Deep Learning for Isotope Hydrology: The Application of Long Short-Term Memory to Estimate High Temporal Resolution of the Stable Isotope Concentrations in Stream and Groundwater

Abstract

Recent advances in laser spectroscopy has made it feasible to measure stable isotopes of water in high temporal resolution (i.e., sub-daily). High-resolution data allow the identification of fine-scale, short-term transport and mixing processes that are not detectable at coarser resolutions. Despite such advantages, operational routine and long-term sampling of stream and groundwater sources in high temporal resolution is still far from being common. Methods that can be used to interpolate infrequently measured data at multiple sampling sites would be an important step forward. This study investigates the application of a Long Short-Term Memory (LSTM) deep learning model to predict complex and non-linear high-resolution (3 h) isotope concentrations of multiple stream and groundwater sources under different landuse and hillslope positions in the Schwingbach Environmental Observatory (SEO), Germany. The main objective of this study is to explore the prediction performance of an LSTM that is trained on multiple sites, with a set of explanatory data that are more straightforward and less expensive to measure compared to the stable isotopes of water. The explanatory data consist of meteorological data, catchment wetness conditions, and natural tracers (i.e., water temperature, pH and electrical conductivity). We analyse the model's sensitivity to different input data and sequence lengths. To ensure an efficient model performance, a Bayesian optimization approach is employed to optimize the hyperparameters of the LSTM. Our main finding is that the LSTM allows for predicting stable isotopes of stream and groundwater by using only short-term sequence (6 h) of measured water temperature, pH and electrical conductivity. The best performing LSTM achieved, on average of all sampling sites, an RMSE of 0.7‰, MAE of 0.4‰, R2 of 0.9 and NSE of 0.7. The LSTM can be utilized to predict and interpolate the continuous isotope concentration time series either for data gap filling or in case where no continuous data acquisition is feasible. This is very valuable in practice because measurements of these tracers are still much cheaper than stable isotopes of water and can be continuously conducted with relatively minor maintenance.

Number of Chamber Measurement Locations for Accurate Quantification of Landscape‐Scale Greenhouse Gas Fluxes: Importance of Land Use, Seasonality, and Greenhouse Gas Type

“…Bedrock geology consists mainly of argillaceous shale, greywacke, and loess (Orlowski et al., 2016). The climate is temperate oceanic (Cfb, Köppen climate classification) with mean annual precipitation and temperature of 623 mm and 9.6°C, respectively, for the period 1969–2019 (Sahraei et al., 2021). Crops are mainly barley, wheat, and rapeseed (Houska et al., 2017).…”

Nitrate isotopes in catchment hydrology: Insights, ideas and implications for models

“…Cemek et al (2022) used different AI techniques to predict the isotopic composition (δ 18 O and δ 2 H) in groundwater, whereas, more recently, Erdélyi et al (2023) combined conventional regression techniques with Random Forest to predict the water stable isotope composition of precipitation in areas with large spatial data variability. Sahraei et al (2021) used AI techniques and physical and hydrological variables (e.g., meteorological data, catchment wetness, water temperature, pH) to predict water stable isotopes in streams and groundwater. In relation to nitrate isotopes, Yang et al (2021) developed an AI model to predict the δ 15 N-NO 3 − values in surface waters by using conventional hydrochemical variables, that could enhance the interpretation of δ 15 N-NO 3 − data and potentially improve water quality management.…”

Identifying landscape hot and cold spots of soil GHG fluxes by combining field measurements and remote sensing data

“…The landscape has an average slope of 5% with an elevation range of 233 -415 m a.s.l. The region has a temperate oceanic climate (Cfb, Köppen climate classification) with annual average precipitation and temperature of 623 mm and 9.6°C based on long-term data (1969 -2019) (Sahraei et al, 2021).…”