Yasir H. Kaheil

Predictive downscaling based on non-homogeneous hidden Markov models

Abstract Weather-state models have been shown to be effective in downscaling the synoptic atmospheric information to local daily precipitation patterns. We explore the ability of non-homogeneous hidden Markov models (NHMM) to downscale regional seasonal climate data to daily rainfall at a collection of gauging sites. The predictors used are: ensemble means of seasonal rainfall as forecast by the DEMETER and ECHAM models, and the preceding seasonal outgoing long-wave radiation (OLR). As the downscaling of seasonal GCM-based predictions lacks the ability to capture the intra-seasonal variability, we augment the seasonal GCM-driven inputs with statistically-driven predictions of the monthly rainfall amounts. The pooling effect of combining seasonal and monthly estimates of the regional rainfall enhances the capacity of the NHMM to simulate the stochastic characteristics of rainfall fields. The monthly rainfall prediction is derived from a wide range of climate precursors such as the El Niño-Southern Oscillation, local sea-level pressure, and sea-surface temperature. Application of the methodology to data from the Everglades National Park region in South Florida, USA is presented for the seasons May–July and August–September using a 22-year sequence of seasonal data from eight rainfall stations. The model skill in capturing the seasonal and intra-seasonal rainfall attributes at each station is demonstrated graphically and using simple statistical measures of efficiency. The hidden states derived from NHMM are qualitatively analysed and shown to correspond to the dominant synoptic-scale features of rainfall generating mechanisms, which reinforces the argument that physical processes are appropriately captured. Citation Khalil, A. F., Kwon, H.-H., Lall, U. & Kaheil, Y. H. (2010) Predictive downscaling based on non-homogeneous hidden Markov models. Hydrol. Sci. J. 55(3), 333–350.

Ensemble Evaluation of Hydrologically Enhanced Noah-LSM: Partitioning of the Water Balance in High-Resolution Simulations over the Little Washita River Experimental Watershed

Abstract The ability of two versions of the Noah land surface model (LSM) to simulate the water cycle of the Little Washita River experimental watershed is evaluated. One version that uses the standard hydrological parameterizations of Noah 2.7 (STD) is compared another version that replaces STD’s subsurface hydrology with a simple aquifer model and topography-related surface and subsurface runoff parameterizations (GW). Simulations on a distributed grid at fine resolution are compared to the long-term distribution of observed daily-mean runoff, the spatial statistics of observed soil moisture, and locally observed latent heat flux. The evaluation targets the typical behavior of ensembles of models that use realistic, near-optimal sets of parameters important to runoff. STD and GW overestimate the ratio of runoff to evapotranspiration. In the subset of STD and GW runs that best reproduce the timing and the volume of streamflow, the surface-to-subsurface runoff ratio is overestimated and simulated streamfl...

Detecting and Downscaling Wet Areas on Boreal Landscapes

This letter presents an approach to classify wet areas from European Remote Sensing 2 (ERS-2) synthetic aperture radar (SAR)-, Landsat Thematic Mapper (TM)-, and Light Detection and Ranging (LiDAR)-derived terrain data and downscale the result from the coarse resolution of satellite images to finer resolutions needed for land managers. Using discrete wavelet transform (DWT) and support vector machines (SVM), the algorithm finds multiple relationships between the radar, optical, and terrain data and wet areas at different spatial scales. Decomposing and reconstructing processes are performed using a 2-D DWT (2D-DWT) and inverse 2D-DWT respectively. The underlying relationships between radar, optical, and terrain data and wet areas are learned by training an SVM at the coarse resolution of the wet-area map. The SVM is then applied on the predictors at a finer resolution to produce wet-area detailing images, which are needed to reconstruct a finer resolution wet-area map. The algorithm is applied to a boreal landscape in northern Alberta, Canada, characterized by many wet-area features including ephemeral and permanent streams and wetlands.

Multiobjective Evolutionary Optimization and Machine Learning: Application to Renewable Energy Predictions

The inherent variability in climate processes results in significant impacts on renewable energy production. While a number of advancements have been made over the years, the accurate energy production estimates and the corresponding long-term variability at the full wind farm remains a big challenge. At the same time, long-term energy estimates and the variability are important for financial assessment of the wind farm projects. In this chapter, a machine learning approach to model wind energy output from the wind farm is presented. A multiobjective evolutionary optimization (MOEO) method has been applied for the optimization of an Artificial Intelligence learning methodology the “Support Vector Machines” (SVM). The optimum parameter search is conducted in an intelligent manner by narrowing the desired regions of interest that avoids getting struck in local optima. The National Center for Environmental Prediction (NCEP)’s global reanalysis gridded dataset has been employed in this study. The gridded dataset for this particular application consists of four points each consisting of five variables. A 40-years, 6-hourly energy prediction time series is built using the 40-years of reanalysis data (1968-present) after training against short-term observed farm data. This is useful in understanding the long-term energy production at the farm site. The results of MOEO-SVM for the prediction of wind energy are reported along with the multiobjective trade-off curves.