Climate data is very important and at the same time, voluminous. Every minute a new entry is recorded for different climate parameters in climate databases around the world. Given the explosive growth of data that needs to be transmitted and stored, there is a necessity to focus on developing better transmission and storage technologies. Data compression is known to be a viable and effective solution to reduce bandwidth and storage requirements of bulk data. So, the goal is to develop the best compression methods for climate data.The methodology used is based on predictive analysis. The focus is to implement a hybrid algorithm which utilizes the functionality of Artificial Neural Networks (ANN) for prediction of climate data. ANN is a very efficient tool to generate models for predicting climate data with great accuracy. Two types of ANN’s such as Multilayer Perceptron (MLP) and Cascade Feedforward Neural Network (CFNN) are used. It is beneficial to take advantage of ANN and combine its output with lossless compression algorithms such as differential encoding and Huffman coding to generate high compression ratios.The performance of the two techniques based on MLP and CFNN types are compared using metrics including compression ratio, Mean Square Error (MSE) and Root Mean Square Error (RMSE). The two methods are also compared with a conventional method of differential encoding followed by Huffman Coding.The results indicate that MLP outperforms CFNN. Also compression ratios of both the proposed methods are higher than those obtained by the standard method. Compression ratios as high as 10.3, 9.8, and 9.54 are obtained for precipitation, photosynthetically active radiation, and solar radiation datasets respectively.
展开▼
