Contact at mumbai.academics@gmail.com or 8097636691
Responsive Ads Here

Monday, 26 February 2018

Data Mining Techniques in Weather Prediction


Data Mining Techniques in Weather 

Prediction


Abstract—Weather forecasting is a vital application in meteorology and has been one of the most scientifically and technologically challenging problems around the world in the last century. In this paper, we investigate the use of data mining techniques in forecasting maximum temperature, rainfall, evaporation and wind speed. This was carried out using Artificial Neural Network and Decision Tree algorithms and meteorological data collected between 2000 and 2009 from the city of Ibadan, Nigeria. A data model for the meteorological data was developed and this was used to train the classifier algorithms. The performances of these algorithms were compared using standard performance metrics, and the algorithm which gave the best results used to generate classification rules for the mean weather variables. A predictive Neural Network model was also developed for the weather prediction program and the results compared with actual weather data for the predicted periods. The results show that given enough case data, Data Mining techniques can be used for weather forecasting and climate change studies.Data Mining Techniques in Weather Prediction.
Index Terms— Weather Forecasting, Data Mining, Artificial Neural Networks, Decision Trees
Conclusion In this work the C5 decision tree classification algorithm was used to generate decision trees and rules for classifying weather parameters such as maximum temperature, minimum temperature, rainfall, evaporation and wind speed in terms of the month and year. The data used was for Ibadan metropolis obtained from the meteorological station between 2000 and 2009. The results show how these parameters have influenced the weather observed in these months over the study period. Given enough data the observed trend over time could be studied and important deviations which show changes in climatic patterns identified. Artificial Neural Networks can detect the relationships between the input variables and generate outputs based on the observed patterns inherent in the data without any need for programming or developing complex equations to model these relationships. Hence given enough data ANN’s can detect the relationships between weather parameter and use these to predict future weather conditions. Both TLFN neural networks and Recurrent network architectures were used to developed predictive ANN models for the prediction of future values of Wind speed, Evaporation, Radiation, Minimum Temperature, Maximum Temperature and Rainfall given the Month and Year. Among the recurrent neural network architectures used the recurrent TLFD network which used the TDNN memory component gave a better training and testing result and this better than the best TLFD network which used a Gamma memory component. The results obtained were evaluated with the test data set prepared along with the training data and were found to be acceptable considering the small size of the data available for training and testing. To have a better result a larger data set which will comprise of data collected over many decades will be needed. In future research works neuro-fuzzy models will be used for the weather prediction process. This work is important to climatic change studies because the variation in weather conditions in term of temperature, rainfall and wind speed can be studied using these data mining techniques.

No comments:

Post a Comment