Next Article in Journal
Improving the Landscape and Tourism in Marginal Areas: The Case of Land Consolidation Associations in the North-West of Italy
Previous Article in Journal
Benefits Are Limited with High Nitrogen Fertiliser Rates in Kikuyu-Ryegrass Pasture Systems
Open AccessArticle

Soil Mapping Based on the Integration of the Similarity-Based Approach and Random Forests

by Desheng Wang 1,2,3 and A-Xing Zhu 1,2,3,4,5,*
1
Key Laboratory of Virtual Geographic Environment, Nanjing Normal University, Ministry of Education, Nanjing 210023, China
2
State Key Laboratory Cultivation Base of Geographical Environment Evolution, Jiangsu Province, Nanjing 213323, China
3
Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application, Nanjing 210023, China
4
Department of Geography, University of Wisconsin-Madison, Madison, WI 53706, USA
5
College of Resources and Environment, University of Chinese Academy of Sciences, Beijing 100049, China
*
Author to whom correspondence should be addressed.
Land 2020, 9(6), 174; https://doi.org/10.3390/land9060174
Received: 23 April 2020 / Revised: 27 May 2020 / Accepted: 27 May 2020 / Published: 29 May 2020
Digital soil mapping (DSM) is currently the primary framework for predicting the spatial variation of soil information (soil type or soil properties). Random forests and similarity-based methods have been used widely in DSM. However, the accuracy of the similarity-based approach is limited, and the performance of random forests is affected by the quality of the feature set. The objective of this study was to present a method for soil mapping by integrating the similarity-based approach and the random forests method. The Heshan area (Heilongjiang province, China) was selected as the case study for mapping soil subgroups. The results of the regular validation samples showed that the overall accuracy of the integrated method (71.79%) is higher than that of a similarity-based approach (58.97%) and random forests (66.67%). The results of the 5-fold cross-validation showed that the overall accuracy of the integrated method, similarity-based approach, and random forests range from 55% to 72.73%, 43.48% to 69.57%, and 54.17% to 70.83%, with an average accuracy of 66.61%, 57.39%, and 59.62%, respectively. These results suggest that the proposed method can produce a high-quality covariate set and achieve a better performance than either the random forests or similarity-based approach alone. View Full-Text
Keywords: digital soil mapping; similarity-based approach; random forests; method integration digital soil mapping; similarity-based approach; random forests; method integration
Show Figures

Figure 1

MDPI and ACS Style

Wang, D.; Zhu, A.-X. Soil Mapping Based on the Integration of the Similarity-Based Approach and Random Forests. Land 2020, 9, 174.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop