Conference abstract · 7 Nov 2017
Conference abstractPublished 9 Jun 2018
Long term temperature prediction model based on a long short-term memory neural network in missing data condition
Gwangju Institute of Science and Technology, South Korea
Abstract
Select any words in the title or abstract, or press this and choose a sentence.
Nowadays, global warming not only intimidates humankind but also threatens the ecosystem due to its unpredictability. The ecosystem has warned about its vulnerability, and the need for long-term climate prediction has become indispensable. To build a long-term prediction model, a huge number of training data need without any flawlessness. However, there is a limitation of climate data that once it passed, we could not measure. Thus, the data are apt to be defective. This paper proposes a new long-term temperature prediction model based on a deep neural network, where some defective weather data obtained from a location are calibrated by using those from other locations. Since temperature is seasonal, we use a long short-term memory (LSTM) neural network which is a kind of recurrent neural network (RNN) known as suitable for a very long period of data. In order to predict weather data in advance up to two weeks, the proposed model is trained using actual weather data that are collected in an hourly basis for 36 years (from 1981 to 2016) of 11 different locations of South Korea, including hourly-based measurements for temperature, relative humidity, wind speed, wind direction, precipitation, and accumulated prediction. In particular, when some data are missing, they are filled with those estimated from the refining model. After that, the model is trained again using the refined data. The performance of the proposed LSTM-based model is measured in terms of the root-mean-squared error (RMSE) between actual temperatures and their predicted ones. Consequently, it is achieved that the RMSE averaged over 11 locations is about 2.29 degrees for two weeks prediction. Although the proposed model is applied to refining weather data here, this approach can also be applied to other weather data. Furthermore, the proposed model can be extended to an air pollution prediction model against global warming.
Subjects
Environmental & Earth SciencesAsk about this article
Answers come only from this article's title, abstract and keywords, each sentence pointing to where it comes from. Your question is sent to OpenAI to write the answer. Scholars Central does not store it.
Similar by topic
Brief report · 27 Jun 2023
Global Sea Surface Temperature Short-Term Prediction Using Deep Learning Networks
Commentary · 30 May 2023
Long Short-Term Memory Networks: Overcoming Vanishing Gradient Problem in Recurrent Neural Networks
Research article · 5 Jun 2017
Short-Term Variations of Aerosol Optical Depth during the Severe Dust Storm in 2015 over the Middle East and Long-term Variations of Aerosol Optical Properties
Conference abstract · 21 May 2018
A Long-Term Aerosol Prediction Model Based on a Bi-Directional Long-Short Term Memory Neural Network
More from this journal
The newest in Journal of Earth Science & Climatic Change.
Research article · 21 Apr 2026
Gender and Disturbance Impacts on the Level of Dependece, Floristic and Structural Composition of the Mopane (Colophospermum mopane) Woodlands in Chiredzi South District Zimbabwe
Commentary · 27 Feb 2026
Land Use Change: Environmental Impacts and Sustainable Solutions
Editorial · 27 Feb 2026
Ocean Acidification: Threats, Impacts, and Solutions
Conferences in this field
Upcoming conferences in this field.
Follow
New articles from what you follow go into your email digest, once you agree to alert emails.
- JournalJournal of Earth Science & Climatic Change
- SubjectEnvironmental & Earth Sciences
- BylineArticles whose byline prints “Inyoung Park”
- BylineArticles whose byline prints “Jiwon Lee”
- BylineArticles whose byline prints “Hong Kook Kim”
