Spatiotemporal Variation and Influencing Factors of Vegetation Gross Primary Productivity in the Yangtze River Delta Urban Agglomeration
ZHANG Yanting
TANG Diwei
TAO Wen
WANG Yuxing
Abstract：To clarify the spatiotemporal evolution patterns and driving mechanisms of gross primary productivity(GPP)in the Yangtze River Delta urban agglomeration from 2001 to 2023,remote sensing and meteorological data were integrated.A multi-scale analysis of GPP evolution characteristics was conducted using the coefficient of variation,Theil-Sen median trend combined with the Mann-Kendall test,and the Hurst exponent.By comparing the predictive performance of four machine learning models,the optimal light gradient booster machine(LightGBM)model was selected,and the Shapley additive explanations(SHAP)method was employed to reveal the importance and interaction effects of driving factors.It was found that the top 5 multi-year average GPP in the Yangtze River Delta region from 2001 to 2023 was measured at 1130.41g/(m2·a),with a significant upward trend observed in interannual variation(annual average change rate was 6.71g/(m2·a),P<0.05).Spatially,a pattern of ″high in the south and low in the north″ was presented:the southern forested area was designated as a high-value zone,while the northern region dominated by cultivated land and construction land was classified as a low-value zone.The LightGBM model was proven to be superior to the other models.The SHAP results demonstrated that the top 5 contribution degrees of driving factors were ranked as follows:elevation>vapor pressure deficit>nighttime light>slope>aridity index.The enhancement of GPP by the interaction between elevation and climate-anthropogenic factors was particularly notable.The impacts of various driving factors were found to exhibit distinct nonlinear characteristics,resulting in complex effects on vegetation GPP.This study was expected to provide a scientific reference for vegetation conservation and ecological governance in the Yangtze River Delta.
Keywords：gross primary productivityspatiotemporal distributionmachine learningSHAPinteraction effectdriving factorYangtze River Delta urban agglomeration
Publication Date：2025-12-30
Online Publishing Date：2025-12-10(First online date of this platform, not the publication date of the document)
Pages：8( 593-600 )