Home / Current Issue / Paper 1705276
Sea Surface Temperature Prediction by Using EDA and Exponential Smoothening Algorithm
Subject area: Science,Engineering and Technology · Area of research: Machine Learning, Artificial Intelligence
Abstract
This study proposes an integrated approach for sea surface temperature (SST) prediction, combining Exploratory Data Analysis (EDA) and Exponential Smoothing techniques. The primary objective is to develop a robust predictive model that enhances our ability to monitor and forecast SST dynamics for climate-related applications. The EDA phase involves a comprehensive exploration of historical SST datasets, utilizing descriptive statistics and visualization tools to uncover spatial and temporal patterns. This initial analysis serves as the foundation for subsequent modeling. The study employs Exponential Smoothing, a sophisticated time series forecasting method, to capture and project underlying patterns in SST data. This model considers both short-term and long-term trends, facilitating accurate predictions of future SST values with reduced noise. Calibration and validation are conducted using historical SST data, and the model's performance is compared to traditional forecasting methods. Results demonstrate the effectiveness of the combined EDA and Exponential Smoothing approach in predicting sea surface temperatures. The model exhibits strong predictive capabilities, offering valuable insights for researchers, climatologists, and policymakers to anticipate and respond to changes in oceanic conditions. This research contributes to advancing climate science by emphasizing the importance of integrating exploratory data analysis and advanced forecasting techniques for improved understanding and prediction of sea surface temperatures.
Keywords
Sea Surface Temperature, Exploratory Data Analysis, Exponential Smoothing, Climate Monitoring, Predictive Modeling, Oceanic Conditions
References
[1] Sahai AK, Grimm AM, Satyan V, Pant GB. Long-lead prediction of Indian summer monsoon rainfall from global SST evolution. Climate Dynamics. 2003 May; 20:855-63.
[2] Ahmed MK, Alam MS, Yousuf AH, Islam MM. A long-term trend in precipitation of different spatial regions of Bangladesh and its teleconnections with El Niño/Southern Oscillation and Indian Ocean Dipole. Theoretical and Applied Climatology. 2017 Jul; 129:473-86.
[3] Moron V, Vautard R, Ghil M. Trends, interdecadal and interannual oscillations in global sea-surface temperatures. Climate Dynamics. 1998 Jun; 14:545-69.
[4] Dommenget D. An objective analysis of the observed spatial structure of the tropical Indian Ocean SST variability. Climate dynamics. 2011 Jun; 36:2129-45.
[5] Bosserelle C, Pattiaratchi C, Haigh I. Inter-annual variability and longer-term changes in the wave climate of Western Australia between 1970 and 2009. Ocean Dynamics. 2012 Jan; 62:63-76.
[6] Caloiero T, Aristodemo F, Algieri Ferraro D. Trend analysis of significant wave height and energy period in southern Italy. Theoretical and Applied Climatology. 2019 Oct; 138:917-30.
[7] Fasullo J. A mechanism for land–ocean contrasts in global monsoon trends in a warming climate. Climate Dynamics. 2012 Sep; 39:1137-47.
How to cite this paper
@article{1705276,
author = {Amit Kumar Pandey, Dr. Santosh Singh, Nishant Varma},
title = {Sea Surface Temperature Prediction by Using EDA and Exponential Smoothening Algorithm},
journal = {Iconic Research And Engineering Journals},
year = {2023},
volume = {7},
number = {6},
pages = {159-163},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1705276.pdf},
abstract = {This study proposes an integrated approach for sea surface temperature (SST) prediction, combining Exploratory Data Analysis (EDA) and Exponential Smoothing techniques. The primary objective is to develop a robust predictive model that enhances our ability to monitor and forecast SST dynamics for climate-related applications. The EDA phase involves a comprehensive exploration of historical SST datasets, utilizing descriptive statistics and visualization tools to uncover spatial and temporal patterns. This initial analysis serves as the foundation for subsequent modeling. The study employs Exponential Smoothing, a sophisticated time series forecasting method, to capture and project underlying patterns in SST data. This model considers both short-term and long-term trends, facilitating accurate predictions of future SST values with reduced noise. Calibration and validation are conducted using historical SST data, and the model's performance is compared to traditional forecasting methods. Results demonstrate the effectiveness of the combined EDA and Exponential Smoothing approach in predicting sea surface temperatures. The model exhibits strong predictive capabilities, offering valuable insights for researchers, climatologists, and policymakers to anticipate and respond to changes in oceanic conditions. This research contributes to advancing climate science by emphasizing the importance of integrating exploratory data analysis and advanced forecasting techniques for improved understanding and prediction of sea surface temperatures.},
keywords = {Sea Surface Temperature, Exploratory Data Analysis, Exponential Smoothing, Climate Monitoring, Predictive Modeling, Oceanic Conditions},
month = {December},
}