Compute per-well statistics and quality metrics from LAS logs across multi-well projects.
npx skills add https://github.com/SteadfastAsArt/geoscience-skills --skill welly
Please help me install this Agent Skill. Skill: welly Source: https://github.com/SteadfastAsArt/geoscience-skills/tree/main/welly Command: npx skills add https://github.com/SteadfastAsArt/geoscience-skills --skill welly
Streamlines loading, processing, and cross-well QC of LAS-based well data across projects, reducing manual data wrangling and enabling batch analysis.
Load a LAS file into welly and generate a per-well QC report.
High-intent search queries and answers about installing and using this skill.
Cross-well QC on multiple LAS files is performed by loading wells with metadata, computing per-well statistics, and generating depth coverage analyses. This enables batch comparison and consistent reporting across the entire dataset.
Calculating curve statistics for batch well logs involves reading LAS data, applying despike and smooth operations, and resampling curves. This process ensures consistent cross-well comparisons and accurate project-level summaries.
Yes, welly supports normalizing and resampling well log curves. The toolkit applies despike, smooth, and normalize operations during processing to ensure consistent cross-well comparisons and accurate project statistics.
Processed well logs export to DataFrame, CSV, and LAS formats. This enables integration with downstream analytics pipelines and facilitates the reporting of cross-well quality control and formation top management.
Yes, welly supports managing formation tops alongside LAS data. Users can load LAS files with metadata, process curves, manage tops, and export results to common formats for comprehensive QC and reporting.
Using pandas for petrophysical QC requires welly workflows to handle curve reading, data cleaning, and resampling. Limitations depend on LAS file structure consistency and metadata availability for accurate cross-well analysis.
SteadfastAsArtLoad LAS or DLIS well logs and perform end-to-end formation evaluation.
SteadfastAsArtParse and normalize LAS well-log files into DataFrames or CSV.
hung-phanPerform vectorized numerical computations on large arrays with NumPy.
SteadfastAsArtCompute elastic moduli and impedances from well logs for AVO analysis.
