Health risk assessment of environmental exposure to pathogens requires complete and up to date knowledge. With the rapid growth of scientific publications and the protocolization of literature reviews, an automated approach based on Artificial Intelligence (AI) techniques could help extract meaningful information from the literature and make literature reviews more efficient. The objective of this research was to determine whether it is feasible to extract both qualitative and quantitative information from scientific publications about the waterborne pathogen Legionella on PubMed, using Deep Learning and Natural Language Processing techniques. The model effectively extracted the qualitative and quantitative characteristics with high precision, recall and F-score of 0.91, 0.80, and 0.85 respectively. The AI extraction yielded results that were comparable to manual information extraction. Overall, AI could reliably extract both qualitative and quantitative information about Legionella from scientific literature. Our study paved the way for a better understanding of the information extraction processes and is a first step towards harnessing AI to collect meaningful information on pathogen characteristics from environmental microbiology publications.

Climate and land use changes will affect the hydrological regime, and therefore hydropower. This study which aims to develop a novel modeling framework, does not only determine the changes in hydropower generation and sustainability, but also provide robust operating rules for handling uncertainty attributed to both climate and land use changes, using Xinanjiang Reservoir in Eastern China as a case study. Specifically, projections of five bias-corrected and downscaled General Circulation Models (GCMs) and three modeled land uses representing a range of tradeoffs between ecological protection and urban development are employed to drive the Soil and Water Assessment Tool (SWAT) and to predict streamflow under 15 scenarios. We then develop a set of robust rule curves to consider the potential uncertainty in reservoir inflow and to increase hydropower generation, and a baseline rule is presented for comparison. Results show that both robust and baseline rules increase hydropower generation with increasing reservoir inflows in future, but the robust rule yields better hydropower generation, sustainability and efficiency. The streamflow under the rapid urbanization scenarios differs from that under other scenarios, but there are no significant differences in hydropower among scenarios corresponding to the non-linear relationship between streamflow and hydropower change. Our findings highlight the potential to improve water resource utilization in the future, especially based on the robust operating rule considering optimization and uncertainty, and can provide references for future hydropower planning to the other existing plants.

Proportional-integral (PI) control, as one of the most popular classic control methods, has been applied widely to the real-world practice of canal automatic control. The performance of a PI controller largely depends on two key parameters, namely the proportional constant Kp and the integrational time constant Ti. Rather than tuning these parameters empirically or in terms of the canal morphology, this study proposes a linear quadratic regulator (LQR) to determine their optimal values. The proposed LQR utilizes an integrator delay model to represent the hydrodynamics of open canals in order to minimize changes in water levels and flow rates. In addition, the weights for the optimization objective in the LQR are determined by an optimized quadratic performance indicators estimate (OQPIE), using the precalculated nondimensional integrated square of error and nondimensional integrated absolute discharge change as well as inherent designed parameters, which potentially impact the stability of system states. In this way, the LQR can fit various canal automation applications, especially for low-gradient canals. The optimal PI controller was tested on two different-scaled canals. Results showed that the objective was met satisfactorily, and stability can be reached in hours.

A new Proportional-Integral (PI) tuning method based on Linear Matrix Inequalities (LMIs) is presented. In particular, an LMI-based optimal control problem is solved to obtain a sparse feedback that provides the PI tuning. The ASCE Test Canal 1 is used as a case study. Using a linearised model of the canal, different tunings for the design of the PI controller are developed and tested using the software Sobek. Furthermore, the proposed method is also compared with other tunings proposed for the same canal available in the literature. Our results show that the proposed method reduces by half the maximum errors with respect to other assessed alternatives and minimizes undesired mutual interactions between canal pools. Also, our method improves the optimality degree of the PI tuning by 30%. Therefore, it is concluded that the LMI based PI controllers lead to satisfactory performance in regulating water levels and canal flows/structure outflows, outperforming other tested alternatives, thus becoming a useful tool for irrigation canal control.

Recently, a continuous reinforcement learning model called fuzzy SARSA (state, action, reward, state, action) learning (FSL) was proposed for irrigation canals. The main problem related to FSL is its convergence and generalization in environments with many variables such as large irrigation canals and situations beyond training. Furthermore, due to its architecture, FSL may require high computation demands during its learning process. To deal with these issues, this work proposes a computationally lighter generalizing learned Q-function (GLQ) model, which benefits from the FSL-learned Q-function, to provide operators with a faster and simpler mechanism to obtain operational instructions. The proposed approach is tested for different water requests in the East Aghili Canal, located in the southwest of Iran. Several performance indicators are used for evaluating the GLQ model results, showing convergence in all the investigated cases and the ability to estimate operational instructions (actions) in situations beyond training, delivering water with high accuracy regarding several performance indicators. Hence, the use of the GLQ model is recommended for determining the operational patterns in irrigation canals.

Urban pluvial flooding is a threatening natural hazard in urban areas all over the world, especially in recent years given its increasing frequency of occurrence. In order to prevent flood occurrence and mitigate the subsequent aftermath, urban water managers aim to predict precipitation characteristics, including peak intensity, arrival time and duration, so that they can further warn inhabitants in risky areas and take emergency actions when forecasting a pluvial flood. Previous studies that dealt with the prediction of urban pluvial flooding are mainly based on hydrological or hydraulic models, requiring a large volume of data for simulation accuracy. These methods are computationally expensive. Using a rainfall threshold to predict flooding based on a data-driven approach can decrease the computational complexity to a great extent. In order to prepare cities for frequent pluvial flood events – especially in the future climate – this paper uses a rainfall threshold for classifying flood vs. non-flood events, based on machine learning (ML) approaches, applied to a case study of Shenzhen city in China. In doing so, ML models can determine several rainfall threshold lines projected in a plane spanned by two principal components, which provides a binary result (flood or no flood). Compared to the conventional critical rainfall curve, the proposed models, especially the subspace discriminant analysis, can classify flooding and non-flooding by different combinations of multiple-resolution rainfall intensities, greatly raising the accuracy to 96.5% and lowering the false alert rate to 25%. Compared to the conventional model, the critical indices of accuracy and true positive rate (TPR) were 5%-15% higher in ML models. Such models are applicable to other urban catchments as well. The results are expected to be used to assist early warning systems and provide rational information for contingency and emergency planning.

Climate and land use/cover changes are the main factors altering hydrological regimes. To understand the impacts of climate and land use/cover changes on streamflow within a specific catchment, it is essential to accurately quantify their changes given many possibilities. We propose an integrated framework to assess how individual and combined climate and land use/cover changes impact the streamflow of Xinanjiang Basin, in East China, in the future. Five bias-corrected and downscaled General Circulation Model (GCM) projections are used to indicate the inter-model uncertainties under three Representative Concentration Pathways (RCPs). Additionally, three land use/cover change scenarios representing a range of tradeoffs between ecological protection (EP) and urban development (UD) are projected by Cellular Automata - Markov (CA-Markov). The streamflow in 2021–2050 is then assessed using the calibrated Soil and Water Assessment Tool (SWAT) with 15 scenarios and 75 possibilities. Finally, the uncertainty and attribution of streamflow changes to climate and land use/cover changes at monthly and annual scale are analyzed. Results show that while both land use/cover change alone and combined changes project an increase in streamflow, there is a disagreement on the direction of streamflow change under climate change alone. Future streamflow may undergo a more blurred boundary between the flood and non-flood seasons, potentially easing the operation stress of Xinanjiang Reservoir for water supply or hydropower generation. We find that the impacts of climate and land use/cover changes on monthly mean streamflow are sensitive to the impermeable area (IA). The impacts of climate change are stronger than those induced by land use/cover change under EP (i.e., lower IA); and land use/cover change has a greater impact in case of UD (i.e., higher IA). However, changes in annual mean streamflow are mainly driven by land use/cover change, and climate change may decrease the influence attributed to land use/cover change.

Rainfall-triggered shallow landslides are widespread natural hazards around the world, causing many damages to human lives and property. In this study, we focused on predicting landslides in a large region by coupling a 1 km-resolution hydrological model and a 90 m-resolution slope stability model, where a downscaling method for soil moisture via topographic wetness index was applied. The modeled hydrological processes show generally good agreements with the observed discharges: relative biases and correlation coefficients at three validation stations are all <20% and >0.60, respectively. The derived scaling law for soil moisture allows for near-conservative downscaling of the original 1-km soil moisture to 90-m resolution for slope stability assessment. For landslide prediction, the global accuracy and true positive rate are 97.2% and 66.9%, respectively. This study provides an effective and computationally efficient coupling method to predict landslides over large regions in which fine-scale topographical information is incorporated.

Inter-basin water transfers (IBWT) are implemented to re-allocate unevenly distributed water resources. However, many conflicting objectives associated with society, economy, and environment have made the water resources allocation problem in IBWT more complicated than ever before. Thus, there is a continuous need for in-depth research with the latest optimization techniques to secure many-objective allocation of water resources for IBWT. In addition, being troubled of easily falling into local minima and premature convergence in some multi-objective optimization algorithms, it is necessary to explore new alternatives to improve their search quality. Here we propose a many-objective optimization methodology for IBWT, which includes three modules: (1) formulating a many-objective optimization problem based on realistic controls; (2) developing a new multi-objective real-coded quantum inspired shuffled frog leaping algorithm (r-MQSFLA) to solve the optimization problem; (3) utilizing the Analytic Hierarchy Process (AHP)-Entropy method to filter the Pareto solutions. In r-MQSFLA, the real-coded quantum computer and the external archive with dynamic updating mechanism are applied to SFLA. The performance of r-MQSFLA is first compared to that of other multi-objective evolutionary algorithms (MOEAs) in solving mathematical benchmark problems. A case study of the Eastern Route of South-to-North Water Transfer Project in Jiangsu Province, China varying from a normal to an extremely dry year, demonstrates that r-MQSFLA displays approximate performance on some compared algorithms and is improved significantly than MOSFLA in terms of convergence, diversity and reasonable solutions. This study can update the understanding of quantum theory to MOEAs and will provide a reference for better water resources allocation in IBWT under uncertainty.

This paper presents an extended Model Predictive Control scheme called Multi-objective Model Predictive Control (MOMPC) for real-time operation of a multi-reservoir system. The MOMPC approach incorporates the non-dominated sorting genetic algorithm II (NSGA-II), multi-criteria decision making (MCDM) and the receding horizon principle to solve a multi-objective reservoir operation problem in real time. In this study, a water system is simulated using the De Saint Venant equations and the structure flow equations. For solving multi-objective optimization, NSGA-II is used to find the Pareto-optimal solutions for the conflicting objectives and a control decision is made based on multiple criteria. Application is made to an existing reservoir system in the Sittaung river basin in Myanmar, where the optimal operation is required to compromise the three operational objectives. The control objectives are to minimize the storage deviations in the reservoirs, to minimize flood risks at a downstream vulnerable place and to maximize hydropower generation. After finding a set of candidate solutions, a couple of decision rules are used to access the overall performance of the system. In addition, the effect of the different decision-making methods is discussed. The results show that the MOMPC approach is applicable to support the decision-makers in real-time operation of a multi-reservoir system.

In the open channel control algorithm, good feed-forward controllers will reduce the transition time of the canal and improve performance. Feedforward control algorithms based on active storage compensation are greatly affected by delay time. However, there is no literature comparing the three most commonly used algorithms, namely volume step compensation, dynamic wave principle and water balance models, under the operation mode of constant water level downstream. In order to compare the existing three algorithms, and to avoid storage calculation by calculating the constant non-uniform water surface line or identification of relevant parameters, combined with the open channel constant gradient flow theory with the storage compensation algorithm, a delay time explicit algorithm is proposed in this study. Tested on the first canal pool of the American Society of Civil Engineers (ASCE) Test Canal 2, the performance of the delay time explicit algorithm is assessed and compared to that of the three conventional algorithms. In the current water intake plan, i.e., in the second hour, the intake begins to take 1.2 m³/s, and the upstream flow of the canal pool changes from 6 m³/s to 7.2 m³/s, among the three existing algorithms, the volume step compensation algorithm has better performance in terms of time to achieve stability, i.e., 1.25 h. The actual adjusted storage accounts for 99.6% of the target adjusted storage, which can basically meet the requirement of compensated storage of the canal pool. The delay time explicit algorithm only needs 1.47 h to stabilize the regulation system. The fluctuation of water level and discharge in the regulation process is small. The actual adjusted storage accounts for 99.6% of the target adjusted storage, which can basically meet the requirement of compensated storage for the canal pool. The delay time calculated by explicit algorithm can provide references for the determination of delay time in feedforward control.

Urban pluvial flooding is one of the most costly natural hazards worldwide. Risks of flooding are expected to increase in the future due to global warming and urbanization. The complexity of the involved processes and the lack of long-term field observations means that many crucial aspects related to urban flood risks still remain poorly understood. In this paper, the possibility to gain new insight into urban pluvial flooding using citizen flood observations is explored. Using a ten-year dataset of radar rainfall maps and 70,000 citizen flood reports for the city of Rotterdam, we derive critical thresholds beyond which urban pluvial flooding is likely to occur. Three binary decision trees are trained for predicting flood occurrences based on peak rainfall intensities across different temporal scales. Results show that the decision trees correctly predict 37%–52% of all flood occurrences and 95%–97% of all non-flood occurrences, which is a fair performance given the uncertainties associated with citizen data. More importantly, all models agree on which rainfall features are the most important for predicting flooding, reaching optimal performance whenever short- and long-duration rainfall peak intensities are combined together to make a prediction. Additional feature selection using principal component analysis shows that further improvement is possible when critical rainfall thresholds are calculated using a linear combination of peak rainfall intensities across multiple temporal scales. The encouraging results suggest that citizen observatories, although prone to larger errors and uncertainties, constitute a valuable alternative source of information for gaining insight into urban pluvial flooding.

FloodCitiSense aims at developing an urban pluvial flood early warning service for, but also by citizens and city authorities, building upon the state-of-the-art knowledge, methodologies and smart technologies provided by research units and private companies. FloodCitiSense targets the co-creation of this innovative public service in an urban living lab context with all local actors. This service will reduce the vulnerability of urban areas and citizens to pluvial floods, which occur when heavy rainfall exceeds the capacity of the urban drainage system. Due to their fast onset and localized nature, they cause significant damage to the urban environment and are challenging to manage. Monitoring and management of peak events in cities is typically in the hands of local governmental agencies. Citizens most often just play a passive role as people negatively affected by the flooding, despite the fact that they are often the ‘first responders’ and should therefore be actively involved. The FloodCitiSense project aims at integrating crowdsourced hydrological data, collaboratively monitored by local stakeholders, including citizens, making use of low-cost sensors and web-based technologies, into a flood early warning system. This will enable ‘citizens and cities’ to be better prepared for and better respond to urban pluvial floods. Three European pilot cities are targeted: Brussels – Belgium, Rotterdam – The Netherlands and Birmingham – UK.

A variety of methods are in use for the design of controllers for adjusting canal gate positions to maintain a constant water level immediately upstream from check gates. These methods generally rely on a series of tests on the water level's response to changes in canal gate position or flow, either by simulation or on the canal itself. This paper presents a method for tuning these controllers based on wave celerity through use of the integrator delay zero (IDZ) model. These equations can be used to determine the resonance peak height and resonance frequency. Unsteady-flow canal simulation models are used to show the response of controller design using these theoretical equations with a test case for ASCE Test Canal 1. A novel method is presented for avoiding disturbance amplification by considering the delay times in all canal pools downstream.