Exploring the exceptional performance of a deep learning stream temperature model and the value of streamflow data

Rahmani, Farshid; Lawson, Kathryn; Ouyang, Wenyu; Appling, Alison P.; Oliver, Samantha

doi:10.1088/1748-9326/abd501

Cited by 68 publications

(79 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In agreement with the general trend in the field of hydrology, the abovementioned papers have covered most components of the hydrologic cycle. Outside of this Research Topic, machine learning has been applied to soil moisture (Fang et al, 2019), soil data extraction (Chaney et al, 2019), hydrology-influenced water quality variables including in-stream water temperature (Rahmani et al, 2020) and dissolved oxygen (Zhi et al, 2021), human water management through reservoirs (Yang et al, 2019;Ouyang et al, 2021), subsurface reactive transport (Laloy and Jacques, 2019;He et al, 2020), and vadose zone hydrology (Bandai and Ghezzehei, 2021), among others. ML is not only applicable in data-rich regions but can also be leveraged by data-scarce regions (Feng et al, 2021;Ma et al, 2021).…”

Section: Broadening the Use Of Machine Learning In Hydrologymentioning

confidence: 99%

Editorial: Broadening the Use of Machine Learning in Hydrology

Laloy

2021

Front. Water

Self Cite

View full text Add to dashboard Cite

Section: Broadening the Use Of Machine Learning In Hydrologymentioning

confidence: 99%

Editorial: Broadening the Use of Machine Learning in Hydrology

Laloy

2021

Front. Water

Self Cite

View full text Add to dashboard Cite

“…While purely data-driven deep learning techniques, partly led by authors of this whitepaper, have proven to be extremely powerful in hydrologic applications (Shen, 2018;Shen et al, 2018) , especially in modeling soil moisture (Fang et al, 2017(Fang et al, , 2019Fang & Shen, 2020) , streamflow (floods) , snow (Meyal et al, 2020) , and water quality indicators like water temperature (Rahmani et al, 2020) and dissolved oxygen (Zhi et al, 2020) , they are constrained by data availability and cannot make predictions in variables that are not directly observed at large scales, e.g., groundwater flow and evapotranspiration (there are global satellite-based estimates, but they are not direct and contain substantial modeled elements; there are also in-situ data at hundreds of sites, but they are far from covering the heterogeneity of the world). As mentioned earlier, how can we utilize multifaceted observations to inform parts of the water cycle that is not observed?…”

Section: Rationalementioning

confidence: 99%

Integrated parameter and process learning for hydrologic and biogeochemical modules in Earth System Models

Shen,

Hoffman,

2021

Self Cite

View full text Add to dashboard Cite

physics, and big data. Science challengesHow do we maximally leverage big-data observations to improve hydrobiogeochemical process description and parameterization so that such modules more realistically capture hydrologic and vegetation responses and feedbacks under the future climate? For example, how can we leverage physics, limited observations of vegetation and streamflow to better estimate evapotranspiration, and, relatedly, net primary productivity, especially for drought areas? Vegetation plays a critical role in regional and global water cycles; however, existing vegetation models have failed to predict vegetation response to droughts (McDowell & Xu, 2017) , arctic greening (Keenan & Riley, 2018) , and critical transitions between forest and savanna (Hirota et al., 2011) . These studies suggest that when we build process-based models (PBM) parameterized from regional and global plant traits, we tend to poorly describe plant adaptation and local-scale competition processes. The models and their associated parameters assigned for different regions in the world are not capturing essential heterogeneity in vegetation responses at finer spatial scales.

show abstract

“…Some studies have leveraged the relationship between hydrologic variables using data-driven models. Rahmani et al (2020) andVanVliet et al (2011) both found that including streamflow as an input for a ML model and statistical model (respectively) for temperature prediction improved model performance. Our contribution relative to these is that in multi-task learning streamflow is not used as a model input but as an output along with water temperature.…”

Section: Introductionmentioning

confidence: 99%

“…Our contribution relative to these is that in multi-task learning streamflow is not used as a model input but as an output along with water temperature. Furthermore, we examine the benefit of multi-task learning for improving streamflow where the Rahmani et al (2020) and Van Vliet et al (2011) focused on improvements in water temperature predictions. Kraft et al (2020) used a multi-task model to predict different parts of the water balance equation including evapotranspiration, snow water equivalent, and groundwater recharge but did not formally assess the benefits of the multi-task approach.…”

Section: Introductionmentioning

confidence: 99%

Multi-task deep learning of daily streamflow and water temperature

Sadler¹,

Appling²,

Read³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Deep learning models can accurately predict many hydrologic variables including streamflow and water temperature; however, these models have typically predicted hydrologic variables independently. This study explored the benefits of modeling two interdependent variables, daily average streamflow and daily average stream water temperature, together using multi-task deep learning. A multi-task scaling factor controlled the relative contribution of the auxiliary variable's error to the overall loss during training. Our experiments examined the improvement in prediction accuracy of the multi-task approach using paired streamflow and temperature data from sites across the conterminous United States. Our results showed that the best performing multi-task models performed better overall than the single-task models in terms of Nash-Sutcliffe efficiency. The improvement of the multi-task models relative to the single-task models had a seasonal trend with the multi-task models making larger improvements in the high-flow seasons. The multi-task scaling factor was consequential in determining to what extent the multi-task approach was beneficial, and a naïve selection of this factor led to worse-performing multi-task models for stream temperature. Our findings indicate that, when configured properly, a multitask approach could make more accurate predictions of interdependent hydrologic variables.

show abstract

Exploring the exceptional performance of a deep learning stream temperature model and the value of streamflow data

Cited by 68 publications

References 43 publications

Editorial: Broadening the Use of Machine Learning in Hydrology

Editorial: Broadening the Use of Machine Learning in Hydrology

Integrated parameter and process learning for hydrologic and biogeochemical modules in Earth System Models

Multi-task deep learning of daily streamflow and water temperature

Contact Info

Product

Resources

About