TSIT-PatchTST模型:一种净生态系统交换量(NEE)缺失值插补方法  

TSIT-PatchTST model:a missing value interpolation method for net ecosystem exchange(NEE)

作　　者：齐建东[1,2] 石成城 吴鹏 Qi Jiandong;Shi Chengcheng;Wu Peng(School of Information,Beijing Forestry University,Beijing 100083,China;Engineering Research Center for Forestry-Oriented Intelligent Information Processing of National Forestry and Grassland Administration,Beijing 100083,China)

机构地区：[1]北京林业大学信息学院,北京100083 [2]国家林业和草原局林业智能信息处理工程技术研究中心,北京100083

出　　处：《北京林业大学学报》2025年第2期105-118,共14页Journal of Beijing Forestry University

基　　金：国家自然科学基金项目(32071842);国家重点研发计划项目(2022YFD2200304)。

摘　　要：【目的】净生态系统交换量(NEE)是评估陆地生态系统在全球碳循环中作用的重要指标,NEE原始观测数据缺失值的插补精度会直接影响生态系统关键参数的可靠性和精确性。为提高不同植被NEE在长时间连续性数据缺失情景下的插补精度,提出一种融合时间序列表征向量的TSIT-PatchTST深度学习模型。【方法】以全球长期通量观测网络站点的碳通量因子数据为研究对象,通过构造短缺失(1 d)、中缺失(7 d)、长缺失(30 d)3种随机连续数据缺失场景,评估边际分布采样法(MDS)、PatchTST模型、TS2Vec-PatchTST模型和TSIT-PatchTST模型在8种不同植被类型下NEE的插补结果。【结果】在短缺失场景下,4种插补方法都表现出最优的性能。随着连续缺失天数的增多,MDS的插补精度逐渐下降,该方法在长缺失场景下已不能对NEE进行有效插补,而其他3种深度学习模型能够有效地插补NEE缺失数据。综合3种缺失场景,TSIT-PatchTST模型表现出最优的插补性能,尤其在长缺失场景下该模型具有较高的插补精度。长缺失场景下,TSIT-PatchTST模型对31个站点插补结果的平均均方误差(MSE)为0.942μmol/(m2·s),平均绝对误差(MAE)为0.628μmol/(m2·s),平均R2为0.457。与PatchTST模型的插补结果相比,TSIT-PatchTST模型平均MSE下降了53.3%,平均MAE下降了39.7%,平均R2相持平。【结论】综合8种植被类型和3种缺失场景的应用结果,得出TSITPatchTST模型的插补效果最佳,并具有适应性。TSIT-PatchTST模型可应用于时间序列数据缺失场景以提高数据插补精度。[Objective] Net ecosystem exchange(NEE) is an important indicator for evaluating the role of terrestrial ecosystems in the global carbon cycle.The accuracy of imputation of missing values in NEE raw observation data directly affects the reliability and precision of key ecosystem parameters.To enhance the imputation accuracy of NEE in scenarios of continuous long-term data gaps across different vegetation types,a TSIT-PatchTST model was proposed based on deep learning.[Method] Using carbon flux factor data from sites within the global long-term flux observation network as the research object,three types of random continuous data gap scenarios were constructed,including short missing(1 d),medium missing(7 d),and long missing(30 d).The imputation results of marginal distribution sampling(MDS) method,PatchTST model,TS2Vec-PatchTST model,and TSIT-PatchTST model under eight different vegetation types were evaluated.[Result] In the scenario of short missing,all imputation methods demonstrated optimal performance.As the number of consecutive missing days increased,the imputation accuracy of MDS method gradually declined,and it was no longer effective for imputing NEE in the long missing scenario.In contrast,the three deep learning models were capable of effectively imputing missing NEE data.Considering all three missing scenarios,the TSIT-PatchTST model exhibited the best imputation performance,particularly with a high accuracy in long missing scenarios.In the long missing scenario,the TSIT-PatchTST model achieved an average mean squared error(MSE) of 0.942 μmol/(m2·s),an average mean absolute error(MAE) of 0.628 μmol/(m2·s),and an average R2 of 0.457 across 31 sites.Compared with PatchTST model,the TSIT-PatchTST model reduced the average MSE by 53.3%,average MAE by 39.7%and the average R2 remained unchanged.[Conclusion] Integrating the performance across eight vegetation types and three missing scenarios,the TSIT-PatchTST model demonstrates the best imputation effect and adaptability.It can be applied to the problem

关 键 词：深度学习 模型开发 数据插补 TSIT-PatchTST模型 碳循环 植被类型 净生态系统交换量(NEE) 

分 类 号：S718.5[农业科学—林学] TP181[自动化与计算机技术—控制理论与控制工程]