Performance evaluation of AR4 Climate Models in simulating daily precipitation over the Indian region using skill scores

The ability of Coupled General Circulation Models (CGCMs) participating in the Intergovernmental Panel for Climate Change's fourth assessment report (IPCC AR4) for the 20th century climate (20C3M scenario) to simulate the daily precipitation over the Indian region is explored. The skill is evaluated on a 2.5A degrees x 2.5A degrees grid square compared with the Indian Meteorological Department's (IMD) gridded dataset, and every GCM is ranked for each of these grids based on its skill score. Skill scores (SSs) are estimated from the probability density functions (PDFs) obtained from observed IMD datasets and GCM simulations. The methodology takes into account (high) extreme precipitation events simulated by GCMs. The results are analyzed and presented for three categories and six zones. The three categories are the monsoon season (JJASO - June to October), non-monsoon season (JFMAMND - January to May, November, December) and for the entire year (''Annual''). The six precipitation zones are peninsular, west central, northwest, northeast, central northeast India, and the hilly region. Sensitivity analysis was performed for three spatial scales, 2.5A degrees grid square, zones, and all of India, in the three categories. The models were ranked based on the SS. The category JFMAMND had a higher SS than the JJASO category. The northwest zone had higher SSs, whereas the peninsular and hilly regions had lower SS. No single GCM can be identified as the best for all categories and zones. Some models consistently outperformed the model ensemble, and one model had particularly poor performance. Results show that most models underestimated the daily precipitation rates in the 0-1 mm/day range and overestimated it in the 1-15 mm/day range.

No-reference image quality assessment using modified extreme learning machine classifier

In this paper, we present a machine learning approach to measure the visual quality of JPEG-coded images. The features for predicting the perceived image quality are extracted by considering key human visual sensitivity (HVS) factors such as edge amplitude, edge length, background activity and background luminance. Image quality assessment involves estimating the functional relationship between HVS features and subjective test scores. The quality of the compressed images are obtained without referring to their original images ('No Reference' metric). Here, the problem of quality estimation is transformed to a classification problem and solved using extreme learning machine (ELM) algorithm. In ELM, the input weights and the bias values are randomly chosen and the output weights are analytically calculated. The generalization performance of the ELM algorithm for classification problems with imbalance in the number of samples per quality class depends critically on the input weights and the bias values. Hence, we propose two schemes, namely the k-fold selection scheme (KS-ELM) and the real-coded genetic algorithm (RCGA-ELM) to select the input weights and the bias values such that the generalization performance of the classifier is a maximum. Results indicate that the proposed schemes significantly improve the performance of ELM classifier under imbalance condition for image quality assessment. The experimental results prove that the estimated visual quality of the proposed RCGA-ELM emulates the mean opinion score very well. The experimental results are compared with the existing JPEG no-reference image quality metric and full-reference structural similarity image quality metric.