Weather Pattern Extraction using Statistical Methods & Machine Learning Techniques

Weather Pattern Extraction using Statistical Methods & Machine Learning Techniques

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2021.

Dettagli Bibliografici
Autore principale: Habib, Adria Binte
Altri autori: Ashraf, Faisal Bin
Natura: Tesi
Lingua:English
Pubblicazione: Brac University 2021
Soggetti:
Statistical Methods
Machine Learning
Weather
Prediction
ARIMA
Trend Analysis
Accesso online:http://hdl.handle.net/10361/15010
id 10361-15010
record_format dspace
spelling 10361-150102022-01-26T10:04:57Z Weather Pattern Extraction using Statistical Methods & Machine Learning Techniques Habib, Adria Binte Ashraf, Faisal Bin Mostakim, Moin Department of Computer Science and Engineering, Brac University Statistical Methods Machine Learning Weather Prediction ARIMA Trend Analysis Machine Learning This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2021. Cataloged from PDF version of thesis. Includes bibliographical references (page 26-28). It is known to all that the existence of life is highly dependent on the weather. Due to the unfavorable condition of current global weather the existence of life is in danger already. Since for the existence of lives a livable environment which lies in the weather is very much intrinsic, it should be taken care of before it is too late. This is the main context of this research. The goal of this research is to find out the future condition of temperature of some particular places of California using machine learning and statistical methods and compare which place will be more livable after two years. Currently, one of the most alarming issue in the world is the global warming. The effect of global warming is increasing rapidly every day without any sign of slowing down. As a result of this, it’s very concerning and important to understand the state of the temperature of the world and the route it will take in the future. As such, the objective of this reseach is to predict the temperature conditions of the future. The research starts by collecting data of few select areas in california and hence, extracted data from 14 stations of california. The data was then fed to the ARIMA model to find the future trend with the respective ARIMA orders and other paremeters per station. The research has successfully identified the trend of the next 730 days (2 years) while considering the errors that the model creates. Furthermore, the research tried to identify the most favorable place to live, in california, by comparing the RMSE of the different stations by comparing the distance between the favorable human ambient temperature of 70◦F with the results that we got from the prediction. As such, the ‘Miramar’ station gave the least RMSE value of 10.7824 while the ‘lake Arrowhead’ gave the worst RMSE of 24.3605. From these RMSE values and also the learning curves it was decided, the most favorable place to live around was the ‘Miramar’ station, while ‘lake Arrowhead’ station was the worst in terms of favourable temperature for humans. Adria Binte Habib B. Computer Science 2021-09-14T07:20:17Z 2021-09-14T07:20:17Z 2021 2021-06 Thesis http://hdl.handle.net/10361/15010 en Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 55 pages application/pdf Brac University
institution Brac University
collection Institutional Repository
language English
topic Statistical Methods
Machine Learning
Weather
Prediction
ARIMA
Trend Analysis
Machine Learning
spellingShingle Statistical Methods
Machine Learning
Weather
Prediction
ARIMA
Trend Analysis
Machine Learning
Habib, Adria Binte
Weather Pattern Extraction using Statistical Methods & Machine Learning Techniques
description This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2021.
author2 Ashraf, Faisal Bin
author_facet Ashraf, Faisal Bin
Habib, Adria Binte
format Thesis
author Habib, Adria Binte
author_sort Habib, Adria Binte
title Weather Pattern Extraction using Statistical Methods & Machine Learning Techniques
title_short Weather Pattern Extraction using Statistical Methods & Machine Learning Techniques
title_full Weather Pattern Extraction using Statistical Methods & Machine Learning Techniques
title_fullStr Weather Pattern Extraction using Statistical Methods & Machine Learning Techniques
title_full_unstemmed Weather Pattern Extraction using Statistical Methods & Machine Learning Techniques
title_sort weather pattern extraction using statistical methods & machine learning techniques
publisher Brac University
publishDate 2021
url http://hdl.handle.net/10361/15010
work_keys_str_mv AT habibadriabinte weatherpatternextractionusingstatisticalmethodsmachinelearningtechniques
_version_ 1814307062461497344

Documenti analoghi