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

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...

Full description

Saved in:
Bibliographic Details
Main Authors: Italo Francyles Santos da Silva, Alan de Carvalho Araújo, João Dallyson Sousa de Almeida, Anselmo Cardoso de Paiva, Aristófanes Corrêa Silva, Deane Roehl
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:AgriEngineering
Subjects:
Online Access:https://www.mdpi.com/2624-7402/7/2/27
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850081494324740096
author Italo Francyles Santos da Silva
Alan de Carvalho Araújo
João Dallyson Sousa de Almeida
Anselmo Cardoso de Paiva
Aristófanes Corrêa Silva
Deane Roehl
author_facet Italo Francyles Santos da Silva
Alan de Carvalho Araújo
João Dallyson Sousa de Almeida
Anselmo Cardoso de Paiva
Aristófanes Corrêa Silva
Deane Roehl
author_sort Italo Francyles Santos da Silva
collection DOAJ
description 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.
format Article
id doaj-art-7491440d2a9740fea4e2a72ab0e45fcb
institution DOAJ
issn 2624-7402
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series AgriEngineering
spelling doaj-art-7491440d2a9740fea4e2a72ab0e45fcb2025-08-20T02:44:43ZengMDPI AGAgriEngineering2624-74022025-01-01722710.3390/agriengineering7020027Soil Structure Analysis with Attention: A Deep-Learning-Based Method for 3D Pore Segmentation and CharacterizationItalo Francyles Santos da Silva0Alan de Carvalho Araújo1João Dallyson Sousa de Almeida2Anselmo Cardoso de Paiva3Aristófanes Corrêa Silva4Deane Roehl5Applied Computing Group (NCA), Federal University of Maranhão, São Luís 65085-580, MA, BrazilApplied Computing Group (NCA), Federal University of Maranhão, São Luís 65085-580, MA, BrazilApplied Computing Group (NCA), Federal University of Maranhão, São Luís 65085-580, MA, BrazilApplied Computing Group (NCA), Federal University of Maranhão, São Luís 65085-580, MA, BrazilApplied Computing Group (NCA), Federal University of Maranhão, São Luís 65085-580, MA, BrazilTecgraf Institute, Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro 22453-900, RJ, BrazilThe 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.https://www.mdpi.com/2624-7402/7/2/273D pore segmentationsoil characterizationporosity estimationconvolutional neural networksattention mechanismscomputed tomography
spellingShingle Italo Francyles Santos da Silva
Alan de Carvalho Araújo
João Dallyson Sousa de Almeida
Anselmo Cardoso de Paiva
Aristófanes Corrêa Silva
Deane Roehl
Soil Structure Analysis with Attention: A Deep-Learning-Based Method for 3D Pore Segmentation and Characterization
AgriEngineering
3D pore segmentation
soil characterization
porosity estimation
convolutional neural networks
attention mechanisms
computed tomography
title Soil Structure Analysis with Attention: A Deep-Learning-Based Method for 3D Pore Segmentation and Characterization
title_full Soil Structure Analysis with Attention: A Deep-Learning-Based Method for 3D Pore Segmentation and Characterization
title_fullStr Soil Structure Analysis with Attention: A Deep-Learning-Based Method for 3D Pore Segmentation and Characterization
title_full_unstemmed Soil Structure Analysis with Attention: A Deep-Learning-Based Method for 3D Pore Segmentation and Characterization
title_short Soil Structure Analysis with Attention: A Deep-Learning-Based Method for 3D Pore Segmentation and Characterization
title_sort soil structure analysis with attention a deep learning based method for 3d pore segmentation and characterization
topic 3D pore segmentation
soil characterization
porosity estimation
convolutional neural networks
attention mechanisms
computed tomography
url https://www.mdpi.com/2624-7402/7/2/27
work_keys_str_mv AT italofrancylessantosdasilva soilstructureanalysiswithattentionadeeplearningbasedmethodfor3dporesegmentationandcharacterization
AT alandecarvalhoaraujo soilstructureanalysiswithattentionadeeplearningbasedmethodfor3dporesegmentationandcharacterization
AT joaodallysonsousadealmeida soilstructureanalysiswithattentionadeeplearningbasedmethodfor3dporesegmentationandcharacterization
AT anselmocardosodepaiva soilstructureanalysiswithattentionadeeplearningbasedmethodfor3dporesegmentationandcharacterization
AT aristofanescorreasilva soilstructureanalysiswithattentionadeeplearningbasedmethodfor3dporesegmentationandcharacterization
AT deaneroehl soilstructureanalysiswithattentionadeeplearningbasedmethodfor3dporesegmentationandcharacterization