The fusion of machine olfactory data and UV–Vis-NIR-MIR spectra enabled accurate prediction of key soil nutrients

Conventional approaches for evaluating soil nutrients typically involved lengthy and resource-intensive analytical procedures, rendering them inadequate for large-scale and high-throughput testing. To address these limitations, this study proposed an innovative solution based on sensor data fusion t...

Full description

Saved in:
Bibliographic Details
Main Authors: Shuyan Liu, Lili Fu, Xiaomeng Xia, Jiamu Wang, Yvhang Cao, Xinming Jiang, Honglei Jia, Zengming Feng, Dongyan Huang
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Geoderma
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S0016706124003902
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846091662156103680
author Shuyan Liu
Lili Fu
Xiaomeng Xia
Jiamu Wang
Yvhang Cao
Xinming Jiang
Honglei Jia
Zengming Feng
Dongyan Huang
author_facet Shuyan Liu
Lili Fu
Xiaomeng Xia
Jiamu Wang
Yvhang Cao
Xinming Jiang
Honglei Jia
Zengming Feng
Dongyan Huang
author_sort Shuyan Liu
collection DOAJ
description Conventional approaches for evaluating soil nutrients typically involved lengthy and resource-intensive analytical procedures, rendering them inadequate for large-scale and high-throughput testing. To address these limitations, this study proposed an innovative solution based on sensor data fusion to predict the content of key soil nutrients. The proposed methodology entailed collecting olfactory data after soil pyrolysis using gas sensors and spectral data from soil samples utilizing ultraviolet–visible-near infrared (UV–Vis-NIR) and mid-infrared (MIR) techniques. Three fusion strategies including series and parallel modes were designed to effectively amalgamate the gathered data and supplemented with machine learning algorithms to predict the content of key soil nutrients. Tested a testing set consisting of 33 soil samples. The findings demonstrated that introducing a self-attention procedure into the series splicing fusion strategy significantly improved the predictive performance. This highlights the synergistic benefits of integrating information from olfactory and spectral data sources. Predicting multiple nutrient contents within the framework of the multi-layer perceptron combined with random forest (MLP-RF) fusion model showed superior performance, with the coefficient of determination (R2) ranging from 0.80 to 0.96. The predictive validity for the content of fundamental nutrients and available nutrients in the soil can benefit from the combination of biological and structural information captured by olfactory data and chemical information provided by spectroscopy.
format Article
id doaj-art-7fcd16d405e74c158a7e07f4ba8a1e10
institution Kabale University
issn 1872-6259
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Geoderma
spelling doaj-art-7fcd16d405e74c158a7e07f4ba8a1e102025-01-10T04:36:49ZengElsevierGeoderma1872-62592025-01-01453117161The fusion of machine olfactory data and UV–Vis-NIR-MIR spectra enabled accurate prediction of key soil nutrientsShuyan Liu0Lili Fu1Xiaomeng Xia2Jiamu Wang3Yvhang Cao4Xinming Jiang5Honglei Jia6Zengming Feng7Dongyan Huang8Key Laboratory of Bionics Engineering, Ministry of Education, Jilin University, Changchun 130022, China; College of Biological and Agricultural Engineering, Jilin University, Changchun 130022, ChinaKey Laboratory of Bionics Engineering, Ministry of Education, Jilin University, Changchun 130022, China; College of Biological and Agricultural Engineering, Jilin University, Changchun 130022, ChinaKey Laboratory of Bionics Engineering, Ministry of Education, Jilin University, Changchun 130022, China; College of Biological and Agricultural Engineering, Jilin University, Changchun 130022, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Engineering and Technology, Jilin Agricultural University, Changchun 130118, ChinaKey Laboratory of Bionics Engineering, Ministry of Education, Jilin University, Changchun 130022, China; College of Biological and Agricultural Engineering, Jilin University, Changchun 130022, ChinaCollege of Engineering and Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Engineering and Technology, Jilin Agricultural University, Changchun 130118, China; Corresponding author.Conventional approaches for evaluating soil nutrients typically involved lengthy and resource-intensive analytical procedures, rendering them inadequate for large-scale and high-throughput testing. To address these limitations, this study proposed an innovative solution based on sensor data fusion to predict the content of key soil nutrients. The proposed methodology entailed collecting olfactory data after soil pyrolysis using gas sensors and spectral data from soil samples utilizing ultraviolet–visible-near infrared (UV–Vis-NIR) and mid-infrared (MIR) techniques. Three fusion strategies including series and parallel modes were designed to effectively amalgamate the gathered data and supplemented with machine learning algorithms to predict the content of key soil nutrients. Tested a testing set consisting of 33 soil samples. The findings demonstrated that introducing a self-attention procedure into the series splicing fusion strategy significantly improved the predictive performance. This highlights the synergistic benefits of integrating information from olfactory and spectral data sources. Predicting multiple nutrient contents within the framework of the multi-layer perceptron combined with random forest (MLP-RF) fusion model showed superior performance, with the coefficient of determination (R2) ranging from 0.80 to 0.96. The predictive validity for the content of fundamental nutrients and available nutrients in the soil can benefit from the combination of biological and structural information captured by olfactory data and chemical information provided by spectroscopy.http://www.sciencedirect.com/science/article/pii/S0016706124003902Soil nutrient contentMulti-source dataFusion strategyMachine learning
spellingShingle Shuyan Liu
Lili Fu
Xiaomeng Xia
Jiamu Wang
Yvhang Cao
Xinming Jiang
Honglei Jia
Zengming Feng
Dongyan Huang
The fusion of machine olfactory data and UV–Vis-NIR-MIR spectra enabled accurate prediction of key soil nutrients
Geoderma
Soil nutrient content
Multi-source data
Fusion strategy
Machine learning
title The fusion of machine olfactory data and UV–Vis-NIR-MIR spectra enabled accurate prediction of key soil nutrients
title_full The fusion of machine olfactory data and UV–Vis-NIR-MIR spectra enabled accurate prediction of key soil nutrients
title_fullStr The fusion of machine olfactory data and UV–Vis-NIR-MIR spectra enabled accurate prediction of key soil nutrients
title_full_unstemmed The fusion of machine olfactory data and UV–Vis-NIR-MIR spectra enabled accurate prediction of key soil nutrients
title_short The fusion of machine olfactory data and UV–Vis-NIR-MIR spectra enabled accurate prediction of key soil nutrients
title_sort fusion of machine olfactory data and uv vis nir mir spectra enabled accurate prediction of key soil nutrients
topic Soil nutrient content
Multi-source data
Fusion strategy
Machine learning
url http://www.sciencedirect.com/science/article/pii/S0016706124003902
work_keys_str_mv AT shuyanliu thefusionofmachineolfactorydataanduvvisnirmirspectraenabledaccuratepredictionofkeysoilnutrients
AT lilifu thefusionofmachineolfactorydataanduvvisnirmirspectraenabledaccuratepredictionofkeysoilnutrients
AT xiaomengxia thefusionofmachineolfactorydataanduvvisnirmirspectraenabledaccuratepredictionofkeysoilnutrients
AT jiamuwang thefusionofmachineolfactorydataanduvvisnirmirspectraenabledaccuratepredictionofkeysoilnutrients
AT yvhangcao thefusionofmachineolfactorydataanduvvisnirmirspectraenabledaccuratepredictionofkeysoilnutrients
AT xinmingjiang thefusionofmachineolfactorydataanduvvisnirmirspectraenabledaccuratepredictionofkeysoilnutrients
AT hongleijia thefusionofmachineolfactorydataanduvvisnirmirspectraenabledaccuratepredictionofkeysoilnutrients
AT zengmingfeng thefusionofmachineolfactorydataanduvvisnirmirspectraenabledaccuratepredictionofkeysoilnutrients
AT dongyanhuang thefusionofmachineolfactorydataanduvvisnirmirspectraenabledaccuratepredictionofkeysoilnutrients
AT shuyanliu fusionofmachineolfactorydataanduvvisnirmirspectraenabledaccuratepredictionofkeysoilnutrients
AT lilifu fusionofmachineolfactorydataanduvvisnirmirspectraenabledaccuratepredictionofkeysoilnutrients
AT xiaomengxia fusionofmachineolfactorydataanduvvisnirmirspectraenabledaccuratepredictionofkeysoilnutrients
AT jiamuwang fusionofmachineolfactorydataanduvvisnirmirspectraenabledaccuratepredictionofkeysoilnutrients
AT yvhangcao fusionofmachineolfactorydataanduvvisnirmirspectraenabledaccuratepredictionofkeysoilnutrients
AT xinmingjiang fusionofmachineolfactorydataanduvvisnirmirspectraenabledaccuratepredictionofkeysoilnutrients
AT hongleijia fusionofmachineolfactorydataanduvvisnirmirspectraenabledaccuratepredictionofkeysoilnutrients
AT zengmingfeng fusionofmachineolfactorydataanduvvisnirmirspectraenabledaccuratepredictionofkeysoilnutrients
AT dongyanhuang fusionofmachineolfactorydataanduvvisnirmirspectraenabledaccuratepredictionofkeysoilnutrients