AI inversion#
The AI inversion guide documents the complete learned-inversion lifecycle in pyCSAMT: scientific assumptions, training-data generation, architecture selection, training, inference, validation, uncertainty, PINN workflows, agent-assisted execution, and reporting.
AI inversion is a peer of Forward Modelling and Classical model integrations. Forward modeling generates responses from known earth models; classical inversion estimates models through numerical optimization; AI inversion learns an inverse mapping from representative examples. These approaches can support one another, but their assumptions and validation requirements remain distinct.
Validation is part of the model
A network prediction is not trustworthy merely because inference is fast or a training loss is small. Field use requires representative training data, strict data separation, out-of-distribution checks, physical diagnostics, uncertainty assessment, and comparison with independent evidence.
Build the workflow#
Understand surrogate inversion, supported dimensions, assumptions, limitations, and the relationship to forward and classical inversion.
Build synthetic and field datasets, define features and targets, normalize consistently, split safely, and preserve provenance.
Choose 1-D, profile-based 2-D, graph-based 3-D, or physics-informed approaches according to geometry, data volume, and scientific goals.
Configure optimization, monitor learning, resume safely, diagnose overfitting, and retain reproducible checkpoints and histories.
Apply a trained model to compatible observations, verify preprocessing, detect unsupported inputs, and export predictions with metadata.
Evaluate held-out synthetic tests, field responses, physical consistency, baselines, failure modes, and independent geological evidence.
Review and extend#
Quantify predictive spread, calibration, ensemble behavior, domain shift, and uncertainty sources not captured by the network.
Add physical residuals and constraints to learned 2-D inversion while keeping numerical assumptions and validation explicit.
Use pyCSAMT agents to configure and coordinate AI workflows without hiding the underlying science API or review requirements.
Package datasets, configurations, checkpoints, metrics, predictions, uncertainty, limitations, and approvals into an auditable model record.
Recommended reading order#
For a new AI inversion project:
Read AI inversion concepts and define why AI inversion is appropriate.
Prepare representative data with AI inversion data preparation.
Choose an architecture using AI model selection.
Follow Training AI inversion models and preserve every resolved setting.
Complete AI inversion validation before field inference.
Apply the model with AI inversion inference and evaluate AI inversion uncertainty.
Use AI inversion reporting before releasing predictions.
Use Physics-informed 2-D inversion when the workflow explicitly includes physics-informed constraints. Use AI inversion agents only after understanding the corresponding manual science workflow.