基于人工智能的地球物理参数反演范式理论及判定条件

• 作者： 毛克彪 ^1,2,3 张晨阳 ⁴ 施建成 ⁵ 王旭明 ² 郭中华 ² 李春树 ² 董立新 ⁶ 吴门新 ⁷ 孙瑞静 ⁶ 武胜利 ⁶ 姬大彬 ³ 蒋玲梅 ⁸ 赵天杰 ³ 邱玉宝 ³ 杜永明 ³ 徐同仁 ⁸
• 作者单位：
  1.  中国农业科学院农业资源与农业区划研究所 北方干旱半干旱耕地高效利用全国重点实验室，北京 100081

  2.  宁夏大学 物理与电子电气工程学院，宁夏银川 750021

  3.  中国科学院空天信息创新研究院 遥感科学国家重点实验室，北京 100094

  4.  北京大学 环境科学与工程学院，北京 100871

  5.  中国科学院国家空间科学中心，北京 100190

  6.  国家卫星气象中心，北京 100081

  7.  国家气象中心，北京 100081

  8.  北京师范大学 地理科学部，北京 100875
• 提交时间：2023-05-30

摘要: 人工智能 （Artificial Intelligence） 技术已在学术领域和工程应用掀起了研究高潮，在地球物理参数和农业气象遥感参数反演方面也表现出了强大的应用潜力。目前大部分人工智能技术在地学和农学的应用还是黑箱，应用没有物理意义或缺乏可解释性及通用性。本研究提出基于人工智能耦合物理和统计方法的地球物理参数反演范式理论，即先基于物理能量平衡方程进行物理逻辑推理，从理论上构造反演方程组，然后基于物理推导构建泛化的统计方法。通过物理模型模拟获得物理方法的代表性解以及利用多源数据获得统计方法代表性的解作为深度学习的训练和测试数据库，最后利用深度学习进行优化求解。判定形成具有通用性和物理可解释的范式条件包括：（1） 输入与输出变量 （参数） 之间必须存在因果关系；（2） 输入和输出变量 （参数） 之间理论上可以构建闭合的方程组 （未知数个数少于或等于方程组个数），也就是说输出参数可以被输入参数唯一确定。如果输入参数 （变量） 和输出参数 （变量） 之间存在很强的因果关系，则可以直接使用深度学习进行反演。如果输入参数和输出参数之间存在弱相关性，则需要添加先验知识来提高输出参数的反演精度。此外，本研究以农业遥感中的关键参数地表温度、发射率、近地表空气温度和大气水汽含量联合反演作为案例对理论进行了证明，分析结果表明本理论是可行的，并且可以辅助优化设计卫星传感器波段组合。本理论和判定条件的提出在地球物理参数反演史上具有里程碑意义。

Abstract: Deep learning is one of the most important technologies in the field of artificial intelligence, which has sparked a research boom in academic and engineering applications. It also shows strong application potential in remote sensing retrieval of geophysical parameters. The cross-disciplinary research is just beginning, and most deep learning applications in geosciences are still black boxes, with most applications lacking physical significance, interpretability, and universality. A paradigm theory for geophysical parameter retrieval based on artificial intelligence coupled physics and statistical methods was proposed in this research. Firstly, physical logic deduction was performed based on the physical energy balance equation, and the inversion equation system was constructed theoretically. Then, a fuzzy statistical method was constructed based on physical deduction. Representative solutions of physical methods were obtained through physical model simulation, and other representative solutions as the training and testing database for deep learning were obtained using multi-source data. Finally, the solution using deep learning was optimized. The conditions for determining the formation of a universal and physically interpretable paradigm are: (1) There must be a causal relationship between input and output variables (parameters); (2) In theory, a closed system of equations (with unknowns less than or equal to the number of equations) can be constructed between input and output variables (parameters), which means that the output parameters can be uniquely determined by the input parameters. If there is a strong causal relationship between input parameters (variables) and output parameters (variables),deep learning can be directly used for inversion. If there is a weak correlation between the input and output parameters, prior knowledge needs to be added to improve the inversion accuracy of the output parameters. Thermal infrared remote sensing data were used to retrieve land surface temperature, emissivity, near surface air temperature and atmospheric water vapor content as a case to prove the theory. The analysis results show that the proposed theory and conditions are feasible, and the accuracy and applicability are better than traditional methods. The theory and judgment conditions of geophysical parameter retrieval paradigms are also applicable for target recognition such as remote sensing classification, but it needs to be interpreted from a different perspective. For example, the feature information extracted by different convolutional kernels must be able to uniquely determine the target. Under satisfying with the conditions of paradigm theory, the inversion of geophysical parameters based on artificial intelligence is the best choice. The proposal of this theory is of milestone significance in the history of geophysical parameter retrieval.

• 期刊： 智慧农业（中英文）
• 分类： 农、林、牧、渔 >> 农业基础学科
• 引用： ChinaXiv:202305.00234 (或此版本 ChinaXiv:202305.00234V1)
  DOI:10.12133/j.smartag.SA202304013
  CSTR:32003.36.ChinaXiv.202305.00234.V1
• 推荐引用方式： 毛克彪,张晨阳,施建成,王旭明,郭中华,李春树,董立新,吴门新,孙瑞静,武胜利,姬大彬,蒋玲梅,赵天杰,邱玉宝,杜永明,徐同仁.(2023).基于人工智能的地球物理参数反演范式理论及判定条件.智慧农业（中英文）.doi:10.12133/j.smartag.SA202304013 (点此复制)