Predicting stable gravel-bed river hydraulic geometry: A test of novel, advanced, hybrid data mining algorithms
نویسندگان
چکیده
Accurate prediction of stable alluvial hydraulic geometry, in which erosion and sedimentation are equilibrium, is one the most difficult but critical topics field river engineering. Data mining algorithms have been gaining more attention this due to their high performance flexibility. However, an understanding potential for these provide fast, cheap, accurate predictions geometry lacking. This study provides first quantification potential. Using at-a-station data, flow depth, water-surface width longitudinal water surface slope made using three standalone data techniques -, Instance-based Learning (IBK), KStar, Locally Weighted (LWL) - along with four types novel hybrid models trained Vote, Attribute Selected Classifier (ASC), Regression by Discretization (RBD), Cross-validation Parameter Selection (CVPS) (Vote-IBK, Vote-Kstar, Vote-LWL, ASC-IBK, ASC-Kstar, ASC-LWL, RBD-IBK, RBD-Kstar, RBD-LWL, CVPS-IBK, CVPS-Kstar, CVPS-LWL). Through a comparison predictive sensitivity analysis driving variables, results reveal: (1) Shield stress was effective parameter all dimensions; (2) had higher power than models, empirical equations traditional machine learning algorithms; (3) Vote-Kstar model highest predicting depth width, ASC-Kstar estimating slope, each providing very good performance. algorithms, any can potentially be predicted accurately ease just few, readily available channel parameters. Thus, reveal that great use design poor catchments, especially developing nations where technical modelling skills sediment processes occurring system may
منابع مشابه
development of analytical model on determination of stable hydraulic geometry of alluvial gravel bed rivers
modeling the hydraulic geometry of gravel rivers is of intrest to hydraulic engineers, hydrologists and enviromental scientists who are engaged in predicting the adjustments of an alluvial channel to an altered upstream runoff or sediment supply. the widely used qualitative and regime models, while indicating the general direction of river adjustment, are not able to deal with river response at...
متن کاملPredicting Type2 Diabetes Using Data Mining Algorithms
Background and purpose: Today, information systems and databases are widely used and in order to achieve higher accuracy and speed in making diagnosis, preventing the diseases, and choosing treatments they should be merged with traditional methods. This study aimed at presenting an accurate system for diagnosis of diabetes using data mining and a heuristic method combining neural network and pa...
متن کاملA Randomness Test for Stable Data
In this paper, we propose a new method for checking randomness of non-Gaussian stable data based on a characterization result. This method is more sensitive with respect to non-random data compared to the well-known non-parametric randomness tests.
متن کاملComparison of the Efficiency of Data Mining Algorithms in Predicting the Diagnosis of Diabetes
Background: Diabetes is one of the major health problems in Iran and about 4.6 million adults suffer from this disease. Poor diagnosis of this disease has caused half of this number to be unaware of their disease. In recent years, along with the use of computers in data analysis and storage, the volume and complexity of data has increased dramatically. Methods: In health organizations, data pl...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Environmental Modelling and Software
سال: 2021
ISSN: ['1364-8152', '1873-6726']
DOI: https://doi.org/10.1016/j.envsoft.2021.105165