Journal article Open Access

Earthquake Analyzer using Prediction Commands

Abhishek Singh; Sarthak Bansal; Madhav Chaturvedi

Blue Eyes Intelligence Engineering and Sciences Publication(BEIESP)

Destructive earthquakes usually causes gargantuan casualties. So, to cut back these inimical casualties’ analysis are made to reduce despicable and forlorn impacts which they left upon others to just ponder and become lugubrious. These factors measure the decisive casualties it brings and also earthquake and therefore the development of rational prediction model to casualties become a crucial analysis topic, as a result of quality and cognitive content of gift prediction methodology of price, an additional correct prediction model is mentioned by gray correlation theory and BP neural networks. The earthquake can be analyzed succinct by using various technique mainly predictive commands to marshal all the calculated time and magnitude of a potential earthquake have been the topic of the many studies varied ways are tried mistreatment several input variables like temperature exorable, seismic movements and particularly the variable climatic conditions. The relation between recorded seismal-acoustic information associate degreed occurring an abnormal seismic process (ASP). However, it's obstreperous to predict all parameters the placement, time and magnitude of the earthquake by mistreatment this information. This model description is different from others as with the help of the prediction commands most of the paragons and domains are identified and tend to explore the activity of serious Earthquakes. We use the preemptive data information which is collected around the planet. We retrieved the data to perceive that associate degree earthquake reaches the class of exceeds a grade range of eight on Richter Scale. The two main affected areas are in the field of Data Exploration and Data Mapping. Number of occurrences of an earthquake with different magnitude ranges, severity of an earthquake. Mapping is thereby crucial to identify highly affected areas based on Magnitude and Correlation between depth and magnitude. So, based on the above explorations we have made the following predictions. Predictions Magnitude based on depth. Magnitude based on Latitude and Longitude. Depth based on Latitude and Longitude The primitive algorithm used here are the Machine Learning Algorithm I.e. Linear Regression and K-Means Clustering. Firstly, we have made all the predictions via Linear Regression and made different clusters of the Earthquakes which belong to the same subdivision as that of Magnitude or Depth.

Files (258.9 kB)
Name Size
258.9 kB Download
Views 9
Downloads 8
Data volume 2.1 MB
Unique views 9
Unique downloads 8


Cite as