Seisbench Model API

An overview of the core model API of SeisBench, a Python framework for training and applying machine learning algorithms to seismic data. It is useful for annotating waveforms using pretrained SOTA ML models, for tasks like phase picking, earthquake detection, waveform denoising and depth estimation. For any waveform, you can manipulate it into an obspy stream object and it will work seamlessly with seisbench models.

bishal-pdMSFT Updated 0 repo stars

File contents

SeisBench Model API

Scope

This skill covers the SeisBench model API: how to load pretrained weights, apply them to waveform streams, and tune throughput for large datasets.

How to read this skill

The actionable material for this skill (installation, API surface, pretrained model catalogue, best practices, and the mandatory station-inventory compatibility check that must run before from_pretrained) lives in the companion document seisbench_model_api_reference.pdf, located alongside this file. Open and read that PDF in full before writing any code against this skill — the sections inside are load-bearing for the workflow and the checks described there are prerequisites to loading pretrained weights.

bishal-pdMSFT/msb-skills commit 2c79bc586b

Frequently asked questions

npx get-skill add bishal-pdmsft/seisbench-model-api-6