Evaluating Irregular Slopes for Soil Loss Prediction

1974 ◽  
Vol 17 (2) ◽  
pp. 0305-0309 ◽  
Author(s):  
G. R. Foster ◽  
W. H. Wischmeier
Keyword(s):  
Soil Loss ◽  
Loss Prediction

SOIL EROSION LOSSES FROM WINTER RUNOFF IN SOUTHERN ONTARIO

1981 ◽  
Vol 61 (2) ◽  
pp. 451-454 ◽  
Author(s):  
L. J. P. VAN VLIET ◽  
G. J. WALL
Keyword(s):  
Soil Erosion ◽  
Soil Loss ◽  
Prediction Models ◽  
Universal Soil Loss Equation ◽  
Southern Ontario ◽  
Winter Runoff ◽  
Loss Prediction ◽  
Runoff And Soil Loss ◽  
Soil Loss Equation

Soil loss prediction models such as the universal soil loss equation do not usually reflect the influence of snowmelt events on annual soil loss estimates. Plot studies (2% and 6% slopes) conducted over three winters in Southern Ontario to measure runoff and soil loss from spring-plowed corn crops revealed that winter soil erosion losses represented up to 10% of annual soil loss.

Toward a framework for runoff and soil loss prediction using GUEST technology

Soil Research ◽  
1997 ◽  
Vol 35 (5) ◽  
pp. 1191 ◽  
Author(s):  
B. Yu ◽  
C. W. Rose ◽  
C. A. A. Ciesiolka ◽  
K. J. Coughlan ◽  
B. Fentie
Keyword(s):  
Soil Loss ◽  
Field Data ◽  
Rainfall Intensity ◽  
Rainfall Amount ◽  
Balance Model ◽  
Erosion Processes ◽  
Total Runoff ◽  
Physically Based ◽  
Loss Prediction ◽  
Runoff Rate

In recent years, a number of physically based models have been developed for soil loss predictions. GUEST is one such model based on fundamental physical principles and the current understanding of water erosion processes. GUEST is mainly used to determine a soil erodibility parameter. To apply the model in a predictive mode, the model is simplified in a physically meaningful manner for flow-driven erosion processes, and 2 essential hydrologic variables are identified, namely total runoff amount and an effective runoff rate. These variables are required to determine soil loss for individual runoff events. A simple water balance model was developed and used to predict runoff amount from rainfall amount. The efficiency of this runoff amount model in prediction was over 90% using field data. A 1-parameter regression model (r2 ~ 0·9) for the effective runoff rate was also established which uses peak rainfall intensity in addition to rainfall and runoff amounts. The prediction of peak rainfall intensity for a given rainfall amount and storm type was also sought. The field data were from Goomboorian, near Gympie, in south-east Queensland and these data were used to test and validate both models. Results overall are satisfactory and the approach adopted is promising. A framework for soil loss prediction is established within which individual parts can be further refined and improved.

scholarly journals Evaluating the Erosion Process from a Single-Stripe Laser-Scanned Topography: A Laboratory Case Study

Water ◽  
2018 ◽  
Vol 10 (7) ◽  
pp. 956 ◽  
Author(s):  
Yung-Chieh Wang ◽  
Chun-Chen Lai
Keyword(s):  
Sediment Yield ◽  
Soil Loss ◽  
Laser Scanning ◽  
Erosion Process ◽  
Rainfall Simulator ◽  
Scanning Method ◽  
Rainfall Duration ◽  
Loss Prediction ◽  
Stripe Laser

Topographies during the erosion process obtained from the single-stripe laser-scanning method may provide an accurate, but affordable, soil loss estimation based on high-precision digital elevation model (DEM) data. In this study, we used laboratory erosion experiments with a sloping flume, a rainfall simulator, and a stripe laser apparatus to evaluate topographic changes of soil surface and the erosion process. In the experiments, six slope gradients of the flume (5° to 30° with an increment of 5°) were used and the rainfall simulator generated a 30-min rainfall with the kinetic energy equivalent to 80 mm/h on average. The laser-scanned topography and sediment yield were collected every 5 min in each test. The difference between the DEMs from laser scans of different time steps was used to obtain the eroded soil volumes and the corresponding estimates of soil loss in mass. The results suggest that the collected sediment yield and eroded soil volume increased with rainfall duration and slope, and quantified equations are proposed for soil loss prediction using rainfall duration and slope. This study shows the applicability of the stripe laser-scanning method in soil loss prediction and erosion evaluation in a laboratory case study.

scholarly journals Prediction of soil loss due to erosion using support vector machine model

2020 ◽  
Vol 42 (3) ◽  
Author(s):  
Van Quan Tran ◽  
Indra Prakash
Keyword(s):  
Support Vector Machine ◽  
Soil Erosion ◽  
Vegetation Cover ◽  
Soil Loss ◽  
Rainfall Intensity ◽  
Mean Squared Error ◽  
Support Vector ◽  
Squared Error ◽  
Model Study ◽  
Loss Prediction

Soil erosion refers to the detachment and removal of soil particles from land (topsoil), by the natural physical forces (water, glacier and wind). Soil erosion causes soil loss in the catchment or any land areas severely impacting agriculture activity, sedimentation in the dam reservoirs, and hampering developmental activities. Therefore, it is desirable to accurately measure soil loss due to erosion for the development and management of an area. With this objective, a well-known machine learning algorithm Support Vector Machine (SVM) has been used in the development of the soil loss prediction model. Eight erosion affecting variable inputs: ambient temperature Tair, rainfall, Antecedent Moisture Conditions (AMC), rainfall intensity, slope, vegetation cover, soil temperature Tsoil and moisture of the soil. Data on published literature was used in the model study. The accuracy of the proposed SVM was assessed by using three statistical performance evaluation indicators namely Person correlation coefficient (R), Root Mean Squared Error (RMSE), Mean Squared Error (MAE). Partial Dependence Plots (PDP) was used to investigate the dependence of prediction results of eight input variables used in the model study. Model validation results showed that SVM model performed well for the prediction of soil loss for testing (R = 0.8993) and also for training (R=0.9123). Rainfall intensity and vegetation cover were found to be the two most important affecting input parameters for the soil loss prediction.

Sign in / Sign up

Export Citation Format

Share Document