Comparisons of numerical phenology models and machine learning methods on predicting the spring onset of natural vegetation across the Northern Hemisphere. (November 2021)

• Record Type: Journal Article
• Authors: Li, Wanjing; Xin, Qinchuan; Zhou, Xuewen; Zhang, Zhicheng; Ruan, Yongjian
• Is Part Of: Ecological indicators. Volume 131(2021)
• Publication Date: 2021-11
• Subjects: AGSI accumulated growing season index model -- DV deciduous vegetation -- EV evergreen vegetation -- GDD growing degree day -- GLDAS global land data assimilation system -- MGDD1 modified growing degree day model version 1 -- MGDD2 modified growing degree day model version 2 -- MGDD3 modified growing degree day model version 3 -- MODIS moderate resolution imaging spectroradiometer -- PAR parallel model -- PHO daily photoperiod -- RF random forests -- RMSE root mean square error -- SCE-UA shuffled complex evolution method developed at the university of Arizona -- SD stressed deciduous vegetation -- SGDD standard growing degree day model -- SGSI standard growing season index model -- SVM support vector machine -- TMX daily maximum temperature -- TMN daily minimum temperature -- VPD daily vapor pressure deficit -- WIA Willmott's index of agreement; Numerical models -- Machine learning -- Phenology modeling -- Remote sensing; Environmental monitoring -- Periodicals; Environmental management -- Periodicals; Environmental impact analysis -- Periodicals; Environmental risk assessment -- Periodicals; Sustainable development -- Periodicals; 333.71405
• DOI: 10.1016/j.ecolind.2021.108126
• Languages: English
• ISSNs: 1470-160X

Abstract

Highlights: Numerical models perform well on predicting spring onsets of deciduous vegetation. Numerical models calibrated using field data outperform machine learning models. Machine learning shows potential in predicting vegetation spring onset. Abstract: The timing of vegetation spring onset is largely influenced by climate factors, making it sensitive to climate variation. Robust models that predict vegetation spring onset via the climate forcing data are needed in the land surface models for understanding the impacts of climate change on vegetation processes. In this study, we apply and assess both numerical phenology models and the machine learning models on predicting the timing of spring onset for different vegetation types, including deciduous vegetation, evergreen vegetation and stressed deciduous vegetation. We perform model calibration for numerical phenology models and machine learning models using both in-situ observations of spring onset dates from National Phenology Network in the United States and satellite-derived green-up dates in the Northern Hemisphere. Our experiment showed better performance of numerical models calibrated by ground phenology observations. Among all the numerical phenology models, the models developed based on Growing Season Index perform well on predicting the spring onsets of deciduous vegetation and stressed deciduous vegetation across the Northern Hemisphere. Machine learning models if trained appropriately could also capture the spatial variation of satellite-derived spring onset dates. Our study highlights the need of improvements on numerical phenology models for their uses in the land surface models. We also illustrate the benchmarking role of the machine learning models on predicting vegetation spring onsets via climate variables.