Blockly Earthquake Transformer

Blockly Earthquake Transformer is a no-code, deep learning approach using the EqT model. BET presents users with an interactive form enabling them to upload their data and customize the model and arguments to create their workflows. Once the form is filled out, BET executes the corresponding phase picking task without requiring the user to interact directly with the code. This tool is designed to simplify EqT applications to various fields, such as local events, teleseismic earthquakes and microseismicity. Here, users can detect events using the pretrained EqT model, re-train and deploy new models with the EqT architecture. In addition, transfer learning and fine-tuning functions are implemented in BET. In the transfer learning module, BET extends the phase picking range from P and S phase to additional phase types, e.g., Pn, Pg, Sn, Sg (based on the labeled training data), etc. In the fine-tuning module, detailed model architecture can be customized by users to build new models that may achieve better performance on specific projects than currently published models. This repository is for fast deployment of reusable workflows, building customized models, visualizing training processes and producing publishable figures in a lightweight, interactive, open-source Python toolbox.

Installation, usage, documentation and scripts are described at https://github.com/maihao14/BlocklyEQTransformer

Note that Blockly Earthquake Transformer (BET) is driven by the-state-of-art AI model - EQTranformer(EqT) from Mousavi et al. (2020).