Research on optimizing the inversion of thermal infrared remote sensing surface temperature and emissivity based on mixture of experts
文献类型: 外文期刊
作者: Liu Ma;Kebiao Mao;Zhonghua Guo;Zijin Yuan
作者机构:
关键词: iterative optimization strategy;land surface emissivity;Land surface temperature;mixture of experts
期刊名称: Remote Sensing Letters
ISSN: 2150-7058
年卷期: 2025 年 16 卷 12 期
页码:
收录情况: SCIE(2025版) ; ; EI(2025版)
摘要: To further improve the inversion accuracy of land surface temperature (LST) and land surface emissivity (LSE) of moderate resolution imaging spectroradiometer (MODIS) data, an iterative optimization strategy based on a mixture of experts (MoE) is proposed. In the simulation experiment, compared with the 4-band combination, the mean absolute error (MAE) of LST inversion of 5-band input is reduced from 0.7572 K to 0.5089 K, and the Pearson correlation coefficient (PCC) is increased from 0.9812 to 0.9989. The LSE inversion accuracy is also significantly improved, and the error between the optimized disturbance simulation data and the original simulation data is tiny. In the actual data verification, after optimization, the LST inversion MAE is reduced from 1.7768 K to 1.1237 K, and the PCC is increased from 0.9816 to 0.9946. The iterative optimization strategy proposed in this study significantly improves the accuracy of LST and LSE in MODIS data, provides reliable data support for climate change, environmental assessment, and agricultural disaster monitoring, and has broad application prospects.
分类号:
- 相关文献
作者其他论文 更多>>
-
Joint optimization of AI large and small models for surface temperature and emissivity retrieval using knowledge distillation
作者:Wang Dai;Kebiao Mao;Zhonghua Guo;Zhihao Qin;Jiancheng Shi;Sayed M. Bateni;Liurui Xiao
关键词:Artificial intelligence;Automated machine learning;Knowledge distillation;Large models;Remote sensing parameter retrieval
-
AI-Based Downscaling of MODIS LST Using SRDA-Net Model for High-Resolution Data Generation
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
-
An AI-Based Nested Large–Small Model for Passive Microwave Soil Moisture and Land Surface Temperature Retrieval Method
作者:Mengjie Liang;Kebiao Mao;Jiancheng Shi;Sayed M. Bateni;Fei Meng
关键词:joint iterative retrieval;land surface temperature;multi-hierarchy classification;passive microwave remote sensing;soil moisture
-
Evaluation and prediction of the effects of planetary orbital variations to earth’s temperature changes
作者:Mengmeng Cao;Kebiao Mao;Sayed M. Bateni;Jing M. Chen;Essam Heggy;Jong Seong Kug;Xinyi Shen
关键词:Earth’s temperature;Greenhouse gases;Planetary motion
-
Global spatiotemporal variation analysis and AI prediction of terrestrial high-temperature droughts
作者:Xiangxiang Ma;Kebiao Mao;Zijin Yuan;Zhonghua Guo;Xuehong Sun;Sayed M. Bateni
关键词:Agricultural Disaster Prevention and Control;Deep Learning;Extreme Climate;Spatiotemporal Variation Patterns;SPI STI;Wavelet Transform
-
A normal form for synchronous land surface temperature and emissivity retrieval using deep learning coupled physical and statistical methods
作者:Han Wang;Kebiao Mao;Jiancheng Shi;Sayed M. Bateni;Dorjsuren Altantuya;Bayarsaikhan Sainbuyan;Yuhai Bao
关键词:Deep learning (DL);Land surface emissivity (LSE);Land surface temperature (LST);Physical and statistical methods;Retrieval
-
Developing a land development compensation model for returned land in tract expropriation: Towards a unified urban-rural land market in China
作者:Jingpeng Guo;Yinghui Zhao;Frank Yonghong Li;Kebiao Mao;Jinfeng He;Qiang He
关键词:Empirical analysis;Land development compensation;Land expropriation;Land valuation;Returned land