• P-ISSN 0974-6846 E-ISSN 0974-5645

Indian Journal of Science and Technology


Indian Journal of Science and Technology

Year: 2021, Volume: 14, Issue: 3, Pages: 190-196

Original Article

Convolutional Neural Network approach for the prediction of Soil texture properties

Received Date:13 November 2020, Accepted Date:01 December 2021, Published Date:25 January 2021


Background/Objectives: The main objective is to achieve improved performance of soil properties prediction for hyperspectral data. In this work, convolutional neural network is trained to understand the pattern of hyperspectral data by spatial interpolation. Methods/Statistical analysis: The proposed methodology is used to predict six soil properties- Organic Carbon content (OC), Cation Exchange Capacity (CEC), Nitrogen Content (N), pH level in water, Clay particle and Sand Particle. Soil texture which defines the relative content of soil particles is determined by the percentage of clay, sand and silt in the soil. The input to the Convolutional Neural Network (CNN) is the Hyperspectral data in the form of multiple arrays. The statistical evaluation of model performance is evaluated using root-mean-square error and r square. Findings: In this research, deep learning approach is used to capture the pattern hidden in the soil. Deep learning is a kind of neural network which can model complex relationship for representing non-linearity for a scalable data. The main challenge is predicting a soil type, as it involves complex structural characteristics and soil features. Novelty/Improvements: The performance of soil texture prediction is improved by automatic feature learning capability in the proposed CNN model. The average rmse value obtained in proposed method for all the six soil texture properties is 5.68%.

Keywords: Soil texture; convolutional neural network; hyperspectral data; deep learning


  1. Barman U, Choudhury RD, Talukdar N, Deka P, Kalita I, Rahman N. Predication of soil pH using HSI colour image processing and regression over Guwahati, Assam, India. Journal of Applied and Natural Science. 2018;10(2):805–809. Available from: https://dx.doi.org/10.31018/jans.v10i2.1701
  2. Morais PAO, Souza DMD, Carvalho MTM, Madari BE, Oliveira AE. Predicting soil texture using image analysis. Microchemical Journal. 2019;146:455–463. Available from: https://doi.org/10.1016/j.microc.2019.01.009
  3. O’Shealand K, Nash R. An Introduction to Convolutional Neural Networks. Ceredigion, UK. Aberystwyth University . 2014.
  4. Benuwa BB, Zhan Y, Ghansah B. Dickson Keddy Wornyo and Frank Banaseka Kataka. A Review of Deep Machine Learning. International Journal of Engineering Research in Africa. 2016;24:124–136. Available from: https://doi.org/10.4028/www.scientific.net/JERA.24.124
  5. Schmidhuber J. Deep learning in neural networks: An overview. Neural Networks. 2015;61:85–117. Available from: https://dx.doi.org/10.1016/j.neunet.2014.09.003
  6. Riese FM, Keller S. Soil Texture Classification with 1D Convolutional Neural Networks based on Hyperspectral Data. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences. 2019;IV-2/W5:615–621. Available from: https://dx.doi.org/10.5194/isprs-annals-iv-2-w5-615-2019
  7. Barman U, Choudhury RD. Soil texture classification using multi class support. Information Processing in Agriculture. 7. Available from: https://doi.org/10.1016/j.inpa.2019.08.001
  8. Padarian J, Minasny B, McBratney AB. Using deep learning to predict soil properties from regional spectral data. Geoderma Regional. 2019;16. Available from: https://dx.doi.org/10.1016/j.geodrs.2018.e00198
  9. Aitkenhead M, Coull M, Gwatkin R, Donnelly D. Automated soil physical parameter assessment using smartphone and digital camera imagery. Journal of Imaging. 2016;2(4):35. Available from: https://dx.doi.org/10.3390/jimaging2040035
  10. Abraham S, Huynh C, Vu H. Classification of Soils into Hydrologic Groups Using Machine Learning. Data. 2019;5(1):2. Available from: https://dx.doi.org/10.3390/data5010002
  11. Orgiazzi A, Ballabio C, Panagos P, Jones A, Fernández-Ugalde O. LUCAS Soil, the largest expandable soil dataset for Europe: a review. European Journal of Soil Science. 2018;69(1):140–153. Available from: https://dx.doi.org/10.1111/ejss.12499
  12. Ballabio C, Panagos P, Monatanarella L. Mapping topsoil physical properties at European scale using the LUCAS database. Geoderma. 2016;261(1):110–123. Available from: https://dx.doi.org/10.1016/j.geoderma.2015.07.006


© 2021 Anandan et al.This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Published By Indian Society for Education and Environment (iSee)


Subscribe now for latest articles and news.