Amin Elshorbagy

Traditionally streamflow forecasting is accomplished using process-based hydrological models. These models could range from simple lumped type to more detailed distributed models. Lumped type models are easy to setup while distributed models require considerable skill and experience for setup. Due to the growing availability of large amounts of spatial and temporal data from various sources, such as remote sensing and re-analyses, and recent advances in the computational power, machine learning models are gaining momentum for solving applied engineering problems, triggering conceptual shifts perhaps led by rapid progress in data science and availability of ready-to-be-deployed software tools. These models have the ability to extract complex dynamical nonlinearities without explicitly defining the involved physical processes and their governing mathematical formulations, as is followed in the case of hydrological models. It is believed that new trends and conceptual shifts are essential for generating new knowledge, challenging or validating prevailing assumptions, and enhancing operational applications, which may include several water management-related functions, hydropower generation operations, and flood risk management across a range of temporal and spatial scales.In this study, two deep learning variants of machine learning models, i.e., (1) the attention-based encoder-decoder bidirectional long short-term memory (AB-ED-BiLSTM) network and (2) the attention-based encoder-decoder bidirectional gated recurrent units (AB-ED-BiGRU) network, were tested on multiple watersheds selected from the Ottawa River Basin, Canada. After developing and successfully evaluating watershed-specific models, regional versions of both models were developed and tested based on the leave-one-watershed-out strategy to emulate an ungauged scenario. Both models were driven mainly by soil moisture states of watersheds and meteorological data in order to evaluate their usefulness for streamflow forecasting at ungauged locations. Although not as ideal as one would desire, these models demonstrated reasonable skill in forecasting streamflow with one to seven days lead time when assessed in terms of coefficient of determination, Nash-Sutcliff Efficiency, and Kling-Gupta Efficiency performance metrics. However, considerable discrepancies were noticed in simulating peak flow values for certain watersheds. Overall results of the study suggest that soil moisture driven machine learning models can potentially be used to develop streamflow forecasting tools for ungauged locations, with AB-ED-BiGRU being computationally an inexpensive option compared to the AB-ED-BiLSTM model. Additional investigations will be required to improve their performance further, e.g., by employing multiple soil moisture products, available through remote sensing and re-analyses sources, and ensemble modelling techniques. Based on continuous scientific progress, emerging machine learning frameworks and architectures, and better understanding of the origins and limitations of existing models, improved hydrological forecasting at ungagged locations can be made possible. In essence, this study contributes towards enhancing our understanding of the role of soil moisture in developing machine learning based streamflow modelling and forecasting tools to support operational applications at ungauged locations, which are often neglected when developing real-time streamflow forecasting systems.

Over the past few years, the of use machine learning (ML) models in hydrology has shifted towards deep learning (DL), perhaps because of the icreasing availability of big data and ready-to-be-deployed software tools. It seems that the underlying assumption is that more complex (DL) models are desired, however, there are less efforts to systematically investigate and validate this perception. Deep learning models like LSTM have greatly improved sequential data forecasting, but their success depends on large labeled datasets, limiting their effectiveness in data-scarce domains. This study investigates whether complex ML models offer significant advantages over simpler approaches in predicting seasonal streamflow in Canada. Using a comprehensive case study, we examine multiple subbasin types—mountain, prairie, and non-prairie—along with headwater and downstream locations, exhibiting both natural and human-influenced regulated flow regimes. These variations introduce distinct hydrological behaviors, making them an ideal testbed for assessing model complexity requirements. Our case study includes 135 subbasins from the Canadian Nelson-Churchill River Basin, comprising the vast area starting from the Rocky mountains up to the Hudson Bay, with the monthly temporal resolution and spatial scales of the order of 200 km2 to ~1.0 x106 km2, as reflected by drainage areas of all subbasins.We implemented a suite of ML techniques, ranging from traditional algorithms to advanced DL architectures. Specifically, we compared models developed based on Artificial Neural Networks (ANNs), Random Forests (RF), Long Short-Term Memory (LSTM) networks, attention-based LSTM networks, and stacked LSTM configurations. Each model was trained and tested using historical flow data across multiple subbasins, with performance evaluated through metrics, such as Nash-Sutcliffe Efficiency and Percent Mean Bias Error. We also experimented with alternative sets of input features, i.e., (i) all potential hydrometeorological inputs, (ii) correlation and partial mutual information-based inputs, and (iii) causality-based inputs.Our findings reveal that while simpler models like RF and ANNs perform adequately in certain contexts—particularly in headwater subbasins with natural flow regimes—complex architectures, such as LSTM and stacked LSTM configurations demonstrate superior performance for downstream and regulated basins, where flow patterns exhibit higher variability and nonlinearity. In contrast, attention-based LSTM networks do not appear to outperform other options across certain basins. Interestingly, the benefits of DL models are not uniform across all subbasin types; prairie and non-prairie basins show mixed results, suggesting that model complexity should be tailored to basin characteristics rather than universally applied. These results highlight the importance of context-driven model selection to inform operational forecasting. Thus, water managers can leverage simpler models in less complex basins to reduce computational costs and data requirements, while reserving advanced architectures for highly regulated or downstream basins where accuracy gains justify the added complexity. This approach can potentially optimize resource allocation, enhance forecast reliability, and support informed decision-making in water allocations, reservoir operations, and drought/flood preparedness. Additionally, in the absence of data and computational constraints, multi-model outputs can be synthesized further through fusion modelling techniques to enhnace overall prediction accuracy.

The use of artifical intelligence (AI) and machine learning (ML) approaches in various scientific and engineering disciplines has grown exponentially over recent years. This upsurge also includes applications of physics-guided ML models and explainable AI. However, in addition to the dificulties involved in the identification of relevant model inputs, the advantages, contributions, and credibility of ML models are still open challenges, especially when these models are evaluated against the perceptual hydrologic understanding of the system in question. In this study, we aim to investigate some of these challenges using the case of seasonal streamflow forecasting with lead times up to three months in several hydrologically challenging river basins of prairie provinces of Canada (i.e., Alberta, Saskatchewan, and Manitoba).Multiple ML techniques, including Random Forest (RF) and Long Short-Term Memory (LSTM) models, are used to produce ensemble forecasts for 135 sub-basins of the Nelson-Churchill River Basin, comprising the vast area from the Rocky mountains up to the Hudson Bay, with the monthly temporal resolution and spatial scales of the order of 200 km2 to ~1.0 x106 km2, as reflected by drainage areas of all sub-basins. A large set of potential inputs (105 predictors) is used in this study. These potential inputs include hydrometeorological variables derived from the Daymet database, Environment and Climate Change Canada’s hydrometric network, and hydrometeorological forecasts from the European Centre for Medium-Range Weather Forecasts, and various static attributes of all sub-basins.The Pearson’s correlation coefficient (CC) and Partial Mutual Information (PMI) were used, as model agnostic methods, to analyze the set of potential predictors and identify the most appropriate inputs for seasonal flow forecasting, prior to ML model development. Subsequently, modeling experiments were designed to investigate the ML model performance and test the usefulness of CC and PMI based techniques on modeling results. The model-agnostic and model-dependent findings were compared and analyzed in light of the perceptual understanding of the hydrological system. Furthermore, the Convergent Cross-Mapping (CCM) method was used with selected variables to further explore the causal, rather than correlational, relationships and interpret the results with the aim of developing ethical and responsible ML (ERML) models. We define ERML models as data driven models that are transparent and hydrologically explainable.The preliminary results of this study indicate that PMI is quite effective in filtering some of the CC-based selections, which might form multiple equifinale sets of predictors. This step is critical for identifying the most relevant and necessary inputs. In spite of the coarse spatial and temporal resolutions, which complicate crisp hydrologic perceptions, the CCM method seems to support the selection of various input variables with hydrologic causality, strengthening the transparency and credibility of ML models.

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 rhetoric to actual implementation is impeded by incongruence in semantics, methodologies, and discourse among disciplinary scientists and societal actors. Here, we embrace “integrated modeling”—both quantitatively and qualitatively—as a vital exploratory instrument to advance such integration, providing a means to navigate complexity and manage the uncertainty associated with understanding, diagnosing, predicting, and governing human‐water systems. From this standpoint, we confront disciplinary barriers by offering seven focused reviews and syntheses of existing and missing links across the frontiers distinguishing surface and groundwater hydrology, engineering, social sciences, economics, Indigenous and place‐based knowledge, and studies of other interconnected natural systems such as the atmosphere, cryosphere, and ecosphere. While there are, arguably, no bounds to the pursuit of inclusivity in representing the spectrum of natural and human processes around water resources, we advocate that integrated modeling can provide a focused approach to delineating the scope of integration, through the lens of three fundamental questions: (a) What is the modeling “purpose”? (b) What constitutes a sound “boundary judgment”? and (c) What are the “critical uncertainties” and their compounding effects? More broadly, we call for investigating what constitutes warranted “systems complexity,” as opposed to unjustified “computational complexity” when representing complex natural and human‐natural systems, with careful attention to interdependencies and feedbacks, scaling issues, nonlinear dynamics and thresholds, hysteresis, time lags, and legacy effects.

The global food supply and food security are altered by field, soil, and weather conditions during crop production. Researching food productivity became crucial as the global population increased. In particular, crop losses bring low food supply and price instabilities at the regional and global levels. With that in mind, we reviewed ten crop models and the most simulated impacts from soil-crop-atmosphere interactions in maize, rice, and wheat production. Since 2012, modellers have mainly used APSIM to predict water availability, temperature changes and Greenhouse Gas (GHG) concentration to predict crop phenology, growth and development, grain filling and nutrient content, and yield. Since 2013, AquaCrop has been used to simulate scenarios focused on water balance in crop production systems, water stress and irrigation planning. Interestingly, Biome-BGCMuso was developed as a biogeochemical model and was not considered good by crop modellers. However, After updates, version v6.2 can simulate different management and field conditions for fifteen crops, considering heat, nitrogen and drought stress. Since 2008, crop modellers used CropSyst to evaluate water availability, nitrogen use efficiency (UE), temperature shifts and GHG concentration in rainfed and irrigated crop systems. Since 2002, crop modellers have used DAISY to predict crop growth, nitrogen and water UE, grain content, yield gap, and losses. Since 2011, researchers have used DSSAT-CERES for mitigation strategy planning by predicting crop growth, soil characteristics, changes in land use, and nitrogen and water UE. Since 2015, JULES has been used to determine land-atmosphere interactions, changes in land use and GHG impacts on agriculture. Since 2008, ORYZA modellers have mainly predicted nitrogen and water UE, salinity impacts, and toxicity to rice. STICS was developed in 1996, and since 2008, it has been primarily used to simulate fertilization and irrigation systems, nitrogen leaching, and water availability. Since 2000, researchers have used WOFOST to analyze water availability, crop growth, and productivity under temperature changes. Crop models are fast and reliable resources when simulating crop production and food availability.

The Eastern Nile Basin (ENB) countries of Egypt, Sudan, South Sudan, and Ethiopia are subject to pronounced water, energy, and food (WEF) insecurity. There is a need to manage the WEF nexus to meet rapidly increasing demands, but this is extremely challenging due to resource scarcity and climate change. If countries that rely on shared transboundary water resources have contradictory WEF plans, that could diminish the expected outcomes, both nationally and regionally. Egypt as the most downstream Nile country is concerned about ongoing and future developments upstream, which could exacerbate Egypt's water scarcity and affect its ability to meet its WEF objectives. In this context, we introduce a multi‐model WEF framework that simulates the ENB water resources, food production, and hydropower generation systems. The models were calibrated and validated for the period 1983–2016, then utilized to project a wide range of future development plans, up to 2050, using four performance measures to evaluate the WEF nexus. A thematic pathway for regional development that shows high potential for mutual benefits is identified. However, the WEF planning outcomes for the region are sensitive to climate change, but, if social drivers could be managed (e.g., by lowering population growth rates) despite the difficulties involved, climate change impacts on WEF security could be less severe.

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 rhetoric to actual implementation is impeded by incongruence in semantics, methodologies, and discourse among disciplinary scientists and societal actors. This paper confronts these disciplinary barriers by advocating a synthesis of existing and missing links across the frontiers distinguishing hydrology from engineering, the social sciences and economics, Indigenous and place-based knowledge, and studies of other interconnected natural systems such as the atmosphere, cryosphere, and ecosphere. Specifically, we embrace ‘integrated modeling’, in both quantitative and qualitative senses, as a vital exploratory instrument to advance such integration, providing a means to navigate complexity and manage the uncertainty associated with understanding, diagnosing, predicting, and governing human-water systems. While there are, arguably, no bounds to the pursuit of inclusivity in representing the spectrum of natural and human processes around water resources, we advocate that integrated modeling can provide a focused approach to delineating the scope of integration, through the lens of three fundamental questions: a) What is the modeling ‘purpose’? b) What constitutes a sound ‘boundary judgment’? and c) What are the ‘critical uncertainties’ and how do they propagate through interconnected subsystems? More broadly, we call for investigating what constitutes warranted ‘systems complexity’, as opposed to unjustified ‘computational complexity’ when representing complex natural and human-natural systems, with particular attention to interdependencies and feedbacks, nonlinear dynamics and thresholds, hysteresis, time lags, and legacy effects.