Soil & Water Res., 2023, 18(3):158-168 | DOI: 10.17221/133/2022-SWR

Strategies and methods for predicting soil organic matter at the field scale based on the provincial near infrared spectral databaseOriginal Paper

Shengyao Jia1,2, Chunbo Hong1,2, Hongyang Li1,2*, Yuchan Li1,2, Siyuan Hu3
1 College of Mechanical and Electrical Engineering, China Jiliang University, Hangzhou, P.R. China
2 Key Laboratory of Intelligent Manufacturing Quality Big Data Tracing and Analysis of Zhejiang Province, China Jiliang University, Hangzhou, P.R. China
3 Zhejiang Provincial Emergency Management Science Research Institute, Hangzhou, P.R. China

The development and provision of soil spectral library (SSL) could facilitate the application of near infrared (NIR) spectroscopy for economical, accurate, and efficient determination of soil organic matter (SOM). In this work, the performances of partial least squares regression (PLSR) and convolutional neural network (CNN) combined with the datasets of Zhejiang provincial SSL (ZSSL) and the feature subset (FS) were compared for the prediction of SOM at the target field. The FS dataset was chosen from ZSSL based on similarity to the spectral characteristics of the target samples. The results showed that compared with modelling using ZSSL, modelling using FS can greatly improve the prediction accuracy of the PLSR model, but the impact on the performance of the CNN model was limited. The method of mean squared Euclidean distance (MSD) was an effective way for determining the optimal spiking sample size for the PLSR model only using the spectral data of the spiking subset and the prediction set. The PLSR model combined with the FS dataset and the spiking subset determined by MSD achieved the optimal prediction results among all developed models, which is an accurate and easy-to-implement solution for the SOM determination based on ZSSL.

Keywords: convolutional neural network; soil organic content; soil spectral library; spiking sample size; strategy

Received: September 23, 2022; Accepted: June 14, 2023; Prepublished online: June 29, 2023; Published: August 31, 2023  Show citation

ACS AIP APA ASA Harvard Chicago Chicago Notes IEEE ISO690 MLA NLM Turabian Vancouver
Jia S, Hong C, Li H, Li Y, Hu S. Strategies and methods for predicting soil organic matter at the field scale based on the provincial near infrared spectral database. Soil & Water Res. 2023;18(3):158-168. doi: 10.17221/133/2022-SWR.
Share...
Download citation
  • BibTeX (.bib)
  • Bookends (.ris)
  • EasyBib (.ris)
  • EndNote (.enw)
  • EndNote 8 (.xml)
  • ISI WoS (.isi)
  • Medlars (.medlars)
  • Mendeley (.ris)
  • MODS (.xml)
  • Papers (.ris)
  • RefWorks (.txt)
  • RefManager (.ris)
  • RIS (.ris)
  • MS Word (.xml)
  • Zotero (.ris)
    • Open full article

    References

    1. Araújo S.R., Wetterlind J., Demattê J.A.M., Stenberg B. (2014): Improving the prediction performance of a large tropical vis-NIR spectroscopic soil library from Brazil by clustering into smaller subsets or use of data mining calibration techniques. European Journal of Soil Science, 65: 718-729. Go to original source...
    2. Davari M., Karimi S.A., Bahrami H.A., Hossaini S.M.T., Fahmideh S. (2021): Simultaneous prediction of several soil properties related to engineering uses based on laboratory Vis-NIR reflectance spectroscopy. Catena, 179: 104987. Go to original source...
    3. Gogé F., Gomez C., Jolivet C., Joffre R. (2014): Which strategy is best to predict soil properties of a local site from a national Vis-NIR database? Geoderma, 213: 1-9. Go to original source...
    4. Guerrero C., Wetterlind J., Stenberg B., Mouazen A.M., Gabarron-Galeote M.A., Ruiz-Sinoga J.D., Zornoza R., Rossel R.A.V. (2016): Do we really need large spectral libraries for local scale SOC assessment with NIR spectroscopy? Soil & Tillage Research, 155: 501-509. Go to original source...
    5. Havens T.C., Bezdek J.C., Leckie C., Hall L.O., Palaniswami M. (2012): Fuzzy c-means algorithms for very large data. IEEE Transactions on Fuzzy Systems, 20: 1130-1146. Go to original source...
    6. Hong R.C., Liu D.Q., Mo X.Y., He X.N., Zhang H.W. (2022): Learning to compose and reason with language tree structures for visual grounding. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44: 684-696. Go to original source... Go to PubMed...
    7. Hong Y., Chen Y., Zhang Y., Liu Y., Liu Y., Yu L., Liu Y., Cheng H. (2018): Transferability of Vis-NIR models for soil organic carbon estimation between two study areas by using spiking. Soil Science Society of America Journal, 82: 1231-1242. Go to original source...
    8. Jia S., Li H., Wang Y., Tong R., Li Q. (2016): Recursive variable selection to update near-infrared spectroscopy model for the determination of soil nitrogen and organic carbon. Geoderma, 268: 92-99. Go to original source...
    9. Jiang Q.H., Li Q.X., Wang X.G., Wu Y., Yang X.L., Liu F. (2017): Estimation of soil organic carbon and total nitrogen in different soil layers using VNIR spectroscopy: Effects of spiking on model applicability. Geoderma, 293: 54-63. Go to original source...
    10. Kennard R.W., Stone L.A. (1969): Computer aided design of experiments. Technometrics, 11: 137-148. Go to original source...
    11. Knadel M., Gislum R., Hermansen C., Peng Y., Moldrup P., de Jonge L.W., Greve M.H. (2017): Comparing predictive ability of laser-induced breakdown spectroscopy to visible near-infrared spectroscopy for soil property determination. Biosystems Engineering, 156: 157-172. Go to original source...
    12. Li H., Jia S., Le Z. (2020): Prediction of soil organic carbon in a new target area by near-infrared spectroscopy: Comparison of the effects of spiking in different scale soil spectral libraries. Sensors, 20: 4357. Go to original source... Go to PubMed...
    13. Li H., Li Y., Yang M., Chen S., Shi Z. (2022): Strategies for efficient estimation of soil organic content at the local scale based on a national spectral database. Land Degradation & Development, 33: 1649-1661. Go to original source...
    14. McKay M.D., Beckman R.J., Conover W.J. (1979): A comparison of three methods for selecting values of input variables in the analysis of output from a computer code. Technometrics, 21: 239-245. Go to original source...
    15. Munnaf M.A., Guerrero A., Nawar S., Haesaert G., Van Meirvenne M., Mouazen A.M. (2021): A combined data mining approach for on-line prediction of key soil quality indicators by Vis-NIR spectroscopy. Soil & Tillage Research, 205: 104808. Go to original source...
    16. Mustaqeem, Kwon S. (2021): Att-Net: Enhanced emotion recognition system using lightweight self-attention module. Applied Soft Computing, 102: 107101. Go to original source...
    17. Nawar S., Mouazen A.M. (2017): Predictive performance of mobile vis-near infrared spectroscopy for key soil properties at different geographical scales by using spiking and data mining techniques. Catena, 151: 118-129. Go to original source...
    18. Ng W., Minasny B., Mendes W.D., Dematt J.A.M. (2020): The influence of training sample size on the accuracy of deep learning models for the prediction of soil properties with near-infrared spectroscopy data. Soil, 6: 565-578. Go to original source...
    19. Padarian J., Minasny B., McBratney A.B. (2019): Using deep learning to predict soil properties from regional spectral data. Geoderma Regional, 16: e00198. Go to original source...
    20. Ramirez-Lopez L., Schmidt K., Behrens T., van Wesemael B., Dematte J.A.M., Scholten T. (2014): Sampling optimal calibration sets in soil infrared spectroscopy. Geoderma, 226: 140-150. Go to original source...
    21. Seidel M., Hutengs C., Ludwig B., Thiele-Bruhn S., Vohland M. (2019): Strategies for the efficient estimation of soil organic carbon at the field scale with vis-NIR spectroscopy: Spectral libraries and spiking vs. local calibrations. Geoderma, 354: 113856. Go to original source...
    22. Shi Z., Wang Q., Peng J., Ji W., Liu H., Li X., Rossel R.A.V. (2014): Development of a national VNIR soil-spectral library for soil classification and prediction of organic matter concentrations. Science China-Earth Sciences, 57: 1671-1680. Go to original source...
    23. Tsakiridis N.L., Tziolas N.V., Theocharis J.B., Zalidis G.C. (2019): A genetic algorithm-based stacking algorithm for predicting soil organic matter from vis-NIR spectral data. European Journal of Soil Science, 70: 578-590. Go to original source...
    24. Tsakiridis N.L., Keramaris K.D., Theocharis J.B., Zalidis G.C. (2020): Simultaneous prediction of soil properties from VNIR-SWIR spectra using a localized multi-channel 1-D convolutional neural network. Geoderma, 367: 114208. Go to original source...
    25. Viscarra Rossel R.A., Behrens T. (2010): Using data mining to model and interpret soil diffuse reflectance spectra. Geoderma, 158: 46-54. Go to original source...
    26. Vohland M., Emmerling C. (2011): Determination of total soil organic C and hot water-extractable C from VIS-NIR soil reflectance with partial least squares regression and spectral feature selection techniques. European Journal of Soil Science, 62: 598-606. Go to original source...
    27. Wang W.L., Ma X.H., Leng L.C., Wang Y.J., Liu B.D., Sun J.F. (2022): A Hybrid CNN based on global reasoning for hyperspectral image classification. IEEE Geoscience and Remote Sensing Letters, 19: 6012605. Go to original source...
    28. Yang J.C., Wang X.L., Wang R.H., Wang H.J. (2020): Combination of convolutional neural networks and recurrent neural networks for predicting soil properties using Vis-NIR spectroscopy. Geoderma, 380: 114616. Go to original source...

    This is an open access article distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International (CC BY NC 4.0), which permits non-comercial use, distribution, and reproduction in any medium, provided the original publication is properly cited. No use, distribution or reproduction is permitted which does not comply with these terms.


    Return to the content