At the 2024 China International Big Data Industry Expo (Big Data Expo), the project "Remote Sensing Parameter AI Inversion Paradigm Theory and Multi-Parameter Integrated Inversion Technology," jointly developed by the Institute of Agricultural Resources and Regional Planning (IARRP) of the Chinese Academy of Agricultural Sciences (CAAS), the National Space Science Center of the Chinese Academy of Sciences, Ningxia University, and the National Satellite Meteorological Center, was honored with the Excellence Award for Outstanding Scientific and Technological Achievements at the 2024 China International Big Data Industry Expo. This recognition showcases China's leading position in the integration of agricultural remote sensing monitoring and artificial intelligence technology .

In recent years, Artificial Intelligence (AI) technology has sparked a research boom in both academic and engineering applications, demonstrating significant potential in the inversion of geophysical parameters and agricultural meteorological remote sensing parameters. Most AI technologies currently applied in geosciences and agriculture are still considered as "black boxes," lacking physical significance, interpretability, and generality. Led by experts including Mao Kebiao, Wang Han, Yuan Zijin, Shi Jiancheng, Sun Xuehong, and Wu Shengli, the project proposed innovative theories and conditions for remote sensing parameter AI inversion paradigms and made a breakthrough by developing a groundbreaking multi-parameter artificial intelligence integrated inversion technology based on thermal infrared remote sensing.

Targeting parameters such as land surface temperature, emissivity, near-surface air temperature, and atmospheric water vapor content, the team combined deep learning techniques with a combination of physical and statistical methods to develop a comprehensive inversion solution. By leveraging "direct synchronous inversion" and "iterative inversion" modes, the team fully explored the inherent relationships between remote sensing parameters, combined with parameter validation from different band combinations and multiple-source databases, showing an accuracy improvement of over 10% and a significant enhancement in the overall accuracy of remote sensing multi-parameter inversion.

This project not only achieved significant results in the academic field, with over 70 papers published, 15 invention patents granted, and 10 software copyrights authorized, but also successfully developed a large AI parameter inversion model widely applied in agricultural remote sensing monitoring. The project established a theoretical and technical foundation for remote sensing parameter AI inversion big model, driving the intelligent development of agricultural remote sensing and providing strong technical support for precision agriculture and meteorological disaster monitoring in China.

This award fully demonstrates the innovative strength of IARRP in applying big data and artificial intelligence technologies to the field of agricultural remote sensing, laying a foundation for further promoting agricultural modernization and smart agriculture development in the future.