrological characteristics of soil are predominantly determined by the three-dimensional pore pore-space structure. A precise analysis of pore structure can help specialists understand how these shapes impact plant root activity, leading to better cultivation practices. X-ray computed tomography provides detailed information without destroying the sample. However, manually delineating pore structure and estimating porosity are challenging tasks. This work proposes an automated method for 3D pore segmentation and characterization using convolutional neural networks with attention mechanisms. The method introduces a novel approach that combines attention at both channel and spatial levels, enhancing the segmentation and property estimation, providing valuable insights for a more detailed study of soil conditions. In experiments conducted with a private dataset, the segmentation results achieved mean Dice values of 99.10% ± 0.0004 and mean IoU values of 98.23% ± 0.0008. Additionally, in tests with Phaeozem Albic, the automatic method provided porosity estimates comparable to those obtained by a method based on integral geometry and morphology.
Keywords: 3D pore segmentation; soil characterization; porosity estimation; convolutional neural networks; attention mechanisms; computed tomography 3D pore segmentation; soil characterization; porosity estimation; convolutional neural networks; attention mechanisms; computed tomography

Share and Cite

MDPI and ACS Style

Silva, I.F.S.d.; Araújo, A.d.C.; Almeida, J.D.S.d.; Paiva, A.C.d.; Silva, A.C.; Roehl, D. Soil Structure Analysis with Attention: A Deep Deep-Learning-Based Method for 3D Pore Segmentation and Characterization. AgriEngineering 2025, 7, 27. https://doi.org/10.3390/agriengineering7020027

AMA Style

Silva IFSd, Araújo AdC, Almeida JDSd, Paiva ACd, Silva AC, Roehl D. Soil Structure Analysis with Attention: A Deep Deep-Learning-Based Method for 3D Pore Segmentation and Characterization. AgriEngineering. 2025; 7(2):27. https://doi.org/10.3390/agriengineering7020027

Chicago/Turabian Style

Silva, Italo Francyles Santos da, Alan de Carvalho Araújo, João Dallyson Sousa de Almeida, Anselmo Cardoso de Paiva, Aristófanes Corrêa Silva, and Deane Roehl. 2025. "Soil Structure Analysis with Attention: A Deep Deep-Learning-Based Method for 3D Pore Segmentation and Characterization" AgriEngineering 7, no. 2: 27. https://doi.org/10.3390/agriengineering7020027

APA Style

Silva, I. F. S. d., Araújo, A. d. C., Almeida, J. D. S. d., Paiva, A. C. d., Silva, A. C., & Roehl, D. (2025). Soil Structure Analysis with Attention: A Deep Deep-Learning-Based Method for 3D Pore Segmentation and Characterization. AgriEngineering, 7(2), 27. https://doi.org/10.3390/agriengineering7020027

Article Metrics

Back to TopTop