中国地理科学 ›› 2019, Vol. 20 ›› Issue (2): 258-269.doi: 10.1007/s11769-019-1020-8

• 论文 • 上一篇    下一篇

Combining Environmental Factors and Lab VNIR Spectral Data to Predict SOM by Geospatial Techniques

GUO Long1, ZHANG Haitao1, CHEN Yiyun2, QIAN Jing2   

  1. 1. College of Resources and Environment, Huazhong Agricultural University, Wuhan 430070, China;
    2. School of Resource and Envi-ronment, Wuhan University, Wuhan 430070, China
  • 收稿日期:2017-06-09 出版日期:2019-04-27 发布日期:2019-02-23
  • 通讯作者: QIAN Jing.E-mail:2011202050149@whu.edu.cn E-mail:2011202050149@whu.edu.cn
  • 基金资助:

    Under the auspices of the Natural Science Foundation of Hubei (No. 2018CFB372), the Fundamental Research Funds for the Central Universities (No. 2662016QD032), the Key Laboratory of Aquatic Plants and Watershed Ecology of Chinese Academy of Sciences (No. Y852721s04), the Chinese National Natural Science Foundation (No. 41371227), the National Undergraduate Inno-vation and Entrepreneurship Training Program (No. 201810504023, 201810504030)

Combining Environmental Factors and Lab VNIR Spectral Data to Predict SOM by Geospatial Techniques

GUO Long1, ZHANG Haitao1, CHEN Yiyun2, QIAN Jing2   

  1. 1. College of Resources and Environment, Huazhong Agricultural University, Wuhan 430070, China;
    2. School of Resource and Envi-ronment, Wuhan University, Wuhan 430070, China
  • Received:2017-06-09 Online:2019-04-27 Published:2019-02-23
  • Contact: QIAN Jing E-mail:2011202050149@whu.edu.cn
  • Supported by:

    Under the auspices of the Natural Science Foundation of Hubei (No. 2018CFB372), the Fundamental Research Funds for the Central Universities (No. 2662016QD032), the Key Laboratory of Aquatic Plants and Watershed Ecology of Chinese Academy of Sciences (No. Y852721s04), the Chinese National Natural Science Foundation (No. 41371227), the National Undergraduate Inno-vation and Entrepreneurship Training Program (No. 201810504023, 201810504030)

摘要:

Soil organic matter (SOM) is an important parameter related to soil nutrient and miscellaneous ecosystem services. This paper attempts to improve the performance of traditional partial least square regression (PLSR) model by considering the spatial autocorrelation and soil forming factors. Surface soil samples (n=180) were collected from Honghu City located in the middle of Jianghan Plain, China. The visible and near infrared (VNIR) spectra and six environmental factors (elevation, land use types, roughness, relief amplitude, enhanced vegetation index, and land surface water index) were used as the auxiliary variables to construct the multiple linear regression (MLR), PLSR and geographically weighted regression (GWR) models. Results showed that:1) the VNIR spectra can increase about 39.62% prediction accuracy than the environmental factors in predicting SOM; 2) the comprehensive variables of VNIR spectra and the environmental factors can improve about 5.78% and 44.90% relative to soil spectral models and soil environmental models, respectively; 3) the spatial model (GWR) can improve about 3.28% accuracy than MLR and PLSR. Our results suggest that the combination of spectral reflectance and the environmental variables can be used as the suitable auxiliary variables in predicting SOM, and GWR is a promising model for predicting soil properties.

关键词: visible near infrared spectral reflectance, environmental factors, spatial characteristics, partial least squares regression, geographically weighted regression

Abstract:

Soil organic matter (SOM) is an important parameter related to soil nutrient and miscellaneous ecosystem services. This paper attempts to improve the performance of traditional partial least square regression (PLSR) model by considering the spatial autocorrelation and soil forming factors. Surface soil samples (n=180) were collected from Honghu City located in the middle of Jianghan Plain, China. The visible and near infrared (VNIR) spectra and six environmental factors (elevation, land use types, roughness, relief amplitude, enhanced vegetation index, and land surface water index) were used as the auxiliary variables to construct the multiple linear regression (MLR), PLSR and geographically weighted regression (GWR) models. Results showed that:1) the VNIR spectra can increase about 39.62% prediction accuracy than the environmental factors in predicting SOM; 2) the comprehensive variables of VNIR spectra and the environmental factors can improve about 5.78% and 44.90% relative to soil spectral models and soil environmental models, respectively; 3) the spatial model (GWR) can improve about 3.28% accuracy than MLR and PLSR. Our results suggest that the combination of spectral reflectance and the environmental variables can be used as the suitable auxiliary variables in predicting SOM, and GWR is a promising model for predicting soil properties.

Key words: visible near infrared spectral reflectance, environmental factors, spatial characteristics, partial least squares regression, geographically weighted regression