Predicting Playa Inundation Using a Long Short‐Term Memory Neural Network

Abstract

AbstractIn the Great Plains, playas are critical wetland habitats for migratory birds and a source of recharge for the agriculturally important High Plains aquifer. The temporary wetlands exhibit complex hydrology, filling rapidly via local rain storms and then drying through evaporation and groundwater infiltration. Using a long short‐term memory (LSTM) neural network to account for these complex processes, we modeled the probability of playa inundation for 71,842 playas in the Great Plains from 1984 to 2018. At the level of individual playas, the model achieved an F1‐score of 0.522 on a withheld test set, displaying the ability to predict complex inundation patterns. When simulating playa inundation over the entire region, the model is able to very closely track inundation trends, even during periods of drought. Our results demonstrate potential for using LSTMs to model complex hydrological dynamics. Our modeling approach could be used to model playa inundation into the future under different climate scenarios to better understand how wetland habitats and groundwater will be impacted by changing climate.