Comparison of the use of a physical-based model with data assimilation and machine learning methods for simulating soil water dynamics

Li, Peijun; Shi, Liangsheng; Tso, Chak-Hau Michael; Zhang, Yonggen; Zeng, Wenzhi

doi:10.1016/j.jhydrol.2020.124692

Cited by 45 publications

(29 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The complexity of an ML model is related to the model structure and model parameters (e.g., hidden layers and weighting factors in ANN algorithm, or considering leaves and nodes in RT) used to capture the patterns in target values. Increasing the number of model parameters increases the complexity and improves the ability of the model to find the relation between features and target values [49][50][51].…”

Section: Machine Learning (Ml) Methodsmentioning

confidence: 99%

“…Complexity improves accuracy in both the training and prediction steps, although in some cases, complex nonlinear models have been observed to decrease the accuracy in the prediction step [51]. In the prediction step, the relation between features and the target values is evaluated by applying the trained model (using a training dataset) to a prediction dataset.…”

Section: Machine Learning (Ml) Methodsmentioning

confidence: 99%

“…Another factor contributing to the overfitting problem could have been the limited number of datapoints. Having a larger number of datapoints may have reduced the overfitting problem and may have led to better performance in both the training and prediction steps [51].…”

Section: Single Bagging and Boosting Modelsmentioning

confidence: 99%

See 2 more Smart Citations

Supervised Machine Learning for Estimation of Total Suspended Solids in Urban Watersheds

Moeini

Shojaeizadeh

Geza

2021

Water

View full text Add to dashboard Cite

Machine Learning (ML) algorithms provide an alternative for the prediction of pollutant concentration. We compared eight ML algorithms (Linear Regression (LR), uniform weighting k-Nearest Neighbor (UW-kNN), variable weighting k-Nearest Neighbor (VW-kNN), Support Vector Regression (SVR), Artificial Neural Network (ANN), Regression Tree (RT), Random Forest (RF), and Adaptive Boosting (AdB)) to evaluate the feasibility of ML approaches for estimation of Total Suspended Solids (TSS) using the national stormwater quality database. Six factors were used as features to train the algorithms with TSS concentration as the target parameter: Drainage area, land use, percent of imperviousness, rainfall depth, runoff volume, and antecedent dry days. Comparisons among the ML methods demonstrated a higher degree of variability in model performance, with the coefficient of determination (R2) and Nash–Sutcliffe (NSE) values ranging from 0.15 to 0.77. The Root Mean Square (RMSE) values ranged from 110 mg/L to 220 mg/L. The best fit was obtained using the AdB and RF models, with R2 values of 0.77 and 0.74 in the training step and 0.67 and 0.64 in the prediction step. The NSE values were 0.76 and 0.72 in the training step and 0.67 and 0.62 in the prediction step. The predictions from AdB were sensitive to all six factors. However, the sensitivity level was variable.

show abstract

Section: Machine Learning (Ml) Methodsmentioning

confidence: 99%

Section: Machine Learning (Ml) Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Supervised Machine Learning for Estimation of Total Suspended Solids in Urban Watersheds

Moeini

Shojaeizadeh

Geza

2021

Water

View full text Add to dashboard Cite

show abstract

“…Parameter estimation for groundwater system modeling is a key and important challenge due to our incomplete knowledge of the spatial distributions of hydrogeological attributes, such as hydraulic conductivity. The ensemble Kalman filter (EnKF; Evensen, 1994) is a powerful approach to parameter estimation in subsurface flow (Hendricks Franssen and Kinzelbach, 2008;Zheng et al, 2019) and solute transport (Liu et al, 2008;Li et al, 2012;Chen et al, 2018;Xu and Gomez-Hernandez, 2018) scenarios. Estimated system parameters can include conductivity (Botto et al, 2018), permeability (Zovi et al, 2017), porosity (Li et al, 2012), specific storage (Hendricks Franssen et al, 2011), dispersivity (Liu et al, 2008), riverbed conductivity (Kurtz et al, 2014), or unsaturated flow characteristic quantities (Zha et al, 2019;Li et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

“…Mo et al (2019) use a deeplearning-based model as a surrogate of a solute transport model to reduce the CPU time associated with ensemblebased data assimilation through an iterative local update ensemble smoother in a contaminant identification problem considering a synthetic two-dimensional heterogeneous conductivity field. Li et al (2020) compare benefits and drawbacks of embedding machine-learning-based (artificial neural network, ANN) and physics-based models into an IES for a set of synthetic unsaturated flow scenarios and find that (a) the performance of an IES relying on the Richards' equation is significantly impacted by soil heterogeneity, initial, and boundary conditions, and (b) an IES based on either ANN or Richards' equation can be notably affected by the quality of the measurements.…”

Section: Introductionmentioning

confidence: 99%

Data assimilation with multiple types of observation boreholes via the ensemble Kalman filter embedded within stochastic moment equations

Xia

Luo

et al. 2021

Hydrol. Earth Syst. Sci.

View full text Add to dashboard Cite

Abstract. We employ an approach based on the ensemble Kalman filter coupled with stochastic moment equations (MEs-EnKF) of groundwater flow to explore the dependence of conductivity estimates on the type of available information about hydraulic heads in a three-dimensional randomly heterogeneous field where convergent flow driven by a pumping well takes place. To this end, we consider three types of observation devices corresponding to (i) multi-node monitoring wells equipped with packers (Type A) and (ii) partially (Type B) and (iii) fully (Type C) screened wells. We ground our analysis on a variety of synthetic test cases associated with various configurations of these observation wells. Moment equations are approximated at second order (in terms of the standard deviation of the natural logarithm, Y, of conductivity) and are solved by an efficient transient numerical scheme proposed in this study. The use of an inflation factor imposed to the observation error covariance matrix is also analyzed to assess the extent at which this can strengthen the ability of the MEs-EnKF to yield appropriate conductivity estimates in the presence of a simplified modeling strategy where flux exchanges between monitoring wells and aquifer are neglected. Our results show that (i) the configuration associated with Type A monitoring wells leads to conductivity estimates with the (overall) best quality, (ii) conductivity estimates anchored on information from Type B and C wells are of similar quality, (iii) inflation of the measurement-error covariance matrix can improve conductivity estimates when a simplified flow model is adopted, and (iv) when compared with the standard Monte Carlo-based EnKF method, the MEs-EnKF can efficiently and accurately estimate conductivity and head fields.

show abstract

How to enhance hydrological predictions in hydrologically distinct watersheds of the Indian subcontinent?

Mangukiya

Sharma

2023

Hydrological Processes

View full text Add to dashboard Cite

Accurate hydrological predictions are required to prepare for the impacts of climate change, especially in India, which experiences frequent floods and droughts. However, the complex hydrological processes of its distinct watersheds and limited data make it challenging to deliver highly‐performant hydrologic predictions using conventional models. Moreover, it remains uncertain where the limits of predictability are and whether recently‐popular deep learning approaches can offer significant improvements. Here, we tested the first instance of the hydrologic model based on long short‐term memory (LSTM) for 55 Indian watersheds, using a new dataset comprising forcing, attributes, and discharge data. Our results show that the LSTM model provides much‐improved performance compared to conventional models in India, providing a median Nash‐Sutcliffe efficiency (NSE) of 0.56. The LSTM model trained on all the watersheds is more favourable to those trained on individual or homogeneous watersheds, as it benefits from a broader range of hydrological processes and patterns in the input data. However, the LSTM model performs poorly for non‐perennial, large, and semi‐arid climate zone watersheds due to its inability to simulate the complex hydrological processes specific to these environments. Integrating lagged observations with the LSTM model (referred to as DI‐LSTM) improved the predictions in such watersheds and enhanced the median NSE to 0.76 by capturing the temporal dependencies and historical patterns that influence hydrological processes. Overall, the contrast of model performance across watersheds suggests major limitations could be associated with the quality of forcing data, and the slow flow or groundwater processes are highly important in the Indian subcontinent. Notably, both LSTM and DI‐LSTM models performed reasonably well for predictions in ungauged watersheds. The findings of this study demonstrate that data‐sparse countries, too, can benefit from big‐data deep learning and point out further avenues toward model improvements.

show abstract

Comparison of the use of a physical-based model with data assimilation and machine learning methods for simulating soil water dynamics

Cited by 45 publications

References 70 publications

Supervised Machine Learning for Estimation of Total Suspended Solids in Urban Watersheds

Supervised Machine Learning for Estimation of Total Suspended Solids in Urban Watersheds

Data assimilation with multiple types of observation boreholes via the ensemble Kalman filter embedded within stochastic moment equations

How to enhance hydrological predictions in hydrologically distinct watersheds of the Indian subcontinent?

Contact Info

Product

Resources

About