Time-Series-Analysis-Weather-Data

This repository contains the project "Time Series Analysis of Weather Data" completed at Bhaskaracharya Insitutute for Space Applications and Geo-Informatics under Mr. Prem Pattini from May 2021 to July 2021 by Sai Ankit and Sarveshwar Mahapatro.

Demo

Time.Series.Website.mp4

About BISAG

Modern day planning for inclusive development and growth calls for transparent,efficient, effective,responsive and low cost decision making systems involving multi-disciplinary information such that it not only encourages people's participation, ensuring equitable development but also takes into account the sustainability of natural resources. The applications of space technology and Geo–informatics have contributed significantly towards the socio-economic development. Taking cognizance of the need of geo-spatial information for developmental planning and management of resources, the Department of Science and Technology, Government of Gujarat established "Bhaskaracharya Institute for Space Applications and Geo-informatics" (BISAG). BISAG is an ISO 9001:2008, ISO 27001:2005 and CMMI: 5 certified institute. BISAG which was initially set up to carryout space technology applications, has evolved into a centre of excellence, where research and innovations are combined with the requirements of users and thus acts as a value added service provider, a technology developer and as a facilitator for providing direct benefits of space technologies to the grass root level functions/functionaries.

Project Objectives:

Our objective was to develop a deep learning model of analysis of Time Series Data of weather data. Further the technique was to be rendered to the end-user within an easy to operate web application.

Flow of the Project:

1. Obtain required data from Australian Bureau of Meteorology of Daily minimum and maximum temperatures in Melbourne.
2. Process and analyse the time series data.
3. Create a deep learning model to forecast the time series weather data ( minimum and maximum temperature ).
4. Create a user friendly web application for the model.

Tools Used

1. Python 3: A common purpose programming language
2. Tensorflow: An open-source software library for machine learning
3. Streamlit: An open-source Python library that makes it easy to create and share beautiful, custom web apps for machine learning and data science

Dataaset

Daily minimum temperatures in Melbourne, Australia, 1981-1990 

Daily maximum temperatures in Melbourne, Australia, 1981-1990

Degrees Celsius

Source: Time Series Data Library (citing: Australian Bureau of Meteorology)

References:

1. Dataset from ​Time Series Data Library (citing: Australian Bureau of Meteorology)

2. Documentation on Tensorflow python package retrieved from https://www.tensorflow.org/api_docs

3. Streamlit Documentation retrieved from ​ https://docs.streamlit.io/en/stable/