Journal of Computation Physics and Earth Science
Vol 1 No 2 (2021): Journal of Computation Physics and Earth Science

Time Series Forecasting for Average Temperature with the Long Short-Term Memory Network in Deli Serdang Geophysics Station

Nora Valencia Sinaga (Unknown)
Feriomex Hutagalung (Unknown)
Martha Manurung (Unknown)
Eva Darnila (Unknown)



Article Info

Publish Date
01 Oct 2021

Abstract

An understanding of trends analysis, and prediction of time series of average temperature as one of parameter weather and climate data for climate variables. It is the central process in assessing the state of the climate of a region and provides an overall estimate about the variations in the climate variables. Explore weather trends using normal and local yearly average temperatures, compare and make observations. In this study, we try to analyze local and normal average temperature data in Deli Serdang geophysc Station based on observation station in situ. The main goal of this study to compare the normal temperature to local station and to predict the average temperature data in BMKG Geophysics Station, Deli Serdang, North Sumatra using Long Short-Term Memory Model (LSTM). Based on the result of normal data science of exploring temperature with local temperature correlation, we got the display of training curve, residual plot and the scatter plot are shown using these codes. Based on the temperature series data from Geophysic station, the MSE value is 0.83 and the R2 value is 0.86.

Copyrights © 2021






Journal Info

Abbrev

jocpes

Publisher

Subject

Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering Physics

Description

Journal of Computation Physics and Earth Science (JoCPES) publishes cutting-edge research in computational physics and earth sciences. It offers a platform for researchers to share insights on computational methods, physical sciences, environmental science, and more. Topics include computational ...