Hoshin V. Gupta
YOU?
Author Swipe
View article: AI Powered Career Advisor: Bridging the Gap between the Aspirations and Opportunities
AI Powered Career Advisor: Bridging the Gap between the Aspirations and Opportunities Open
The job market is changing at an accelerating rate, creating challenges to both the future employees and organizations engaged in the hiring process. It is difficult for the majority of job applicants to make decisions about their careers …
View article: Are Deep Learning Models in Hydrology Entity Aware?
Are Deep Learning Models in Hydrology Entity Aware? Open
Hydrology is experiencing a shift from process‐based toward deep learning (DL) models. Entity‐aware (EA) DL models with static features (predominantly physiographic proxies) merged to dynamic forcing features show significant performance i…
View article: On Robustness of the Explanatory Power of Machine Learning Models: Insights From a New Explainable AI Approach Using Sensitivity Analysis
On Robustness of the Explanatory Power of Machine Learning Models: Insights From a New Explainable AI Approach Using Sensitivity Analysis Open
Machine learning (ML) is increasingly considered the solution to environmental problems where limited or no physico‐chemical process understanding exists. But in supporting high‐stakes decisions, where the ability to explain possible solut…
View article: Exploring Soil Moisture Dynamics and Variability Across Scales and Geological Settings Using Gaussian Mixture-Long Short-Term Memory Networks
Exploring Soil Moisture Dynamics and Variability Across Scales and Geological Settings Using Gaussian Mixture-Long Short-Term Memory Networks Open
View article: Using Machine Learning to Discover Parsimonious and Physically-Interpretable Representations of Catchment-Scale Rainfall-Runoff Dynamics
Using Machine Learning to Discover Parsimonious and Physically-Interpretable Representations of Catchment-Scale Rainfall-Runoff Dynamics Open
Due largely to challenges associated with physical interpretability of machine learning (ML) methods, and because model interpretability is key to credibility in management applications, many scientists and practitioners are hesitant to di…
View article: Deep Learning Models in Hydrology Have Not Yet Achieved Entity Awareness
Deep Learning Models in Hydrology Have Not Yet Achieved Entity Awareness Open
View article: Creating Sustainable Flood Maps Using Machine Learning and Free Remote Sensing Data in Unmapped Areas
Creating Sustainable Flood Maps Using Machine Learning and Free Remote Sensing Data in Unmapped Areas Open
This study leverages a Random Forest model to predict flood hazard in Arizona, New Mexico, Colorado, and Utah, focusing on enhancing sustainability in flood management. Utilizing the National Flood Hazard Layer (NFHL), an intricate flood m…
View article: Towards Interpretable Physical‐Conceptual Catchment‐Scale Hydrological Modeling Using the Mass‐Conserving‐Perceptron
Towards Interpretable Physical‐Conceptual Catchment‐Scale Hydrological Modeling Using the Mass‐Conserving‐Perceptron Open
We investigate the applicability of machine learning technologies to the development of parsimonious, interpretable, catchment‐scale hydrologic models using directed‐graph architectures based on the mass‐conserving perceptron (MCP) as the …
View article: Convergent and transdisciplinary integration: On the future of integrated modeling of human-water systems
Convergent and transdisciplinary integration: On the future of integrated modeling of human-water systems Open
The notion of convergent and transdisciplinary integration, which is about braiding together different knowledge systems, is becoming the mantra of numerous initiatives aimed at tackling pressing water challenges. Yet, the transition from …
View article: Virtual Hydrological Laboratories: Developing the Next Generation of Conceptual Models to Support Decision Making Under Change
Virtual Hydrological Laboratories: Developing the Next Generation of Conceptual Models to Support Decision Making Under Change Open
As hydrological systems are pushed outside the envelope of historical experience, the ability of current hydrological models to serve as a basis for credible prediction and decision making is increasingly challenged. Conceptual models are …
View article: A Mass‐Conserving‐Perceptron for Machine‐Learning‐Based Modeling of Geoscientific Systems
A Mass‐Conserving‐Perceptron for Machine‐Learning‐Based Modeling of Geoscientific Systems Open
Although decades of effort have been devoted to building Physical‐Conceptual (PC) models for predicting the time‐series evolution of geoscientific systems, recent work shows that Machine Learning (ML) based Gated Recurrent Neural Network t…
View article: HVG Comment on hess-2024-59
HVG Comment on hess-2024-59 Open
Abstract. The evaluation of model performance is an essential part of hydrological modeling. However, leveraging the full information that performance criteria provide, requires a deep understanding of their properties. Th…
View article: On Robustness of the Explanatory Power of Machine Learning Models
On Robustness of the Explanatory Power of Machine Learning Models Open
Machine learning (ML) is increasingly considered the solution to environmental problems where only limited or no physico-chemical process understanding is available. But when there is a need to provide support for high-stake decisions, whe…
View article: Neglecting hydrological errors can severely impact predictions of water resource system performance 
Neglecting hydrological errors can severely impact predictions of water resource system performance  Open
Risk-based decision making for water resource systems often relies on streamflow predictions from hydrological models. These predictions are integral for estimating the frequency of high consequence extreme events, such as floods and droug…
View article: Virtual Hydrological Laboratories to develop the next generation of conceptual models and support decision-making under change
Virtual Hydrological Laboratories to develop the next generation of conceptual models and support decision-making under change Open
The ability of contemporary hydrological models to serve as a basis for credible prediction and decision making is increasingly challenged – especially as hydrological systems are pushed outside the envelope of historical experience.…
View article: Exploring Catchment Regionalization through the Eyes of HydroLSTM
Exploring Catchment Regionalization through the Eyes of HydroLSTM Open
Regionalization is an issue that hydrologists have been working on for decades. It is used, for example, when we transfer parameters from one calibrated model to another, or when we identify similarities between gauged to ungauged catchmen…
View article: Neglecting hydrological errors can severely impact predictions of water resource system performance
Neglecting hydrological errors can severely impact predictions of water resource system performance Open
Risk-based decision making for water resource systems often relies on streamflow predictions from hydrological models. These predictions are integral for estimating the frequency of high consequence extreme events, such as floods and droug…
View article: Development of Groundwater Levels Dataset for Chile since 1970
Development of Groundwater Levels Dataset for Chile since 1970 Open
Access to accurate spatio-temporal groundwater level data is crucial for sustainable water management in Chile. Despite this importance, a lack of unified, quality-controlled datasets have hindered large-scale groundwater studies. Our obje…
View article: Sahra integrated modeling approach to address water resources management in semi-arid river basins
Sahra integrated modeling approach to address water resources management in semi-arid river basins Open
Water resources decisions in the 21Sf Century that will affect allocation of water for economic and environmental will rely on simulations from integrated models of river basins. These models will not only couple natural systems such as su…
View article: Towards Interpretable Physical-Conceptual Catchment-Scale Hydrological Modeling using the Mass-Conserving-Perceptron
Towards Interpretable Physical-Conceptual Catchment-Scale Hydrological Modeling using the Mass-Conserving-Perceptron Open
We investigate the applicability of machine learning technologies to the development of parsimonious, interpretable, catchment-scale hydrologic models using directed-graph architectures based on the mass-conserving perceptron (MCP) as the …
View article: Rainfall distributional properties control hydrologic model parameter importance.
Rainfall distributional properties control hydrologic model parameter importance. Open
Study region: Semi-arid region of the Western United States of America in 16.6 km2 WS10 watershed using data from the highly instrumented Walnut Gulch Experimental Watershed managed by the USDA-Agricultural Research Services. Study focus: …
View article: A Robust Method to Simultaneously Place Sensors and Calibrate Parameters for Urban Drainage Pipe System Models Using Bayesian Decision Theory
A Robust Method to Simultaneously Place Sensors and Calibrate Parameters for Urban Drainage Pipe System Models Using Bayesian Decision Theory Open
View article: A Robust Method to Simultaneously Place Sensors and Calibrate Parameters for Urban Drainage Pipe System Models Using Bayesian Decision Theory
A Robust Method to Simultaneously Place Sensors and Calibrate Parameters for Urban Drainage Pipe System Models Using Bayesian Decision Theory Open
View article: Position Paper: Bridging the Gap Between Machine Learning and Sensitivity Analysis
Position Paper: Bridging the Gap Between Machine Learning and Sensitivity Analysis Open
We argue that interpretations of machine learning (ML) models or the model-building process can be seen as a form of sensitivity analysis (SA), a general methodology used to explain complex systems in many fields such as environmental mode…
View article: Comment on hess-2023-252
Comment on hess-2023-252 Open
Abstract. Several studies have demonstrated the ability of Long Short-Term Memory (LSTM) machine learning based modeling to outperform traditional spatially-lumped process-based modeling approaches for streamflow predictio…
View article: Supplementary material to "Towards Interpretable LSTM-based Modelling of Hydrological Systems"
Supplementary material to "Towards Interpretable LSTM-based Modelling of Hydrological Systems" Open
View article: A Mass-Conserving-Perceptron for Machine Learning-Based Modeling of Geoscientific Systems
A Mass-Conserving-Perceptron for Machine Learning-Based Modeling of Geoscientific Systems Open
Although decades of effort have been devoted to building Physical-Conceptual (PC) models for predicting the time-series evolution of geoscientific systems, recent work shows that Machine Learning (ML) based Gated Recurrent Neural Network t…
View article: Comment on egusphere-2023-666
Comment on egusphere-2023-666 Open
Abstract. Several studies have demonstrated the ability of Long Short-Term Memory (LSTM) machine learning based modeling to outperform traditional spatially lumped process-based modeling approaches for streamflow predictio…
View article: Differentiable modelling to unify machine learning and physical models for geosciences
Differentiable modelling to unify machine learning and physical models for geosciences Open
View article: Comment on egusphere-2023-666
Comment on egusphere-2023-666 Open
Abstract. Several studies have demonstrated the ability of Long Short-Term Memory (LSTM) machine learning based modeling to outperform traditional spatially lumped process-based modeling approaches for streamflow predictio…