Using UAV-Based RGB and Multispectral Imagery to Estimate Cotton Above-Ground Biomass by Integrating Multi-Modal Features and Machine Learning Algorithms.
Saved in:
| Title: | Using UAV-Based RGB and Multispectral Imagery to Estimate Cotton Above-Ground Biomass by Integrating Multi-Modal Features and Machine Learning Algorithms. |
|---|---|
| Authors: | Be, Madjebi Collela1 (AUTHOR), Zhang, Jie2,3 (AUTHOR) zhangjie10@caas.cn, Yang, Beifang1,3 (AUTHOR), Liu, Shengping2,3,4 (AUTHOR), Han, Yingchun1,5 (AUTHOR), Lei, Yaping1,6 (AUTHOR), Zhi, Xiaoyu1 (AUTHOR), Xiong, Shiwu1,2 (AUTHOR), Jiao, Yahui1,3 (AUTHOR), Ma, Yunzhen1,4 (AUTHOR), Shang, Shilong1,5 (AUTHOR), Randrianantenaina, Antsa Sarobidy4,5,6 (AUTHOR), Khan, Hamad1 (AUTHOR), Zhang, Haoshen1 (AUTHOR), Wang, Yaru1 (AUTHOR), Lin, Tao6 (AUTHOR), Li, Yabing1 (AUTHOR) |
| Source: | Remote Sensing. Jul2026, Vol. 18 Issue 14, p2278. 33p. |
| Subjects: | Biomass estimation, Multispectral imaging, Agricultural remote sensing, Remote sensing, Machine learning, Feature selection, Crop growth, Drone photography |
| Abstract: | Highlights: What are the main findings? Sensor performance is strongly influenced by the cotton growth stage rather than a consistent superiority of any single sensor type. Model performance varies across growth stages: XGBoost and Random Forest perform best at the seedling stage, while Ridge Regression and Partial Least Squares Regression perform better at the squaring and flowering stages. What are the implications of the main findings? Coupling multi-source UAV data (RGB and multispectral imagery) provides a stage-dependent and complementary approach for cotton biomass monitoring, improving prediction robustness by integrating structural and physiological information. The integration of machine learning models with recursive feature elimination with cross-validation-based feature selection enables more reliable and adaptive biomass estimation, but its effectiveness is dependent on growth stage and feature composition, rather than providing uniform improvement across all conditions. Real-time monitoring of cotton above-ground biomass (AGB) is crucial for monitoring crop growth and optimizing management practices. This study evaluated UAV-based RGB and multispectral (MS) imagery for cotton AGB estimation across multiple growth stages under different planting densities and sowing dates in Anyang, China. Spectral features, vegetation indices (VIs), and Gray Level Co-occurrence Matrix (GLCM) texture metrics were extracted and organized into three scenarios: RGB + MS, RGB-only, and MS-only. Recursive feature elimination with cross-validation (RFECV) was applied for feature selection, and six machine learning models were evaluated using both baseline and selected feature sets. Results showed that model performance was strongly influenced by growth stage, sensor configuration, and feature composition. Accuracy was highest at the seedling and squaring stages and decreased at flowering due to canopy complexity and spectral saturation. MS-only and fused features generally performed best at the seedling stage, while RGB-only features were competitive or superior at the squaring stage, highlighting the importance of high-resolution structural information. At flowering, fused RGB–MS features provided the most stable performance, although improvements were limited. RFECV exhibited stage-dependent behavior, improving performance mainly at early growth stages but showing inconsistent benefits later. SHAP analysis revealed a shift from texture-dominated predictors at the seedling stage to balanced feature contributions at squaring and vegetation index (VIs) dominance at flowering. Overall, cotton AGB estimation is a stage-dependent process requiring adaptive sensor and feature selection strategies. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Highlights: What are the main findings? Sensor performance is strongly influenced by the cotton growth stage rather than a consistent superiority of any single sensor type. Model performance varies across growth stages: XGBoost and Random Forest perform best at the seedling stage, while Ridge Regression and Partial Least Squares Regression perform better at the squaring and flowering stages. What are the implications of the main findings? Coupling multi-source UAV data (RGB and multispectral imagery) provides a stage-dependent and complementary approach for cotton biomass monitoring, improving prediction robustness by integrating structural and physiological information. The integration of machine learning models with recursive feature elimination with cross-validation-based feature selection enables more reliable and adaptive biomass estimation, but its effectiveness is dependent on growth stage and feature composition, rather than providing uniform improvement across all conditions. Real-time monitoring of cotton above-ground biomass (AGB) is crucial for monitoring crop growth and optimizing management practices. This study evaluated UAV-based RGB and multispectral (MS) imagery for cotton AGB estimation across multiple growth stages under different planting densities and sowing dates in Anyang, China. Spectral features, vegetation indices (VIs), and Gray Level Co-occurrence Matrix (GLCM) texture metrics were extracted and organized into three scenarios: RGB + MS, RGB-only, and MS-only. Recursive feature elimination with cross-validation (RFECV) was applied for feature selection, and six machine learning models were evaluated using both baseline and selected feature sets. Results showed that model performance was strongly influenced by growth stage, sensor configuration, and feature composition. Accuracy was highest at the seedling and squaring stages and decreased at flowering due to canopy complexity and spectral saturation. MS-only and fused features generally performed best at the seedling stage, while RGB-only features were competitive or superior at the squaring stage, highlighting the importance of high-resolution structural information. At flowering, fused RGB–MS features provided the most stable performance, although improvements were limited. RFECV exhibited stage-dependent behavior, improving performance mainly at early growth stages but showing inconsistent benefits later. SHAP analysis revealed a shift from texture-dominated predictors at the seedling stage to balanced feature contributions at squaring and vegetation index (VIs) dominance at flowering. Overall, cotton AGB estimation is a stage-dependent process requiring adaptive sensor and feature selection strategies. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 20724292 |
| DOI: | 10.3390/rs18142278 |
