Application of deep neural networks to forecast 60Co soil to plant transfer factor values based in pedological parameters

The soil-plant transfer factor (Fv) is used methods in the computational models for radiological risk assessment by ingestion of radiocobalt-contaminated food. Different soil types, plants types and agricultural practices contribute to a wide dispersion of Fv values, indicating the need to study the...

Full description

Saved in:
Bibliographic Details
Main Authors: Lucas Iwahara, Cláudio Pereira, Maria Angélica Wasserman, Flávia Bartoly
Format: Article
Language:English
Published: Brazilian Radiation Protection Society (Sociedade Brasileira de Proteção Radiológica, SBPR) 2022-06-01
Series:Brazilian Journal of Radiation Sciences
Subjects:
Online Access:https://bjrs.org.br/revista/index.php/REVISTA/article/view/2042
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850104102989594624
author Lucas Iwahara
Cláudio Pereira
Maria Angélica Wasserman
Flávia Bartoly
author_facet Lucas Iwahara
Cláudio Pereira
Maria Angélica Wasserman
Flávia Bartoly
author_sort Lucas Iwahara
collection DOAJ
description The soil-plant transfer factor (Fv) is used methods in the computational models for radiological risk assessment by ingestion of radiocobalt-contaminated food. Different soil types, plants types and agricultural practices contribute to a wide dispersion of Fv values, indicating the need to study the criteria that influence root uptake in a regional view. In this scenario, Artificial Neural Networks (ANN) have become a possibility to predict Fv values based on critical pedological parameters. This work aims to apply ANN to evaluate the possibility of predicting Fv for 60Co in reference plants as a function of soil properties considered relevant for transfer processes in the soil-plant system. Through the systematic literature review, mineralogy, organic matter, texture, pH, CEC and nutrients were identified as soil properties that affect Fv values for 60Co. However, although these attributes were not always reported, still it was possible to create databases of Fv for 60Co in radish root and leaf, with pH, organic matter, and CTC as potential edaphic indicators. Learning sets were structured and due to the complexity of the search space and the small amount of available data, deep ANN with regularization (dropout) layers were required to achieve good prediction and avoid overfitting. The best model obtained showed good correlation in the validation and training set, considering the chosen parameters.
format Article
id doaj-art-0bb3fe37174d40f6840cb8e792b9d300
institution DOAJ
issn 2319-0612
language English
publishDate 2022-06-01
publisher Brazilian Radiation Protection Society (Sociedade Brasileira de Proteção Radiológica, SBPR)
record_format Article
series Brazilian Journal of Radiation Sciences
spelling doaj-art-0bb3fe37174d40f6840cb8e792b9d3002025-08-20T02:39:23ZengBrazilian Radiation Protection Society (Sociedade Brasileira de Proteção Radiológica, SBPR)Brazilian Journal of Radiation Sciences2319-06122022-06-0110210.15392/2319-0612.2022.20421660Application of deep neural networks to forecast 60Co soil to plant transfer factor values based in pedological parametersLucas Iwahara0Cláudio Pereira1Maria Angélica Wasserman2Flávia Bartoly3Institute of Radiation Protection and DosimetryNuclear Engineering InstituteInstitute of Radiation Protection and Dosimetry Flavia Bartoly AgroambientalThe soil-plant transfer factor (Fv) is used methods in the computational models for radiological risk assessment by ingestion of radiocobalt-contaminated food. Different soil types, plants types and agricultural practices contribute to a wide dispersion of Fv values, indicating the need to study the criteria that influence root uptake in a regional view. In this scenario, Artificial Neural Networks (ANN) have become a possibility to predict Fv values based on critical pedological parameters. This work aims to apply ANN to evaluate the possibility of predicting Fv for 60Co in reference plants as a function of soil properties considered relevant for transfer processes in the soil-plant system. Through the systematic literature review, mineralogy, organic matter, texture, pH, CEC and nutrients were identified as soil properties that affect Fv values for 60Co. However, although these attributes were not always reported, still it was possible to create databases of Fv for 60Co in radish root and leaf, with pH, organic matter, and CTC as potential edaphic indicators. Learning sets were structured and due to the complexity of the search space and the small amount of available data, deep ANN with regularization (dropout) layers were required to achieve good prediction and avoid overfitting. The best model obtained showed good correlation in the validation and training set, considering the chosen parameters.https://bjrs.org.br/revista/index.php/REVISTA/article/view/2042cobaltsystematic reviewsoil-plant transfer factorneural network
spellingShingle Lucas Iwahara
Cláudio Pereira
Maria Angélica Wasserman
Flávia Bartoly
Application of deep neural networks to forecast 60Co soil to plant transfer factor values based in pedological parameters
Brazilian Journal of Radiation Sciences
cobalt
systematic review
soil-plant transfer factor
neural network
title Application of deep neural networks to forecast 60Co soil to plant transfer factor values based in pedological parameters
title_full Application of deep neural networks to forecast 60Co soil to plant transfer factor values based in pedological parameters
title_fullStr Application of deep neural networks to forecast 60Co soil to plant transfer factor values based in pedological parameters
title_full_unstemmed Application of deep neural networks to forecast 60Co soil to plant transfer factor values based in pedological parameters
title_short Application of deep neural networks to forecast 60Co soil to plant transfer factor values based in pedological parameters
title_sort application of deep neural networks to forecast 60co soil to plant transfer factor values based in pedological parameters
topic cobalt
systematic review
soil-plant transfer factor
neural network
url https://bjrs.org.br/revista/index.php/REVISTA/article/view/2042
work_keys_str_mv AT lucasiwahara applicationofdeepneuralnetworkstoforecast60cosoiltoplanttransferfactorvaluesbasedinpedologicalparameters
AT claudiopereira applicationofdeepneuralnetworkstoforecast60cosoiltoplanttransferfactorvaluesbasedinpedologicalparameters
AT mariaangelicawasserman applicationofdeepneuralnetworkstoforecast60cosoiltoplanttransferfactorvaluesbasedinpedologicalparameters
AT flaviabartoly applicationofdeepneuralnetworkstoforecast60cosoiltoplanttransferfactorvaluesbasedinpedologicalparameters