Crop residue plays a vital role in maintaining soil health, reducing erosion, enhancing water retention, and contributing to carbon sequestration in agricultural systems. Accurate estimation of crop residue biomass is essential for understanding its distribution patterns, advancing sustainable agricultural practices and improving land management. This study integrates high-resolution UAV multispectral imagery, advanced feature selection methods, and machine learning models to develop a scalable framework for crop residue biomass prediction. An ensemble model, combining predictions from CatBoost, Support Vector Regression, Random Forest, and K-Nearest Neighbor, was created and compared to these individual models to evaluate its performance for predicting crop residue biomass. A variety of predictor variables, including spectral indices, topographic features, textural features, and raw bands, were used in these models. To improve modeling efficiency and accuracy, four feature selection techniques—Recursive Feature Elimination, Pearson correlation, Least Absolute Shrinkage and Selection Operator regression—were tested and compared to identify the most relevant predictor features. Results show that red band and variance from the blue band emerged as consistently selected top predictors across methods. Additionally, the results highlighted the importance of integrating topographic and textural features alongside spectral features to enhance crop residue biomass estimation accuracy. The ensemble approach, combined with Recursive Feature Elimination-selected features, produced the most accurate crop residue biomass predictions (R ² = 0.425, RMSE = 243.465 g/ha). This study demonstrates the potential of ensemble models with optimized feature selection to enhance crop residue monitoring for precision agriculture and sustainable land management.

Accurate mapping of crop residue cover (CRC) is important for sustainable agricultural management because residue supports soil health, erosion control, and carbon sequestration. Traditional ground-based CRC methods are labor-intensive and spatially limited, increasing interest in UAV-based remote sensing. UAVs can carry RGB, multispectral, and hyperspectral sensors, which capture different spectral information for distinguishing crop residue from soil. This study compared four high-spatial-resolution (2.5 cm) UAV imagery types—RGB, multispectral, visible–near-infrared (VNIR) hyperspectral, and shortwave infrared (SWIR) hyperspectral—for fine-scale CRC classification. A fully connected neural network (FCNN) was developed to classify residue and soil pixels. Performance was evaluated using two complementary approaches: pixel-level accuracy assessment based on manually delineated image samples and plot-level validation against residue percentages derived from ground photos. Results showed that high pixel-level classification accuracy values were achieved across all imagery types, with overall accuracies above 94%. However, plot-level validation revealed that sensor performance depended on the evaluation metric considered. Multispectral imagery produced the highest R² with ground photo-derived reference CRC values (R² = 0.672). These results indicate that greater spectral dimensionality did not necessarily improve plot-level CRC estimation under the tested field conditions. More importantly, the findings show that high pixel-level classification accuracy does not necessarily translate into stronger plot-level CRC estimation, highlighting the importance of using complementary validation approaches when evaluating UAV-based CRC estimation.