Deep learning has shown great promise in hydrological modeling, especially when large sample data sets are used to capture generalizable patterns across basins. However, challenges remain in addressing data scarcity and ensuring model reliability, particularly when key hydrological observations are modeled as individual tasks. In this study, we shift from traditional single‐task learning (STL) to multi‐task learning (MTL) to leverage the interconnections among hydrological variables and potentially improve modeling outcomes in data‐limited settings. Using a Long Short‐Term Memory (LSTM) neural network with the Catchment Attributes and Meteorology for Large‐Sample Studies data set, we developed an MTL model to predict streamflow and evapotranspiration across 591 basins. The MTL model exhibited comparable predictions for streamflow and evapotranspiration to STL models, with similar spatiotemporal generalization across varying data sizes. MTL's strength appeared when using LSTM cell state probes to predict the non‐target variable, surface soil moisture (SSM), showing slightly higher correlation coefficients. This highlights MTL's ability to capture intrinsic hydrological rules, enhancing model reliability. Leveraging this ability, we further explored MTL's advantages under two data‐limited scenarios: one with less‐observed SSM data and another with no available streamflow data. In both cases, MTL, supported by another well‐observed variable, outperformed STL models by a notable difference. These findings highlight MTL's potential to address the challenges of hydrological modeling in data‐limited basins. As Earth observation data continues to grow, MTL could become a valuable approach for building more reliable and generalizable hydrological models.

Predicting river flow in places without streamflow records is challenging because basins respond differently to climate, terrain, vegetation, and soils. Traditional basin attributes describe some of these differences, but they cannot fully represent the complexity of natural environments. This study examines whether AlphaEarth Foundation embeddings, which are learned from large collections of satellite images rather than designed by experts, offer a more informative way to describe basin characteristics. These embeddings summarize patterns in vegetation, land surface properties, and long-term environmental dynamics. We find that models using them achieve higher accuracy when predicting flows in basins not used for training, suggesting that they capture key physical differences more effectively than traditional attributes. We further investigate how selecting appropriate donor basins influences prediction in ungauged regions. Similarity based on the embeddings helps identify basins with comparable environmental and hydrological behavior, improving performance, whereas adding many dissimilar basins can reduce accuracy. The results show that satellite-informed environmental representations can strengthen hydrological forecasting and support the development of models that adapt more easily to different landscapes.

Despite advances in hydrological Deep Learning (DL) models using Single Task Learning (STL), the intricate relationships among multiple hydrological components and model inputs might not be comprehensively encapsulated. This study employed a Long Short-Term Memory (LSTM) neural network and the CAMELS dataset to develop a Multi-Task Learning (MTL) model, predicting streamflow and evapotranspiration across multiple basins. An optimal multi-task loss weight ratio was determined manually during the validation phase for all 591 selected basins with streamflow data-gaps under 5%. During test period, MTL showed median Nash-Sutcliffe Efficiency predictions for streamflow and evapotranspiration at 0.69 and 0.92, consistent with two STL models. The MTL's strength appeared when predicting the non-target variable, surface soil moisture, using probes derived from LSTM cell states—representative of the internal DL model workings. This prediction showed a median correlation coefficient of 0.90, surpassing the 0.88 and 0.89 achieved by the streamflow and evapotranspiration STL models, respectively. This outcome suggests that MTL models could reveal additional rules aligned with hydrological processes through the inherent correlations among multiple hydrological variables, thereby enhancing their reliability. We termed this as "variable synergy," where MTL can simultaneously predict varied targets with comparable STL performance, augmented by its robust internal representation. Harnessing this, MTL promises enhanced predictions for high-cost observational variables and a comprehensive hydrological model.