Đăng nhập
Tìm kiếm nâng cao
Tên bài báo
Tác giả
Năm xuất bản
Tóm tắt
Lĩnh vực
Phân loại
Số tạp chí

Bản tin định kỳ
Báo cáo thường niên
Tạp chí khoa học ĐHCT
Tạp chí tiếng anh ĐHCT
Tạp chí trong nước
Tạp chí quốc tế
Kỷ yếu HN trong nước
Kỷ yếu HN quốc tế
Book chapter
Tạp chí quốc tế 2017
Số tạp chí 153(2017) Trang: 12-27
Tạp chí: Biosystems Engineering

Although a great number of studies have been devoted to develop and evaluate pedotransfer functions (PTFs), several questions still are to be addressed, particularly pertaining to tropical delta soils which received very little attention. One such question relates to the optimal structural dependency between basic soil properties and soil water retention characteristics (SWRC), which could be formulated by various regression methods. It is hypothesised that data mining techniques provide more accurate SWRC-PTFs than statistical linear regression. However, data-mining techniques are often proven as highly data-demanding techniques. The aim of this study was, therefore, to verify that hypothesis for a limited data set of tropical delta soils by comparing the predictive capabilities of point PTFs and pseudo-continuous (PC) PTFs developed by Multiple Linear Regression (MLR), Artificial Neural Networks (ANN), Support Vector Machine for Regression (SVR), and k-Nearest Neighbours (kNN) methods. The results show that point-PTFs derived from datamining techniques (i.e. ANN, SVR, kNN) offer accurate and reliable estimation of soil water content at several matric potentials. In case of PC-PTFs, ANN and kNN models outperformed SVR and MLR PTFs in validation phase (RMSE of ANN and kNN PTFs were around 0.05 m3 m3, while those of SVR PTFs and MLR PTFs rose up to 0.068 and 0.066 m3 m3). Our findings confirm the superiority of data-mining approaches in modelling the complex system of soil and water, even when a limited data set is available. The non-parametric kNN method, though being constrained in estimating SWRC in pseudo-continuous manner, has great benefits due to its flexibility, simplicity, accuracy and capacity to append new observations. 

Các bài báo khác
Số tạp chí 41(2017) Trang: 1591-1607
Tạp chí: Turkish Journal of Mathematics
Số tạp chí 6(2017) Trang: 93-102
Tạp chí: International Journal of Geometry
Số tạp chí 12(2017) Trang: 70-77
Tạp chí: Applications and Applied Mathematics
Số tạp chí 12(2017) Trang: 3651-3664
Tạp chí: FILOMAT
Số tạp chí 5 (4)(2017) Trang: 793-803
Tạp chí: International Journal of Advanced Research
Số tạp chí 5(8)(2017) Trang: 200-207
Tạp chí: International Journal of Advanced Research
Số tạp chí 2 (3)(2017) Trang: 30-48
Tạp chí: European Journal of Foreign Language Teaching
Số tạp chí 02(2017) Trang: 84-90
Tạp chí: International Journal of Advanced Scientific Research and Management

Vietnamese | English

Vui lòng chờ...