Laurent Kouadio

Sustainable Groundwater Exploration

AI-assisted hydrogeophysics for siting productive wells and estimating aquifer properties.

>90%
Prediction Accuracy
Achieved with ensemble models
30%
Sensitivity Increase
In leak detection with MADF
87%
Initial SVM Accuracy
Predicting successful wells
2+
Open-Source Tools
Supporting the community

Smart Wells, Secure Water

My research transforms the uncertain quest for groundwater into a science of prediction. By developing novel geo-electrical features and harnessing machine learning, we can significantly reduce the guesswork and risk, ensuring every well counts for the communities that need water most.

Methodology Progression:

SVM
Ensemble Learning
Mixture Learning (MXS)
Geophysical survey in an arid landscape

Environmental Geophysics

Beyond discovery, my work focuses on protecting our precious groundwater resources. I develop integrated methods to detect, map, and monitor subsurface pollution from industrial and mining activities, providing actionable data to safeguard water for future generations.

The Multifaceted Anomaly Detection Framework (MADF) improved leak detection sensitivity by 30% and reduced false positives by 25% at a test site in China.
Water quality testing in a lab

Key Outcomes

  • Reduce dry wells with predictive models from geo-electrical features.
  • Improve decision trust via robust ensemble learning and smart data imputation (MXS).
  • Operationalize workflows with open-source tools like pyCSAMT and watex.
  • Safeguard water quality by localizing leaks with integrated ML and geophysical surveys.

Key Outputs & Tooling

Groundwater flow rate via SVM (WRR)
Ensemble learning for flow rate (WRM)
Mixture learning for aquifer K (C&G)
pyCSAMT toolbox (J. Appl. Geophys.)
CSAMT reservoir mapping (Geophys. Prospect.)
Landfill leachate anomaly detection (JEM)
watex: ML for water exploration (SoftwareX)
pyCSAMT docs
watex docs

Related publications

  • A mixture learning strategy for predicting aquifer permeability coefficient K
    Kouadio, K. L.; Liu, J.; Liu, W.; Liu, R. · Computers & Geosciences · 2025
  • A novel approach for water reservoir mapping using controlled-source audio-frequency magnetotelluric in Xingning area, Hunan Province, China
    Kouadio, K. L.; Liu, R.; Malory, A. O.; Liu, W.; Liu, C. · Geophysical Prospecting · 2023
  • Ensemble Learning Paradigms for Flow-Rate Prediction Boosting
    Kouadio, K. L.; Liu, J.; Kouamelan, S. K.; Liu, R. · Water Resources Management · 2023
  • watex: machine learning research in water exploration
    Kouadio, K. L.; Liu, J.; Liu, R. · SoftwareX · 2023
  • Groundwater Flow-Rate Prediction from Geo-Electrical Features using Support Vector Machines
    Kouadio, K. L.; Loukou, N. K.; Coulibaly, D.; Mi, B.; Kouamelan, S. K.; Gnoleba, S. P. D.; Zhang, H.; Xia, J. · Water Resources Research · 2022
  • pyCSAMT: An alternative Python toolbox for groundwater exploration using controlled-source audio-frequency magnetotelluric
    Kouadio, K. L.; Liu, R.; Mi, B.; Liu, C. · Journal of Applied Geophysics · 2022
View all →