The Soil Nutrient Spatial Interpolation Algorithm Based on KNN and IDW - Archive ouverte HAL Access content directly
Conference Papers Year : 2016

The Soil Nutrient Spatial Interpolation Algorithm Based on KNN and IDW

(1, 2) , (1, 2) , (1, 2) , (1, 2) , (3)
1
2
3

Abstract

For breaking the limitation of the GIS platform and realizing the soil nutrients spatial interpolation algorithm for any points in the monitoring area to transplant to the mobile platforms, this paper established the spatial index of the soil nutrient sampling points utilizing the K-D Tree as the space splitting algorithm of the soil nutrient sampling points. On this basis, the K nearest neighbor search of the soil nutrient sampling points was also implemented employing KNN algorithm. Finally, the soil nutrient spatial interpolation was realized based on KNN and IDW algorithm. Meanwhile, the accuracy of the algorithm and the influence to the different soil nutrient elements affected by the K value in KNN algorithm were also verified. The results show that the soil nutrient spatial interpolation algorithm was viable to predict the element contents of soil nutrient during the running time was less than 3 s. To reach the best accuracy, the values of the proximal point K for predicting the PH, organic matter, rapid available phosphorus and rapid available potassium should be set as 85, 15, the largest sample space and 65 respectively. The optimal average absolute error of the pH, organic matter, rapid available phosphorus and rapid available potassium was 0.0405, 0.3870, 0.0015 respectively.
Fichier principal
Vignette du fichier
434296_1_En_40_Chapter.pdf (403.13 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01557849 , version 1 (06-07-2017)

Licence

Attribution - CC BY 4.0

Identifiers

Cite

Xin Xu, Hua Yu, Guang Zheng, Hao Zhang, Lei Xi. The Soil Nutrient Spatial Interpolation Algorithm Based on KNN and IDW. 9th International Conference on Computer and Computing Technologies in Agriculture (CCTA), Sep 2015, Beijing, China. pp.412-424, ⟨10.1007/978-3-319-48357-3_40⟩. ⟨hal-01557849⟩
156 View
102 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More