A Random Forest-Based Approach to Map Soil Erosion Risk Distribution in Hickory Plantations in Western Zhejiang Province, China

Abstract

Increasing agroforestry areas with improper management has produced serious environmental problems, such as soil erosion. It is necessary to rapidly predict the spatial distribution of such erosion risks in a large area, but there is a lack of approaches that are suitable for mountainous regions. The objective of this research was to develop an approach that can effectively employ remotely-sensed and ancillary data, to map soil erosion risks in an agroforestry ecosystem in a mountainous region. This research employed field survey data, soil-type maps, digital elevation model data, weather station data, and Landsat imagery, for extraction of potential variables. It used the random forest approach to identify eight key variables—slope, slope of slope, normalized difference greenness index at leaf-on season, soil organic matter, fractional vegetation at leaf-on season, fractional soil at leaf-off season, precipitation in June, and percent of soil clay—for mapping soil erosion risk distribution in hickory plantations in Western Zhejiang Province, China. The results showed that an overall accuracy of 89.8% was obtained for three levels of soil erosion risk. Approximately one-fourth of hickory plantations were at high-risk, requiring the owners or decision makers to take proper measures to reduce the soil erosion problem. This research provides a new approach to predict soil erosion risk, based on the primary variables that can be extracted directly from remotely-sensed data and ancillary data. This proposed approach will be valuable for other agroforestry and plantations, such as Torreya grandis, eucalyptus, and the rubber tree, that are playing important roles in improving economic conditions for the local farmers but face soil erosion problems.

Soil Erosion Susceptibility Mapping in Kozetopraghi Catchment, Iran: A Mixed Approach Using Rainfall Simulator and Data Mining Techniques

“…The results of the AUC curve, MSE criteria, and the number of eroded points in high and very high susceptibility classes indicate that the RF model had a better performance than the SVM and Adaboost models. The ability and accuracy of the RF model in mapping soil erosion susceptibility is mentioned in other studies [86,87]. The three models show different results when it comes to identifying the extent of high and very high soil erosion susceptibilities.…”

Modeling Landslide Susceptibility in Forest-Covered Areas in Lin’an, China, Using Logistical Regression, a Decision Tree, and Random Forests

“…In the past three decades, hickory plantations have continuously increased and reached an area of 28,700 hectares in Lin'an [16]. Both bamboo and Chinese hickory plantations are pure stands (i.e., single tree species) with a relatively simple canopy structure; these plantations are intensively managed by frequently applying herbicides to control understory vegetation, as well as fertilizers and insecticides to improve productivity [17][18][19]. This intensive management likely exacerbates soil erosion from rainfall-induced runoff and causes slope instability and other landslide triggers, particularly in hilly regions [17,20].…”

“…Both bamboo and Chinese hickory plantations are pure stands (i.e., single tree species) with a relatively simple canopy structure; these plantations are intensively managed by frequently applying herbicides to control understory vegetation, as well as fertilizers and insecticides to improve productivity [17][18][19]. This intensive management likely exacerbates soil erosion from rainfall-induced runoff and causes slope instability and other landslide triggers, particularly in hilly regions [17,20]. There are differences between hickory and bamboo plantations, with the former having a lower density and greater distribution on steeper slopes [16].…”

Integrated Use of Satellite Remote Sensing, Artificial Neural Networks, Field Spectroscopy, and GIS in Estimating Crucial Soil Parameters in Terms of Soil Erosion

“…Therefore, the combination of laboratory analysis with geostatistics and remote sensing may be ideal to enable the environmental change monitoring in terms of cost and time. Earth observation (EO) satellites in particular have proven very beneficial in upscaling local field studies to relatively large areas [14][15][16][17]. Satellite remote sensing is virtually the only data source that permits a repeated monitoring of land degradation dynamics [18].…”