Abstract: Accurate and efficient estimation of aboveground biomass (AGB) is important for peanut phenotyping and field management. This study evaluates spectral and textural features derived from unmanned aerial vehicle (UAV) multispectral imagery for nondestructive and high-throughput estimation of peanut AGB. Vegetation indices (VIs) and gray-level co-occurrence matrix (GLCM) texture features (TFs) are derived from the green, red, red-edge, and near-infrared bands and assessed via six regression models. The results reveal that near-infrared TFs exhibit the highest sensitivity to AGB. Among the GLCM configurations, a setting of a 7×7 window size, a 45° orientation, and 16 gray levels produces the most stable texture representation. Although combining all VIs and TFs slightly improves prediction accuracy, the relatively large differences between the coefficient of determination (R²) and adjusted R² in some models suggest that the full feature set contains redundant predictors and has limited model parsimony. An extreme gradient boosting (XGBoost)–Shapley additive explanation (SHAP) feature selection strategy is therefore used to identify five key variables: difference vegetation index (DVI), variance, mean, energy, and modified soil-adjusted vegetation index (MSAVI). This compact feature set substantially reduces predictor dimensionality, limits the differences between R² and adjusted R² to below 0.020, and achieves consistent predictive accuracy, with R² above 0.840 and the root mean square error ( RMSE) below 0.055 kg/m². The proposed approach provides a practical tool for high-throughput peanut biomass monitoring, phenotyping, and production management.

基于无人机多光谱影像优化光谱—纹理特征的花生地上生物量高通量估算

[1]Balling J, Herold M, Reiche J, 2023. How textural features can improve SAR-based tropical forest disturbance mapping. Int J Appl Earth Obs Geoinf, 124:103492.

[2]Bodoira R, Cittadini MC, Velez A, et al., 2022. An overview on extraction, composition, bioactivity and food applications of peanut phenolics. Food Chem, 381:132250.

[3]Burnett AC, Anderson J, Davidson KJ, et al., 2021. A best-practice guide to predicting plant traits from leaf-level hyperspectral data using partial least squares regression. J Exp Bot, 72(18):6175-6189.

[4]Burns BW, Green VS, Hashem AA, et al., 2022. Determining nitrogen deficiencies for maize using various remote sensing indices. Precision Agric, 23(3):791-811.

[5]Cen HY, Wan L, Zhu JP, et al., 2019. Dynamic monitoring of biomass of rice under different nitrogen treatments using a lightweight UAV with dual image-frame snapshot cameras. Plant Methods, 15(1):32.

[6]Chen H, Li W, Zhu YY, 2021. Improved window adaptive gray level co-occurrence matrix for extraction and analysis of texture characteristics of pulmonary nodules. Comput Methods Programs Biomed, 208:106263.

[7]Fan YG, Feng HK, Yue JB, et al., 2023. Using an optimized texture index to monitor the nitrogen content of potato plants over multiple growth stages. Comput Electr Agric, 212:108147.

[8]Franceschini MHD, Becker R, Wichern F, et al., 2022. Quantification of grassland biomass and nitrogen content through UAV hyperspectral imagery—active sample selection for model transfer. Drones, 6(3):73.

[9]Freitas RG, Pereira FRS, Dos Reis AA, et al., 2022. Estimating pasture aboveground biomass under an integrated crop-livestock system based on spectral and texture measures derived from UAV images. Comput Electr Agric, 198:107122.

[10]He LM, Wang R, Mostovoy G, et al., 2021. Crop biomass mapping based on ecosystem modeling at regional scale using high resolution Sentinel-2 data. Remote Sens, 13(4):806.

[11]Hosseini Taheri SE, Bazargan M, Rahnama Vosough P, et al., 2024. A comprehensive insight into peanut: chemical structure of compositions, oxidation process, and storage conditions. J Food Compost Anal, 125:105770.

[12]Hou XH, Zhang JY, Luo XB, et al., 2025. Peanut yield prediction using remote sensing and machine learning approaches based on phenological characteristics. Comput Electr Agric, 232:110084.

[13]Kayad A, Rodrigues FA, Naranjo S, et al., 2022. Radiative transfer model inversion using high-resolution hyperspectral airborne imagery–retrieving maize LAI to access biomass and grain yield. Field Crops Res, 282:108449.

[14]Kursa MB, Rudnicki WR, 2010. Feature selection with the Boruta package. J Stat Softw, 36(11):1-13.

[15]Li S, Potter C, 2012. Patterns of aboveground biomass regeneration in post-fire coastal scrub communities. GISci Remote Sens, 49(2):182-201.

[16]Liang YY, Kou WL, Lai HY, et al., 2022. Improved estimation of aboveground biomass in rubber plantations by fusing spectral and textural information from UAV-based RGB imagery. Ecol Ind, 142:109286.

[17]Liu Y, Feng HK, Fan YG, et al., 2024a. Improving potato above ground biomass estimation combining hyperspectral data and harmonic decomposition techniques. Comput Electr Agric, 218:108699.

[18]Liu Y, Fan YG, Feng HK, et al., 2024b. Estimating potato above-ground biomass based on vegetation indices and texture features constructed from sensitive bands of UAV hyperspectral imagery. Comput Electr Agric, 220:108918.

[19]Lundberg SM, Lee SI, 2017. A unified approach to interpreting model predictions. Proc 31^st Int Conf on Neural Information Processing Systems, p.4768-4777.

[20]Niu YX, Song XY, Zhang LX, et al., 2025. Enhancing model accuracy of UAV-based biomass estimation by evaluating effects of image resolution and texture feature extraction strategy. IEEE J Sel Top Appl Earth Obs Remote Sens, 18:878-891.

[21]Nohara Y, Matsumoto K, Soejima H, et al., 2022. Explanation of machine learning models using Shapley additive explanation and application for real data in hospital. Comput Methods Programs Biomed, 214:106584.

[22]Qiao L, Tang WJ, Gao DH, et al., 2022. UAV-based chlorophyll content estimation by evaluating vegetation index responses under different crop coverages. Comput Electr Agric, 196:106775.

[23]Schober P, Boer C, Schwarte LA, 2018. Correlation coefficients: appropriate use and interpretation. Anesth Analg, 126(5):1763-1768.

[24]Shu MY, Li Q, Ghafoor A, et al., 2023. Using the plant height and canopy coverage to estimation maize aboveground biomass with UAV digital images. Eur J Agron, 151:126957.

[25]Song MX, Bai B, Yang JT, et al., 2025. Robust UAV-based method for peanut plant height estimation using bare-soil invariant constraints. Smart Agric, 7(6):124-135(in Chinese).

[26]Tan HJ, Kou WL, Xu WH, et al., 2025. Enhancing aboveground biomass estimation in rubber plantations using UAV multispectral data for satellite upscaling. Remote Sens, 17(17):2955.

[27]Wang F, Yang M, Ma LF, et al., 2022. Estimation of above-ground biomass of winter wheat based on consumer-grade multi-spectral UAV. Remote Sens, 14(5):1251.

[28]Wang S, Guan KY, Wang ZH, et al., 2021. Airborne hyperspectral imaging of nitrogen deficiency on crop traits and yield of maize by machine learning and radiative transfer modeling. Int J Appl Earth Obs Geoinf, 105:102617.

[29]Xu L, Zhou LF, Meng R, et al., 2022. An improved approach to estimate ratoon rice aboveground biomass by integrating UAV-based spectral, textural and structural features. Precision Agric, 23(4):1276-1301.

[30]Xu TY, Wang FM, Xie LL, et al., 2022. Integrating the textural and spectral information of UAV hyperspectral images for the improved estimation of rice aboveground biomass. Remote Sens, 14(11):2534.

[31]Yang N, Zhang ZT, Zhang JR, et al., 2023. Improving estimation of maize leaf area index by combining of UAV-based multispectral and thermal infrared data: the potential of new texture index. Comput Electr Agric, 214:108294.

[32]Yu FH, Bai JC, Fang JY, et al., 2024. Integration of a parameter combination discriminator improves the accuracy of chlorophyll inversion from spectral imaging of rice. Agric Commun, 2(3):100055.

[33]Yue JB, Yang H, Yang GJ, et al., 2023. Estimating vertically growing crop above-ground biomass based on UAV remote sensing. Comput Electr Agric, 205:107627.

[34]Zhang JY, Qiu XL, Wu YT, et al., 2021. Combining texture, color, and vegetation indices from fixed-wing UAS imagery to estimate wheat growth parameters using multivariate regression methods. Comput Electr Agric, 185:106138.

[35]Zhang SH, Duan JZ, Qi XH, et al., 2024. Combining spectrum, thermal, and texture features using machine learning algorithms for wheat nitrogen nutrient index estimation and model transferability analysis. Comput Electr Agric, 222:109022.

[36]Zhang Y, Xia CZ, Zhang XY, et al., 2021. Estimating the maize biomass by crop height and narrowband vegetation indices derived from UAV-based hyperspectral images. Ecol Ind, 129:107985.

[37]Zheng HB, Cheng T, Li D, et al., 2018. Combining unmanned aerial vehicle (UAV)-based multispectral imagery and ground-based hyperspectral data for plant nitrogen concentration estimation in rice. Front Plant Sci, 9:936.

Similar articles