18 AI-Driven and Machine Learning Approaches in Geospatial Modeling for Hydrologic and Geologic Mapping

This session features GIS, remote sensing, and AI-driven/machine learning approaches to geologic and hydrologic mapping, emphasizing predictive modeling, cross-scale analysis, and innovative workflows that extend beyond traditional cartographic methods.

Tuesday, 10 March 2026
8:30 AM - 9:30 AM
RCC, 104

“A Cool- and Warm-Season Streamflow Reconstruction for Memphis, Tennessee”

Paper number: 18-3
Program: Technical Sessions
Time: 9:15 AM – 9:30 AM

Authors

Abstract

Gridded drought atlases developed from tree-ring proxy data have revealed large variations in soil moisture balance backward in time as far as two millennia. These gridded reconstructions have also been used to reconstruct past streamflow, but this has been limited to annual or water year only. The North American Seasonal Precipitation Atlas (NASPA) contains reconstructions of total precipitation for cool- (December-April) and warm-seasons (May-July). The objective is to use streamflow data from the U.S. Geological Survey Monthly and total precipitation from the NASAP to examine streamflow in the cool (December-April) and warm (May-July) seasons at Memphis, Tennessee. Separate reconstructions will be made using 1) principal component regression of statistically significant grid points (p<0.05) and 2) machine learning methods. Deep learning, random forest, and generalized linear model will be used, with limitations being the tendency for overfitting. This proposed research will show the NASPA and machine learning models’ capabilities regarding streamflow reconstruction, long term patterns of seasonal streamflow, and observable teleconnection impacts, and provide insight and discernable patterns of the climatic forces driving fluvial processes.

Geological Society of America Abstracts with Programs. Vol. 58, No. 1

doi: 10.1130/abs/2026SE-411690

© Copyright 2026 The Geological Society of America (GSA), all rights reserved. Permission is hereby granted to the author(s) of this abstract to reproduce and distribute it freely, for noncommercial purposes. Permission is hereby granted to any individual scientist to download a single copy of this electronic file and reproduce up to 20 paper copies for noncommercial purposes advancing science and education, including classroom use, providing all reproductions include the complete content shown here, including the author information. All other forms of reproduction and/or transmittal are prohibited without written permission from GSA Copyright Permissions.