Spatiotemporal database in above- and belowground net primary production across multi-data-driven models on the Tibetan Plateau at 1km resolution
Corresponding author: Peng Hou (houpcy@163.com)
Abstract: The Tibetan Plateau (TP), a climate-sensitive region pivotal to global carbon cycling, encounters challenges in assessing vegetation carbon dynamics due to sparse observations and data-scarcity, particularly for Belowground Net Primary Production (BNPP). To address those, we employed 96 data-driven models—encompassing linear, machine-learning, and deep-learning—integrated with filed observations and Monte Carlo methods to simulate Aboveground Net Primary Production (ANPP) and BNPP at 1 km resolution on the TP. Top-performing ANPP models (xgbLinear, Rborist, and HyFIS) achieved efficiencies (R2) between 0.80 and 0.88, while BNPP models (xgbLinear, xgbTree, and HyFIS) ranged from 0.93 to 0.96. Spatially, ANPP decreased from southeast to northwest, whereas BNPP varied with latitude, with notable interannual changes in Lhasa, Nyingchi, and so on. ANPP declined significantly at a rate of −0.003 to −0.004 Pg C yr−1, while BNPP fluctuated between −0.003 and 0.004 Pg C yr−1. Notably, Rborist and xgbTree excelled for ANPP and BNPP, respectively. This multi-data-driven approach significantly enhances the precision of ANPP and BNPP assessments, providing novel insights into carbon storage, distribution, and cycling in the TP. These findings establish a robust foundation for predicting ecosystem responses to climate change and guiding adaptive management strategies for carbon sustainability in one of the world's most vulnerable regions.
Filename: ANPP_xgblinear_Tibetan _1981-2018_1km_tif.zip; ANPP_Rborist_Tibetan _1981-2018_1km_tif.zip; ANPP_HYFIS_Tibetan _1981-2018_1km_tif.zip; BNPP_xgblinear_Tibetan _1981-2018_1km_tif.zip; BNPP_xgbTree_Tibetan _1981-2018_1km_tif.zip; BNPP_HYFIS_Tibetan _1981-2018_1km_tif.zip.
File information：The names of each Zip compressed file are composed of the observation object, simulation model, region, time range, spatial resolution, and data format. For example, 'ANPP_xgblinear_Tibetan_1981 - 2018_1km_tif.zip' consists of ANPP (observation object) + '_' + xgblinear (simulation model) + '_' + Tibetan (region) + '_' + 1981-2018 (time range) + '_' + 1km (spatial resolution) + '_' + 1km (spatial resolution) + '_' + tif (data format) + '.zip'. Among them, ANPP is Aboveground Net Primary Production; BNPP is Belowground Net Primary Production; xgbLinear is a linear model, Rborist/xgbTree are machine - learning models of the linear model, and HYFIS is a deep - learning model.The unit for these data is 'g C m-2 yr-1'.
Author contributions: Tao Zhou contributed to the conceptualization, methodology, software, and writing - original draft, review, editing; Benjamin Laffitte, Jianfei Cao and Guangjin Zhou supervised manuscript writing; Yuting Hou contributed to the data curation and software; Qiao Wang contributed to writing – review; Peng Hou contributed to data curation, writing - original draft preparation, software, and writing–review, editing; all authors contributed to the final preparation of the manuscript.
