Prediction of temperature and relative humidity with AI on the Ecuadorian coast
DOI:
https://doi.org/10.37868/hsd.v6i2.629Abstract
Artificial intelligence (AI) has established itself as an essential tool in climatology. It facilitates accurate analysis and prediction of variables such as temperature and humidity, which are crucial for understanding global warming and its effects. In this context, this study aims to implement predictive simulations of temperature and relative humidity on the Ecuadorian coast using artificial intelligence (AI). This study adopts a quantitative methodology, utilizing daily historical data collected from 2015 to 2020. Monthly averages for maximum temperature and relative humidity were calculated, based on 72 observations for each variable. The climate simulation employed statistical techniques such as linear regression and simple correlation, along with the implementation of various AI libraries in Rstudio, including readxl, QuantPsyc, and ggplot2, among others. Additionally, the ARIMA model was applied to analyze time series, facilitating detailed simulation and prediction of both climatic variables. The results indicate a significant inverse correlation between maximum temperature and relative humidity, revealing high-temperature variability in recent years. The optimized ARIMA predictive models showed AICC indices of 180.47 for temperature and 283.16 for humidity, after 96 iterations, demonstrating the high reliability of AI in climate prediction for the Ecuadorian coastal region. The study concludes with the importance of integrating advanced technologies such as AI in climatology to improve the accuracy and efficiency of climate predictions.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Ángel Ramón Sabando-García, Jenniffer Sobeida Moreira-Choez, Luis Javier Castillo-Heredia, Anthony Andrés Bazurto Loor, Rafael Romero-Carazas, Eduardo Espinoza-Solís
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
This journal permits and encourages authors to post items submitted to the journal on personal websites or institutional repositories after publication, while providing bibliographic details that credit its publication in this journal.