Using Machine Learning-Based Algorithms to Analyze Erosion Rates of a Watershed in Northern Taiwan

Abstract

This study continues a previous study with further analysis of watershed-scale erosion pin measurements. Three machine learning (ML) algorithms—Support Vector Machine (SVM), Adaptive Neuro-Fuzzy Inference System (ANFIS), and Artificial Neural Network (ANN)—were used to analyze depth of erosion of a watershed (Shihmen reservoir) in northern Taiwan. In addition to three previously used statistical indexes (Mean Absolute Error, Root Mean Square of Error, and R-squared), Nash–Sutcliffe Efficiency (NSE) was calculated to compare the predictive performances of the three models. To see if there was a statistical difference between the three models, the Wilcoxon signed-rank test was used. The research utilized 14 environmental attributes as the input predictors of the ML algorithms. They are distance to river, distance to road, type of slope, sub-watershed, slope direction, elevation, slope class, rainfall, epoch, lithology, and the amount of organic content, clay, sand, and silt in the soil. Additionally, measurements of a total of 550 erosion pins installed on 55 slopes were used as the target variable of the model prediction. The dataset was divided into a training set (70%) and a testing set (30%) using the stratified random sampling with sub-watershed as the stratification variable. The results showed that the ANFIS model outperforms the other two algorithms in predicting the erosion rates of the study area. The average RMSE of the test data is 2.05 mm/yr for ANFIS, compared to 2.36 mm/yr and 2.61 mm/yr for ANN and SVM, respectively. Finally, the results of this study (ANN, ANFIS, and SVM) were compared with the previous study (Random Forest, Decision Tree, and multiple regression). It was found that Random Forest remains the best predictive model, and ANFIS is the second-best among the six ML algorithms.

Comparison of Ensemble Machine Learning Methods for Soil Erosion Pin Measurements

“…Note that we do not use R 2 (coefficient of determination) as a statistical index in the model evaluation. As pointed out by Nguyen et al [18,19], R 2 evaluates the fit to the regression line only. High R 2 does not mean small differences between predictions and observations.…”

“…The field measurements (such as those of erosion pins) are used directly to formulate rules and make generalizations from the data (i.e., predictions). Although ML-based approaches have been extensively used in relevant fields such as landslides susceptibility mapping [13,14], soil thickness prediction [15], digital soil mapping [16], and biomass retrieval [17], it has only recently been applied to soil erosion pin study [18,19]. To improve upon previous methods of quantifying soil erosion, the study explored the possible application of ensemble machine learning algorithms to the Shihmen Reservoir watershed in northern Taiwan.…”

Use of Machine Learning and Statistical Algorithms to Predict Hospital Length of Stay Following Colorectal Cancer Resection: A South African Pilot Study

“…Two-sided tests were employed, and a p-value <0.05 was considered statistically significant. This non-parametric test has been used in several studies for the comparison of predictive models (25). We also compared the sensitivity and specificity of the models to evaluate the model performance further.…”

Combined Generative Adversarial Network and Fuzzy C-Means Clustering for Multi-Class Voice Disorder Detection with an Imbalanced Dataset

“…To determine if CGAN-IFCM statistically outperformed other approaches, adopting a t-test is not suitable because both TNR and TPR are bounded by 0% and 100% which does not follow normal distribution [46,47]. Non-parametric Wilcoxon signed-rank test [48,49] was chosen to confirm if CGAN-IFCM is statistically significant compared with other approaches. We assumed the significance level is 0.05.…”