Learning landscape features from streamflow with autoencoders

Recent successes with machine learning (ML) models in catchment hydrology have highlighted their ability to extract crucial information from catchment properties pertinent to the rainfall-runoff relationship. In this study, we aim to identify a minimal set of catchment signatures in streamflow that, when combined with meteorological drivers, enable an accurate reconstruction of the entire streamflow time series. To achieve this, we utilize an explicit noise-conditional autoencoder (ENCA), which, assuming an optimal architecture, separates the influences of meteorological drivers and catchment properties on streamflow. The ENCA architecture feeds meteorological forcing and climate attributes into the decoder in order to incentivize the encoder to only learn features that are related to landscape properties minimally related to climate. By isolating the effect of meteorology, these hydrological features can thus be interpreted as landscape fingerprints. The optimal number of features is found by means of an intrinsic dimension estimator. We train our model on the hydro-meteorological time series data of 568 catchments of the continental United States from the Catchment Attributes and Meteorology for Large-sample Studies (CAMELS) dataset. We compare the reconstruction accuracy with models that take as input a subset of static catchment attributes (both climate and landscape attributes) along with meteorological forcing variables. Our results suggest that available landscape attributes can be summarized by only two relevant learnt features (or signatures), while at least a third one is needed for about a dozen difficult-to-predict catchments in the central United States, which is mainly characterized by a high aridity index. The principal components of the learnt features strongly correlate with the baseflow index and aridity indicators, which is consistent with the idea that these indicators capture the variability of catchment hydrological responses. The correlation analysis further indicates that soil-related and vegetation attributes are of importance.