Earthquake Aftershock Prediction Based Solely on Seismograph Data

Lu, Yu-Ching; Sawada, Erika; Chakraborty, Goutam

doi:10.1109/bigcomp.2019.8679491

Cited by 4 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lu et al [75] proposed a GA-based clustering algorithm to predict the location and timing of earthquake aftershocks. They have used seismographs of Southern California and Japan, which was used to create a directed graph.…”

Section: ) Earthquake and Aftershock Prediction Studiesmentioning

confidence: 99%

“…[63] PR-KNN Time interval between aftershocks [64] HWT with RF, NB, J48, REP Tree, and BP Seismic signal [66] RST and DT (C4.5) Location and climatic factors [67] PHMM Initial probability, transition probability [68] KMC b-value, date of occurrence, mg. [69] KMC and TBS Seismicity indicators, increments of b-value [71] HKMC with ANN Seven seismicity indicators [72] b-value, Bath's law, and OU's law parameters [70] HKMC lo., la. [73] Dobrovolsky-based Clustering SES [74] AHC Over Sampling Seismicity indicators [75] GA based Clustering Time, lo., la., tremor mg., dpt. of seismograph [76] ACC algorithm Belt, water level, b-value, tilt, frequency etc.…”

Section: ) Earthquake and Aftershock Prediction Studiesmentioning

confidence: 99%

“…Lu et al [75] have used GA based clustering for predicting the time and location of aftershocks. They created a weighted graph where the correlated aftershocks were clustered to- gether.…”

Section: B Shallow Machine Learning Approachesmentioning

confidence: 99%

“…of RF was 100% [66] RST and DT (C4.5) Acc., Sn., Sp., F-measure Acc. was 93.5% (DT) [ Dobrovolsky-based Clustering PHIVOLCS Prediction validation Clustered the zones successfully [74] AHC Over Sampling CEDC G-value Improved the precision and prediction hit rate [75] GA based Clustering Clustered eq. prone areas [76] ACC algorithm Average distance, time Average distance covered was 41.488 [77] PSO Clustering Algorithm Acc., Average distance, time Acc.…”

mentioning

confidence: 99%

See 3 more Smart Citations

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%

Section: ) Earthquake and Aftershock Prediction Studiesmentioning

confidence: 99%

“…Lu et al [75] have used GA based clustering for predicting the time and location of aftershocks. They created a weighted graph where the correlated aftershocks were clustered to- gether.…”

Section: B Shallow Machine Learning Approachesmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

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

“…One category relies on Statistical Seismology, and one usually speaks of earthquake forecasts in this case. For example, sometimes, the information on historical earthquakes, including magnitude, location of hypocenter or epicenters, and occurrence time of events, will be directly taken as the input of ANNs (Asencio‐Cortés et al., 2016; Asim et al., 2017; D’Amico et al., 2009; Kamath & Kamat, 2017; Lu et al., 2019; Moustra et al., 2011; Wang et al., 2020). Moreover, as inputs of the ANNs, researchers also consider features retrieved from the earthquake catalogs, such as the b‐value of Gutenberg‐Richter law (Gutenberg & Richter, 1944), Region‐Time‐Length indicator (Huang et al., 2002), Bath's law (Båth, 1965), Omori's law (Utsu, 1961), mean seismicity rate, the cumulative frequency of events, estimated released energy of earthquakes and so on (Asim et al., 2016; Basuki et al., 2018; Fuentes et al., 2022; Huang et al., 2020; Jiang et al., 2009; Konstantaras et al., 2008; Reyes et al., 2013; Shodiq et al., 2017; Sri Lakshmi & Tiwari, 2009; Wang et al., 2009; Zhang et al., 2019).…”

Section: Introductionmentioning

confidence: 99%

Seismically Informed Reference Models Enhance AI‐Based Earthquake Prediction Systems

Zhang,

Zhan,

Huang

et al. 2024

JGR Solid Earth

View full text Add to dashboard Cite

Given the robust nonlinear regression capabilities of Artificial Intelligence (AI) technology, its commendable performance in numerous geophysical tasks is expected. Yet, AI technology suffers from (a) its “black box” nature and (b) the fact that some complicated artificial neural networks (ANNs) claiming superior performance do not surpass some simple geophysical models that clearly describe the underlying physical processes. Numerous reports rely on standard machine learning metrics, often using a spatially uniform Poisson (SUP) distribution as their reference. A good performance just means that the artificial neural network (ANN) outperforms this basic reference, potentially offering little novelty to the scientific community. Worse, this can lead to spurious inference. We demonstrate this by using the monthly average human‐made Nighttime Light Map and the cumulative energy of earthquakes in various space‐time units as inputs for an Long short‐term memory model. The goal is to predict earthquakes with a magnitude of M ≥ 5.0 across the entire Chinese Mainland. With the SUP reference model, the ANN concludes that human‐made Nighttime Light possesses substantial earthquake prediction capability. This is evidently flawed reasoning. We show that this stems from the poor reference model and this spurious inference disappears when using a better benchmark consisting of a spatially varying Poisson (SVP) model informed from statistical seismology. This is implemented by weighting the punishments/rewards of our ANN associated with failed/successful predictions by prior probabilities provided by the stronger SVP model. Scores obtained with the time‐space Molchan diagram demonstrate the strong performance improvement obtained by training ANN with a better reference model.

show abstract

Applications of machine learning for earthquake prediction: A review

Saleem¹,

Rashid²

2023

AIP Conference Proceedings

View full text Add to dashboard Cite

Earthquake Aftershock Prediction Based Solely on Seismograph Data

Cited by 4 publications

References 7 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

Seismically Informed Reference Models Enhance AI‐Based Earthquake Prediction Systems

Applications of machine learning for earthquake prediction: A review

Contact Info

Product

Resources

About