数字农科院2.0

A Novel Framework Based on Data Fusion and Machine Learning for Upscaling Evapotranspiration from Flux Towers to the Regional Scale

文献类型： 外文期刊

作者： Pengyuan Zhu;Qisheng Han;Shenglin Li;Hao Liu;Caixia Li;Yanchuan Ma;Jinglei Wang

作者机构：

关键词： data fusion;evapotranspiration upscaling;interpretability;one-dimensional convolutional neural network;remote sensing

期刊名称： Remote Sensing

ISSN：

年卷期： 2025 年 17 卷 23 期

页码：

收录情况： SCIE（2025版） ; ; EI（2025版）

摘要： Highlights: What are the main findings? An integrated framework was developed that combines multi-source data fusion (MODIS, Landsat, and CLDAS), a footprint model, and machine learning to upscale evapotranspiration from site to field scale, successfully achieving daily seamless 30 m ET estimation. The 1D CNN model using both remote sensing and meteorological data performed best in homogeneous croplands (R = 0.90, RMSE = 0.66 mm/d), while the model using only remote sensing data achieved superior accuracy in heterogeneous urban–agricultural areas (R = 0.93, RMSE = 0.88 mm/d). SHAP analysis indicated that LST and EVI2 were the most influential drivers of ET. What are the implications of the main findings? By integrating multi-source remote sensing and reanalysis data, the framework enables accurate daily seamless 30 m estimation of LST and vegetation indices, effectively bridging the gap between remote sensing observations and flux measurements and providing strong support for the application of upscaling methods at the field scale. By generating high-spatiotemporal-resolution evapotranspiration maps, the framework offers a practical tool for precision water resource management in heterogeneous landscapes. Accurate quantification of regional ET is essential for agricultural water management. Upscaling methods based on flux tower observations have been widely applied in large-scale ET estimation. However, the coarse spatial resolution of existing upscaling approaches limits their utility in field-scale management. Therefore, this study proposes an integrated upscaling framework that combines data fusion and machine learning, enabling spatiotemporally continuous ET estimation at the field scale (30 m × 30 m). First, daily 30 m resolution land surface temperature (LST) and vegetation indices were generated by fusing MODIS, Landsat, and China Land Data Assimilation System (CLDAS) datasets. These variables, along with meteorological data and the footprint model, were used as inputs for machine learning. The upscaled ET was evaluated under varying surface heterogeneity using optical-microwave scintillometers (OMS). The results show that a one-dimensional convolutional neural network (1D CNN) using both remote sensing and meteorological data performed best in relatively homogeneous croplands, achieving a correlation coefficient (R) of 0.90, a bias of −0.14 mm/d, a mean absolute error (MAE) of 0.46 mm/d, and a root mean square error (RMSE) of 0.66 mm/d. In contrast, for heterogeneous urban-agricultural landscapes, the 1D CNN using only remote sensing data outperformed other models, with R, bias, MAE, and RMSE of 0.93, −0.14 mm/d, 0.66 mm/d, and 0.88 mm/d, respectively. Furthermore, SHapley Additive exPlanations (SHAP) revealed that LST and the two-band enhanced vegetation index (EVI2) were the most influential drivers in the models. The framework successfully enables ET modeling and spatial extrapolation in heterogeneous regions, providing a foundation for precision water resource management.

分类号：

  • 相关文献

[1]Estimation of soil moisture content under high maize canopy coverage from UAV multimodal data and machine learning. Minghan Cheng,Xiyun Jiao,Yadong Liu,Mingchao Shao,Xun Yu,Yi Bai,Zixu Wang,Siyu Wang,Nuremanguli Tuohuti,Shuaibing Liu,Lei Shi,Dameng Yin,Xiao Huang,Chenwei Nie,Xiuliang Jin. 2022

[2]Editorial: Remote sensing for field-based crop phenotyping. Jiangang Liu,Zhenjiang Zhou,Bo Li. 2024

[3]In-season prediction of maize stem lodging risk using an active canopy sensor. Rui Dong,Yuxin Miao,Pete Berry,Xinbing Wang,Fei Yuan,Krzysztof Kusnierek,Chris Baker,Mark Sterling. 2023

[4]UAV-Based Multimodal Monitoring of Tea Anthracnose with Temporal Standardization. Yu, Qimeng,Zhang, Jingcheng,Yuan, Lin,Li, Xin,Zeng, Fanguo,Xu, Ke,Huang, Wenjiang,Shen, Zhongting. 2025

[5]Study on detection method of microplastics in farmland soil based on hyperspectral imaging technology. Lijia Xu,Yanjun Chen,Ao Feng,Xiaoshi Shi,Yanqi Feng,Yuping Yang,Yuchao Wang,Zhijun Wu,Zhiyong Zou,Wei Ma,Yong He,Ning Yang,Jing Feng,Yongpeng Zhao. 2023

[6]Predicting physiological responses of dairy cows using comprehensive variables. Hang Shu,Yongfeng Li,Jérôme Bindelle,Zhongming Jin,Tingting Fang,Mingjie Xing,Leifeng Guo,Wensheng Wang. 2023

[7]An interpretable integrated machine learning framework for genomic selection. Jinbu Wang,Jia Zhang,Wenjie Hao,Wencheng Zong,Mang Liang,Fuping Zhao,Longchao Zhang,Lixian Wang,Huijiang Gao,Ligang Wang. 2025

[8]Dbert2_LR: A deep learning-based model for predicting cis-regulatory elements in crops. Huan Liu,Faxu Guo,Longyu Huang,Jian Wang,Guomin Zhou,Jianhua Zhang. 2026

[9]DeepAnnotation: A novel interpretable deep learning-based genomic selection model that integrates comprehensive functional annotations. Wenlong Ma,Zheng, Weigang,Qin, Shenghua,Wang, Chao,Lei, Bowen,Liu, Yuwen. 2025

[10]Transfer Learning in Junction With a Light Use Efficiency Model for Estimating Grassland Gross Primary Production. Yu, Ruiyang,Yao, Yunjun,Tang, Qingxin,Zhang, Xueyi,Shao, Changliang,Fisher, Joshua B.,Chen, Jiquan,Zhang, Xiaotong,Li, Yufu,Xu, Jia,Liu, Lu,Xie, Zijing,Ning, Jing,Fan, Jiahui,Zhang, Luna. 2025

[11]Mapping global cropland and field size. Fritz, Steffen,See, Linda,McCallum, Ian,Bun, Andriy,Moltchanova, Elena,Duerauer, Martina,Perger, Christoph,Havlik, Petr,Mosnier, Aline,Schepaschenko, Dmitry,van der Velde, Marijn,Dunwoody, Antonia,Kraxner, Florian,Obersteiner, Michael,You, Liangzhi,You, Liangzhi,Wood-Sichra, Ulrike,Moltchanova, Elena,Albrecht, Fransizka,Albrecht, Fransizka,Schill, Christian,Thornton, Philip,Herrero, Mario,Becker-Reshef, Inbal,Justice, Chris,Hansen, Matthew,Gong, Peng,Aziz, Sheta Abdel,Cipriani, Anna,Cipriani, Anna,Malanding, Jaiteh,Cumani, Renato,Conchedda, Giulia,Cecchi, Giuliano,Ferreira, Stefanus,Gomez, Adriana,Haffani, Myriam,Kayitakire, Francois,Vancutsem, Christelle,Mueller, Rick,Newby, Terence,Nonguierma, Andre,Olusegun, Adeaga,Ortner, Simone,Rajak, D. Ram,Rocha, Jansle,Schepaschenko, Maria,Terekhov, Alexey,Tiangwa, Alex,Vintrou, Elodie,Wu Wenbin.

[12]An Enhanced Spatial and Temporal Data Fusion Model for Fusing Landsat and MODIS Surface Reflectance to Generate High Temporal Landsat-Like Data. Zhang, Wei,Qin, Zhihao,Zhang, Wei,Li, Ainong,Jin, Huaan,Bian, Jinhu,Zhang, Zhengjian,Lei, Guangbin,Huang, Chengquan. 2013

[13]Research on moisture content detection method during green tea processing based on machine vision and near-infrared spectroscopy technology. Zhongyuan Liu,Rentian Zhang,Chongshan Yang,Bin Hu,Xin Luo,Yang Li,Chunwang Dong. 2022

[14]An electronic sense-based machine learning model to predict formulas and processes for vegetable-fruit beverages. Hai Bin Ren,Bao Long Feng,Hong Yue Wang,Jing Jian Zhang,Xiao Sen Bai,Fei Gao,Yan Yang,Qi Zhang,Ye Hui Wang,Li Li Wang,Ya Ting Rong,Yu Lin Sun,Xiao Shuang Cai,Li Meng,Ying Hua Zhang,Yu Tang Wang. 2023

[15]Successive challenge for multi-batch overall pharmaceutical manufacturing control from two-step digital process to OQC strategy by integrated intelligent algorithm. Qianqian Li,Jingqi Zeng,Lijuan Ma,Jinyuan Zhu,Fangyu Zhang,Yunan Wei,Mingshuang Li,Lu Yao,Jing Du,Zhisheng Wu. 2023

[16]Evaluation of aroma quality using multidimensional olfactory information during black tea fermentation. Ting An,Yang Li,Xi Tian,Shuxiang Fan,Dandan Duan,Chunjiang Zhao,Wenqian Huang,Chunwang Dong. 2022

[17]Machine learning technique combined with data fusion strategies: A tea grade discrimination platform. Qianqian Li,Chaoyang Zhang,Huawei Wang,Shengfan Chen,Wei Liu,Yi Li,Jianxun Li. 2023

[18]Data fusion strategy for rapid prediction of moisture content during drying of black tea based on micro-NIR spectroscopy and machine vision. Sheng, Xufeng,Zan, Jiezhong,Jiang, Yongwen,Shen, Shuai,Li, Li,Yuan, Haibo. 2023

[19]Comparison Of Two Synergy Approaches F.or Hybrid Cropland Mapping. Chen, D, Lu, M, Zhou, QB, Xiao, JF, Ru, YT, Wei, YB, Wu, WB. 2019

[20]Hyperspectral imaging technology coupled with human sensory information to evaluate the fermentation degree of black tea. Ting An,Wenqian Huang,Xi Tian,Shuxiang Fan,Dandan Duan,Chunwang Dong,Chunjiang Zhao,Guanglin Li. 2022

作者其他论文 更多>>