Abstract: Accurate rapeseed yield and biomass estimation at the meter scale prior to harvest is crucial for precision harvesting. However, there is a scarcity of structured research on the estimation of rapeseed biomass yield. This study aims to address this gap by focusing on rapeseed in Jiangsu Province. Multispectral and RGB images captured by unmanned aerial vehicles (UAVs) were taken during key growth stages (budding, flowering, and podding stages). Using the extracted multidimensional features, we developed biomass-yield estimation models using four machine learning techniques. Subsequently, we employed ensemble learning with multidimensional, multi-stage data and used Shapley additive explanation (SHAP) for feature contribution analysis, thereby constructing a framework for predicting rapeseed harvest characteristics with high estimation accuracy and interpretability. Our analysis indicates that spectral‒texture is the most effective feature combination for biomass estimation, whereas the optimal combination for yield estimation includes three-dimensional (3D) spectral‒textural‒structural features. The synergy of these features, coupled with an ensemble learning model, significantly enhanced the accuracy of rapeseed biomass-yield estimation (biomass: coefficient of determination (R²)=0.72, relative root mean square error (rRMSE)=14.35%; yield: R²=0.68, rRMSE=13.67%). The proposed model also achieved stable prediction results across the variety‒density interaction. Overall, this study presents an accurate and generalizable approach for estimating rapeseed biomass yield across various planting patterns, offering new insights for precision harvesting.

基于集成学习与多维特征协同的油菜生物量与产量估算方法

[1]AdeluyiO, HarrisA, FosterT, et al., 2022. Exploiting centimetre resolution of drone-mounted sensors for estimating mid-late season above ground biomass in rice. Eur J Agron, 132:126411.

[2]BrillRD, JenkinsML, GardnerMJ, et al., 2016. Optimising canola establishment and yield in south-eastern Australia with hybrids and large seed. Crop Pasture Sci, 67(4):409-418.

[3]ChenA, XuC, ZhangM, et al., 2024. Cross-scale mapping of above-ground biomass and shrub dominance by integrating UAV and satellite data in temperate grassland. Remote Sens Environ, 304:114024.

[4]DongTF, LiuJG, ShangJL, et al., 2019. Assessment of red-edge vegetation indices for crop leaf area index estimation. Remote Sens Environ, 222:133-143.

[5]DuRQ, LuJS, XiangYZ, et al., 2024. Estimation of winter canola growth parameter from UAV multi-angular spectral-texture information using stacking-based ensemble learning model. Comput Electron Agric, 222:109074.

[6]DuRQ, LuXH, ZhangY, et al., 2025. Improved estimation of irrigated field soil water (SWC) and salt content (SSC) from Sentinel-2 imagery by combining multi-dimensional spectra decomposition with ensemble learning. Comput Electron Agric, 239:110910.

[7]DuanB, FangSH, GongY, et al., 2021. Remote estimation of grain yield based on UAV data in different rice cultivars under contrasting climatic zone. Field Crops Res, 267:108148.

[8]FanHY, LiuSS, LiJ, et al., 2021. Early prediction of the seed yield in winter oilseed rape based on the near-infrared reflectance of vegetation (NIRv). Comput Electron Agric, 186:106166.

[9]FengDY, YangHY, GaoKX, et al., 2025. Time-series NDVI and greenness spectral indices in mid-to-late growth stages enhance maize yield estimation. Field Crops Res, 333:110069.

[10]GuQ, HuangFD, LouWD, et al., 2024. Unmanned aerial vehicle-based assessment of rice leaf chlorophyll content dynamics across genotypes. Comput Electron Agric, 221:108939.

[11]HanL, YangGJ, DaiHY, et al., 2019. Modeling maize above-ground biomass based on machine learning approaches using UAV remote-sensing data. Plant Methods, 15:10.

[12]HermannD, 2018. Optimisation of Combine Harvesters using Model-based Control. PhD Thesis, DTU-Technical University of Denmark, Lyngby, Denmark.

[13]JiYS, LiuZH, LiuR, et al., 2024. High-throughput phenotypic traits estimation of faba bean based on machine learning and drone-based multimodal data. Comput Electron Agric, 227(Pt 2):109584.

[14]LiPL, ZhangX, WangWH, et al., 2020. Estimating above

[15]ground and organ biomass of plant canopies across the entire season of rice growth with terrestrial laser scanning. Int J Appl Earth Obs Geoinf, 91:102132.

[16]LiZH, ZhaoY, TaylorJ, et al., 2022. Comparison and transferability of thermal, temporal and phenological-based in-season predictions of above-ground biomass in wheat crops from proximal crop reflectance data. Remote Sens Environ, 273:112967.

[17]LiuY, FengHK, YueJB, et al., 2023. Estimating potato above-ground biomass by using integrated unmanned aerial system-based optical, structural, and textural canopy measurements. Comput Electron Agric, 213:108229.

[18]MaYC, ChenS, ErmonS, et al., 2024. Transfer learning in environmental remote sensing. Remote Sens Environ, 301:113924.

[19]MaZH, DuRM, XieJY, et al., 2023. Phenotyping of silique morphology in oilseed rape using skeletonization with hierarchical segmentation. Plant Phenomics, 5:0027.

[20]MalamboL, PopescuSC, MurraySC, et al., 2018. Multitemporal field-based plant height estimation using 3D point clouds generated from small unmanned aerial systems high-resolution imagery. Int J Appl Earth Obs Geoinf, 64:31-42.

[21]Mateo-SanchisA, PilesM, Muñoz-MaríJ, et al., 2019. Synergistic integration of optical and microwave satellite data for crop yield estimation. Remote Sens Environ, 234:111460.

[22]MengL, MingB, LiuY, et al., 2025. Maize biomass estimation by integrating spectral, structural, and textural features from unmanned aerial vehicle data. Eur J Agron, 168:127647.

[23]MokhtariA, YangHB, CroftH, et al., 2025. Satellite-based winter wheat yield estimation with a newly parameterized LUE model based on crop water status and leaf chlorophyll content. Field Crops Res, 333:110106.

[24]Nogueira MartinsR, de Assis de Carvalho Pinto F, Marçal de QueirozD, et al., 2023. Digital mapping of coffee ripeness using UAV-based multispectral imagery. Comput Electron Agric, 204:107499.

[25]PengY, ZhuTE, LiYC, et al., 2019. Remote prediction of yield based on LAI estimation in oilseed rape under different planting methods and nitrogen fertilizer applications. Agric For Meteor, 271:116-125.

[26]RouseJW, HaasRH, SchellJA, et al., 1974. Monitoring vegetation systems in the Great Plains with ERTS. Proceedings of the Third Earth Resources Technology Satellite-1 Symposium- Volume I: Technical Presentations.

[27]SabutA, TripathyKP, MishraA, et al., 2025. Assessing the impact of climate indices on corn yield in the continental USA using machine learning approach. Agric For Meteor, 371:110632.

[28]ShaoGM, HanWT, ZhangHH, et al., 2022. Estimation of transpiration coefficient and aboveground biomass in maize using time-series UAV multispectral imagery. Crop J, 10(5):1376-1385.

[29]ShuMY, ShenMY, DongQZ, et al., 2022. Estimating the maize above-ground biomass by constructing the tridimensional concept model based on UAV-based digital and multi-spectral images. Field Crops Res, 282:108491.

[30]SulikJJ, LongDS, 2015. Spectral indices for yellow canola flowers. Int J Remote Sens, 36(10):2751-2765.

[31]SulikJJ, LongDS, 2016. Spectral considerations for modeling yield of canola. Remote Sens Environ, 184:161-174.

[32]TaoZF, YiLB, BaoAM, et al., 2024. UAV or satellites? How to find the balance between efficiency and accuracy in above ground biomass estimation of artificial young coniferous forest? Int J Appl Earth Obs Geoinf, 134:104173.

[33]TeshomeFT, BayabilHK, HoogenboomG, et al., 2023. Unmanned aerial vehicle (UAV) imaging and machine learning applications for plant phenotyping. Comput Electron Agric, 212:108064.

[34]van der VeldeM, BouraouiF, AloeA, 2009. Pan-European regional-scale modelling of water and N efficiencies of rapeseed cultivation for biodiesel production. Global Change Biol, 15(1):24-37.

[35]WanL, CenHY, ZhuJP, et al., 2020. Grain yield prediction of rice using multi-temporal UAV-based RGB and multispectral images and model transfer ‒ a case study of small farmlands in the South of China. Agric For Meteor, 291:108096.

[36]WangFM, YiQX, HuJH, et al., 2021. Combining spectral and textural information in UAV hyperspectral images to estimate rice grain yield. Int J Appl Earth Obs Geoinf, 102:102397.

[37]WeiMCF, MolinJP, LongchampsL, 2026. Predictive power vs interpretability: machine learning approaches to unravel sugarcane yield drivers. Comput Electron Agric, 243:111353.

[38]YanXY, ZhangZD, HuangMB, et al., 2022. The impact of climate change on growth and drought-induced mortality risk of Robinia pseudoacacia plantations along a precipitation gradient on the Chinese Loess Plateau. Agric For Meteor, 325:109160.

[39]YaoJ, KeXB, GuXY, et al., 2025. Optimized substrate selection for enhanced orchid growth based on high-throughput lysimetric arrays. J Zhejiang Univ-Sci B, online first.

[40]YeYR, JinLP, BianCS, et al., 2024. Estimating potato above

[41]ground biomass using unmanned aerial vehicle RGB imagery and analyzing its relationship with tuber biomass. Field Crops Res, 319:109657.

[42]ZhaiWG, LiCC, ChengQ, et al., 2023. Exploring multisource feature fusion and stacking ensemble learning for accurate estimation of maize chlorophyll content using unmanned aerial vehicle remote sensing. Remote Sens, 15(13):3454.

[43]ZhangJY, QiuXL, WuYT, et al., 2021. Combining texture, color, and vegetation indices from fixed-wing UAS imagery to estimate wheat growth parameters using multivariate regression methods. Compute Electron Agric, 185:106138.

[44]ZhangYN, NiuYX, CuiZH, et al., 2025. Cross-year rapeseed yield prediction for harvesting management using UAV-based imagery. Remote Sens, 17(12):2010.

[45]ZhangZF, GuoJ, GaoYZ, et al., 2025. Increasing yield estimation accuracy for individual apple trees via ensemble learning and growth stage stacking. Comput Electron Agric, 237:110648.

Similar articles