Research software
Open-source libraries and product-grade applications for AI-assisted geoscience, forecasting, and environmental decision support.
- Packages
- 0
- Open source
- 0
- On PyPI
- 0
- Documented
- 0
Flagship product
A desktop application that turns physics-guided forecasting into a guided, visible workflow.
GeoPrior-3.0 Forecaster
A guided desktop environment for operationalizing GeoPrior-v3 from data intake to reproducible geohazard forecasting.
- 19
- interface screens
- 4
- core workflow stages
- 1
- desktop layer over GeoPrior-v3
Featured packages
The open-source libraries at the core of my research, documented and on PyPI.
pyCSAMT
Python toolbox for AMT/CSAMT: end-to-end processing, SEG-EDI/Zonge compatibility, and 2D/3D geophysical inversion workflows.
AMTCSAMTelectromagneticsgroundwater
k-diagram
Polar diagnostics toolkit for forecast uncertainty, coverage, calibration, and severity.
uncertaintyevaluationvisualization
GeoPrior-v3
Scientific Python framework for physics-guided geohazard analysis, forecasting, and risk-oriented interpretation.
geohazardsland-subsidencephysics-guided-airisk-analytics
More tools
Earlier and specialised packages for groundwater, geo-electrical data and machine learning.
Toolkit for adaptive Hammerstein-Wiener system modeling (nonlinear + linear blocks) with a scikit-learn-friendly API for regression/classification/TS.
DocsPyPIBSD-3-ClauseAll-in-one ML utilities designed to streamline data science workflows—fast helpers for preprocessing, modeling, and evaluation.
Docs in progressBSD-3-ClausePython library for groundwater exploration: integrates DC resistivity (ERP/VES), EM, geology, and ML for siting wells, predicting yields, and restoring noisy EM signals.
DocsPyPIBSD-3-ClauseMachine-learning workflows for hydrogeology, from K estimation to drilling support and well productivity analysis.
Docs in progressApache-2.0ML pipeline to predict groundwater flow rate from geology and DC resistivity (ERP/VES); automates optimal drilling-site selection and reduces dry-well risk.
DocsMIT
