This repository contains a Jupyter Notebook focused on climate forecasting using the Jena dataset. The project demonstrates data analysis, preprocessing, visualization, and machine learning modeling for time series forecasting on climate data.
Jena_Climate_Forecasting.ipynb: The main notebook with detailed steps for climate Temperature data analysis and forecasting.
Python 3.x Jupyter Notebook Required libraries: numpy, pandas, matplotlib, seaborn, scikit-learn, tensorflow
Data Preprocessing: Handling missing values, scaling, and preparing the data for modeling. Visualization: Graphical representation of climate variables over time. Modeling: Implementing and evaluating machine learning models for forecasting.
Long Short-Term Memory (LSTM): An advanced RNN capable of learning long-term dependencies, particularly useful for time series data. Convolutional Neural Network (CNN): A deep learning model that can capture spatial patterns, adapted here to capture temporal patterns in the time series data.
The Jena dataset is sourced from https://www.kaggle.com/datasets/mnassrib/jena-climate