Image of 3D hydrostratigraphic and hydraulic conductivity modelling using supervised machine learning

Text

3D hydrostratigraphic and hydraulic conductivity modelling using supervised machine learning

Accurately modeling highly heterogenous aquifers is one of the big challenges in hydrogeology. There is a pressing need to develop new methods that transform high-resolution data into hydrogeological parameters representative of such aquifers. We use random forest-based machine learning to predict the distribution of hydrostratigraphic units and hydraulic conductivity (K) at a regional scale. We used lithologic logs from >2000 boreholes and resistivity-depth models from 2717 km of Airborne Electromagnetics (AEM). Eighty unique lithologic categories are lumped into 5 hydrostratigraphic units. K data is derived from descriptions of grain size and texture. The input data are resampled into a 200 × 200 × 1m grid and split into 70% training and 30% validation. K prediction had a training F1 score of 95% and 87% testing accuracy. After hyperparameter tuning these scores improved to 99.6% and 92%, respectively. Hydrostratigraphic unit prediction showed a training F1 score of 97% and 91% testing accuracy, improving to 100% and 95% after hyperparameter tuning. This method produces a high-resolution 3D model of K and hydrostratigraphic units that fills gaps between widely spaced boreholes. It is applicable in any setting where boreholes and AEM are available and can be used to build robust groundwater models for heterogeneous aquifers.

Availability
152551.136Perpustakaan BIG (Eksternal Harddisk)Available
Detail Information
Series Title
Applied Computing and Geoscience - Open Access
Call Number
551.136
Publisher
Amsterdam : Elsevier.,
Collation
16 hlm PDF, 19.213 KB
Language
Inggris
ISBN/ISSN
2590-1974
Classification
551.136
Content Type
text
Media Type
-
Carrier Type
-
Edition
Vol.19, September 2023
Subject(s)
Machine Learning
3D hydrostratigraphy
Hydraulic conductivity modeling
Airborne electromagnetics
Specific Detail Info
-
Statement of Responsibility
Other version/related

No other version available

File Attachment
  • 3D hydrostratigraphic and hydraulic conductivity modelling using supervised machine learning
    Accurately modeling highly heterogenous aquifers is one of the big challenges in hydrogeology. There is a pressing need to develop new methods that transform high-resolution data into hydrogeological parameters representative of such aquifers. We use random forest-based machine learning to predict the distribution of hydrostratigraphic units and hydraulic conductivity (K) at a regional scale. We used lithologic logs from >2000 boreholes and resistivity-depth models from 2717 km of Airborne Electromagnetics (AEM). Eighty unique lithologic categories are lumped into 5 hydrostratigraphic units. K data is derived from descriptions of grain size and texture. The input data are resampled into a 200 × 200 × 1m grid and split into 70% training and 30% validation. K prediction had a training F1 score of 95% and 87% testing accuracy. After hyperparameter tuning these scores improved to 99.6% and 92%, respectively. Hydrostratigraphic unit prediction showed a training F1 score of 97% and 91% testing accuracy, improving to 100% and 95% after hyperparameter tuning. This method produces a high-resolution 3D model of K and hydrostratigraphic units that fills gaps between widely spaced boreholes. It is applicable in any setting where boreholes and AEM are available and can be used to build robust groundwater models for heterogeneous aquifers.
Comments
You must be logged in to post a comment