数字农科院2.0

AI-Based Downscaling of MODIS LST Using SRDA-Net Model for High-Resolution Data Generation

文献类型： 外文期刊

作者： Hongxia Ma;;Kebiao Mao;;Zijin Yuan;;Longhao Xu;;Jiancheng Shi;;Zhonghua Guo;;Zhihao Qin

关键词： land surface temperature (LST); downscaling; MODIS; SRDA-Net

期刊名称： Remote Sensing

ISSN：

年卷期： 2025 年

页码：

收录情况： SCIE（2025版） ; ; EI（2025版）

摘要： Land surface temperature (LST) is a critical parameter in agricultural drought monitoring, crop growth analysis, and climate change research. However, the challenge of acquiring high-resolution LST data with both fine spatial and temporal scales remains a significant obstacle in remote sensing applications. Despite the high temporal resolution afforded by daily MODIS LST observations, the coarse (1 km) spatial scale of these data restricts their applicability for studies demanding finer spatial resolution. To address this challenge, a novel deep learning-based approach is proposed for LST downscaling: the spatial resolution downscaling attention network (SRDA-Net). The model is designed to upscale the resolution of MODIS LST from 1000 m to 250 m, overcoming the shortcomings of traditional interpolation techniques in reconstructing spatial details, as well as reducing the reliance on linear models and multi-source high-temporal LST data typical of conventional fusion approaches. SRDA-Net captures the feature interaction between MODIS LST and auxiliary data through global resolution attention to address spatial heterogeneity. It further enhances the feature representation ability under heterogeneous surface conditions by optimizing multi-source features to handle heterogeneous data. Additionally, it strengthens the model of spatial dependency relationships through a multi-level feature refinement module. Moreover, this study constructs a composite loss function system that integrates physical mechanisms and data characteristics, ensuring the improvement of reconstruction details while maintaining numerical accuracy and model interpret-ability through a triple collaborative constraint mechanism. Experimental results show that the proposed model performs excellently in the simulation experiment (from 2000 m to 1000 m), with an MAE of 0.928 K and an R2 of 0.95. In farmland areas, the model performs particularly well (MAE = 0.615 K, R2 = 0.96, RMSE = 0.823 K), effectively supporting irrigation scheduling and crop health monitoring. It also maintains good vegetation heterogeneity expression ability in grassland areas, making it suitable for drought monitoring tasks. In the target downscaling experiment (from 1000 m to 500 m and 250 m), the model achieved an RMSE of 1.804 K, an MAE of 1.587 K, and an R2 of 0.915, confirming its stable generalization ability across multiple scales. This study supports agricultural drought warning and precise irrigation and provides data support for interdisciplinary applications such as climate change research and ecological monitoring, while offering a new approach to generating high spatio-temporal resolution LST.

分类号：

  • 相关文献

[1]Evaluation Of Machine Learning Algorithms In Spatial Downscaling Of Modis Land Surface Temperature. Wu, Hua,Duan, Si-Bo,Li, Zhao-Liang,Wu, Hua,Li, Zhao-Liang,Li, Wan,Li, Wan,Ni, Li,Wu, Hua. 2019

[2]Extension Of The Generalized Split-Window A.lgorithm For Land Surface T emperature Retrieval To Atmospheres With Air Temperature Inversion. Zhan, C, Tang, BH, Li, ZL, Wu, H, Zhong, RF. 2017

[3]Evaluation Of Three Parametric Models F.or Estimating Directional Thermal R adiation From Simulation, Airborne, And Satellite Data. Liu, XY, Tang, BH, Li, ZL. 2018

[4]Radiance-Based Validation Of Land Surface T.emperature Products Derived From C ollection 6 Modis Thermal Infrared Data. Duan, SB, Li, ZL, Wu, H, Leng, P, Gao, MF, Wang, CG. 2018

[5]Cross-Satellite Comparison Of Operational Land S.urface Temperature Products Derived F rom Modis And Aster Data Over Bare Soil Surfaces. Duan, SB, Li, ZL, Cheng, J, Leng, P. 2017

[6]多尺度地理加权回归的地表温度降尺度研究. 祝新明,宋小宁,冷佩,胡容海. 2021

[7]中国蒸散时空变化规律及其对耕地旱灾影响研究. 杨艳颖,毛克彪. 2021

[8]Improving Spatial Soil Moisture Representation T.hrough The Integration Of S map And Proba-V Products. Fan, SD, Hu, YM, Wang, L, Liu, ZH, Shi, Z, Wu, WB, Pan, YC, Wang, GX, Zhu, AX, Li, B. 2018

[9]Evaluation Of Machine Learning Algorithms I.n Spatial Downscaling Of M odis Land Surface Temperature. Li, W, Ni, L, Li, ZL, Duan, SB, Wu, H. 2019

[10]Downscaling Land Surface Temperature By U.sing Random Forest Regression A lgorithm. Li, W, Ni, L, Li, ZL, Wu, H. 2018

[11]Selection Of Predictor Variables In Downscaling Land Surface Temperature Using Random Forest Algorithm. Li, W, Wu, H, Duan, SB, Li, ZL, Liu, QS. 2019

[12]Spatial Downscaling of MODIS Land Surface Temperatures Using Geographically Weighted Regression: Case Study in Northern China. Duan, Si-Bo,Li, Zhao-Liang,Li, Zhao-Liang.

[13]Extension of the Generalized Split-Window Algorithm for Land Surface Temperature Retrieval to Atmospheres With Heavy Dust Aerosol Loading. Fan, Xiwei,Tang, Bo-Hui,Wu, Hua,Fan, Xiwei,Fan, Xiwei,Tang, Bo-Hui,Yan, Guangjian,Li, Zhao-Liang,Bi, Yuyun,Zhou, Guoqing,Shao, Kun. 2015

[14]Progress in Retrieving Land Surface Temperature for the Cloud-Covered Pixels from Thermal Infrared Remote Sensing Data. Zhou Yi,Qin Zhi-hao,Bao Gang,Qin Zhi-hao,Bao Gang. 2014

[15]Estimation of Diurnal Cycle of Land Surface Temperature at High Temporal and Spatial Resolution from Clear-Sky MODIS Data. Duan, Si-Bo,Tang, Bo-Hui,Wu, Hua,Tang, Ronglin,Duan, Si-Bo,Li, Zhao-Liang,Bi, Yuyun,Li, Zhao-Liang,Zhou, Guoqing. 2014

[16]Intercomparison of Operational Land Surface Temperature Products Derived From MSG-SEVIRI and Terra/Aqua-MODIS Data. Duan, Si-Bo,Li, Zhao-Liang,Li, Zhao-Liang. 2015

[17]Direct estimation of land-surface diurnal temperature cycle model parameters from MSG-SEVIRI brightness temperatures under clear sky conditions. Duan, Si-Bo,Tang, Bo-Hui,Wu, Hua,Tang, Ronglin,Duan, Si-Bo,Li, Zhao-Liang,Li, Zhao-Liang.

[18]DERIVATION OF NEW SPLIT WINDOW ALGORITHM FOR RETRIEVING LAND SURFACE TEMPERATURE FROM FY-3/VIRR DATA. Chen, Yuanyuan,Duan, Si-Bo,Li, Zhao-Liang,Wei, Zhao,Li, Zhao-Liang. 2015

[19]Cross-satellite comparison of operational land surface temperature products derived from MODIS and ASTER data over bare soil surfaces. Duan, Si-Bo,Li, Zhao-Liang,Leng, Pei,Li, Zhao-Liang,Cheng, Jie.

[20]An Improved Algorithm for Retrieving Land Surface Emissivity and Temperature From MSG-2/SEVIRI Data. Gao, Caixia,Jiang, Xiaoguang,Gao, Caixia,Li, Zhao-Liang,Li, Zhao-Liang,Qiu, Shi,Tang, Bohui,Wu, Hua.

作者其他论文 更多>>