作 者：
Guanghui Zheng;Caixia Jiao;Xinglong Xie;Xuefeng Cui;Gang Shang;Chengyi ZHAO;Rong Zen
单 位：
School of Geographic Sciences, Nanjing University of Information Science&Technology, Nanjing 210044 (China);School of Geographic Sciences, Nanjing University of Information Science&Technology, Nanjing 210044 (China;Meteorology and Climate Centre, School of Mathematics and Statistics, University College Dublin, Belfield, Dublin 4 (Ireland); School of Systems Science, Beijing Normal University, Beijing 100875 (China);Institute of Soil Science, Chinese Academy of Science, Nanjing 210008 (China);School of Geographic Sciences, Nanjing University of Information Science&Technology, Nanjing 210044 (China)
关键词：
partial least squares regression;particle size distribution;soil organic carbon;stepwise multiple linear regression;support vector machine regression;LOESS PLATEAU;CARBON;QUALITY;REGION;FIELD;SE
摘 要：
Soil bulk density (BD) is not only an important physical property but is also an essential factor for weight-to-volume conversion. However, this parameter is often missing from soil databases because its direct measurement is labor-intensive, time-consuming, and sometimes impractical, particularly on a large scale. Therefore, pedotransfer functions (PTFs) have been developed to predict BD for several decades. In this study, six previously revised PTFs (including five basic functions and stepwise multiple linear regression (SMLR)), partial least squares regression (PLSR), and support vector machine regression (SVMR) were used to develop BD PTFs for coastal soil in East China. The independent variables included soil organic carbon (SOC) and particle size distribution (PSD). To compare the robustness and reliability of various methods, the calibration and prediction processes were performed 1,000 times using the calibration and validation sets divided by a random sampling algorithm. The results showed that SOC was the most important predictor, and the revised PTFs performed reasonably, although only SOC was included. The PSD data were useful for a better prediction of BD, and the sand and clay fractions were the second and third most important properties for the prediction of BD. The PLSR showed slightly better PTFs for the study area (the average adjusted coefficient of determination for prediction was 0.581). These results suggest that PLSR with SOC and PSD data can be used for PTFs to fill in the missing BD data in coastal soil databases and provide important information that can be used to estimate coastal carbon storage, which will further improve our understanding of sea-land interactions under global warming.
