Volume 72, Issue 6 - Special Issue: Advanced Water Management; Guest Editors: Thomas Rauschenbach and Jürgen Moßgraber

In the aquaculture industry, maintaining stable levels of dissolved oxygen (DO) is crucial for ensuring the health of aquatic organisms and enhancing farming efficiency. This article delves into the challenges faced in predicting and controlling DO levels, such as the need for real-time monitoring and response, the complexity of systems, and limitations in technology and resources. The paper comprehensively reviews various methods for DO prediction and control, including mechanistic modeling prediction, machine learning techniques, and both classical and intelligent control strategies. It analyzes their advantages, limitations, and applicability in aquaculture environments. Through this review and analysis, the article provides more comprehensive insights and guidance for future research directions in DO prediction and control in aquaculture.

The use of deep learning methods for fluvial flood forecasting is rapidly gaining traction, offering a promising solution to the challenges associated with accurate yet time-consuming numerical models. This paper presents two physics-inspired deep learning approaches specifically designed for fluvial flood forecasting, each embracing different learning principles: centralized and federated learning. The centralized model utilizes an Encoder-Decoder technique to handle input data of varying types and scales, while the federated model is based on a node-link graph with a seq2seq internal model. Both models are enhanced with a probabilistic forecasting head to account for the inherent uncertainty in streamflow forecasts. The objective of these approaches is to address the limitations of traditional numerical models while leveraging the potential of deep learning to improve the speed, accuracy, and scalability of flood forecasting. To validate their effectiveness, the models were tested across different use cases. The findings from the federated learning approach emphasize the importance of catchment clustering before model utilization and demonstrate the models’ ability to generalize effectively in catchments with similar properties. On the other hand, the results of the centralized method highlight the model’s reliance on the test set falling within the data range of the training set (Average NSE and KGE for the sixth hour ahead of 0.88 and 0.78, respectively). To address this limitation, the paper suggests the development of a method for the future, such as leveraging a numerical model or using Generative Adversarial Networks, to generate highly extreme events, particularly in the context of a changing climate. The models are implemented in a flexible operational framework based on open standards, ensuring their adaptability and usability in various settings.

Adjacent mountain area and plain area generally belong to the same climate zone, and a close hydraulic connection is also found between them. However, the flood controls in these two areas belong to different management departments. Flood occurring in these two areas can bring serious waterlog disasters, posing great threat to human lives and property. Previous studies mainly focused on the individual flood event in mountain or plain areas, while the research on the floods simultaneously occurring in both areas is insufficient. Hence, this study establishes a copula function-based assessment method to systematically analyze the characteristics of simultaneously-occurring floods in mountain and plain areas in Hangzhou City, thereby providing a basis for the collaborative management of floods in both areas. Results show that the proposed approach can give water level combinations in mountain and plain areas that are prone to co-occurring floods. Moreover, the water level in plain area is most likely to simultaneously appear with the water level in mountain areas under similar return periods, indicating that floods of equivalent level are likely to occur in plain areas when severe floods occur in mountain areas. This study provides a better understanding on the interplay of floods simultaneously occurring in mountain and plain areas, offering insights for coordinating the flood protection system in these two areas.

The real-time management of multi-purpose storage reservoirs aims at an efficient operation of existing hydraulic infrastructure. This management process can be structured as a prescriptive analytics setup that considers both current and predicted system states to recommend actions and outline potential implications. In application to a reservoir and river system, it combines hydrological modelling components for the system schematization, observations and data assimilation for the identification of the current system state, meteorological and hydrological predictions as well as optimization-based techniques to support decision-making regarding reservoir operations. In this paper, we present the application of such a framework to the short-term management of the Eder and Diemel storage reservoirs. These reservoirs are operated by the German Federal Waterways and Shipping Administration (WSV) with the primary goal to support navigation in the River Weser during low flow periods. In addition, partially conflicting objectives such as flood protection, energy generation and recreation are considered. The implementation includes an explicit consideration of forecast uncertainty and its impact on the decision-making by using probabilistic forecasts in combination with a multi-stage stochastic optimization approach. We demonstrate the applicability of the approach based on low and high water use cases. Special attention is paid on the benefits of the probabilistic forecast in combination with the multi-stage stochastic optimization versus a deterministic setup. It provides an explicit translation of the forecast uncertainty in the decision variables, in this case the reservoir releases helping the operators to better anticipate the range of future release decisions. Furthermore, the stochastic approach is expected to provide more stable decisions in an operational setting, based on more stable forecasts by considering various possible realizations of the future instead of picking a single one, which gets random after 4–5 days.

State-of-the-art modelling tools and dynamic simulations have become important tools for planning and operational decision making in the environmental sector, including wastewater treatment plants. Due to increasing regulatory requirements (energy savings, treatment performance, GHG footprint), the practical application of these instruments is becoming more challenging. AI methods could be a solution to support users in the application of domain-specific modelling and simulation tools. This contribution presents first steps towards the integration of the AI methods Bayesian Networks (BN) and Artificial Neural Networks (ANN) into a modelling and simulation tool for urban waste water systems, including example applications.

In the realm of environmental governance, civil servants confront a plethora of diverse datasets, including time series, geospatial vector data, and raster data. However, unlocking the transformative potential of Artificial Intelligence (AI) models to analyze this data poses the challenge of a widening technical proficiency gap in public administration. This paper explores the intersection of expanding environmental datasets and advanced analytics. Through a real-world project lens, our work aims to guide public administration entities, fostering seamless integration of AI-driven analytics and data-driven decision-making. We present a modular technical architecture that proposes pragmatic solutions that have the potential to empower civil servants. This approach contributes to accelerating environmental governance into an era of more informed and efficient, data-driven practices.