Origin Traceability of Chinese Mitten Crab (<i>Eriocheir sinensis</i>) Using Multi-Stable Isotopes and Explainable Machine Learning

The Chinese mitten crab (<i>Eriocheir sinensis</i>) industry is currently facing the challenges of origin fraud, as well as a lack of precision and interpretability of existing traceability methods. Here, we propose a high-precision origin traceability method based on a combination of st...

Full description

Saved in:
Bibliographic Details
Main Authors: Danhe Wang, Chunxia Yao, Yangyang Lu, Di Huang, Yameng Li, Xugan Wu, Weiguo Song, Qinxiong Rao
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Foods
Subjects:
Online Access:https://www.mdpi.com/2304-8158/14/14/2458
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849246317612630016
author Danhe Wang
Chunxia Yao
Yangyang Lu
Di Huang
Yameng Li
Xugan Wu
Weiguo Song
Qinxiong Rao
author_facet Danhe Wang
Chunxia Yao
Yangyang Lu
Di Huang
Yameng Li
Xugan Wu
Weiguo Song
Qinxiong Rao
author_sort Danhe Wang
collection DOAJ
description The Chinese mitten crab (<i>Eriocheir sinensis</i>) industry is currently facing the challenges of origin fraud, as well as a lack of precision and interpretability of existing traceability methods. Here, we propose a high-precision origin traceability method based on a combination of stable isotope analysis and interpretable machine learning. We sampled Chinese mitten crabs from six origins representing diverse aquatic environments and farming practices, and analyzed their <i>δ</i><sup>13</sup>C, <i>δ</i><sup>15</sup>N, <i>δ</i><sup>2</sup>H, and <i>δ</i><sup>18</sup>O stable isotope compositions in different sexes and tissues (hepatopancreas, muscle, and gonad). By comparing the classification performance of Random Forest, XGBoost, and Logistic Regression models, we found that the Random Forest model outperformed the others, achieving high accuracy (91.3%) in distinguishing samples from different origins. Interpretation of the optimal Random Forest model, using SHAP (SHapley Additive exPlanations) analysis, identified <i>δ</i><sup>2</sup>H in male muscle, <i>δ</i><sup>15</sup>N in female hepatopancreas, and <i>δ</i><sup>13</sup>C in female hepatopancreas as the most influential features for discriminating geographic origin. This analysis highlighted the crucial role of environmental factors, such as water source, diet, and trophic level, in origin discrimination and demonstrated that isotopic characteristics of different tissues provide unique discriminatory information. This study offers a novel paradigm for stable isotope traceability based on explainable machine learning, significantly enhancing the identification capability and reliability of Chinese mitten crab origin traceability, and holds significant implications for food safety assurance.
format Article
id doaj-art-59cea9f1bf3f43769da79e23dad9a4d4
institution Kabale University
issn 2304-8158
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Foods
spelling doaj-art-59cea9f1bf3f43769da79e23dad9a4d42025-08-20T03:58:31ZengMDPI AGFoods2304-81582025-07-011414245810.3390/foods14142458Origin Traceability of Chinese Mitten Crab (<i>Eriocheir sinensis</i>) Using Multi-Stable Isotopes and Explainable Machine LearningDanhe Wang0Chunxia Yao1Yangyang Lu2Di Huang3Yameng Li4Xugan Wu5Weiguo Song6Qinxiong Rao7The Institute of Agro-Food Standards and Testing Technology, Shanghai Academy of Agricultural Sciences, Shanghai 201403, ChinaThe Institute of Agro-Food Standards and Testing Technology, Shanghai Academy of Agricultural Sciences, Shanghai 201403, ChinaThe Institute of Agro-Food Standards and Testing Technology, Shanghai Academy of Agricultural Sciences, Shanghai 201403, ChinaThe Institute of Agro-Food Standards and Testing Technology, Shanghai Academy of Agricultural Sciences, Shanghai 201403, ChinaThe Institute of Agro-Food Standards and Testing Technology, Shanghai Academy of Agricultural Sciences, Shanghai 201403, ChinaResearch Centre on Fish Nutrition and Environmental Ecology of Ministry of Agriculture and Rural Affairs, Shanghai Ocean University, Shanghai 201306, ChinaThe Institute of Agro-Food Standards and Testing Technology, Shanghai Academy of Agricultural Sciences, Shanghai 201403, ChinaShanghai Co-Elite Agri-Food Testing Technical Service Co., Ltd., Shanghai 201403, ChinaThe Chinese mitten crab (<i>Eriocheir sinensis</i>) industry is currently facing the challenges of origin fraud, as well as a lack of precision and interpretability of existing traceability methods. Here, we propose a high-precision origin traceability method based on a combination of stable isotope analysis and interpretable machine learning. We sampled Chinese mitten crabs from six origins representing diverse aquatic environments and farming practices, and analyzed their <i>δ</i><sup>13</sup>C, <i>δ</i><sup>15</sup>N, <i>δ</i><sup>2</sup>H, and <i>δ</i><sup>18</sup>O stable isotope compositions in different sexes and tissues (hepatopancreas, muscle, and gonad). By comparing the classification performance of Random Forest, XGBoost, and Logistic Regression models, we found that the Random Forest model outperformed the others, achieving high accuracy (91.3%) in distinguishing samples from different origins. Interpretation of the optimal Random Forest model, using SHAP (SHapley Additive exPlanations) analysis, identified <i>δ</i><sup>2</sup>H in male muscle, <i>δ</i><sup>15</sup>N in female hepatopancreas, and <i>δ</i><sup>13</sup>C in female hepatopancreas as the most influential features for discriminating geographic origin. This analysis highlighted the crucial role of environmental factors, such as water source, diet, and trophic level, in origin discrimination and demonstrated that isotopic characteristics of different tissues provide unique discriminatory information. This study offers a novel paradigm for stable isotope traceability based on explainable machine learning, significantly enhancing the identification capability and reliability of Chinese mitten crab origin traceability, and holds significant implications for food safety assurance.https://www.mdpi.com/2304-8158/14/14/2458Chinese mitten craborigin traceabilitystable isotopesexplainable machine learningtissue specificity
spellingShingle Danhe Wang
Chunxia Yao
Yangyang Lu
Di Huang
Yameng Li
Xugan Wu
Weiguo Song
Qinxiong Rao
Origin Traceability of Chinese Mitten Crab (<i>Eriocheir sinensis</i>) Using Multi-Stable Isotopes and Explainable Machine Learning
Foods
Chinese mitten crab
origin traceability
stable isotopes
explainable machine learning
tissue specificity
title Origin Traceability of Chinese Mitten Crab (<i>Eriocheir sinensis</i>) Using Multi-Stable Isotopes and Explainable Machine Learning
title_full Origin Traceability of Chinese Mitten Crab (<i>Eriocheir sinensis</i>) Using Multi-Stable Isotopes and Explainable Machine Learning
title_fullStr Origin Traceability of Chinese Mitten Crab (<i>Eriocheir sinensis</i>) Using Multi-Stable Isotopes and Explainable Machine Learning
title_full_unstemmed Origin Traceability of Chinese Mitten Crab (<i>Eriocheir sinensis</i>) Using Multi-Stable Isotopes and Explainable Machine Learning
title_short Origin Traceability of Chinese Mitten Crab (<i>Eriocheir sinensis</i>) Using Multi-Stable Isotopes and Explainable Machine Learning
title_sort origin traceability of chinese mitten crab i eriocheir sinensis i using multi stable isotopes and explainable machine learning
topic Chinese mitten crab
origin traceability
stable isotopes
explainable machine learning
tissue specificity
url https://www.mdpi.com/2304-8158/14/14/2458
work_keys_str_mv AT danhewang origintraceabilityofchinesemittencrabieriocheirsinensisiusingmultistableisotopesandexplainablemachinelearning
AT chunxiayao origintraceabilityofchinesemittencrabieriocheirsinensisiusingmultistableisotopesandexplainablemachinelearning
AT yangyanglu origintraceabilityofchinesemittencrabieriocheirsinensisiusingmultistableisotopesandexplainablemachinelearning
AT dihuang origintraceabilityofchinesemittencrabieriocheirsinensisiusingmultistableisotopesandexplainablemachinelearning
AT yamengli origintraceabilityofchinesemittencrabieriocheirsinensisiusingmultistableisotopesandexplainablemachinelearning
AT xuganwu origintraceabilityofchinesemittencrabieriocheirsinensisiusingmultistableisotopesandexplainablemachinelearning
AT weiguosong origintraceabilityofchinesemittencrabieriocheirsinensisiusingmultistableisotopesandexplainablemachinelearning
AT qinxiongrao origintraceabilityofchinesemittencrabieriocheirsinensisiusingmultistableisotopesandexplainablemachinelearning