|
Abstract
|
Weather Forecasting has always been some important aspects of our daily lives. Accurate predictions of temperature, precipitation, and other weather variables can help us prepare for the day ahead, whether it be for personal activities or for critical decision making in various industries. In recent years, advances in machine learning and deep learning have enabled researchers to develop new and more sophisticated models for weather forecasting [1].
The aim of this thesis is to investigate the potential of machine learning and deep learning techniques for enhancing weather forecasting in Wasit City, Iraq. The city has a unique climate, and understanding its weather patterns is crucial for the residents and businesses in the area. Our focus is on temperature prediction, as temperature is a critical weather variable with a significant impact on many aspects of daily life.
To achieve our goal, we will use weather data from NASA website, which provides daily weather data for Wasit City from year 2000 to 2020. Our study will compare the accuracy of various machine learning models, such as Support Vector Machine (SVN), K-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF), and Logistic Regression (LR), with deep learning models, such as Recurrent Neural Networks (RNN) and Multi-layer Perceptrons (MLP), for temperature prediction.
The results of this study will provide insights into the performance of machine learning and deep learning models for weather forecasting in Wasit City. This research will also contribute to the ongoing development of more accurate and reliable weather forecasting models and help to understand the potential of AI techniques for solving real-world problems. We hope that this study will help to improve our ability to make informed decisions based on accurate weather predictions.
|