Skip to main content
SpringerLink
Log in

Prediction of Soil Organic Matter with Deep Learning

  • Research Article-computer Engineering and Computer Science
  • Published:
Arabian Journal for Science and Engineering Aims and scope Submit manuscript

Abstract

Soil is the most important component of the ecosystem and the most significant characteristic of soil is its organic matter content, because organic matter undertakes many tasks by preventing soil moisture, absorption of water after rainfall, and good aeration by correcting bad textural properties and preventing soil erosion. Therefore, its recognition is critical, but the biggest problem is that determining soil organic matter with traditional methods is very laborious, expensive, and time-consuming. Accordingly, as in many different areas, computer vision methods can be used to determine soil organic matter. In this study, a new method based on deep learning has been proposed for the estimation of soil organic matter. In the study, firstly, images of 20 points where soil organic matter content was determined were taken with a special system. Then, a new segmentation method was applied to these images to separate the soil from the background and datasets were created. A new convolutional neural network was designed for organic matter estimation in these original datasets. In organic matter estimation, there is a difference of 0.01% between the proposed model and the value obtained in laboratory analysis. The proposed model is also compared with state-of-the-art deep learning models such as GoogleNet, ResNet, and MobileNet. In comparison, it has been seen that the proposed model is very successful in predicting organic matter with fewer parameters and in a shorter time, although it gives lower results with a slight difference in accuracy rates.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21
Fig. 22
Fig. 23
Fig. 24
Fig. 25

Similar content being viewed by others

Code Availability

The code developed within the scope of this study was made with MATLAB programming language. The deep learning model is trained with MATLAB Deep Learning Toolbox in MATLAB R2021a. The codes in the study and the CNN model trained for SOM prediction have been published on the public GitHub platform. The codes of the study can be accessed from the link https://github.com/orhaninik/SOM-prediction.git.

References

  1. Bezdicek, D.F.; Papendick, R.I.; Lal, R.: Introduction: importance of soil quality to health and sustainable land management. Methods Assess. Soil. Qual. 49, 1–8 (1997)

    Google Scholar 

  2. Basso, B., et al.: A strategic and tactical management approach to select optimal N fertilizer rates for wheat in a spatially variable field. Eur. J. Agron. 35(4), 215–222 (2011)

    Article  Google Scholar 

  3. Weng, Z., et al.: Probing the nature of soil organic matter. Crit. Rev. Environ. Sci. Technol. 52(22), 4072–4093 (2022)

    Article  Google Scholar 

  4. Ibáñez-Asensio, S., et al.: Statistical relationships between soil colour and soil attributes in semiarid areas. Biosys. Eng. 116(2), 120–129 (2013)

    Article  Google Scholar 

  5. Han, P., et al.: A smartphone-based soil color sensor: for soil type classification. Comput. Electron. Agric. 123, 232–241 (2016)

    Article  Google Scholar 

  6. Budak, M., et al.: Sayısal renk parametrelerinden bazı fiziksel ve kimyasal toprak özelliklerinin belirlenmesi (2018)

  7. Gelder, B., et al.: Estimating soil organic carbon in Central Iowa using aerial imagery and soil surveys. Soil Sci. Soc. Am. J. 75(5), 1821–1828 (2011)

    Article  Google Scholar 

  8. Yakupoğlu, T.; Şişman, A.Ö.; Gündoğan, R.: Toprakların agregat stabilitesi değerlerinin yapay sinir ağları ile tahminlenmesi. Türkiye Tarımsal Araştırmalar Dergisi 2(2), 83–92 (2015)

    Article  Google Scholar 

  9. Lin, L.; Gao, Z.; Liu, X.: Estimation of soil total nitrogen using the synthetic color learning machine (SCLM) method and hyperspectral data. Geoderma 380, 114664 (2020)

    Article  Google Scholar 

  10. Gunal, H.; Erşahin, S.: Toprak özelliklerinin tahmininde sayısallaştırılmış renk parametrelerinin kullanımı. J. Agric. Sci. 12(01), 85–92 (2006)

    Google Scholar 

  11. Yang, J., et al.: Combination of convolutional neural networks and recurrent neural networks for predicting soil properties using Vis–NIR spectroscopy. Geoderma 380, 114616 (2020)

    Article  Google Scholar 

  12. Wadoux, A.M.-C.: Using deep learning for multivariate mapping of soil with quantified uncertainty. Geoderma 351, 59–70 (2019)

    Article  Google Scholar 

  13. Prasad, R., et al.: Soil moisture forecasting by a hybrid machine learning technique: ELM integrated with ensemble empirical mode decomposition. Geoderma 330, 136–161 (2018)

    Article  Google Scholar 

  14. Ng, W., et al.: Convolutional neural network for simultaneous prediction of several soil properties using visible/near-infrared, mid-infrared, and their combined spectra. Geoderma 352, 251–267 (2019)

    Article  Google Scholar 

  15. Bondi, G., et al.: Using machine learning to predict soil bulk density on the basis of visual parameters: tools for in-field and post-field evaluation. Geoderma 318, 137–147 (2018)

    Article  Google Scholar 

  16. Mancini, M., et al.: From sensor data to Munsell color system: machine learning algorithm applied to tropical soil color classification via Nix™ Pro sensor. Geoderma 375, 114471 (2020)

    Article  Google Scholar 

  17. Chen, D., et al.: Mapping dynamics of soil organic matter in croplands with MODIS data and machine learning algorithms. Sci. Total Environ. 669, 844–855 (2019)

    Article  Google Scholar 

  18. Swetha, R., et al.: Predicting soil texture from smartphone-captured digital images and an application. Geoderma 376, 114562 (2020)

    Article  Google Scholar 

  19. Taghizadeh-Mehrjardi, R., et al.: Multi-task convolutional neural networks outperformed random forest for mapping soil particle size fractions in central Iran. Geoderma 376, 114552 (2020)

    Article  Google Scholar 

  20. Fu, Y., et al.: Predicting soil organic matter from cellular phone images under varying soil moisture. Geoderma 361, 114020 (2020)

    Article  Google Scholar 

  21. Taneja, P., et al.: Multi-algorithm comparison to predict soil organic matter and soil moisture content from cell phone images. Geoderma 385, 114863 (2021)

    Article  Google Scholar 

  22. Behçet, L.; Yapar, Y.: Important plants at the Matan Mountain (Bingöl/Turkey) flora with regard to beekeeping. Biolog. Divers. Conserv. 12(1), 149–159 (2019)

    Article  Google Scholar 

  23. OGM, Murat Nehri Havzası Rehabilitasyon Projesi (MNHRP) Çapakçur Mikrohavza Planı, O.G.M. T.C. Tarım ve Orman Bakanlığı, Ankara, Editor. 2013–2021.

  24. Demiralay, İ: Toprak fiziksel analizleri. Atatürk Üniversitesi Ziraat Fakültesi Yayınları 143, 13–19 (1993)

    Google Scholar 

  25. Walkley, A.: A critical examination of a rapid method for determining organic carbon in soils—effect of variations in digestion conditions and of inorganic soil constituents. Soil Sci. 63(4), 251–264 (1947)

    Article  Google Scholar 

  26. Horneck, D.A., et al.: Methods of soil analysis used in the soil testing laboratory at Oregon State University (1989)

  27. Jackson, M.L.: Soil chemical analysis-advanced course. Soil Chemical Analysis-Advanced Course, 2nd edn., (1969)

  28. Allison, L., Moodie, C.: Carbonate. Methods of soil analysis: part 2 chemical and microbiological properties, 9: p. 1379–1396 (1965)

  29. Richards, L.A., Diagnosis and improvement of saline and alkali soils. Vol. 78. (1954) LWW

  30. Tinsley, J.: Soil science manual of experiments. University of Aberdeen, Aberdeen (1967)

    Google Scholar 

  31. ImageNet- Large Scale Visual Recognition Competition, Available online: https://www.image-net.org/challenges/LSVRC/2012/. LSVRC/(accessed on 14 November 2022), 2012.

  32. Bengio, Y.; Courville, A.; Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798–1828 (2013)

    Article  Google Scholar 

  33. Julia, D.L.f. devblogs.nvidia.com. 2016; Available from: https://devblogs.nvidia.com/parallelforall/mocha-jl-deep-learning-julia/.

  34. Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)

  35. He, K., et al.: Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)

  36. Shawahna, A., et al.: FxP-QNet: a post-training quantizer for the design of mixed low-precision DNNs with dynamic fixed-point representation. IEEE Access 10, 30202–30231 (2022)

    Article  Google Scholar 

  37. Shawahna, A.; Sait, S.M.; El-Maleh, A.: FPGA-based accelerators of deep learning networks for learning and classification: a review. IEEE Access 7, 7823–7859 (2018)

    Article  Google Scholar 

  38. Alakbari, F.S., et al.: Deep learning approach for robust prediction of reservoir bubble point pressure. ACS Omega 6(33), 21499–21513 (2021)

    Article  Google Scholar 

  39. İnik, O., et al., Soil Temperature Prediction with Long Short Term Memory (LSTM). Türk Tarım ve Doğa Bilimleri Dergisi. 9(3), 779–785.

  40. Inik, O., Seker, H.:. CnnSound: convolutional neural networks for the classification of environmental sounds. In: 2020 The 4th International Conference on Advances in Artificial Intelligence (2020)

  41. İnik, Ö.; Uyar, K.; Ülker, E.: Gender classification with a novel convolutional neural network (CNN) model and comparison with other machine learning and deep learning CNN models. J. Indus. Eng. Res. 4(4), 57–63 (2018)

    Google Scholar 

  42. İnik, Ö., et al.: A new method for automatic counting of ovarian follicles on whole slide histological images based on convolutional neural network. Comput. Biol. Med. 112, 103350 (2019)

    Article  Google Scholar 

  43. Du, G., et al.: Medical image segmentation based on u-net: a review. J. Imaging Sci. Technol. 64, 1–12 (2020)

    Article  Google Scholar 

  44. Pacal, I., et al.: An efficient real-time colonic polyp detection with YOLO algorithms trained by using negative samples and large datasets. Comput. Biol. Med. 141, 105031 (2022)

    Article  Google Scholar 

  45. Pacal, I.; Karaboga, D.: A robust real-time deep learning based automatic polyp detection system. Comput. Biol. Med. 134, 104519 (2021)

    Article  Google Scholar 

  46. Malakar, S., et al.: A GA based hierarchical feature selection approach for handwritten word recognition. Neural Comput. Appl. 32(7), 2533–2552 (2020)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Soil Science and Plant Nutrition, Bingöl University, Bingöl, Turkey

    Orhan İnik, Yasin Demir & Alaaddin Yüksel

  2. Department of Computer Engineering, Tokat Gaziosmanpasa University, Tokat, Turkey

    Özkan İnik

  3. Department of Soil Science and Plant Nutrition, Atatürk University, Erzurum, Turkey

    Taşkın Öztaş

Authors
  1. Orhan İnik
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Özkan İnik
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Taşkın Öztaş
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yasin Demir
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Alaaddin Yüksel
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Oİ was responsible for fieldwork, soil sample analysis, image acquisition, methodology, conceptualization, article writing, and references. Öİ was involved in conceptualization, methodology, image processing, software, validation, resources, data curation, and writing the original draft. TÖ contributed to basin selection, methodology, conceptualization, article writing, and references. YD took part in fieldwork, soil sample analysis, methodology, and conceptualization. AY participated in basin selection, methodology, conceptualization, and references.

Corresponding author

Correspondence to Orhan İnik.

Ethics declarations

Conflicts of interest

The authors have no conflicts of interest to declare that are relevant to the content of this article.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

İnik, O., İnik, Ö., Öztaş, T. et al. Prediction of Soil Organic Matter with Deep Learning. Arab J Sci Eng 48, 10227–10247 (2023). https://doi.org/10.1007/s13369-022-07575-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13369-022-07575-x

Keywords

Search

Navigation