Comparison of Machine-Learning and CASA Models for Predicting Apple Fruit Yields from Time-Series Planet Imageries
文献类型： 外文期刊
作者： Bai, Xueyuan 1 ; Li, Zhenhai 2 ; Li, Wei 1 ; Zhao, Yu 2 ; Li, Meixuan 1 ; Chen, Hongyan 1 ; Wei, Shaochong 3 ; Jiang, Yua 1 ;
作者机构： 1.Shandong Agr Univ, Coll Resources & Environm, Tai An 271018, Shandong, Peoples R China
2.Natl Engn Res Ctr Informat Technol Agr, Beijing 100097, Peoples R China
3.Shandong Agr Univ, Natl Apple Engn & Technol Res Ctr, Coll Hort Sci & Engn, Tai An 271018, Shandong, Peoples R China
4.Shandong Agr Univ, Natl Engn Lab Efficient Utilizat Soil & Fertilize, Tai An 271018, Shandong, Peoples R China
关键词： apple fruit; yield prediction; remote sensing; planet; time series; Sigma NDVI; random forest; CASA
期刊名称：REMOTE SENSING （ 影响因子：4.848； 五年影响因子：5.353 ）
ISSN：
年卷期： 2021 年 13 卷 16 期
页码：
收录情况： SCI
摘要： Apple (Malus domestica Borkh. cv. "Fuji"), an important cash crop, is widely consumed around the world. Accurately predicting preharvest apple fruit yields is critical for planting policy making and agricultural management. This study attempted to explore an effective approach for predicting apple fruit yields based on time-series remote sensing data. In this study, time-series vegetation indices (VIs) were derived from Planet images and analyzed to further construct an accumulated VI (Sigma VIs)-based random forest (RF Sigma VI) model and a Carnegie-Ames-Stanford approach (CASA) model for predicting apple fruit yields. The results showed that (1) Sigma NDVI was the optimal predictor to construct an RF model for apple fruit yield, and the R-2, RMSE, and RPD values of the RF Sigma NDVI model reached 0.71, 16.40 kg/tree, and 1.83, respectively. (2) The maximum light use efficiency was determined to be 0.499 g C/MJ, and the CASA(SR) model (R-2 = 0.57, RMSE = 19.61 kg/tree, and RPD = 1.53) performed better than the CASA(NDVI) model and the CASA(Average) model (R-2, RMSE, and RPD = 0.56, 24.47 kg/tree, 1.22 and 0.57, 20.82 kg/tree, 1.44, respectively). (3) This study compared the yield prediction accuracies obtained by the models using the same dataset, and the RF Sigma NDVI model (RPD = 1.83) showed a better performance in predicting apple fruit yields than the CASA(SR) model (RPD = 1.53). The results obtained from this study indicated the potential of the RF Sigma NDVI model based on time-series Planet images to accurately predict apple fruit yields. The models could provide spatial and quantitative information of apple fruit yield, which would be valuable for agronomists to predict regional apple production to inform and develop national planting policies, agricultural management, and export strategies.
- 相关文献
作者其他论文 更多>>
-
UssNet: a spatial self-awareness algorithm for wheat lodging area detection
作者：Zhang, Jun;Wu, Qiang;Duan, Fenghui;Liu, Cuiping;Xiong, Shuping;Ma, Xinming;Cheng, Jinpeng;Feng, Mingzheng;Dai, Li;Wang, Xiaochun;Yang, Hao;Yang, Guijun;Chang, Shenglong
关键词：Unmanned aerial vehicle; State space models; Wheat lodging area identification; Semantic segmentation
-
A Comprehensive Evaluation of Monocular Depth Estimation Methods in Low-Altitude Forest Environment
作者：Jia, Jiwen;Kang, Junhua;Gao, Xiang;Zhang, Borui;Yang, Guijun;Chen, Lin;Yang, Guijun
关键词：monocular depth estimation; CNN; vision transformer; forest environment; comparative study
-
Genotyping Identification of Maize Based on Three-Dimensional Structural Phenotyping and Gaussian Fuzzy Clustering
作者：Xu, Bo;Zhao, Chunjiang;Xu, Bo;Zhao, Chunjiang;Yang, Guijun;Zhang, Yuan;Liu, Changbin;Feng, Haikuan;Yang, Xiaodong;Yang, Hao;Xu, Bo;Zhao, Chunjiang;Yang, Guijun;Zhang, Yuan;Liu, Changbin;Feng, Haikuan;Yang, Xiaodong;Yang, Hao
关键词：tassel; 3D phenotyping; TreeQSM; genotyping; clustering
-
Estimation of Leaf Chlorophyll Content of Maize from Hyperspectral Data Using E2D-COS Feature Selection, Deep Neural Network, and Transfer Learning
作者：Chen, Riqiang;Feng, Haikuan;Hu, Haitang;Chen, Riqiang;Ren, Lipeng;Yang, Guijun;Cheng, Zhida;Zhao, Dan;Zhang, Chengjian;Feng, Haikuan;Hu, Haitang;Yang, Hao;Chen, Riqiang;Zhang, Chengjian;Ren, Lipeng;Feng, Haikuan
关键词：maize; chlorophyll; radiative transfer model; feature selection; transfer learning
-
Field-scale irrigated winter wheat mapping using a novel cross-region slope length index in 3D canopy hydrothermal and spectral feature space
作者：Zhang, Youming;Yang, Guijun;Li, Zhenhong;Liu, Miao;Zhang, Jing;Gao, Meiling;Zhu, Wu;Zhang, Youming;Yang, Guijun;Yang, Xiaodong;Song, Xiaoyu;Long, Huiling;Liu, Miao;Meng, Yang;Thenkabail, Prasad S.;Wu, Wenbin;Zuo, Lijun;Meng, Yang
关键词：Winter wheat; Irrigation mapping; Hydrothermal and spectral feature; Cross-region; Rainfed line; Slope Length Index
-
Combining UAV Remote Sensing with Ensemble Learning to Monitor Leaf Nitrogen Content in Custard Apple (Annona squamosa L.)
作者：Jiang, Xiangtai;Xu, Xingang;Wu, Wenbiao;Yang, Guijun;Meng, Yang;Feng, Haikuan;Li, Yafeng;Xue, Hanyu;Chen, Tianen;Jiang, Xiangtai;Xu, Xingang;Gao, Lutao
关键词：canopy nitrogen content; UAV remote sensing; ensemble learning; Lasso model
-
Retrieving the chlorophyll content of individual apple trees by reducing canopy shadow impact via a 3D radiative transfer model and UAV multispectral imagery
作者：Zhang, Chengjian;Chen, Zhibo;Chen, Riqiang;Zhang, Wenjie;Zhang, Chengjian;Chen, Riqiang;Zhang, Wenjie;Zhao, Dan;Yang, Guijun;Xu, Bo;Feng, Haikuan;Yang, Hao
关键词：Chlorophyll content; Shadows; Vegetation index (VI); Radiative transfer models (RTMs); Hybrid inversion model; Individual apple tree crown
