Published March 10, 2026 | Version v1
Dataset Open

The AI-Ready Downhole Microseismic Benchmark Database (AMBER)

Authors/Creators

  • 1. ROR icon University of Bristol
  • 2. ROR icon University of Oxford

Description

AMBER contains labelled waveforms from microseismic events recorded on deep downhole sensor arrays, generated to stimulate research and development in the use of AI tools for downhole microseismic processing tasks. Raw SEGY waveforms can be converted into Seisbench-compatible datasets (waveforms.hdf5 + metadata.csv) using the extraction pipeline extract.py. This repository also provides an event-centric PyTorch dataset with configurable downhole-specific augmentations for training deep-learning models on multi-station, multi-event waveforms.

AMBER has been compiled from 10 datasets (or sub-datasets):

 - Cotton Valley Stage B
 - Aneth CCS
 - Clearfield mw4 monitoring well
 - Clearfield mw6 monitoring well
 - MSEEL stage 3H
 - MSEEL stage 5H
 - FORGE geothermal 2019
 - FORGE geothermal 2022
 - Preston New Road PNR-1
 - Preston New Road PNR-2

Files

AMBER_Public-0.1.0.zip

Files (34.8 GB)

Name Size Download all
md5:116b807b745642c4f3ec145e2f4086af
44.3 MB Preview Download
md5:3bb9b0a730f3d5ba9241813293338f2f
20.7 GB Preview Download
md5:69a66d5f49cb6a895eabbc5e5c26022c
19.2 MB Preview Download
md5:b245acad4d0a7c682fa97fce875c6a12
14.1 GB Download

Additional details

Related works

Is supplement to
Software: https://github.com/kelleuseis/AMBER_Public (URL)