KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Author: search.filters.author.Chen, WalterSubject: search.filters.subject.Shihmen reservoir

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Predicting sheet and rill erosion of Shihmen reservoir watershed in Taiwan using machine learning
    (2019-07-01)
    Nguyen, Kieu Anh
    ;
    Chen, Walter
    ;
    Lin, Bor Shiun
    ;
    Seeboonruang, Uma
    ;
    Thomas, Kent
    Shihmen Reservoir watershed is vital to the water supply in Northern Taiwan but the reservoir has been heavily impacted by sedimentation and soil erosion since 1964. The purpose of this study was to explore the capability of machine learning algorithms, such as decision tree and random forest, to predict soil erosion (sheet and rill erosion) depths in the Shihmen reservoir watershed. The accuracy of the models was evaluated using the RMSE (Root Mean Squared Error), MAE (Mean Absolute Error), and R<sup>2</sup>. Moreover, the models were verified against the multiple regression analysis, which is commonly used in statistical analysis. The predictors of these models were 14 environmental factors which influence soil erosion, whereas the target was 550 erosion pins installed at 55 locations (on 55 slopes) and monitored over a period of approximately three years. The data sets for the models were separated into 70% for the training data and 30% for the testing data, using the simple random sampling and stratified random sampling methods. The results show that the random forest algorithm performed the best of the three methods. Moreover, the stratified random sampling method had better results among the two sampling methods, as anticipated. The average error (RMSE relative to 1:1 line) of the stratified random sampling method of the random forest algorithm is 0.93 mm/yr in the training data and 1.75 mm/yr in the testing data, respectively. Finally, the random forest algorithm predicted that type of slope, slope direction, and sub-watershed are the three most important factors of the 14 environmental factors collected and used in this study for splits in the trees and thus they are the three most important factors affecting the depth of sheet and rill erosion in the Shihmen Reservoir watershed. The results of this study can be employed by decision-makers to improve soil conservation planning and watershed remediation.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Identifying and comparing relatively high soil erosion sites with four DEMs
    (2018-09-01)
    Chen, Walter
    ;
    Li, Dong Huang
    ;
    Yang, Kai Jie
    ;
    Tsai, Fuan
    ;
    Seeboonruang, Uma
    Soil loss due to sheet or rill soil erosion is a critical problem in watersheds of Taiwan. However, an order-of-magnitude discrepancy of soil loss in the literature raises many questions. In this study, we conducted a new analysis using the most recent available data and the Universal Soil Loss Equation (USLE) to compute the amounts of sheet and rill erosion of the Shihmen reservoir watershed in northern Taiwan. Using four different Digital Elevation Models (DEMs), we identified relatively high soil erosion sites and found them to be located at similar locations despite of the difference in DEM. We also determined that the average soil erosion in the Shihmen reservoir watershed is comparable to other watersheds in Asia, but higher than those of the European Union. Furthermore, soil erosion is not uniformly distributed throughout the study area. It is found that the distribution of soil erosion is highly skewed to the right (right-tailed), which means that the majority of the distribution is concentrated to the left side (many cells with low soil erosion). Based on our model, approximately 2% of the areas account for 30% of the soil erosion. In other words, a small proportion of the areas contribute to a large proportion of the total soil loss. Moreover, the DEM created from airborne LiDAR yields the highest amount of soil erosion, the two DEMs created from satellite images yield the lowest amounts of soil erosion, and the DEM created from aerial photographs yields an in-between soil erosion amount. Their vertical resolutions range from high to low. It appears that the amount of soil erosion is influenced by the vertical accuracy of DEMs. In addition to the comparison of DEMs, we demonstrated rudimentary steps to visualize areas of high soil erosion risk using freely available tool for long-term monitoring.