EQTransformersupports a variety of platforms, including macOS, Windows, and Linux operating systems. Note that you will need to have Python 3.x (3.6 or 3.7) installed. TheEQTransformerPython package can be installed using the following options: ...
3.2. Workflow 2: Using pre-trained models The following code blocks show how to load each of the pre-trained deep learning models described in Section 2.2 and apply the model to data provided in the correct input format. 3.2.1. Using pre-trained CREIME The following steps are needed to ...
We utilize Python 3.9 along with Matplotlib 3.4.3 to plot our experimental figures. Additionally, we employ ObsPy 1.1 for the processing of earthquake data. The CRNN model is implemented using TensorFlow 1.14 and Keras 2.2.4. Similarly, the proposed transformer model is implemented using PyTorch ...
In addition to the prediction probabilities, it can also provide estimated model uncertainties. The EQTransformer python 3 package includes modules for downloading continuous seismic data, preprocessing, performing earthquake signal detection, and phase (P & S) picking using pre-trained models, building ...
simultaneously performs the detection and phase picking while modeling the dependency of these tasks on each other through a hierarchical structure; (4) in addition to the prediction probabilities, it provides output variations based on Bayesian inference; (5) it is the first model trained using a...
6. The architecture of the proposed DNN model. lc Iji ¼ Pecl¼x1peðxfpcðfIljiIÞji Þ ð5Þ The DNNs architecture is based on a multilayer feed-forward neural network and was applied using the Keras and TensorFlow libraries in python 3.5 for soil liquefaction ...
Here we present an analysis of the 2016 Mw 7.1 earthquake on the Romanche fracture zone in the equatorial Atlantic, using data from both nearby seafloor seismometers and global seismic networks. We show that this rupture had two phases: (1) upward and eastward propagation towards a weaker ...
3.4 Data pre-processing In this proposed model of using HQNN in the prediction of Tsunami, the input data are the features of earthquakes occurring over different regions which is available in the form of a CSV file from Kaggle. The data couldn't be used directly hence all the null values...
Build the applications using the generated make files make Building the source code on Ubuntu Linux Before building the source code on Ubuntu Linux and running it, the dependencies can be installed using the following commands: sudo apt-get update sudo apt-get install gcc g++ python perl ...
on the training set by minimizing the Huber loss between the true values and the predicted earthquake source parameters using the Adam algorithm49, with its default parameters (β1 = 0.9 andβ2 = 0.999) and a learning rate of 0.001. At the end of each epoch, the model is tested...