Long Short-Term Memory Algorithm for Rainfall Prediction Based on El-Nino and IOD Data

Haq, Dina Zatusiva; Novitasari, Dian Candra Rini; Hamid, Abdulloh; Ulinnuha, Nurissaidah; Arnita., .; Farida, Yuniar; Nugraheni, Rr. Diah; Nariswari, Rinda; Ilham, Ilham; Rohayani, Hetty; Pramulya, Rahmat; Widjayanto, Ari

doi:10.1016/j.procs.2021.01.071

Cited by 28 publications

(22 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is in line with previous research where the researcher used 1344 data [3] which had a larger error than using 744 data [4] and [32]. Meanwhile, the LSTM method is a deep learning algorithm that requires longterm data [33] as described in previous researches [23] and [34]. Therefore, the researchers hope that further research will implement methods that can use short term data, for example, the backpropagation method [4].…”

Section: Resultssupporting

confidence: 81%

“…If the batch size is to large it may take the network too long to reach convergence, but if the batch size is too small the network will bounce back and forth without getting acceptable performance [31]. Meanwhile, the learning rate drop period is the number of iterations that must be determined by the learning rate [23]. This research calculates the sea surface current velocity of U and V components.…”

Section: Resultsmentioning

confidence: 99%

“…In a dataset, there is a high data range. This range will affect the prediction results [23]. Data can be normalized before the training process.…”

Section: Data Normalizationmentioning

confidence: 99%

See 2 more Smart Citations

Prediction of Sea Surface Current Velocity and Direction Using LSTM

Zulfa

Novitasari

Setiawan³

et al. 2021

Indonesian J. Electron. Instrum. Syst.

View full text Add to dashboard Cite

Labuan Bajo is considered to have an important role as a transportation route for traders and tourists. Therefore, it is necessary to have a further understanding of the condition of the waters in Labuan Bajo, one of them is sea currents. The purpose of this research is to predict sea surface flow velocity and direction using LSTM. There are many prediction methods, one of them is Long short-term memory (LSTM). The fundamental of LSTM is to process information from the previous memory by going through three gates, that is forget gate, input gate, and output gate so the output will be the input in the next process. Based on trials with several parameters namely Hidden Layer, Learning Rate, Batch Size, and Learning rate drop period, it achieved the smallest MAPE values of U and V components of 14.15% and 8.43% with 50 hidden layers, 32 Batch size and 150 Learn rate drop.

show abstract

Section: Resultssupporting

confidence: 81%

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of Sea Surface Current Velocity and Direction Using LSTM

Zulfa

Novitasari

Setiawan³

et al. 2021

Indonesian J. Electron. Instrum. Syst.

View full text Add to dashboard Cite

show abstract

“…Because the increase in pH increases the concentration of OH radicals, An increase in pH also impacts the reactivity of certain medications. When pH rises, amines become more reactive due to increased electronegativity; for example, in deionized water, scavengers have been introduced to monitor the optimal pH at which the pace of reaction can be observed (Haq et al, 2021;Keyan et al, 2021). In O 3 disinfection, pH may be an important factor.…”

Section: Factors Affecting the Ozonation Process For Wastewatermentioning

confidence: 99%

Advancement in Ozone base wastewater treatment technologies: Brief review

Hussain¹,

Khan

Vambol

et al. 2022

View full text Add to dashboard Cite

Over 70% of the planet's surface is covered by water. A universal solvent, water can dissolve a wide variety of compounds. The majority of water contamination is caused by human activity. Increasing water use and pollution are to blame for the current shortage of fresh water supplies. Population expansion, agricultural runoff, and municipal wastewater are the primary sources of pollution in the river. To conduct the study, the logical chain was developed. For the review, open sources of scientific information were used. The focus was on publications from the last 10 years and at the same time; earlier works were taken into accounts that have useful information for this study, which were identified in the list of references when studying recent sources. The number of sources published earlier than 10 years ago does not exceed 7% of the total number of references. The present study aims to determine the optimum conditions for best removal of contaminants as the review focuses on advancement in Ozonation/AOP technology, different type of methods used for drugs removal and different operating condition. Various modern treatment procedures make extensive use of drinking water treatment plants. Water shortages in countries can be alleviated by implementing some of the recommendations made in the research. More catchment areas need to be developed; strict management policies and guidelines should be implemented. Ozonation can also more effectively remove certain personal care products (PPCPs) from the skin. Recycled water can be disinfected using ozonation, which breaks down ozone in water. When ozone is used in this way, it is an effective parasiticide, germicide, and virucidal agent. It can also remove the chroma compounds, smells, infections, and many micro-pollutants simultaneously. Ozone-based AOP should be studied in the future to see whether it is cost-effective and to see if it consumes more energy than other traditional treatment methods.

show abstract

“…The batch size is how often the weights will be updated. Learning rate drop is the number of iterations in determining the learning rate [22].…”

Section: Gated Recurrent Unit (Gru)mentioning

confidence: 99%

Sunspot Number Prediction Using Gated Recurrent Unit (GRU) Algorithm

Arfianti

Novitasari

Widodo³

et al. 2021

Indonesian J. Comput. Cybern. Syst.

View full text Add to dashboard Cite

Sunspot is an area on photosphere layer which is dark-colored. Sunspot is very important to be researched because sunspot is affected by sunspot numbers, which present the level of solar activity. This research was conducted to make prediction on sunspot numbers using Gated Recurrent Unit (GRU) algorithm. The work principle of GRU is similar to Long short-term Memory (LSTM) method: the information from the previous memory is processed through two gates, that is update gate and reset gate, then the output generated will be input for the next process. The purpose of predicting sunspot numbers was to find out the information of sunspot numbers in the future, so that if there is a significant increase in sunspot numbers, it can inform other physical consequences that may be caused. The data used was the data of monthly sunspot numbers obtained from SILSO website. The data division and parameters used were based on the results of the trials resulted in the smallest MAPE value. The smallest MAPE value obtained from the prediction was 7.171% with 70% training data, 30% testing data, 150 hidden layer, 32 batch size, 100 learning rate drop.

show abstract

Long Short-Term Memory Algorithm for Rainfall Prediction Based on El-Nino and IOD Data

Cited by 28 publications

References 13 publications

Prediction of Sea Surface Current Velocity and Direction Using LSTM

Prediction of Sea Surface Current Velocity and Direction Using LSTM

Advancement in Ozone base wastewater treatment technologies: Brief review

Sunspot Number Prediction Using Gated Recurrent Unit (GRU) Algorithm

Contact Info

Product

Resources

About