CP-KNN: Seasonal to interannual climate prediction using KNN data mining technique. The impact of seasonal to interannual climate prediction on society, business, agriculture and almost every aspect of human life compels the scientist to give due attention to the matter. Recent years have seen enormous progress in this area. All systems and techniques developed so far use sea surface temperature (SST) as the main factor among other seasonal climate attributes. The statistical and mathematical models are then used for further climate predictions. In this article, we will develop a system that uses historical weather data (rainfall, wind speed, dew point, temperature, etc.) of a region and applies the “k–neighbor” data mining algorithm. nearest (KNN)” for the classification of this historical data. given in a specific time period, the k nearest time periods (K nearest neighbors) are then taken to predict the weather one month in advance. Experiments show that the system generates accurate results in a reasonable time, one month in advance. Objectives The motivation behind the research is to extend the application of Data Mining to the field of meteorology, oceanography and climatology. This will open a new era in the field of Data Mining and climate forecasting. The main objectives are • Use of historical data • Data cleaning to convert the data into a uniform format • Concrete model for climate prediction using data mining • Prediction using numerical data • Improvements in performance and accuracy of climate prediction Hypothesis (problem solution) The enormous amount of climate data has been available for years. Data must be presented in a uniform format. If the data is noisy, it can be cleaned using one of...... middle of paper ......on-1 and Topex/Poseidon data for seasonal climate prediction studies , AVISO Altimetry Newsletter 8, Jason-1 Science Plan, pp. 115-116, 2002.[13] Amanda B. White. Praveen Kumar, David Tcheng; A data mining approach to understanding the control of climate-induced interannual vegetation variability in the United States. Remote Sensing of Environments 98 1 – 20 (2005)[14] Jayanta Basak, Anant Sudarshan, Deepak Trivedi, MS Santhanam; Mining Weather Data Using Component Analysis, Journal of Machine Learning Research 5 239-253 2004[15] WILLIAM W. HSIEH; Nonlinear Canonical Correlation Analysis of Tropical Pacific Climate Variability Using a Neural Network Approach: Journal of Climate Vol – June 14, 2001 Muhammad Abrar, Lecturer at Agricultural University Peshawar, Pakistan This is a summary of the master's degree recently approved by the study committee of the group concerned.