Predicting Soil Quality Index with a Deep Regression Approach


Communications in Soil Science and Plant Analysis, vol.55, no.9, pp.1313-1323, 2024 (SCI-Expanded) identifier

  • Publication Type: Article / Article
  • Volume: 55 Issue: 9
  • Publication Date: 2024
  • Doi Number: 10.1080/00103624.2024.2305838
  • Journal Name: Communications in Soil Science and Plant Analysis
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, PASCAL, Agricultural & Environmental Science Database, Aqualine, BIOSIS, CAB Abstracts, Chemical Abstracts Core, Chimica, Environment Index, Geobase, Pollution Abstracts, Veterinary Science Database
  • Page Numbers: pp.1313-1323
  • Keywords: Convolutional neural network, regression, soil indicators, soil quality index
  • Karadeniz Technical University Affiliated: Yes


The detection, preservation and enhancement of soil quality is essential for ecosystem managers to offer the appropriate support after discovering factors that are linked to soil’s functional capability. In this study, soil quality indicators were combined to establish a soil quality index (SQI) by conducting an efficiency analysis for using Convolutional Neural Network (CNN), Gradient Boosting Methods (GBM) and Decision Tree (DT) approaches. For this purpose, soil’s intrinsic parameters, namely indicators, are utilized in case of fitting a deeper regression model. The experiments were carried out with analysis results of 545 soil samples obtained from previously studies conducted on different areas such as watershed, delta, pasture and farmland. The performance of each model is validated by the reported data. Compared to gradient boosting models, the proposed CNN model with mean absolute loss function achieves a lower error rate of 2.71 in Mean Absolute Percentage Error (MAPE) and best average correlation coefficient 0.90 in R2, which proves generalizability of CNN based regression. The findings show that CNNs may be utilized as an effective tool as giving a better prediction accuracy level and reliability in terms the establishing correlations and providing a conceptual framework for modeling of soil quality.