Prediksi Parameter Cuaca Menggunakan Deep Learning Long-Short Term Memory (Lstm)

Supriyadi, Eko

doi:10.31172/jmg.v21i2.619

Cited by 10 publications

(10 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In Table 4, the average value of the RMSE Sea Surface Topography (SST) in the East Indonesian Sea is 0.076242615 m. The RMSE value gets closer to zero [16]. However, when referring to the vertical accuracy of the Altimetry Satellite Jason-3, which reaches 5 cm [14], the RMSE value obtained is not good enough.…”

Section: Calculation Of Sea Surface Topography (Sst) Value Errormentioning

confidence: 99%

Estimation of Sea Surface Topography Using Jason-3 Satellite Altimetry Across the Eastern Indonesian Seas in a period of 2016 to 2021

Handoko,

Syariz,

Wenda

2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

The measurement of sea level height relative to a fixed reference point, such as the geoid or mean sea level, is known as sea surface topography. There are a number of factors that affect it, such as undulation, sea surface height, and tides. Measurement of sea surface topography is very important to understand ocean dynamics. One of the factors that influences the dynamics of the sea is the flow across Indonesia. The Indonesian traffic flow is the mass flow of water from the Pacific Ocean to the Indian Ocean. The difference in pressure between the two oceans is what causes the flow. The purpose of this study is to provide precise information about the sea surface topography in the East Indonesian Sea region during the 2016–2021 period, which is required for various marine applications. This approach involves processing and analysing Jason-3 altimetry satellite data, which provides precise sea level elevation measurements. The data is then used to determine the value of the sea surface topography, which shows the spatial and temporal variations in sea level height in the region. The average sea surface topography value every month from 2016 to 2021 ranges from 1.05m to 1.30m, with the highest value occurring in January 2021 at 1.2542m and the lowest value occurring in February 2016 at 1.0498m. For the accuracy of processing results, data for 2016–2021 is used as training data for model estimation and 2021 as test data. The root mean square error value is 0.0762m. Changes in sea surface topography values tend to increase every year, except for 2019. The decline that occurred in 2019 was caused by the ENSO phenomenon, which had an effect of -0.807 on sea surface topography with an inverse correlation. The findings of this study provide important details about sea surface topography in Eastern Indonesian waters, which can be applied to enhance our understanding of ocean dynamics.

show abstract

Section: Calculation Of Sea Surface Topography (Sst) Value Errormentioning

confidence: 99%

Estimation of Sea Surface Topography Using Jason-3 Satellite Altimetry Across the Eastern Indonesian Seas in a period of 2016 to 2021

Handoko,

Syariz,

Wenda

2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

show abstract

“…Selain metode SARIMA dalam data mining, terdapat juga metode deep learning dan artificial neural network dalam machine learning. Penerapan metode deep larning dengan jumlah layer sebanyak 200, dan perbandingan antara data training dan data testing sebesar 9:1 untuk melakukan prediksi cuaca dengan beberapa parameter seperti pengukuran kelembapan udara, kecepatan angin, tekanan udara, dan suhu udara [18]. Hasil dari penelitiannya menunjukkan bahwa nilai RMSE dari seluruh validasi parameter cuaca memperoleh hasil yang lebih baik saat digunakan metode LSTM update.…”

Section: Pendahuluanunclassified

Prediksi Kualitas Air Menggunakan Metode Seasonal Autoregressive Integrated Moving Average (SARIMA)

Agustin

Rahani²,

Indikawati³

2022

JAMIKA

View full text Add to dashboard Cite

Water conservation is very necessary to support the creation of clean water quality that is free from harmful substances that can disturb the environment. So a system is needed to monitor water quality to determine the level of pollution that occurs. This system will work to see water quality in real time with several quality parameters such as pH, temperature, and water turbidity. The purpose of this research is to produce a predictive model and find out the prediction results of a data mining-based system. The method used to predict water quality uses the Seasonal Autoregressive Integrated Moving Average (SARIMA) method, because the water quality data is thought to contain seasonal patterns. The results of this study indicate that the SARIMA model can be applied to the dataset used and obtain the accuracy of the forecasting results on each of the tested parameter data. The results of water quality forecasting with this parameter are the result data for testing at a dataset of a depth of 30 cm and a depth of 60 cm for temperature parameters, namely MSE<0.1, and RMSE<0.02. For pH parameters, MSE<0.1, and RMSE<0.1. As well as the turbidity parameter, the results of MSE<0.02, and RMSE<0.13. From these results indicate that this system can predict water quality with past data.

show abstract

“…However, until now the process of making predictions of the speed and direction of ocean currents is still limited from modeling data. Where the modeling still has shortcomings such as the use of the number of parameters, mathematical assumptions, and equation formulations that tend to be complicated [7]. Weaknesses can be understood because producing model results that are close to reality, requires a lot of input parameters and fulfilling assumptions which are sometimes very difficult to do.…”

Section: Introductionmentioning

confidence: 99%

“…Weather and climate predictions have been carried out by several researchers, including Irkhana Indaka Zulfa by predicting the speed and direction of sea surface currents using the LSTM to obtain the smallest MAPE values for the U component and the V component of 14.15% and 8.43% [25]. Eko [7] with research shows that the RMSE results with all-weather parameter validations are getting better when using LSTM with updates.…”

Section: Introductionmentioning

confidence: 99%

Long-Short Term Memory (Lstm) for Predicting Velocity and Direction Sea Surface Current on Bali Strait

Pramesti

Novitasari

Setiawan³

et al. 2022

BAREKENG: J. Il. Mat. & Ter.

View full text Add to dashboard Cite

The strategic role of the Bali Strait as a connection between the islands of Java and Bali is growing in line with the increase in the economy and tourism of the two islands. Therefore, it is necessary to have a further understanding of the condition of the waters in the Bali strait, one of which is ocean currents. This study aims to predict future ocean currents based on 30-minute data in the Bali Strait in the range of 16 May 2021 to 9 June 2021 obtained from the Perak II Surabaya Maritime Meteorological Station. In this study, the Long Short Term Memory method was used. The parameters used are hidden layer, batch size, and learn rate drop. Based on the parameters used, the results showed that the smallest MAPE value was 18.64% for U ocean current velocity data and 5.29% for V ocean current velocity data.

show abstract

Prediksi Parameter Cuaca Menggunakan Deep Learning Long-Short Term Memory (Lstm)

Cited by 10 publications

References 21 publications

Estimation of Sea Surface Topography Using Jason-3 Satellite Altimetry Across the Eastern Indonesian Seas in a period of 2016 to 2021

Estimation of Sea Surface Topography Using Jason-3 Satellite Altimetry Across the Eastern Indonesian Seas in a period of 2016 to 2021

Prediksi Kualitas Air Menggunakan Metode Seasonal Autoregressive Integrated Moving Average (SARIMA)

Long-Short Term Memory (Lstm) for Predicting Velocity and Direction Sea Surface Current on Bali Strait

Contact Info

Product

Resources

About