中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 合肥物质科学研究院
  3. 中国科学院合肥物质科学研究院
Using convolutional neural network combined with multi-scale channel attention module to predict soil properties from visible and near-infrared spectral data

文献类型：期刊论文

作者Tang, Ke1,3; Zhao, Xing4; Qin, Min2; Xu, Zong1,3; Sun, Huojiao1,3; Wu, Yuebo1,3
刊名MICROCHEMICAL JOURNAL
出版日期2024-12-01
卷号207
关键词Soil properties Infrared spectroscopy Convolutional neural network Channel attention
ISSN号0026-265X
DOI10.1016/j.microc.2024.111815
通讯作者Tang, Ke(tk1001@mail.ustc.edu.cn) ; Qin, Min(mqin@aiofm.ac.cn)
英文摘要With the increasing demand for precision agriculture and sustainable land management, it is crucial to quickly and accurately predict soil properties. However, there are still challenges in predicting large-scale soil properties. This study proposes a new convolutional neural network architecture (MCA-CNN) combined with visible and near-infrared spectroscopy for predicting soil properties. The architecture introduces a multi-scale channel attention mechanism, aiming to more effectively capture complex features in the spectrum. The performance of the MCA-CNN model was tested on a large-scale dataset and compared with partial least squares (PLS), extreme gradient boosting tree (XGBoost), and conventional convolutional neural network (CNN) models. The predictive performance of different models in organic carbon (OC), nitrogen (N), pH, Clay, Salt, and Sand was analyzed. The results showed that the MCA-CNN model had the best predictive performance on all soil properties, achieving the lowest root mean square error (RMSE) and the highest coefficient of determination (R2), R 2 ), the R 2 of OC, N, pH, Clay, Silt, and Sand are 0.95, 0.93, 0.95, 0.80, 0.58, 0.64, respectively. The RMSE of OC, N, pH, Clay, Silt, and Sand are 16.60 g kg- 1 , 0.96 g kg- 1 , 0.31, 4.89 %, 8.27 %, and 11.61 %, respectively. Further research has found that soil types (mineral soil and organic soil) affect the predictive performance of OC. It is necessary to distinguish between mineral soil and organic soil when predicting soil OC content. In addition, the effectiveness of the model transfer strategy was explored for situations with small soil sample sizes. By fine-tuning the pre-trained model, the performance of the model can be significantly improved, which provides a feasible solution for predicting soil properties in situations of data scarcity. In summary, this study not only confirms the potential application of deep learning in the field of soil science, but also provides new technological avenues for future soil management and agricultural practices.
WOS关键词ORGANIC-CARBON ; MATTER ; PH
资助项目Natural Science Foundation of Anhui Province[2208085QD104] ; National Natural Science Foundation of China[U21A2028] ; Natural Science Research Key Project of the Education Department of Anhui Province, China[2023AH052646] ; Natural Science Research Key Project of the Education Department of Anhui Province, China[2023AH030112] ; West Anhui University[WGKQ2021044] ; West Anhui University[WGKQ2021043] ; West Anhui University[WGKQ2021046] ; West Anhui University[WGKQ2021050]
WOS研究方向Chemistry
语种英语
WOS记录号WOS:001333939500001
出版者ELSEVIER
资助机构Natural Science Foundation of Anhui Province ; National Natural Science Foundation of China ; Natural Science Research Key Project of the Education Department of Anhui Province, China ; West Anhui University
源URL[http://ir.hfcas.ac.cn:8080/handle/334002/134639]  
专题中国科学院合肥物质科学研究院
通讯作者Tang, Ke; Qin, Min
作者单位1.West Anhui Univ, Anhui Undergrowth Crop Intelligent Equipment Engn, Luan 237012, Peoples R China
2.Chinese Acad Sci, Anhui Inst Opt & Fine Mech, Key Lab Environm Opt & Technol, Hefei 230031, Peoples R China
3.West Anhui Univ, Sch Elect & Photoelect Engn, Luan 237012, Peoples R China
4.Cent South Univ, Big Data Inst, Changsha 410083, Peoples R China
推荐引用方式
GB/T 7714		 Tang, Ke,Zhao, Xing,Qin, Min,et al. Using convolutional neural network combined with multi-scale channel attention module to predict soil properties from visible and near-infrared spectral data[J]. MICROCHEMICAL JOURNAL,2024,207.
APA Tang, Ke,Zhao, Xing,Qin, Min,Xu, Zong,Sun, Huojiao,&Wu, Yuebo.(2024).Using convolutional neural network combined with multi-scale channel attention module to predict soil properties from visible and near-infrared spectral data.MICROCHEMICAL JOURNAL,207.
MLA Tang, Ke,et al."Using convolutional neural network combined with multi-scale channel attention module to predict soil properties from visible and near-infrared spectral data".MICROCHEMICAL JOURNAL 207(2024).

入库方式： OAI收割

来源：合肥物质科学研究院

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。