Analysis of Weather Parameters Using Machine Learning

DOI

10.2991/978-94-6463-196-8_44How to use a DOI?

Keywords

Rainfall; Temperature; Weather; Prediction model; Forecasting Model; Correlation; Autocorrelation; Linear Regression; Data Science; Machine Learning; Marathwada Region

Abstract

Rainfall forecasts at various time and space scales have been one of the essential ingredients for not only industries, businesses, and politicians but also farmers to minimize losses. For agriculture, forecasts of other atmospheric parameters are also relevant. Atmospheric techniques must be known, measurements improved and ongoing study and improvement to ensure reliable weather predictions. In India, the Ministry of Earth Science (MoES) works to develop forecasting in its separate programs and divisions such as India Meteorological Department (IMD). The efforts have culminated in fairly reliable predictions of rainfall patterns. This research aims to enhance prediction accuracy in different geographical areas ranging from weather subdivisions to agro-climate areas. The machine learning techniques have introduced detailed experimental position forecasts for the Marathwada region of Maharashtra state, India. We have developed prediction model for Marathwada region using machine learning techniques. We have used Autocorrelation and seven machine learning techniques for the prediction of weather model such as Linear, Exponential, Quadratic, Additive seasonality, Additive Seasonality Quadratic Trend, Multiplicative Seasonality, and Multiplicative Seasonality Linear Trend. Linear, Exponential, Quadratic and Additive seasonality are not given good result for weather parameter.

Additive Seasonality Quadratic Trend is best fit model for the highest maximum temperature (1.42), lowest minimum temperature (1.87), wind speed (1.06), relative humidity (5.07), mean station (1.19), and mean sea level pressure (1.43). Multiplicative Seasonality model is the best model for mean minimum temperature (1.12) total rainfall in the month (24.13), heavy rainfall (8.74), and number of rainy days (1.2). Multiplicative Seasonality Linear Trend is given good accuracy for mean maximum temperature (1.2). The linear, exponential, quadratic and additive seasonality are not given good result for weather parameter. Rainfall is not the same every year. Some areas get more rain and some areas get less rain and its effect falls on all Marathwada region. The low rainfall and high temperature in the Marathwada region in most of the year due to this comes under the drought condition. So there is a need to change the crop pattern in this region like temperature tolerant crops.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ramdas D. Gore
AU  - Bharti W. Gawali
PY  - 2023
DA  - 2023/08/10
TI  - Analysis of Weather Parameters Using Machine Learning
BT  - Proceedings of the First International Conference on Advances in Computer Vision and Artificial Intelligence Technologies (ACVAIT 2022)
PB  - Atlantis Press
SP  - 569
EP  - 589
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-196-8_44
DO  - 10.2991/978-94-6463-196-8_44
ID  - Gore2023
ER  -