What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
SeisBench is an open-source Python toolbox for applying and training machine-learning models on seismic data. It brings together benchmark datasets, model interfaces, and data-generation pipelines, so researchers can work with existing models or build workflows around their own datasets. It is a software framework—not a seismic sensor—and its results depend on the model, task, and data domain.
What SeisBench provides
SeisBench aims to make seismological datasets and machine-learning models easier to access, reuse, and compare. Its documented capabilities are organized into three parts:
| # | Preview | Product | Price | |
|---|---|---|---|---|
| 1 |
|
Introduction to Seismology | $46.09 | Buy on Amazon |
| 2 |
|
An Introduction to Seismology, Earthquakes, and Earth Structure | $85.25 | Buy on Amazon |
| 3 |
|
Computational Seismology: A Practical Introduction | $63.00 | Buy on Amazon |
| 4 |
|
Introduction to Seismology | $89.99 | Buy on Amazon |
| 5 |
|
Exploration Seismology | $76.78 | Buy on Amazon |
As an Amazon Associate I earn from qualifying purchases.
data: Access and load benchmark datasets.models: Load available models, apply pretrained weights, and train models.generate: Build data-generation pipelines that connect datasets to models.
The project includes introductory notebooks and examples covering phase picking, PhaseNet training, dataset creation, and event-catalog workflows. See the SeisBench repository and official documentation for the current guides and examples.
Quick wins for a faster PC:
Scan for outdated or missing drivers - takes under a minuteDriver Scan →Clear out junk files and repair common Windows errorsFree Scan →Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →Which seismic tasks and data it supports
The model documentation lists phase picking, earthquake detection, denoising, and depth-phase identification. A common model interface supports loading pretrained weights, applying models to new data, and training on custom datasets. GPU and Apple MPS acceleration are documented, but support can vary by model and task; these capabilities are not a guarantee that every model runs on every backend.
#1 Best Overall
SeisBench distinguishes conventional seismic records—such as recordings from seismometers, strong-motion instruments, and geophones—from distributed acoustic sensing (DAS) data. For applying models, the documented interfaces can work directly with ObsPy streams for waveform data or xdas arrays for DAS. A user who only wants to apply models may not need the dataset-training and evaluation functionality.
How to get started
The project recommends installing the package with pip. DAS support is an optional extra. Dependency and extra names can change, so check the SeisBench package page and repository installation instructions for the current commands and requirements.
Rank #2
pip install seisbench
pip install "seisbench[das]"The second command installs the optional DAS support. The repository also describes installation from source. CPU-only PyTorch is an option for users who do not need CUDA acceleration; consult the package and repository instructions to choose the appropriate installation for your environment.
Recommended Free Tools
Choose the workflow that matches your goal
- Apply a pretrained model: Start with the model documentation and examples. Provide the appropriate waveform stream or DAS array, and select a model relevant to your task.
- Train or evaluate using datasets: Explore the dataset access and data-generation modules, then follow an example such as PhaseNet training. Training requires a dataset and suitable transforms; results depend on those inputs and the computing environment.
- Build a different workflow: Use the model and data interfaces as building blocks, checking the documentation for the specific model’s input format and supported features.
The 2022 paper describes pretrained weights and benchmark datasets being downloaded and cached when needed, and illustrates applying models to seismic streams and training PhaseNet with dataset transforms. These are example workflows, not guarantees about performance, hardware compatibility, or access for every user.
How to choose a model—and what the benchmark establishes
The study titled “Which picker fits my data?” compared six previously published deep-learning models across eight datasets spanning local to teleseismic distances. It evaluated three tasks: event detection, phase identification, and onset-time picking. In that study, the authors reported that EQTransformer, GPD, and PhaseNet performed best overall, with a small EQTransformer advantage for teleseismic data.
The same benchmark found mild performance degradation when models were transferred between regions, but failure to transfer between regional and teleseismic data in either direction. These are findings for the tested models, datasets, and task definitions—not a universal ranking of models available in SeisBench or a performance guarantee for a new dataset.
Rank #4
- Used Book in Good Condition
For a practical comparison, assess the model against the intended task and data rather than relying on a single overall ranking:
Windows Errors? Fix Them Before They Spread
Repair common Windows errors and clear accumulated junk for a smoother, more stable PC - no reinstall needed.Free scan · no reinstallCrashes, No Sound, or Screen Glitches?
Random freezes, missing sound and display glitches usually trace back to one bad driver. Find and replace yours safely.Free scan · under a minute- Task: Distinguish detection, phase identification, and onset-time picking; a model’s suitability for one does not establish suitability for another.
- Data domain: Check whether the target records are local, regional, or teleseismic and whether the model was trained on a comparable domain.
- Training-data match: Consider how closely the model’s training data resemble the region and recording conditions you will use.
- Held-out evaluation: Test against data kept separate from training and representative of the intended application. Do not assume cross-domain transfer will work.
How to cite SeisBench
The project asks users to cite its 2022 paper:
Woollam, J., Münchmeyer, J., Tilmann, F., Rietbrock, A., Lange, D., Bornstein, T., Diehl, T., Giuchi, C., Haslinger, F., Jozinović, D., Michelini, A., Saul, J., & Soto, H. (2022). “SeisBench – A Toolbox for Machine Learning in Seismology.” Seismological Research Letters. DOI: 10.1785/0220210324. The arXiv preprint is linked for readers without journal access.
Quick Recap
Best Value
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
