Explainable & Physics-Informed AI
Combining explainability and physical constraints in deep learning — from GeoPriorSubsNet v3 to lunar EM mapping — to build geohazard models that are accurate, interpretable, and physically consistent.
Data-Driven Learning
Multi-resolution attention fusion and encoder-decoder backbones that learn complex spatiotemporal patterns from InSAR, piezometric, and geological datasets.
Physics Heads
Dedicated physics head in GeoPriorSubsNet v3 recovers latent hydrogeological parameters — effective conductivity, porosity, elastic modulus — without extra supervision, enforcing physical plausibility at output time.
Uncertainty-Aware Evaluation
GeoPriorSubsNet's probabilistic outputs are audited with the k-diagram toolkit — ensuring that physical plausibility and statistical reliability go hand in hand across all quantile levels.
- Are physics-constrained forecasts better calibrated than data-only baselines?
- Do physics heads reduce physically implausible predictions?
- Where do data-physics trade-offs emerge in multi-city transfer?
GeoPriorSubsNet v3: A Case Study in Physics-Guided AI
GeoPriorSubsNet v3 unifies a probabilistic data head (quantile outputs for cumulative subsidence and hydraulic head) with a physics head that recovers effective hydrogeological closure fields — conductivity, porosity, and elastic modulus — as latent variables. Trained on multi-city InSAR and piezometric data, it outperforms purely data-driven baselines and transfers across cities with minimal retraining.
The physics head acts as an implicit regularizer — it forces the model to learn representations that remain physically meaningful even under distribution shift across cities.
Lunar Titanium Mapping — EM + PINNs Beyond Earth
Physics-informed neural networks extend beyond terrestrial geohazards. As part of an international expert panel (NASA / JAXA / CNSA collaboration, 2025), I applied Maxwell-equation-constrained PINNs to multi-spectral electromagnetic (MXS) data from lunar surface surveys to map titanium-rich basalt distributions — a setting where physical constraints substitute for the dense ground-truth labels that are impossible to collect on the Moon.
LuSEE — Lunar Surface Electromagnetics Experiment: the EM environment targeted by PINN-based titanium mapping
From Research to Practice
GeoPrior-3.0 Forecaster brings GeoPriorSubsNet to practitioners who don't write code — a desktop GUI that covers the full pipeline from data intake and physics-constraint configuration to training, transfer learning, and operational forecasting.
Related publications
- Machine learning-based techniques for land subsidence simulation in an urban areaLiu, J.; Liu, W.; Allechy, F. B.; Zheng, Z.; Liu, R.; Kouadio, K. L.* · Journal of Environmental Management · 2024
- Physics-Informed Deep Learning Reveals Divergent Urban Land Subsidence RegimesKouadio, K. L.; Liu, R.; Jiang, S.; Liu, J.; Kouamelan, S.; Liu, W.; Qing, Z.; Zheng, Z. · Under review — Nature Communications · 2026
- A Diagnostic Framework for Spatiotemporal Forecast UncertaintyKouadio, K. L.; Liu, R.; Loukou, K. G. H.; Liu, W.; Qing, Z.; Liu, Z. · Under review — Environmental Modelling & Software · 2025
- CAS: Cluster-Aware Scoring for Probabilistic ForecastsKouadio, K. L.; Liu, R. · Submitted — International Journal of Forecasting · 2025
- k-diagram: Rethinking Forecasting Uncertainty via Polar-Based VisualizationKouadio, K. L. · Journal of Open Source Software (JOSS) · 2025
- k-diagram: Technical Report — Derivations and DetailsKouadio, K. L. · Zenodo (Technical Report) · 2025
- XTFT: A Next-Generation Temporal Fusion Transformer for Uncertainty-Rich Time Series ForecastingKouadio, K. L.; Liu, Z.; Liu, R.; Bizimana, P. C.; Yang, G.; Liu, W. · Under review — IEEE TPAMI · 2025