Table 21 Comparison of the proposed method with previous studies.
From: Predicting land suitability for wheat and barley crops using machine learning techniques
Title | Method | Target class | Accuracy | |
|---|---|---|---|---|
Algorithm | Feature selection | |||
Predictive modeling for land suitability assessment for cassava cultivation8 | SVM & DT | Information gain | Five class | DT with 87.5 |
Using parallel random forest classifier in predicting land suitability for crop production9 | RF, LR, LDA, KNN, GNB, SVM | None | Four class | RF with 96 |
Support vector machines based-modeling of land suitability analysis for rainfed agriculture10 | SVM | None | Binary class | RMSE of 3.72 & R square of 0.84 |
A machine learning approach to assess crop specific suitability for small/marginal scale croplands11 | DT | None | Five class | DT with 98.9 |
A web-based decision support system for evaluating soil suitability for cassava cultivation12 | DT | None | Four class | DT with 76.5 |
Proposed method | RF, GB and KNN | UFS, RFECV and SFS | Five class | GB with SFS has got 99.41% |
