An innovative approach for integrating two-dimensional conversion of Vis-NIR spectra with the Swin Transformer model to leverage deep learning for predicting soil properties

Beattie "Exploration of principal component analysis: deriving principal component analysis visually using spectra" Appl. Spectrosc. (2021) 10.1177/0003702820987847

[3]

Near‐Infrared Reflectance Spectroscopy–Principal Components Regression Analyses of Soil Properties

Cheng-Wen Chang, David A. Laird, Maurice J. Mausbach et al.

Soil Science Society of America Journal 2001 10.2136/sssaj2001.652480x

[4]

Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929.

[5]

Guo, C., Li, H., Pan, D., 2010. An improved piecewise aggregate approximation based on statistical features for time series mining. In Knowledge Science, Engineering and Management: 4th International Conference, KSEM 2010, Belfast, Northern Ireland, UK, September 1-3, 2010. Proceedings 4. Springer, pp. 234–244. 10.1007/978-3-642-15280-1_23

[6]

Han "Transformer in transformer" Adv. Neural Inf. Proces. Syst. (2021)

[7]

Deep Residual Learning for Image Recognition

Kaiming He, Xiangyu Zhang, Shaoqing Ren et al.

2016 IEEE Conference on Computer Vision and Patter... 10.1109/cvpr.2016.90

[8]

Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., Adam, H., 2017. Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861.

[9]

Jin "Classifying wheat hyperspectral pixels of healthy heads and Fusarium head blight disease using a deep neural network in the wild field" Remote Sens. (Basel) (2018) 10.3390/rs10030395

[10]

Keesstra "The significance of soils and soil science towards realization of the United Nations Sustainable Development Goals" Soil (2016) 10.5194/soil-2-111-2016

[11]

Transformers in Vision: A Survey

Salman Khan, Muzammal Naseer, Munawar Hayat et al.

ACM Computing Surveys 2022 10.1145/3505244

[12]

The concept and future prospects of soil health

Johannes Lehmann, Deborah A. Bossio, Ingrid Kögel-Knabner et al.

Nature Reviews Earth & Environment 2020 10.1038/s43017-020-0080-8

[13]

Liu "Transfer learning for soil spectroscopy based on convolutional neural networks and its application in soil clay content mapping using hyperspectral imagery" Sensors (2018) 10.3390/s18093169

[14]

Ndikumana "Deep recurrent neural network for agricultural classification using multitemporal SAR Sentinel-1 for Camargue, France" Remote Sens. (2018) 10.3390/rs10081217

[15]

Ng "Convolutional neural network for simultaneous prediction of several soil properties using visible/near-infrared, mid-infrared, and their combined spectra" Geoderma (2019) 10.1016/j.geoderma.2019.06.016

[16]

Nocita "Soil spectroscopy: an alternative to wet chemistry for soil monitoring" Adv. Agron. (2015) 10.1016/bs.agron.2015.02.002

[17]

Orgiazzi "LUCAS Soil, the largest expandable soil dataset for Europe: a review" Eur. J. Soil Sci. (2018) 10.1111/ejss.12499

[18]

Padarian "Using deep learning to predict soil properties from regional spectral data" Geoderma Reg. (2019) 10.1016/j.geodrs.2018.e00198

[19]

European Soil Data Centre: Response to European policy support and public data requirements

Panos Panagos, Marc Van Liedekerke, Arwyn Jones et al.

Land Use Policy 2012 10.1016/j.landusepol.2011.07.003

[20]

Soil Erosion, Climate Change and Global Food Security: Challenges and Strategies

Christopher J. Rhodes

Science Progress 2014 10.3184/003685014x13994567941465

[21]

Singh "Estimation of soil properties from the EU spectral library using long short-term memory networks" Geoderma Reg. (2019) 10.1016/j.geodrs.2019.e00233

[22]

How to measure, report and verify soil carbon change to realize the potential of soil carbon sequestration for atmospheric greenhouse gas removal

Pete Smith, Jean‐Francois Soussana, Denis Angers et al.

Global Change Biology 2020 10.1111/gcb.14815

[23]

Stenberg "Visible and near infrared spectroscopy in soil science" Adv. Agron. (2010) 10.1016/s0065-2113(10)07005-7

[24]

Stevens "Prediction of soil organic carbon at the European scale by visible and near infrared reflectance spectroscopy" PLoS One (2013) 10.1371/journal.pone.0066409

[25]

Tan "Efficientnet: rethinking model scaling for convolutional neural networks" International conference on machine learning. PMLR (2019)

[26]

Tavakoli "Predicting key soil properties from Vis-NIR spectra by applying dual-wavelength indices transformations and stacking machine learning approaches" Soil Tillage Res. (2023) 10.1016/j.still.2023.105684

[27]

Tian "Computer vision technology in agricultural automation—a review" Inform. Process. Agric. (2020)

[28]

Tsakiridis "Simultaneous prediction of soil properties from VNIR-SWIR spectra using a localized multi-channel 1-D convolutional neural network" Geoderma (2020) 10.1016/j.geoderma.2020.114208

[29]

Tsimpouris "Using autoencoders to compress soil VNIR–SWIR spectra for more robust prediction of soil properties" Geoderma (2021) 10.1016/j.geoderma.2021.114967

[30]

Veres, M., Lacey, G., Taylor, G.W., 2015. Deep learning architectures for soil property prediction. In 2015 12th Conference on Computer and Robot Vision. IEEE, pp. 8–15. 10.1109/crv.2015.15

[31]

Viscarra Rossel "A global spectral library to characterize the world's soil" Earth Sci. Rev. (2016) 10.1016/j.earscirev.2016.01.012

[32]

Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned

Elena Voita, David Talbot, Fedor Moiseev et al.

Proceedings of the 57th Annual Meeting of the Asso... 10.18653/v1/p19-1580

[33]

Wang (2015)

[34]

A Learning Algorithm for Continually Running Fully Recurrent Neural Networks

Ronald J. Williams, David Zipser

Neural Computation 1989 10.1162/neco.1989.1.2.270

[35]

Yang, Y., Jiao, L., Liu, X., Liu, F., Yang, S., Feng, Z., Tang, X., 2022. Transformers meet visual learning understanding: a comprehensive review. arXiv preprint arXiv:2203.12944.

[36]

Yang "Combination of convolutional neural networks and recurrent neural networks for predicting soil properties using Vis–NIR spectroscopy" Geoderma (2020) 10.1016/j.geoderma.2020.114616

[37]

Zhang "Transfer-learning-based Raman spectra identification" J. Raman Spectrosc. (2020) 10.1002/jrs.5750

[38]

Zhao "Attention-based CNN ensemble for soil organic carbon content estimation with spectral data" IEEE Geosci. Remote Sens. Lett. (2022)

Metrics

45

Citations

38

References

Details

Published: Aug 01, 2023
Vol/Issue: 436
Pages: 116555
License: View

Authors

X

Xiu Jin

College of Information and Artificial Intelligence; Anhui Agricultural University; Anhui Province Key Laboratory of Smart Agricultural Technology and Equipment; Anhui Agricultural University

Department of Hepatobiliary and Pancreatic Surgery, the Second Affiliated Hospital Zhejiang University School of Medicine Hangzhou Zhejiang China; Key Laboratory of Precision Diagnosis and Treatment for Hepatobiliary and Pancreatic Tumor of Zhejiang Province Hangzhou Zhejiang China; Research Center of Diagnosis and Treatment Technology for Hepatocellular Carcinoma of Zhejiang Province Hangzhou Zhejiang China; National Innovation Center for Fundamental Research on Cancer Medicine Hangzhou Zhejiang China; Cancer Center Zhejiang University Hangzhou Zhejiang China

T

Tong Zhang

Laboratoire de Biochimie Théorique, Institut de Biologie Physico-Chimique (IBPC), UPR9080 CNRS, Université Paris Diderot, Sorbonne Paris Cité, 13 rue Pierre et Marie Curie, 75005 Paris, France; School of Biological Sciences, Nanyang Technological University, 60 Nanyang Drive, 637551 Singapore

Cite This Article

Xiu Jin, Jun Zhou, Yuan Rao, et al. (2023). An innovative approach for integrating two-dimensional conversion of Vis-NIR spectra with the Swin Transformer model to leverage deep learning for predicting soil properties. Geoderma, 436, 116555. https://doi.org/10.1016/j.geoderma.2023.116555

An innovative approach for integrating two-dimensional conversion of Vis-NIR spectra with the Swin Transformer model to leverage deep learning for predicting soil properties

You May Also Like