Probabilistic prediction of hydroclimatic variables with nonparametric quantification of uncertainty
نویسندگان
چکیده
[1] A semiparametric, copula-based approach is proposed to capture the dependence between teleconnected hydroclimatic variables for the prediction of response variable using the information of climate precursors. The copulas have an excellent property to study the scale-free dependence structure while preserving such dependence during simulation. This property is utilized in the proposed approach. The usefulness of the proposed method can be recognized in three distinct aspects: (1) It captures the dependence pattern preserving scale-free or rank-based ‘‘measure of association’’ between the variables. (2) The proposed method is able to quantify the uncertainty associated with the relationship between teleconnected variables due to various factors; thus, the probabilistic predictions are available along with information of uncertainty. (3) Instead of parametric probability distribution, nonparametrically estimated probability densities for data sets can be handled by the proposed approach. Thus, the proposed method can be applied to capture the relationship between teleconnected hydroclimatic variables having some linear and/or nonlinear cause-effect relationship. The proposed method is illustrated by an example of the most discussed problem of Indian summer monsoon rainfall (ISMR) and two different large-scale climate precursors, namely, El Niño– Southern Oscillation (ENSO) and Equatorial Indian Ocean Oscillation (EQUINOO). The dependence between them is captured and investigated for its potential use to predict the monthly variation of ISMR using the proposed method. Predicted rainfall is shown to correspond well with the observed rainfall with a correlation coefficient of 0.81 for the summer monsoon months, i.e., June through September. Moreover, the uncertainty associated with the predicted values is also made available through boxplots. The method, being general, can be applied to similar analysis to assess the dependence between teleconnected hydroclimatic variables for other regions of the world and for different temporal scales such as seasonal.
منابع مشابه
The Quantification of Uncertainties in Production Prediction Using Integrated Statistical and Neural Network Approaches: An Iranian Gas Field Case Study
Uncertainty in production prediction has been subject to numerous investigations. Geological and reservoir engineering data comprise a huge number of data entries to the simulation models. Thus, uncertainty of these data can largely affect the reliability of the simulation model. Due to these reasons, it is worthy to present the desired quantity with a probability distribution instead of a sing...
متن کاملBayesian dynamic modelling for nonstationary hydroclimatic time series forecasting along with uncertainty quantification
Forecasting of hydrologic time series, with the quantification of uncertainty, is an important tool for adaptive water resources management. Nonstationarity, caused by climate forcing and other factors, such as change in physical properties of catchment (urbanization, vegetation change, etc.), makes the forecasting task too difficult to model by traditional Box–Jenkins approaches. In this paper...
متن کاملUncertainty Quantification and Model Validation under Epistemic Uncertainty due to Sparse and Imprecise data
This paper develops a methodology for uncertainty quantification and model validation in the presence of epistemic uncertainty due to sparse and imprecise data. Three types of epistemic uncertainty regarding input random variables – interval data, sparse point data, and probability distributions with parameter uncertainty – are considered. When the model inputs are described using sparse point ...
متن کاملNumerical approach for quantification of epistemic uncertainty
In the field of uncertainty quantification, uncertainty in the governing equations may assume two forms: aleatory uncertainty and epistemic uncertainty. Aleatory uncertainty can be characterised by known probability distributions whilst epistemic uncertainty arises from a lack of knowledge of probabilistic information. While extensive research efforts have been devoted to the numerical treatmen...
متن کاملA Nonparametric Online Model for Air Quality Prediction
We introduce a novel method for the continuous online prediction of particulate matter in the air (more specifically, PM10 and PM2.5) given sparse sensor information. A nonparametric model is developed using Gaussian Processes, which eschews the need for an explicit formulation of internal – and usually very complex – dependencies between meteorological variables. Instead, it uses historical da...
متن کامل