Explainable Deep Learning to Predict Kelp Geographical Origin from Volatile Organic Compound Analysis

In addition to its flavor and nutritional value, the origin of kelp has become a crucial factor influencing consumer choices. Nevertheless, research on kelp’s origin traceability by volatile organic compound (VOC) analysis is lacking, and the application of deep learning in this field remains scarce...

Full description

Saved in:
Bibliographic Details
Main Authors: Xuming Kang, Zhijun Tan, Yanfang Zhao, Lin Yao, Xiaofeng Sheng, Yingying Guo
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Foods
Subjects:
Online Access:https://www.mdpi.com/2304-8158/14/7/1269
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850188117798027264
author Xuming Kang
Zhijun Tan
Yanfang Zhao
Lin Yao
Xiaofeng Sheng
Yingying Guo
author_facet Xuming Kang
Zhijun Tan
Yanfang Zhao
Lin Yao
Xiaofeng Sheng
Yingying Guo
author_sort Xuming Kang
collection DOAJ
description In addition to its flavor and nutritional value, the origin of kelp has become a crucial factor influencing consumer choices. Nevertheless, research on kelp’s origin traceability by volatile organic compound (VOC) analysis is lacking, and the application of deep learning in this field remains scarce due to its black-box nature. To address this gap, we attempted to identify the origin of kelp by analyzing its VOCs in conjunction with explainable deep learning. In this work, we identified 115 distinct VOCs in kelp samples using gas chromatography coupled with ion mobility spectroscopy (GC-IMS), of which 68 categories were discernible. Consequently, we developed a comprehensible one-dimensional convolutional neural network (1D-CNN) model that incorporated 107 VOCs exhibiting significant regional disparities (<i>p</i> < 0.05). The model successfully discerns the origin of kelp, achieving perfect metrics across accuracy (100%), precision (100%), recall (100%), F1 score (100%), and AUC (1.0). SHapley Additive exPlanations (SHAP) analysis highlighted the impact of features such as 1-Octen-3-ol-M, (+)-limonene, allyl sulfide-D, 1-hydroxy-2-propanone-D, and (<i>E</i>)-2-hexen-1-al-M on the model output. This research provides deeper insights into how critical product features correlate with specific geographic information, which in turn boosts consumer trust and promotes practical utilization in actual settings.
format Article
id doaj-art-d3ad60b0ec134228934d8849dedd70d0
institution OA Journals
issn 2304-8158
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Foods
spelling doaj-art-d3ad60b0ec134228934d8849dedd70d02025-08-20T02:15:58ZengMDPI AGFoods2304-81582025-04-01147126910.3390/foods14071269Explainable Deep Learning to Predict Kelp Geographical Origin from Volatile Organic Compound AnalysisXuming Kang0Zhijun Tan1Yanfang Zhao2Lin Yao3Xiaofeng Sheng4Yingying Guo5Key Laboratory of Testing and Evaluation for Aquatic Product Safety and Quality, Ministry of Agriculture and Rural Affairs, Yellow Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences, Qingdao 266071, ChinaKey Laboratory of Testing and Evaluation for Aquatic Product Safety and Quality, Ministry of Agriculture and Rural Affairs, Yellow Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences, Qingdao 266071, ChinaKey Laboratory of Testing and Evaluation for Aquatic Product Safety and Quality, Ministry of Agriculture and Rural Affairs, Yellow Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences, Qingdao 266071, ChinaKey Laboratory of Testing and Evaluation for Aquatic Product Safety and Quality, Ministry of Agriculture and Rural Affairs, Yellow Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences, Qingdao 266071, ChinaKey Laboratory of Testing and Evaluation for Aquatic Product Safety and Quality, Ministry of Agriculture and Rural Affairs, Yellow Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences, Qingdao 266071, ChinaKey Laboratory of Testing and Evaluation for Aquatic Product Safety and Quality, Ministry of Agriculture and Rural Affairs, Yellow Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences, Qingdao 266071, ChinaIn addition to its flavor and nutritional value, the origin of kelp has become a crucial factor influencing consumer choices. Nevertheless, research on kelp’s origin traceability by volatile organic compound (VOC) analysis is lacking, and the application of deep learning in this field remains scarce due to its black-box nature. To address this gap, we attempted to identify the origin of kelp by analyzing its VOCs in conjunction with explainable deep learning. In this work, we identified 115 distinct VOCs in kelp samples using gas chromatography coupled with ion mobility spectroscopy (GC-IMS), of which 68 categories were discernible. Consequently, we developed a comprehensible one-dimensional convolutional neural network (1D-CNN) model that incorporated 107 VOCs exhibiting significant regional disparities (<i>p</i> < 0.05). The model successfully discerns the origin of kelp, achieving perfect metrics across accuracy (100%), precision (100%), recall (100%), F1 score (100%), and AUC (1.0). SHapley Additive exPlanations (SHAP) analysis highlighted the impact of features such as 1-Octen-3-ol-M, (+)-limonene, allyl sulfide-D, 1-hydroxy-2-propanone-D, and (<i>E</i>)-2-hexen-1-al-M on the model output. This research provides deeper insights into how critical product features correlate with specific geographic information, which in turn boosts consumer trust and promotes practical utilization in actual settings.https://www.mdpi.com/2304-8158/14/7/1269kelpvolatile organic compoundsexplainable deep learningSHAPgeographical origin
spellingShingle Xuming Kang
Zhijun Tan
Yanfang Zhao
Lin Yao
Xiaofeng Sheng
Yingying Guo
Explainable Deep Learning to Predict Kelp Geographical Origin from Volatile Organic Compound Analysis
Foods
kelp
volatile organic compounds
explainable deep learning
SHAP
geographical origin
title Explainable Deep Learning to Predict Kelp Geographical Origin from Volatile Organic Compound Analysis
title_full Explainable Deep Learning to Predict Kelp Geographical Origin from Volatile Organic Compound Analysis
title_fullStr Explainable Deep Learning to Predict Kelp Geographical Origin from Volatile Organic Compound Analysis
title_full_unstemmed Explainable Deep Learning to Predict Kelp Geographical Origin from Volatile Organic Compound Analysis
title_short Explainable Deep Learning to Predict Kelp Geographical Origin from Volatile Organic Compound Analysis
title_sort explainable deep learning to predict kelp geographical origin from volatile organic compound analysis
topic kelp
volatile organic compounds
explainable deep learning
SHAP
geographical origin
url https://www.mdpi.com/2304-8158/14/7/1269
work_keys_str_mv AT xumingkang explainabledeeplearningtopredictkelpgeographicaloriginfromvolatileorganiccompoundanalysis
AT zhijuntan explainabledeeplearningtopredictkelpgeographicaloriginfromvolatileorganiccompoundanalysis
AT yanfangzhao explainabledeeplearningtopredictkelpgeographicaloriginfromvolatileorganiccompoundanalysis
AT linyao explainabledeeplearningtopredictkelpgeographicaloriginfromvolatileorganiccompoundanalysis
AT xiaofengsheng explainabledeeplearningtopredictkelpgeographicaloriginfromvolatileorganiccompoundanalysis
AT yingyingguo explainabledeeplearningtopredictkelpgeographicaloriginfromvolatileorganiccompoundanalysis