数字农科院2.0

Multimodel ensemble estimation of Landsat-like global terrestrial latent heat flux using a generalized deep CNN-LSTM integration algorithm

文献类型： 外文期刊

作者： Xiaozheng Guo;Yunjun Yao;Qingxin Tang;Shunlin Liang;Changliang Shao;Joshua B. Fisher;Jiquan Chen;Kun Jia;Xiaotong Zhang;Ke Shang;Junming Yang;Ruiyang Yu;Zijing Xie;Lu Liu;Jing Ning;Lilin Zhang

作者机构：

关键词： CNN-LSTM;High-spatial-resolution products;Integration algorithm;Landsat;Latent heat flux

期刊名称： Agricultural and Forest Meteorology

ISSN： 0168-1923

年卷期： 2024 年 349 卷

页码：

收录情况： SCIE（2024版）

摘要： Accurate estimates of high-spatial-resolution global terrestrial latent heat flux (LE) from Landsat data are crucial for many basic and applied research. Yet current Landsat-derived LE products were developed using single algorithm with large uncertainties and discrepancies. Here we proposed a convolutional neural network-long short-term memory (CNN-LSTM)-based integrated LE (CNN-LSTM-ILE) framework that integrates five Landsat-derived physical LE algorithms, topography-related variables (elevation, slope and aspect) and eddy covariance (EC) observations to estimate 30-m global terrestrial LE. CNN-LSTM-ILE not only conserves good performance of LE estimation from pure deep learning (DL) algorithm, but partially inherits physical mechanism of the individual physical algorithms for improving the generalization of the integration algorithms for extreme cases. CNN-LSTM is an algorithm that combines two deep learning structures (CNN and LSTM) to effectively utilize the spatial and temporal information contained in the forcing inputs. The data were collected from 190 globally distributed EC observations from 2000 to 2015 and were provided by FLUXNET. The cross-validation results indicated that the CNN-LSTM integration algorithm improved the LE estimates by reducing the root mean square error (RMSE) of 5–8 W/m2 and increasing Kling-Gupta efficiency (KGE) of 0.05–0.16 when compared with the individual LE algorithms and the results of three other machine learning integration algorithms (multiple linear regression, MLR; random forest, RF; and deep neural networks, DNN). The CNN-LSTM integration algorithm had highest KGE (0.81) and R2 (0.66) compared to ground-measured and was applied to generate the Landsat-like regional and global terrestrial LE. An innovation of our strategy is that the CNN-LSTM-ILE model integrates pixel proximity effects and daily LE variations to enhance the accuracy of 16-day LE estimations. This approach can produce a more reliable Landsat-like global terrestrial LE product to improve the representativeness of heterogeneous regions for monitoring hydrological variables.

分类号：

  • 相关文献

[1]基于改进型CNN—LSTM神经网络蔬菜价格预测与解释研究. 包维嘉,代辛,张永恩,庄家煜,赵泽英,李莉婕,彭丽镕. 2025

[2]江汉平原稻虾共作技术时空扩散的过程及特征. 魏妍冰,陆苗,唐华俊,吴文斌. 2023

[3]2023年新疆塔城地区草地类型Landsat8影像训练数据集. 杨延晓,李全胜,胡林,张鲜花,孙伟. 2025

[4]Bayesian multimodel estimation of global terrestrial latent heat flux from eddy covariance, meteorological, and satellite observations. Yao, Yunjun,Liang, Shunlin,Li, Xianglan,Cheng, Jie,Zhang, Xiaotong,Jiang, Bo,Jia, Kun,Feng, Fei,Liang, Shunlin,Hong, Yang,Hong, Yang,Hong, Yang,Fisher, Joshua B.,Zhang, Nannan,Chen, Jiquan,Zhao, Shaohua,Sun, Liang,Wang, Kaicun,Chen, Yang,Mu, Qiaozhen. 2014

[5]A novel TIR-derived three-source energy balance model for estimating daily latent heat flux in mainland China using an all-weather land surface temperature product. Junming Yang,Yunjun Yao,Changliang Shao,Yufu Li,Joshua B. Fisher,Jie Cheng,Jiquan Chen,Kun Jia,Xiaotong Zhang,Ke Shang,Ruiyang Yu,Xiaozheng Guo,Zijing Xie,Lu Liu,Jing Ning,Lilin Zhang. 2022

[6]A review of global products of air-sea turbulent heat flux: accuracy, mean, variability, and trend. Ronglin Tang,Yizhe Wang,Yazhen Jiang Meng Liu,Meng Liu,Zhong Peng,Yongxin Hu,Lingxiao Huang,Zhao-Liang Li. 2024

[7]Spatial-temporal patterns of land surface evapotranspiration from global products. Tang R.,Peng Z.,Liu M.,Li Z.-L.,Jiang Y.,Hu Y.,Huang L.,Wang Y.,Wang J.,Jia L.,Zheng C.,Zhang Y.,Zhang K.,Yao Y.,Chen X.,Xiong Y.,Zeng Z.,Fisher J.B.. 2024

[8]Assessment for aerodynamic and canopy resistances in simulating latent heat flux of Venlo-type greenhouse tomato. Yi P.,Liu H.,Liu S.,Han Y.,Zhang X.,Yang G.,Wang C.,Kader A.,Qiang X.,Wang J.. 2024

[9]A Bowen ratio-informed method for coordinating the estimates of air-sea turbulent heat fluxes. Wang, Yizhe,Tang, Ronglin,Huang, Lingxiao,Liu, Meng,Jiang, Yazhen,Li, Zhao-Liang. 2024

[10]Coordinated estimates of 4-day 500 m global land surface energy balance components. Junrui Wang,Ronglin Tang,Meng Liu,Yazhen Jiang,Lingxiao Huang,Zhao Liang Li. 2025

[11]Spatio-Temporal Dynamics of Land-Use and Land-Cover in the Mu Us Sandy Land, China, Using the Change Vector Analysis Technique. Karnieli, Arnon,Panov, Natalya,Qin, Zhihao,Wu, Bo,Yan, Feng. 2014

[12]The effects of Landsat image acquisition date on winter wheat classification in the North China Plain. Lingling Fan,Jing Yang,Xiao Sun,Fen Zhao,Shefang Liang,Dingding Duan,Hao Chen,Lang Xia,Jing Sun,Peng Yang. 2022

[13]Evaluation of Three Land Surface Temperature Products From Landsat Series Using in Situ Measurements. Wang M.,He C.,Zhang Z.,Hu T.,Duan S.-B.,Mallick K.,Li H.,Liu X.. 2023

[14]Remote Sensing Of Spatiotemporal Changes I.n Wetland Geomorphology Based O n Type 2 Fuzzy Sets: A Case Study Of Beidagang Wetland From 1975 To 2015. Huo, HY, Guo, JF, Li, ZL, Jiang, XG. 2017

[15]Post-Soviet changes in cropping practices in the irrigated drylands of the Aral Sea basin. Rufin, Philippe,Pena-Guerrero, Mayra Daniela,Umirbekov, Atabek,Wei, Yanbing,Mueller, Daniel. 2022

[16]A full resolution deep learning network for paddy rice mapping using Landsat data. Xia L.,Zhao F.,Chen J.,Yu L.,Lu M.,Yu Q.,Liang S.,Fan L.,Sun X.,Wu S.,Wu W.,Yang P.. 2022

[17]Long-term (2013-2022) mapping of winter wheat in the North China Plain using Landsat data: classification with optimal zoning strategy. Liu, Yifei,Chen, Xuehong,Chen, Jin,Zang, Yunze,Wang, Jingyi,Lu, Miao,Sun, Liang,Dong, Qi,Qiu, Bingwen,Zhu, Xiufang. 2024

[18]Paddy Rice Phenological Mapping throughout 30-Years Satellite Images in the Honghe Hani Rice Terraces. Jianbo Yang,Jianchu Xu,Ying Zhou,Deli Zhai,Huafang Chen,Qian Li,Gaojuan Zhao. 2023

[19]Integrated UAV and Satellite Multi-Spectral for Agricultural Drought Monitoring of Winter Wheat in the Seedling Stage. Xiaohui Yang,Feng Gao,Hongwei Yuan,Xiuqing Cao. 2024

[20]SPTS: Single Pixel in Time-Series triangle model for estimating surface soil moisture. Tian Ma,,Pei Leng,,Yu-Xin Gao,, Abba Aliyu Kasim,, Xiaonan Guo,, Xia Zhang,, Guo-Fei Shang,, Zhao-Liang Li. 2025

作者其他论文 更多>>