A Physics‐Aware Machine Learning‐Based Framework for Minimizing Prediction Uncertainty of Hydrological Models

Roy, Abhinanda; Kasiviswanathan, K. S.; Patidar, Sandhya; Adeloye, Adebayo J.; Soundharajan, B.; Ojha, Chandra Shekhar Prasad

doi:10.1029/2023wr034630

Cited by 4 publications

(2 citation statements)

References 118 publications

(253 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The framework demonstrated consistent accuracy, especially for long lead time and low flow predictions. In a subsequent study [96], the authors evaluated different scenarios, such as using only weather data, only intermediate variables prediction intervals, only SFP intervals, or all these variables together. They found that simulations incorporating all variables outperformed the others consistently.…”

Section: Residual Error Modelingmentioning

confidence: 99%

Enhancing Streamflow Prediction Physically Consistently Using Process-Based Modeling and Domain Knowledge: A Review

Yifru,

Lim,

Lee

2024

Sustainability

View full text Add to dashboard Cite

Streamflow prediction (SFP) constitutes a fundamental basis for reliable drought and flood forecasting, optimal reservoir management, and equitable water allocation. Despite significant advancements in the field, accurately predicting extreme events continues to be a persistent challenge due to complex surface and subsurface watershed processes. Therefore, in addition to the fundamental framework, numerous techniques have been used to enhance prediction accuracy and physical consistency. This work provides a well-organized review of more than two decades of efforts to enhance SFP in a physically consistent way using process modeling and flow domain knowledge. This review covers hydrograph analysis, baseflow separation, and process-based modeling (PBM) approaches. This paper provides an in-depth analysis of each technique and a discussion of their applications. Additionally, the existing techniques are categorized, revealing research gaps and promising avenues for future research. Overall, this review paper offers valuable insights into the current state of enhanced SFP within a physically consistent, domain knowledge-informed data-driven modeling framework.

show abstract

Section: Residual Error Modelingmentioning

confidence: 99%

Enhancing Streamflow Prediction Physically Consistently Using Process-Based Modeling and Domain Knowledge: A Review

Yifru,

Lim,

Lee

2024

Sustainability

View full text Add to dashboard Cite

show abstract

“…According to (Ashwin et al, 2018), their study deals with obtaining models of the rainfall precipitation by using Deep Learning Architectures (LSTM and ConvNet) and determining the better architecture and claiming that for any time series dataset, Deep Learning models will be effective and e cient for the modelers. (Roy et al,2023), the authors investigate the potential of a hybrid modeling framework that couples the random forest algorithm, particle lter, and the HBV model for improving the overall accuracy of forecasts at higher lead times through the dynamic error correction schematic. We can improve our understanding of natural resource dynamics and create e cient plans for their sustainable management by utilizing the capabilities of grid-based technologies and GIS.1.1.…”

mentioning

confidence: 99%

Review on Grid-based system and applied GIS in Natural Resource management: A Comparative Analysis

Kumari,

Geetha,

Shashank

et al. 2023

Preprint

View full text Add to dashboard Cite

In this review study, grid-based methods and applied Geographic Information methods (GIS) for resource management are compared. The analysis looks at research or comparison studies to illustrate the benefits and drawbacks of grid-based resource management systems. Through a collection of real-world case studies in water, air, soil, forestry, and disaster monitoring, it discusses the practical impact of GIS in assisting resource management techniques. In order to effectively use GIS for resource management, the findings highlight the significance of data availability and quality, integration of various data sources, spatial analytical complexity, data privacy and security, and cost concerns. The potential of GIS in resolving these issues and promoting sustainable decision-making in natural resource management is covered in the paper's conclusion. Recent research is represented through graphic representation from different websites for upcoming Grid-based approach references. Citation-based statistics are utilized in this research to identify significant publishing sectors, such as the most popular keywords, best-selling books, most-cited journal articles, nations, and writers who have found success in the Grid-based system. The knowledge gained from this review aids in a better understanding of the relative merits and drawbacks of grid-based systems and applied GIS in resource management, offering helpful recommendations for further study and real-world implementations.

show abstract

Contribution to advancing aquifer geometric mapping using machine learning and deep learning techniques: a case study of the AL Haouz-Mejjate aquifer, Marrakech, Morocco

El Mezouary,

Hadri,

Kharrou

et al. 2024

Appl Water Sci

View full text Add to dashboard Cite

Groundwater resources in Morocco often face sustainability challenges due to increased exploitation and climate change. Specifically, the Al-Haouz-Mejjate groundwater in the Marrakesh region is faced with overexploitation and insufficient recharge. However, the complex subsurface geometries hamper hydrogeological modeling, characterization, and effective management. Reliably estimating aquifer substrate topography is critical for groundwater models but is challenged by limited direct measurements. This study develops nonlinear machine learning models to infer substrate depths by fusing sparse borehole logs with regional geospatial data. A Gaussian process regression approach provided robust holistic mapping, leveraging flexibility, and uncertainty quantification. Supplementary neural network architectures focus on isolating specific variable relationships, like surface elevation–substrate. Model accuracy exceeded 0.8 R-squared against validation boreholes. Spatial visualizations confirmed consistency across landscape transects. Elevation and piezometric data proved most predictive, though multivariate inputs were required for the lowest errors. The results highlight the power of statistical learning to extract meaningful patterns from disparate hydrological data. However, model opacity and the need for broader training datasets remain barriers. Overall, the work demonstrates advanced machine learning as a promising avenue for illuminating complex aquifer geometries essential for sustainability. Hybrid approaches that use both data-driven and physics-based methods can help solve long-standing problems with hydrogeological characterization.

show abstract

A Physics‐Aware Machine Learning‐Based Framework for Minimizing Prediction Uncertainty of Hydrological Models

Abstract: The availability of water resources is not uniform across different time and spatial scale. Therefore, effectively managing the available water resources is crucial for the wide range of applications such as irrigation, hydropower generation, flood, and drought management, etc.

Cited by 4 publications

References 118 publications

Enhancing Streamflow Prediction Physically Consistently Using Process-Based Modeling and Domain Knowledge: A Review

Enhancing Streamflow Prediction Physically Consistently Using Process-Based Modeling and Domain Knowledge: A Review

Review on Grid-based system and applied GIS in Natural Resource management: A Comparative Analysis

Contribution to advancing aquifer geometric mapping using machine learning and deep learning techniques: a case study of the AL Haouz-Mejjate aquifer, Marrakech, Morocco

Contact Info

Product

Resources

About