Mapping Topsoil Total Nitrogen Using Random Forest and Modified Regression Kriging in Agricultural Areas of Central China
Accurate understanding of spatial distribution and variability of soil total nitrogen (TN) is critical for the site-specific nitrogen management. Based on 4337 newly obtained soil observations and 33 covariates, this study applied the random forest (RF) algorithm and modified regression kriging (RF...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Plants |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2223-7747/12/7/1464 |
| _version_ | 1797607209665822720 |
|---|---|
| author | Liyuan Zhang Zhenfu Wu Xiaomei Sun Junying Yan Yueqi Sun Peijia Liu Jie Chen |
| author_facet | Liyuan Zhang Zhenfu Wu Xiaomei Sun Junying Yan Yueqi Sun Peijia Liu Jie Chen |
| author_sort | Liyuan Zhang |
| collection | DOAJ |
| description | Accurate understanding of spatial distribution and variability of soil total nitrogen (TN) is critical for the site-specific nitrogen management. Based on 4337 newly obtained soil observations and 33 covariates, this study applied the random forest (RF) algorithm and modified regression kriging (RF combined with residual kriging: RFK, hereafter) model to spatially predict and map topsoil TN content in agricultural areas of Henan Province, central China. According to the RFK prediction, topsoil TN content ranged from 0.52 to 1.81 g kg<sup>−1</sup>, and the farmland with the topsoil TN contents of 1.00–1.23 g kg<sup>−1</sup> and 0.80–1.23 g kg<sup>−1</sup> accounted for 48.2% and 81.2% of the total farmland area, respectively. Spatially, the topsoil TN in the study area was generally higher in the west and lower in the east. By using the Boruta variable selection algorithm, soil organic matter (SOM) and available potassium contents in topsoil, nitrogen deposition, average annual precipitation, livestock discharges, and topsoil pH were identified as the main factors driving the spatial distribution and variation of soil TN in the study area. The RF and RFK models used showed the expected performance and achieved acceptable TN prediction accuracy. In comparison, RFK performed slightly better than the RF model. The R<sup>2</sup> and RMSE achieved by the RFK model were improved by 4.5% and 4.5%, respectively, compared with that by the RF model. However, the results suggest that RFK was inferior to the RF model in quantifying prediction uncertainty and thus may have a slight disadvantage in model reliability. |
| first_indexed | 2024-03-11T05:28:01Z |
| format | Article |
| id | doaj.art-a430e1b5fc484cddbef20aa25274e47d |
| institution | Directory Open Access Journal |
| issn | 2223-7747 |
| language | English |
| last_indexed | 2024-03-11T05:28:01Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Plants |
| spelling | doaj.art-a430e1b5fc484cddbef20aa25274e47d2023-11-17T17:22:55ZengMDPI AGPlants2223-77472023-03-01127146410.3390/plants12071464Mapping Topsoil Total Nitrogen Using Random Forest and Modified Regression Kriging in Agricultural Areas of Central ChinaLiyuan Zhang0Zhenfu Wu1Xiaomei Sun2Junying Yan3Yueqi Sun4Peijia Liu5Jie Chen6School of Agricultural Sciences, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Agricultural Sciences, Zhengzhou University, Zhengzhou 450001, ChinaHenan Provincial Station of Soil and Fertilizer, Zhengzhou 450002, ChinaHenan Provincial Station of Soil and Fertilizer, Zhengzhou 450002, ChinaSchool of Agricultural Sciences, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Politics and Public Administration, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Agricultural Sciences, Zhengzhou University, Zhengzhou 450001, ChinaAccurate understanding of spatial distribution and variability of soil total nitrogen (TN) is critical for the site-specific nitrogen management. Based on 4337 newly obtained soil observations and 33 covariates, this study applied the random forest (RF) algorithm and modified regression kriging (RF combined with residual kriging: RFK, hereafter) model to spatially predict and map topsoil TN content in agricultural areas of Henan Province, central China. According to the RFK prediction, topsoil TN content ranged from 0.52 to 1.81 g kg<sup>−1</sup>, and the farmland with the topsoil TN contents of 1.00–1.23 g kg<sup>−1</sup> and 0.80–1.23 g kg<sup>−1</sup> accounted for 48.2% and 81.2% of the total farmland area, respectively. Spatially, the topsoil TN in the study area was generally higher in the west and lower in the east. By using the Boruta variable selection algorithm, soil organic matter (SOM) and available potassium contents in topsoil, nitrogen deposition, average annual precipitation, livestock discharges, and topsoil pH were identified as the main factors driving the spatial distribution and variation of soil TN in the study area. The RF and RFK models used showed the expected performance and achieved acceptable TN prediction accuracy. In comparison, RFK performed slightly better than the RF model. The R<sup>2</sup> and RMSE achieved by the RFK model were improved by 4.5% and 4.5%, respectively, compared with that by the RF model. However, the results suggest that RFK was inferior to the RF model in quantifying prediction uncertainty and thus may have a slight disadvantage in model reliability.https://www.mdpi.com/2223-7747/12/7/1464topsoiltotal nitrogenrandom forestmodified regression krigingdigital soil mappingHenan province |
| spellingShingle | Liyuan Zhang Zhenfu Wu Xiaomei Sun Junying Yan Yueqi Sun Peijia Liu Jie Chen Mapping Topsoil Total Nitrogen Using Random Forest and Modified Regression Kriging in Agricultural Areas of Central China Plants topsoil total nitrogen random forest modified regression kriging digital soil mapping Henan province |
| title | Mapping Topsoil Total Nitrogen Using Random Forest and Modified Regression Kriging in Agricultural Areas of Central China |
| title_full | Mapping Topsoil Total Nitrogen Using Random Forest and Modified Regression Kriging in Agricultural Areas of Central China |
| title_fullStr | Mapping Topsoil Total Nitrogen Using Random Forest and Modified Regression Kriging in Agricultural Areas of Central China |
| title_full_unstemmed | Mapping Topsoil Total Nitrogen Using Random Forest and Modified Regression Kriging in Agricultural Areas of Central China |
| title_short | Mapping Topsoil Total Nitrogen Using Random Forest and Modified Regression Kriging in Agricultural Areas of Central China |
| title_sort | mapping topsoil total nitrogen using random forest and modified regression kriging in agricultural areas of central china |
| topic | topsoil total nitrogen random forest modified regression kriging digital soil mapping Henan province |
| url | https://www.mdpi.com/2223-7747/12/7/1464 |
| work_keys_str_mv | AT liyuanzhang mappingtopsoiltotalnitrogenusingrandomforestandmodifiedregressionkriginginagriculturalareasofcentralchina AT zhenfuwu mappingtopsoiltotalnitrogenusingrandomforestandmodifiedregressionkriginginagriculturalareasofcentralchina AT xiaomeisun mappingtopsoiltotalnitrogenusingrandomforestandmodifiedregressionkriginginagriculturalareasofcentralchina AT junyingyan mappingtopsoiltotalnitrogenusingrandomforestandmodifiedregressionkriginginagriculturalareasofcentralchina AT yueqisun mappingtopsoiltotalnitrogenusingrandomforestandmodifiedregressionkriginginagriculturalareasofcentralchina AT peijialiu mappingtopsoiltotalnitrogenusingrandomforestandmodifiedregressionkriginginagriculturalareasofcentralchina AT jiechen mappingtopsoiltotalnitrogenusingrandomforestandmodifiedregressionkriginginagriculturalareasofcentralchina |