Integration of Multisource Data to Estimate Downward Longwave Radiation Based on Deep Neural Networks

Zhu, Fuxin; Li, Xiaoqiong; Qin, Jun; Yang, Kun; Cuo, Lan; Tang, Wenjun

doi:10.1109/tgrs.2021.3094321

Cited by 6 publications

(4 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural networks (NNs) like long short‐term memory (LSTM), GraphWaveNet (Sun et al., 2021), or convolutional networks (Duan et al., 2020) have demonstrated their prowess in learning hydrologic dynamics from big data. They are applicable not only to streamflow hydrology but also to variables across the entire hydrologic cycle (Shen, Chen, & Laloy, 2021; Shen & Lawson, 2021) such as soil moisture (Fang et al., 2017, 2019; J. Liu et al., 2022, 2023; O & Orth, 2021), groundwater (Wunsch et al., 2022), snow (Meyal et al., 2020), longwave radiation (Zhu et al., 2021), and water quality parameters like water temperature, dissolved oxygen, and nitrogen (He et al., 2022; Hrnjica et al., 2021; Lin et al., 2022; Rahmani, Lawson, et al., 2021; Saha et al., 2023; Zhi et al., 2021). However, these approaches are mostly suitable for relatively homogeneous headwater basins; spatial heterogeneities in forcings and basin characteristics are generally not well represented in these approaches.…”

Section: Introductionmentioning

confidence: 99%

Improving River Routing Using a Differentiable Muskingum‐Cunge Model and Physics‐Informed Machine Learning

Bindas,

Tsai,

Liu

et al. 2024

Water Resources Research

Self Cite

View full text Add to dashboard Cite

Recently, rainfall‐runoff simulations in small headwater basins have been improved by methodological advances such as deep neural networks (NNs) and hybrid physics‐NN models—particularly, a genre called differentiable modeling that intermingles NNs with physics to learn relationships between variables. However, hydrologic routing simulations, necessary for simulating floods in stem rivers downstream of large heterogeneous basins, had not yet benefited from these advances and it was unclear if the routing process could be improved via coupled NNs. We present a novel differentiable routing method (δMC‐Juniata‐hydroDL2) that mimics the classical Muskingum‐Cunge routing model over a river network but embeds an NN to infer parameterizations for Manning's roughness (n) and channel geometries from raw reach‐scale attributes like catchment areas and sinuosity. The NN was trained solely on downstream hydrographs. Synthetic experiments show that while the channel geometry parameter was unidentifiable, n can be identified with moderate precision. With real‐world data, the trained differentiable routing model produced more accurate long‐term routing results for both the training gage and untrained inner gages for larger subbasins (>2,000 km2) than either a machine learning model assuming homogeneity, or simply using the sum of runoff from subbasins. The n parameterization trained on short periods gave high performance in other periods, despite significant errors in runoff inputs. The learned n pattern was consistent with literature expectations, demonstrating the framework's potential for knowledge discovery, but the absolute values can vary depending on training periods. The trained n parameterization can be coupled with traditional models to improve national‐scale hydrologic flood simulations.

show abstract

Section: Introductionmentioning

confidence: 99%

Improving River Routing Using a Differentiable Muskingum‐Cunge Model and Physics‐Informed Machine Learning

Bindas,

Tsai,

Liu

et al. 2024

Water Resources Research

Self Cite

View full text Add to dashboard Cite

show abstract

“…Since 2017, it has been demonstrated that deep learning (DL) networks (Shen, 2018; Shen et al., 2018), like long short‐term memory (LSTM; Hochreiter & Schmidhuber, 1997), can learn to predict environmental variables including stream temperature with exceptionally high accuracy (Rahmani, Lawson, et al., 2021; Rahmani, Shen, et al., 2021; Rehana & Rajesh, 2023; Sadler et al., 2022; Weierbach et al., 2022; S. Zhu & Piotrowski, 2020; Zwart et al., 2023). LSTM has shown its strength and versatility in simulating hydrologic variables such as soil moisture (Fang et al., 2017, 2019; J. Liu et al., 2022; O & Orth, 2021), streamflow (Feng et al., 2020, 2021; Khoshkalam et al., 2023; Xiang et al., 2020), dissolved oxygen (Heddam et al., 2022; Zhi et al., 2023), snow water equivalent (Broxton et al., 2019; Meyal et al., 2020), stream nitrate concentration (Saha et al., 2023; Samarinas et al., 2020), and radiation (Y. Liu et al., 2020; F. Zhu et al., 2021). However, mostly used as a forward simulator in hydrology, LSTM is also limited by its black‐box nature: it does not provide an interpretable explanation of internal processes, and its intermediate variables lack physical meaning and thus cannot be compared against observations to diagnose the model's internal logic (Appling et al., 2022).…”

Section: Introductionmentioning

confidence: 99%

“…LSTM has shown its strength and versatility in simulating hydrologic variables such as soil moisture (Fang et al, , 2019O & Orth, 2021), streamflow (Feng et al, 2020(Feng et al, , 2021Khoshkalam et al, 2023;Xiang et al, 2020), dissolved oxygen (Heddam et al, 2022;Zhi et al, 2023), snow water equivalent (Broxton et al, 2019;Meyal et al, 2020), stream nitrate concentration (Saha et al, 2023;Samarinas et al, 2020), and radiation (Y. Liu et al, 2020;F. Zhu et al, 2021).…”

mentioning

confidence: 99%

Identifying Structural Priors in a Hybrid Differentiable Model for Stream Water Temperature Modeling

Rahmani,

Appling,

Feng

et al. 2023

Water Resources Research

Self Cite

View full text Add to dashboard Cite

Although deep learning models for stream temperature (Ts) have recently shown exceptional accuracy, they have limited interpretability and cannot output untrained variables. With hybrid differentiable models, neural networks (NNs) can be connected to physically based equations (called structural priors) to output intermediate variables such as water source fractions (specifying what portion of water is groundwater, subsurface, and surface flow). However, it is unclear if such outputs are physically meaningful when only limited physics is imposed, and if structural priors have enough impacts to be identifiable from data. Here, we tested four alternative structural priors describing basin‐scale water temperature memory and instream heat processes in a differentiable stream temperature model where NNs freely estimate the water source fractions. We evaluated models’ abilities to predict Ts and baseflow ratio. The four priors exhibited noticeably different behaviors in these two metrics and their tradeoffs, with some dominating others. Therefore, the better structural priors can be identified. Moreover, testing different priors yielded valuable insights: having a separate shallow subsurface flow component better matches observations, and a recency‐weighted averaging of past air temperature for calculating source water temperature resulted in better Ts and baseflow prediction than traditionally employed simple averaging. However, we also highlight the limitations when insufficient physical constraints are implemented: the internal variables (water source fractions) may not be adequately constrained by a single target variable (stream temperature) alone. To ensure the physical significance of the internal fluxes, one can either employ multivariate data for model selection, or include more physical processes in the priors.

show abstract

“…They are applicable not only to streamflow hydrology but also variables across the entire hydrologic cycle such as soil moisture (Fang et al, 2017(Fang et al, , 2019J. Liu et al, 2022;O & Orth, 2021), groundwater (Wunsch et al, 2022), snow (Meyal et al, 2020), longwave radiation (Zhu et al, 2021), and water quality parameters (He et al, 2022;Hrnjica et al, 2021;Lin et al, 2022;Zhi et al, 2021). However, these approaches are mostly suitable for relatively homogeneous headwater basins; spatial heterogeneities in forcings and basin characteristics are generally not captured well, and large basins often turn out to have poorer performance for LSTM models.…”

Section: Introductionmentioning

confidence: 99%

Improving large-basin streamflow simulation using a modular, differentiable, learnable graph model for routing

Bindas

Tsai

Liu

et al. 2022

Preprint

View full text Add to dashboard Cite

Recently, runoff simulations in small, headwater basins have been improved by methodological advances such as deep learning (DL). Hydrologic routing modules are typically needed to simulate flows in stem rivers downstream of large, heterogeneous basins, but obtaining suitable parameterization for them has previously been difficult. It is unclear if downstream daily discharge contains enough information to constrain spatially-distributed parameterization. Building on recent advances in differentiable modeling principles, here we propose a differentiable, learnable physics-based routing model. It mimics the classical Muskingum-Cunge routing model but embeds a neural network (NN) to provide parameterizations for Manning's roughness coefficient (n) and channel geometries. The embedded NN, which uses (imperfect) DL-simulated runoffs as the forcing data and reach-scale attributes as inputs, was trained solely on downstream hydrographs. Our synthetic experiments show that while channel geometries cannot be identified, we can learn a parameterization scheme for n that captures the overall spatial pattern. Training on short real-world data showed that we could obtain highly accurate routing results for both the training and inner, untrained gages. For larger basins, our results are better than a DL model assuming homogeneity or the sum of runoff from subbasins. The parameterization learned from a short training period gave high performance in other periods, despite significant bias in runoff. This is the first time an interpretable, physics-based model is learned on the river network to infer spatially-distributed parameters. The trained n parameterization can be coupled to traditional runoff models and ported to traditional programming environments.

show abstract

Integration of Multisource Data to Estimate Downward Longwave Radiation Based on Deep Neural Networks

Cited by 6 publications

References 61 publications

Improving River Routing Using a Differentiable Muskingum‐Cunge Model and Physics‐Informed Machine Learning

Improving River Routing Using a Differentiable Muskingum‐Cunge Model and Physics‐Informed Machine Learning

Identifying Structural Priors in a Hybrid Differentiable Model for Stream Water Temperature Modeling

Improving large-basin streamflow simulation using a modular, differentiable, learnable graph model for routing

Contact Info

Product

Resources

About