ADVANCED WEATHER FORECAST PREDICTION RESULT USING ARTIFICIAL NEURAL NETWORK



Authors

  • 1Shaik Parvez 2Dr. Nagesh Babu Dasari 3Dr. Pucha Venkata Subbarama Sarma

DOI:

https://doi.org/10.15282/jmes.17.1.2023.10.0759


Keywords:

Indian Metrological dataset, Weather Prediction, Neural networks, Pattern Classification, Machine Learning, Deep Learning. Genetic Algorithm, Classification, Artificial Neural Network, Weather Forecast, Optimization.


Abstract

Prediction of weather condition is important to take efficient decisions. In general, the relationship between the input weather parameters and the output weather condition is nonlinear and predicting the weather conditions in nonlinear relationship task. Weather forecasts are done by collecting data of a specified location with different attributes of climate. Recently many researchers recommended that the machine learning models can produce sensible weather predictions in spite of having no precise knowledge of atmospheric physics. Algorithms such as Gradient Boosting, Artificial Neural Network, Stacking Random Forest Stacking Neural Network, and Stacking KNN are evaluated and compared based on their performance metrics, including Confusion matrix measurements. In this paper ANN has used to classify the patients with the optimized weight by using Genetic algorithm. GA based ANN model has been proposed which significantly overcomes the problem of using local search-based learning algorithms to train NNs. Long Short Term Memory network based on the time series data of the rainfall. Further the prediction efficiency is enhanced by the utilization of the Circle Inspired Optimization Algorithm for the weight optimization of the Deep Long Short Term Memory. The attention mechanism is used for improving the performance and the hyper parameter of GRU are optimized by the adaptive wild horse algorithm (AWHA). We propose a neural networks based model for weather prediction. The superiority of the proposed model is tested with the weather data collected from Indian metrological Department (IMD).



Published

2024-06-30

How to Cite