What question did this study set out to answer?

The study aims to improve streamflow predictions across Australia by utilizing LSTM models.

February 11, 2026Open Access

Better continental-scale streamflow predictions for Australia: LSTM as a land surface model post-processor and standalone hydrological model

ASAshkan ShokriCommonwealth Scientific and Industrial Research Organisation JBJames C. BennettCommonwealth Scientific and Industrial Research Organisation DRDavid RobertsonCommonwealth Scientific and Industrial Research Organisation

Key Points

The study aims to improve streamflow predictions across Australia by utilizing LSTM models.
Assessed two LSTM-based approaches: LSTM-C and LSTM-QC.
Utilized inputs like precipitation and potential evapotranspiration for LSTM-C.
Incorporated AWRA-L runoff outputs for LSTM-QC as a post-processor.
Tested in 218 catchments using three cross-validation techniques.
Evaluated predictive skill against AWRA-L and GR4J models.
Both LSTM approaches outperformed AWRA-L runoff in nearly all catchments.
LSTM-QC showed better performance than LSTM-C, especially with local data.
LSTM-C effectively generalized to ungauged conditions under various validations.
LSTM models corrected systematic biases in traditional models.

Abstract

Abstract. Accurate large-scale hydrological predictions are essential for water resource planning. However, many land surface models encounter difficulties in capturing streamflow timing and magnitudes, particularly in large catchments and when calibrated across broad regions and multiple hydrological variables. In this study, two Long Short-Term Memory (LSTM)-based approaches are assessed to enhance streamflow predictions across Australia: (i) LSTM-C, a standalone rainfall–runoff LSTM that relies solely on precipitation and potential evapotranspiration as inputs, and (ii) LSTM-QC, a rainfall–runoff LSTM that incorporates runoff outputs from the Australian Water Resources Assessment–Landscape model (AWRA-L), which can also be interpreted as a post-processor for AWRA-L. These approaches are tested in 218 minimally impacted catchments from the CAMELS-AUS dataset under three cross-validation strategies – temporally out-of-sample, spatially out-of-sample, and spatiotemporal out-of-sample – to evaluate their robustness for historical reconstructions, predictions in ungauged basins, and a proxy for climate-projection scenarios. The results indicate that both LSTM-QC and LSTM-C consistently outperform AWRA-L runoff across nearly all catchments and exceed the predictive skill of a widely used conceptual model (GR4J) in most basins. Under a temporally out-of-sample framework, LSTM-QC demonstrates a performance advantage over LSTM-C by leveraging information embedded in AWRA-L, particularly when fine-tuned to local catchment observed data. This advantage is primarily attributed to the LSTM's ability to correct systematic biases in AWRA-L and enhance channel-routing signals. However, under spatial and spatiotemporal cross-validation LSTM-C performs comparably well, suggesting that a purely data-driven approach can generalize effectively to ungauged or future conditions without reliance on AWRA-L.

Ask AI

Helpful

Bookmark

View Full Paper