Skip to content
Research Article Open access CC BY 4.0

Identifying Prominent Environmental Covariates Using Variable Selection Methodologies for Digital Soil Mapping of Tamil Nadu, India

T. Tarun Kshatriya, R. Kumaraperumal, D. Muthumanickam, S. Pazhanivelan, K. P. Ragunath, M. Nivas Raj

International Journal of Environment and Climate Change · pp. 2358–2376 · Published 29 Jul 2023

10.9734/ijecc/2023/v13i92469

Abstract

High dimensional datasets that depict intricate spatial variations are necessary to predict complex landscape structures and the corresponding soil properties taking into account the size of the research region in addition to the data attributes. The number and quality of the input datasets taken into consideration essentially determine the quantity and quality of the soil properties that may be predicted thanks to data-driven learning algorithms.  The use of variable selection strategies both before and after the prediction can have a significant impact on the outcome and can lower the related computing load. The majority of commonly used variable selection techniques such as correlation analysis, stepwise regression and recursive feature elimination, among others perform recursive statistical/mathematical comparison to identify the significant covariates that improve the effectiveness of the algorithm proposed. In order to identify the effective environmental variables in predicting the soil attribute, this article investigated a widely used recursive ranking method called recursive feature elimination. The covariate layer that produced the lowest RMSE was placed first according to the rankings of the covariates provided by recursive feature elimination. The findings showed that among other factors physiography, mean rainfall, rock outcrop difference ratio, elevation and mean temperature will be effective in predicting the soil properties required for digital soil mapping.

Digital soil mapping variable selection techniques environmental covariates recursive feature elimination

References (28)

  1. 1 Digital soil mapping: A brief history and some lessons [DOI]
  2. 2 Machine learning for digital soil mapping: Applications, challenges and suggested solutions [DOI]
  3. 3 Improving performance of spatio-temporal machine learning models using forward feature selection and target-oriented validation [DOI]
  4. 4 Machine learning for predicting soil classes in three semi-arid landscapes [DOI]
  5. 5 Multi-scale digital terrain analysis and feature selection for digital soil mapping [DOI]
  6. 6 Digital mapping of soil organic carbon at multiple depths using different data mining techniques in Baneh region, Iran [DOI]
  7. 7 Improving the spatial prediction of soil organic carbon using environmental covariates selection: A comparison of a group of environmental covariates [DOI]
  8. 8 Recent progress and future prospect of digital soil mapping: A review [DOI]
  9. 9 Conventional and digital soil mapping in Iran: Past, present, and future [DOI]
  10. 10 Multi-task convolutional neural networks outperformed random forest for mapping soil particle size fractions in central Iran [DOI]
  11. 11 Comparison of feature selection methods for mapping soil organic matter in subtropical restored forests [DOI]
  12. 12 High-resolution agriculture soil property maps from digital soil mapping methods, Czech Republic [DOI]
  13. 13 Legacy data-based national-scale digital mapping of key soil properties in India [DOI]
  14. 14 The effectiveness of digital soil mapping with temporal variables in modeling soil organic carbon changes [DOI]
  15. 15 Soil Quality and Methods for its Assessment [DOI]
  16. 16 Digital Soil Mapping Using Machine Learning Algorithms in a Tropical Mountainous Area [DOI]
  17. 17 Comparing the use of training data derived from legacy soil pits and soil survey polygons for mapping soil classes [DOI]
  18. 18 Predicting spatial variability of selected soil properties using digital soil mapping in a rainfed vineyard of central Chile [DOI]
  19. 19 Multinomial Logistic Regression and Random Forest Classifiers in Digital Mapping of Soil Classes in Western Haiti [DOI]
  20. 20 Identifying opportunities to improve digital soil mapping in India: A systematic review [DOI]
  21. 21 Comparison of Machine Learning-Based Prediction of Qualitative and Quantitative Digital Soil-Mapping Approaches for Eastern Districts of Tamil Nadu, India [DOI]
  22. 22 Optimal scaling of predictors for digital mapping of soil properties [DOI]
  23. 23 A representativeness heuristic for mitigating spatial bias in existing soil samples for digital soil mapping [DOI]
  24. 24 National-scale maps for soil aggregate size distribution parameters using pedotransfer functions and digital soil mapping data products [DOI]
  25. 25 Digital soil mapping based on empirical mode decomposition components of environmental covariates [DOI]
  26. 26 The mapping of soil taxonomic units via fuzzy clustering – A case study from the Outer Carpathians, Czechia [DOI]
  27. 27 Digital mapping of soil chemical properties with limited data in the Thung Kula Ronghai region, Thailand [DOI]
  28. 28 Generating Soil Parent Material Environmental Covariates Using Sentinel – 2A Images for Delineating Soil Attributes [DOI]

Cited by 1

Generation of digital soil mapping for Coimbatore districts using multinomial logistic regression approach

S. Vishnu Shankar, R. Kumaraperumal, M. Radha · Environmental Earth Sciences · 2024

Related research

Article metrics

Real usage data collected on this platform.

29

Page views

0

PDF downloads

1

Outbound clicks

1

Citations

Views over time

Views by country

Approximate, from request IP at view time — not citizenship or institution. Countries with fewer than 5 views are grouped as "Other".

Traffic sources

Referring site, by host.

Views and downloads exclude known bots/crawlers. Citations combines this platform's own DOI-resolved index with each external source's own reported total — see Cited by above for individually listed citing works. Last refreshed 0 seconds ago.