Bayesian Learning and Relevance Vector Machines Approach for Downscaling of Monthly Precipitation

Date

2015-04-01

Author

OKKAN, UMUT
İnan, Gül

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

307
views

0
downloads

In this study, statistical downscaling of large-scale general circulation model (GCM) simulations to monthly precipitation of Kemer Dam, in Turkey, has been performed through relevance vector machines (RVMs). All possible regression methods along with statistical measures have been used to select potential predictors through reanalysis data providing air850, hgt850, and prate variables as the optimal. The determined explanatory variables are then used for training RVM-based statistical downscaling model. A least-squares support vector machine (LSSVM)-based downscaling model is also constructed to compare the downscaling performance of RVM through some performance evaluation measures such as R-2, AdjR(2) and RMS error (RMSE). Because RVM is able to obtain the better modeling accuracy in terms of all performance measures during the testing period, third-generation coupled climate model (CGCM3) simulations run through the trained RVM to obtain future scenario results. The effectiveness of the RVM model is illustrated through its integration to climate scenarios (20C3M and A2). The statistical significance of the probable changes obtained with used methods is examined by Mann-Whitney U (M-W) and t-tests considering scenario forecasts. According to pessimistic A2 scenario results, statistically significant decreasing trends are foreseen for both seasonal and annual precipitation in the study basin. (C) 2014 American Society of Civil Engineers.

Subject Keywords

Civil and Structural Engineering, General Environmental Science, Water Science and Technology, Environmental Chemistry

URI

https://hdl.handle.net/11511/56529

Journal

JOURNAL OF HYDROLOGIC ENGINEERING

DOI

https://doi.org/10.1061/(asce)he.1943-5584.0001024

Collections

Department of Statistics, Article

Suggestions

OpenMETU
Core

Regional frequency analysis of precipitation using time series clustering approaches Zaifoğlu, Hasan; Akıntuğ, Bertuğ; Yanmaz, Ali Melih (American Society of Civil Engineers (ASCE), 2018-06-01) A regional frequency analysis using L-moments was performed with time series clustering approaches to identify homogeneous regions using dynamic data sets in Northern Cyprus. In this context, the conventional approach, based on station characteristics and different time series clustering approaches, classified as shape-based, feature-based, and model-based, were compared. Hierarchical Ward's method with the correlation-based similarity measure of the feature-based approach was determined as the best method ...
Quality control, homogeneity analysis, and trends of extreme precipitation indices in Northern Cyprus Zaifoğlu, Hasan; Akıntuğ, Bertuğ; Yanmaz, Ali Melih (American Society of Civil Engineers (ASCE), 2017-12-01) In this study, the annual and seasonal changes in extreme precipitation indices were investigated in Northern Cyprus by using the non-parametric Mann–Kendal trend test and Sen’s slope estimator. To this end, quality control of data procedure including estimation of missing data, detection of unreasonable values, and outliers were applied to 36 daily precipitation series to identify different errors. In order to test the homogeneity of the daily series, a two-step approach with four homogeneity tests and ove...
Analytical formulation of maximum length limits of integral bridges on cohesive soils Dicleli, Murat (Canadian Science Publishing, 2005-08-01) This paper presents an analytical approach for predicting the length limits of integral bridges built on cohesive soils based on the flexural strength of the abutments and the low cycle fatigue performance of the steel H-piles at the abutments under cyclic thermal loading. First, H-piles that can accommodate large inelastic deformations are determined considering their local buckling instability. Then, a damage model is used to determine the maximum cyclic deformations that such piles can sustain. Next, non...
Statistical downscaling of monthly reservoir inflows for Kemer watershed in Turkey: use of machine learning methods, multiple GCMs and emission scenarios OKKAN, UMUT; İnan, Gül (Wiley, 2015-09-01) In this study, statistical downscaling of general circulation model (GCM) simulations to monthly inflows of Kemer Dam in Turkey under A1B, A2, and B1 emission scenarios has been performed using machine learning methods, multi-model ensemble and bias correction approaches. Principal component analysis (PCA) has been used to reduce the dimension of potential predictors of National Centers for Environmental Prediction and National Center for Atmospheric Research (NCEP/NCAR) reanalysis data. Then, the reasonabl...
Risk assessment of international construction projects using the analytic network process Bu-Qammaz, Amani Suliman; Dikmen Toker, İrem; Birgönül, Mustafa Talat (Canadian Science Publishing, 2009-07-01) In this study, an analytic network process (ANP), which can handle the interrelations between risk related factors, is proposed as a reliable technique for measuring the level of risk associated with international construction projects. Within this context, ANP is used to derive the relative priorities of risk factors as an input to a decision support tool, which can be utilized during bidding decisions. The decision support tool may help a decision maker to estimate the level of risk so that alternative pr...

Citation Formats

U. OKKAN and G. İnan, “Bayesian Learning and Relevance Vector Machines Approach for Downscaling of Monthly Precipitation,” JOURNAL OF HYDROLOGIC ENGINEERING, pp. 0–0, 2015, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/56529.