What question did this study set out to answer?

The study aims to evaluate the sensitivity of machine learning model outputs to feature selection and hyperparameter tuning in crop-type mapping.

February 12, 2026Open Access

Machine-Learning Crop-Type Mapping Sensitivity to Feature Selection and Hyperparameter Tuning

Key Points

The study aims to evaluate the sensitivity of machine learning model outputs to feature selection and hyperparameter tuning in crop-type mapping.
Integration of Sentinel-1 and Sentinel-2 features into machine learning models
Comparison of five models: Random Forest, Support Vector Machine, Light Gradient Boosting, Histogram-based Gradient Boosting, Extreme Gradient Boosting
Assessment of feature selection methods: Variance Inflation Factor and Sequential Feature Selector
Application of Grid-Search for hyperparameter tuning across models
Implementation of a three-step nested modeling setup to enhance model output reliability.
Preprocessing with Variance Inflation Factor results in less reliable crop-type mapping compared to Sequential Feature Selector
Hyperparameter tuning shows sensitivity to input features, improving crop-type mapping when applied post-feature selection
Light Gradient Boosting and Extreme Gradient Boosting yield higher reliability than Support Vector Machine for crop-type mapping
Combining Sentinel-1 and Sentinel-2 features enhances model reliability compared to using either alone.

Abstract

To improve crop yields and incomes, farmers consistently adapt their practices to climate and market fluctuations, resulting in highly variable crop field distribution and coverage in space and time. As these dynamics illustrate farmers’ challenges, up-to-date crop-type mapping is essential for understanding farmers’ needs and supporting their adoption of sustainable practices. With global coverage and frequent temporal observations, remote sensing data are generally integrated into machine learning models to monitor crop dynamics. Unlike physical-based models that rely on straightforward use, implementing machine learning models requires extensive user interaction. In this context, this study assesses how sensitive the models’ outputs are to feature selection and hyperparameter tuning, as both processes rely on user judgment. To achieve this, Sentinel-1 (S1) and Sentinel-2 (S2) features are integrated into five distinct models (Random Forest (RF), Support Vector Machine (SVM), Light Gradient Boosting (LGB), Histogram-based Gradient Boosting (HGB), and Extreme Gradient Boosting (XGB)), considering several features selection (Variance Inflation Factor (VIF) and Sequential Feature Selector (SFS)) and hyperparameter tuning (Grid-Search) setup. Results show that the preprocess modeling feature selection (VIF) discards the features that the wrapped method (SFS) keeps, resulting in less reliable crop-type mapping. Additionally, hyperparameter tuning appears to be sensitive to the input features, and considering it after any feature selection improved the crop-type mapping. In this context a three-step nested modeling setup, including first hyperparameter tuning, followed by a wrapped feature selection (SFS) and additional hyperparameter tuning, leads to the most reliable model outputs. For the study region, LGB and XGB (SVM) are the most (least) suitable models for crop-type mapping, and model reliability improves when integrating S1 and S2 features rather than considering S1 or S2 alone. Finally, crop-type maps are derived across different regions and time periods to highlight the benefits of the proposed method for monitoring crop dynamics in space and time.

Ask AI

Mark Helpful

Bookmark

Relay

View Full Paper