Neural Network for Earthquake Prediction Based on Automatic Clustering in Indonesia

Shodiq, Mohammad Nur; Kusuma, Dedy Hidayat; Rifqi, Mirza Ghulam; Barakbah, Ali Ridho; Harsono, Tri

doi:10.30630/joiv.2.1.106

Cited by 16 publications

(15 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hierarchical K-means algorithm was used by Shodiq et al for researches [70]- [71]. Shodiq et al [70] proposed a spatial analysis and automatic clustering-based technique to predict earthquake's time period.…”

Section: ) Earthquake and Aftershock Prediction Studiesmentioning

confidence: 99%

See 1 more Smart Citation

Application of Artificial Intelligence in Predicting Earthquakes: State-of-the-Art and Future Challenges

et al. 2020

View full text Add to dashboard Cite

Predicting the time, location and magnitude of an earthquake is a challenging job as an earthquake does not show specific patterns resulting in inaccurate predictions. Techniques based on Artificial Intelligence (AI) are well known for their capability to find hidden patterns in data. In the case of earthquake prediction, these models also produce a promising outcome. This work systematically explores the contributions made to date in earthquake prediction using AI-based techniques. A total of 84 scientific research papers, which reported the use of AI-based techniques in earthquake prediction, have been selected from different academic databases. These studies include a range of AI techniques including rule-based methods, shallow machine learning and deep learning algorithms. Covering all existing AI-based techniques in earthquake prediction, this paper provides an account of the available methodologies and a comparative analysis of their performances. The performance comparison has been reported from the perspective of used datasets and evaluation metrics. Furthermore, using comparative analysis of performances the paper aims to facilitate the selection of appropriate techniques for earthquake prediction. Towards the end, it outlines some open challenges and potential research directions in the field.

show abstract

Section: ) Earthquake and Aftershock Prediction Studiesmentioning

confidence: 99%

“…Shodiq et al [71] proposed a hierarchical K-means clustering algorithm for predicting aftershocks of earthquakes within five days. The earthquakes of magnitude greater or equal to 5.1 were selected for calculating seismicity parameters.…”

Section: ) Earthquake and Aftershock Prediction Studiesmentioning

confidence: 99%

Application of Artificial Intelligence in Predicting Earthquakes: State-of-the-Art and Future Challenges

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Barakbah et al [10,27] analyzed cluster-oriented seismicity predictions of earthquakes in Indonesia and semantic interpretation of predicted results projected into each region. Shodiq et al [11][12][13][14] performed earthquake predictions using the Automatic Clustering and spatial analysis of magnitude distribution to cluster the earthquake data based on the location of the source point and Neural Networks methods.…”

Section: Related Workmentioning

confidence: 99%

Incremental Associative Mining based Risk-Mapping System for Earthquake Analysis in Indonesia

Edelani

Barakbah

Harsono

et al. 2019

JOIV : Int. J. Inform. Visualization

Self Cite

View full text Add to dashboard Cite

Indonesia is one of the largest archipelagic countries in the world that has the highest risk of an earthquake. The major causes of earthquakes in this country are plate movements and volcanic activity. Earthquakes in Indonesia has a cause and effect relationship between each province. This disaster caused severe damage including a lot of people to get killed, injured and lose their money and property. We must minimize the impact of the earthquake by forming earthquake risk mapping. The risk of seismicity in Indonesia can vary each year, so it needs to be analyzed how the changes in risk are each addition of earthquake data. This paper proposes an earthquake risk mapping system with Associative Mining based on incremental earthquake data that have the highest values of confidence rates from the seismic association between provinces in Indonesia. The system uses the Incremental Association rule method to see the trend in the value of changes in confidence for each addition of earthquake data every 5 years. This system proposes 3 main features, which are (1) Data Retrieval and Preprocessing, (2) Association Rule Mining, (3) Incremental Associative Mining based risk mapping. For the experimental study, the system used data from 1963-2018. The results show that the provinces of Maluku, North Maluku, Nusa Tenggara Timur, North Sulawesi, and Papua have an incremental association risk of an earthquake.

show abstract

“…In this study, we use two clustering method of nonhierarchical method. Clustering has its own significance, but it is also used as a pre-processing step when performing complex analyses such as predicting [13].…”

Section: Clusteringmentioning

confidence: 99%

Spatial Clustering based Meteorological Fields Construction for Regional Vulnerability Assessment

Lee

Choi

Sohn

et al. 2018

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

Chemical accidents have affected the social-environmental system. For the regional vulnerability assessment, which is the baseline work to assess the impact on the environment, a meteorological field is needed to determine how chemicals from multiple adjacent companies are propagated. In this study, we present the method of meteorological field based on the spatial cluster which is the main component of vulnerability assessment on regional chemical accident scenario. To integrate spatially dense chemical companies into a cluster, we adopt spatial clustering algorithms. Experiment result shows that DBSCAN-based approach reduces 80.5% total area of the meteorological field against brute-force algorithm, and shows good performance on the average of the overlap ratio, and utility ratio for clustering results.

show abstract

Neural Network for Earthquake Prediction Based on Automatic Clustering in Indonesia

Cited by 16 publications

References 12 publications

Application of Artificial Intelligence in Predicting Earthquakes: State-of-the-Art and Future Challenges

Application of Artificial Intelligence in Predicting Earthquakes: State-of-the-Art and Future Challenges

Incremental Associative Mining based Risk-Mapping System for Earthquake Analysis in Indonesia

Spatial Clustering based Meteorological Fields Construction for Regional Vulnerability Assessment

Contact Info

Product

Resources

About