| 摘要: |
|
| 关键词: |
| DOI： |
|
| 基金项目: |
|
| Predicting soil elements spatial distribution with two models |
| Zheng Jia,Li Xiaochuan,Ding Xiaogang,Mo Xiaoyong,Zhang Yingzhong,Zhao Zhengyong,Zhang Xiangyu,Qi Ye |
| (Guangdong Academy of Forestry;College of Forestry and Landscape Architecture, South China
Agricultural University;College of Forestry, Guangxi University) |
| Abstract: |
| The BP artificial neural network and the
spatial interpolations model (Universal Kriging, Spline
method and Inverse Distance Weighted) were used to
predict the forest soil elements (exchangeable calcium,
sulfur and exchangeable magnesium) spatial distribution
in Yuncheng district and Yun’an district in Yunfu city,
Guangdong province. It was showed that the highest
content element in the forestry soil was exchangeable
Ca (of 17.333—1 169.033 mg·kg -1 ), followed by total S
and exchangeable Mg with concentration of (60.787—
354.600 and 8.320—51.580 mg·kg -1 , respectively. The
coefficient of variation for the three elements varied
from 33.43%—106.34%. The variation coefficient of
exchangeable Ca in Yun’an district reached 106.34%,
indicating high variation in the concentration of ex-
changeable Ca. Among three interpolation methods,
deviation from the Universal Kriging was smaller than
from other methods. But the Universal Kriging was un-
able to predict other elements well in the three elements,
except exchangeable Mg. By comparison, we can con-
clude that the BP artificial neural network was the best
model to predict the element spatial distribution in this
study. |
| Key words: Forest soil · Elements · Spatial interpola-
tion model · BP artificial neural network · Yunfu |
