数字农科院2.0

Joint optimization of AI large and small models for surface temperature and emissivity retrieval using knowledge distillation

文献类型： 外文期刊

作者： Wang Dai;Kebiao Mao;Zhonghua Guo;Zhihao Qin;Jiancheng Shi;Sayed M. Bateni;Liurui Xiao

作者机构：

关键词： Artificial intelligence;Automated machine learning;Knowledge distillation;Large models;Remote sensing parameter retrieval

期刊名称： Artificial Intelligence in Agriculture

ISSN： 2589-7217

年卷期： 2025 年 15 卷 3 期

页码：

收录情况： SCIE（2025版） ; ; EI（2025版） ; ; CSCD（2025-2026年度） ; ; 农林核心（2024版）

摘要： The rapid advancement of artificial intelligence in domains such as natural language processing has catalyzed AI research across various fields. This study introduces a novel strategy, the AutoKeras-Knowledge Distillation (AK-KD), which integrates knowledge distillation technology for joint optimization of large and small models in the retrieval of surface temperature and emissivity using thermal infrared remote sensing. The approach addresses the challenges of limited accuracy in surface temperature retrieval by employing a high-performance large model developed through AutoKeras as the teacher model, which subsequently enhances a less accurate small model through knowledge distillation. The resultant student model is interactively integrated with the large model to further improve specificity and generalization capabilities. Theoretical derivations and practical applications validate that the AK-KD strategy significantly enhances the accuracy of temperature and emissivity retrieval. For instance, a large model trained with simulated ASTER data achieved a Pearson Correlation Coefficient (PCC) of 0.999 and a Mean Absolute Error (MAE) of 0.348 K in surface temperature retrieval. In practical applications, this model demonstrated a PCC of 0.967 and an MAE of 0.685 K. Although the large model exhibits high average accuracy, its precision in complex terrains is comparatively lower. To ameliorate this, the large model, serving as a teacher, enhances the small model's local accuracy. Specifically, in surface temperature retrieval, the small model's PCC improved from an average of 0.978 to 0.979, and the MAE decreased from 1.065 K to 0.724 K. In emissivity retrieval, the PCC rose from an average of 0.827 to 0.898, and the MAE reduced from 0.0076 to 0.0054. This research not only provides robust technological support for further development of thermal infrared remote sensing in temperature and emissivity retrieval but also offers important references and key technological insights for the universal model construction of other geophysical parameter retrievals.

分类号：

  • 相关文献

[1]Using automated machine learning techniques to explore key factors in anaerobic digestion: At the environmental factor, microorganisms and system levels. Yi Zhang,Zhangmu Jing,Yijing Feng,Shuo Chen,Yeqing Li,Yongming Han,Lu Feng,Junting Pan,Mahmoud Mazarji,Hongjun Zhou,Xiaonan Wang,Chunming Xu. 2023

[2]An Industrial-Grade Solution for Crop Disease Image Detection Tasks. Guowei Dai,Jingchao Fan. 2022

[3]Accelerating integrated prediction, analysis and targeted optimization for anaerobic digestion of biomass after hydrothermal pretreatment using automated machine learning. Yi Zhang,Xingru Yang,Yijing Feng,Zhiyue Dai,Zhangmu Jing,Yeqing Li,Lu Feng,Yanji Hao,Shasha Yu,Weijin Zhang,Yanjuan Lu,Chunming Xu,Junting Pan. 2024

[4]Two-step fusion framework for generating 10 m resolution soil moisture with high accuracy in the cotton fields of southern Xinjiang. Shenglin Li,Shuqi Jiang,Ni Song,Yang Han,Jinglei Wang. 2025

[5]Regional Soil Moisture Estimation Leveraging Multi-Source Data Fusion and Automated Machine Learning. Shenglin Li,Pengyuan Zhu,Ni Song,Caixia Li,Jinglei Wang. 2025

[6]Compressing recognition network of cotton disease with spot-adaptive knowledge distillation. Xinwen Zhang,Quan Feng,Dongqin Zhu,Xue Liang,Jianhua Zhang. 2024

[7]A novel framework for multi-layer soil moisture estimation with high spatio-temporal resolution based on data fusion and automated machine learning. Shenglin Li,Yang Han,Caixia Li,Jinglei Wang. 2024

[8]A new training strategy: Coordinating distillation techniques for training lightweight weed detection model. Peng Zhou,Yangxin Zhu,Chengqian Jin,Yixiang Gu,Yinuo Kong,Yazhou Ou,Xiang Yin,Shanshan Hao. 2025

[9]Ls-Svm Data Mining Analysis: How D.oes Biochar Influence Soil N et Nitrogen Mineralization In The Field?. Du, Zhenjie,Nan, Jiangkuan,Wang, Rui,Du, Zhenjie,Chen, Xiaomin,Deng, Jianqiang,Deng, Jianqiang. 2017

[10]LS-SVM data mining analysis: how does biochar influence soil net nitrogen mineralization in the field?. Deng, Jianqiang,Chen, Xiaomin,Nan, Jiangkuan,Du, Zhenjie,Deng, Jianqiang,Wang, Rui,Du, Zhenjie.

[11]Quantitative assessment of wheat quality using near-infrared spectroscopy: A comprehensive review. Du, Zhenjiao,Tian, Wenfei,Tilley, Michael,Wang, Donghai,Zhang, Guorong,Li, Yonghui. 2022

[12]High-throughput phenotyping of plant leaf morphological, physiological, and biochemical traits on multiple scales using optical sensing. Zhang, Huichun,Wang, Lu,Jin, Xiuliang,Bian, Liming,Ge, Yufeng. 2023

[13]Machine Learning Enables Selection of Epistatic Enzyme Mutants for Stability Against Unfolding and Detrimental Aggregation. Guangyue Li,Youcai Qin,Nicolas T. Fontaine,Matthieu Ng Fuk Chong,Miguel A. Maria‐Solano,Ferran Feixas,Xavier F. Cadet,Rudy Pandjaitan,Marc Garcia‐Borràs,Frederic Cadet,Manfred T. Reetz. 2021

[14]A bibliometric and visual analysis of artificial intelligence technologies-enhanced brain MRI research. Chen Xieling,Zhang Xinxin,Xie Haoran,Tao Xiaohui,Wang Fu Lee,Xie Nengfu,Hao Tianyong. 2021

[15]Harnessing Current Knowledge of DNA N6-Methyladenosine From Model Plants for Non-model Crops. Chachar Sadaruddin,Liu Jingrong,Zhang Pingxian,Riaz Adeel,Guan Changfei,Liu Shuyuan. 2021

[16]Smart breeding driven by big data, artificial intelligence, and integrated genomic-enviromic prediction. Xu Y.,Zhang X.,Li H.,Zheng H.,Zhang J.,Olsen M.S.,Varshney R.K.,Prasanna B.M.,Qian Q.. 2022

[17]Experimental Study of Garlic Root Cutting Based on Deep Learning Application in Food Primary Processing. Yang K.,Yu Z.,Gu F.,Zhang Y.,Wang S.,Peng B.,Hu Z.. 2022

[18]Development potential of nanoenabled agriculture projected using machine learning. Peng Deng,Yiming Gao,Li Mu,Xiangang Hu,Fubo Yu,Yuying Jia,Zhenyu Wang,Baoshan Xing. 2023

[19]Exploring blockchain and artificial intelligence in intelligent packaging to combat food fraud: A comprehensive review. Yang Y.,Du Y.,Gupta V.K.,Ahmad F.,Amiri H.,Pan J.,Aghbashlo M.,Tabatabaei M.,Rajaei A.. 2024

[20]Transcriptomics, proteomics, and metabolomics interventions prompt crop improvement against metal(loid) toxicity. Ali Raza,Hajar Salehi,Shanza Bashir,Javaria Tabassum,Monica Jamla,Sidra Charagh,Rutwik Barmukh,Rakeeb Ahmad Mir,Basharat Ahmad Bhat,Muhammad Arshad Javed,Dong Xing Guan,Reyazul Rouf Mir,Kadambot H.M. Siddique,Rajeev K. Varshney. 2024

作者其他论文 更多>>