Integration of deep learning and improved multi-objective algorithm to optimize reservoir operation for balancing human and downstream ecological needs

Dam (reservoir)-induced alterations of flow and water temperature regimes can threaten downstream fish habitats and native aquatic ecosystems. Alleviating the negative environmental impacts of dam-reservoir and balancing the multiple purposes of reservoir operation have attracted wide attention. While previous studies have incorporated ecological flow requirements in reservoir operation strategies, a comprehensive analysis of trade-offs among hydropower benefits, ecological flow, and ecological water temperature demands is lacking. Hence, this study develops a multi-objective ecological scheduling model, considering total power generation, ecological flow guarantee index, and ecological water temperature guarantee index simultaneously. The model is based on an integrated multi-objective simulation-optimization (MOSO) framework which is applied to Three Gorges Reservoir. To that end, first, a hybrid long short-term memory and one-dimensional convolutional neural network (LSTM_1DCNN) model is utilized to simulate the dam discharge temperature. Then, an improved epsilon multi-objective ant colony optimization for continuous domain algorithm (ε-MOACOR) is proposed to investigate the trade-offs among the competing objectives. Results show that LSTM _1DCNN outperforms other competing models in predicting dam discharge temperature. The conflicts among economic and ecological objectives are often prominent. The proposed ε-MOACOR has potential in resolving such conflicts and has high efficiency in solving multi-objective benchmark tests as well as reservoir optimization problem. More realistic and pragmatic Pareto-optimal solutions for typical dry, normal and wet years can be generated by the MOSO framework. The ecological water temperature guarantee index objective, which should be considered in reservoir operation, can be improved as inflow discharge increases or the temporal distribution of dam discharge volume becomes more uneven.

Analyzing river disruption factors and ecological flow in China's Liu River Basin amid environmental changes

Water resources variability and availability in a basin affect river flows and sustain river ecosystems. Climate change and human activities disrupt runoff sequences, causing water environmental issues like river channel interruptions. Therefore, determining ecological flow in changing environments is challenging in hydrological research. Based on an analysis of long-term changes in hydrological and meteorological variables and interruption conditions in the semi-arid Liu River Basin (LRB), this study summarizes the controlling factors of river interruption at different temporal and spatial scales and proposes a framework to determine ecological flow under changing environments. Hydrological model and the monthly optimal probability distribution were used to determine the optimal ecological runoff of LRB. The results showed that from 1956 to 2017, precipitation and potential evapotranspiration in the basin showed no significant decreasing trend, but the streamflow significantly decreased, and the downstream interruption worsened, with an average annual interruption duration of 194 days at Xinmin Station from 1988 to 2017. The controlling factors of river interruption are as follows: (1) soil and water conservation measures in the upstream significantly reduce the runoff capacity; (2) the operation mode of the controlling reservoir in the middle reaches changes from "all-year discharge" to "winter storage and spring release" to "combined storage and supply," severing the hydraulic connection between upstream and downstream; and (3) siltation in the downstream river channel coupled with over-extraction of groundwater increases the seepage capacity of the river. The monthly ecological flow of Naodehai Reservoir was determined by considering the monthly seepage losses after reconstructing the natural runoff using the SWAT model and determining the optimal probability distribution function for monthly runoff. The findings are important for downstream LRB ecological restoration and for determining the ecological flow of other river basins in changing environments.

Evolution and attribution of ecological flow in the Xiangjiang River basin since 1961

Climate change and human activities have greatly altered the ecological flow of rivers, and the conflict between human water use and natural water demand is becoming more and more prominent. Using two ecological flow indicators (ecodeficit and ecosurplus), this study focuses on assessing the characteristics of ecological flow changes at multiple time scales and introduces the Long Short-Term Memory model to construct a meteorological streamflow model for the Xiangjiang River (XJR) basin, using a separation framework to quantify the effects of human disturbance and climate change on ecological flow at multiple time scales. In addition, the fluvial biodiversity Shannon Index (SI) was used to assess the response processes of riverine ecosystems under changing conditions. The results show that the increase of XJR flow is larger (11%) after 1991, the increase in precipitation and potential evapotranspiration in the basin is 5.60%, and the decrease is 3.09%, respectively, and there are obvious cycles of all three on annual and seasonal scales. The annual ecosurplus increased, and the annual ecodeficit decreased after the hydrological variation; on the seasonal scale, the ecodeficit decreased significantly in summer and autumn, and the ecosurplus increased substantially in winter. Climatic factors were the main drivers of the increased frequency and magnitude of annual, summer, and fall high flows (91%, 94%, and 65% contributions, respectively), while urbanization expansion and reservoir diversions drove the increase in spring ecodeficit. Changes in river flow maintained the ecosurplus at a low level after 2002, further causing a decrease in river biodiversity, and the annual and summer ecosurplus were highly correlated with SI indicators (0.824 and 0.711, respectively). Our study contributes to the development of effective ecological flow regulation policies for the XJR basin.

Digitalization and real-time control to mitigate environmental impacts along rivers: Focus on artificial barriers, hydropower systems and European priorities

Hydropower globally represents the main source of renewable energy, and provides several benefits, e.g., water storage and flexibility; on the other hand, it may cause significant impacts on the environment. Hence sustainable hydropower needs to achieve a balance between electricity generation, impacts on ecosystems and benefits on society, supporting the achievement of the Green Deal targets. The implementation of digital, information, communication and control (DICC) technologies is emerging as an effective strategy to support such a trade-off, especially in the European Union (EU), fostering both the green and the digital transitions. In this study, we show how DICC can foster the environmental integration of hydropower into the Earth spheres, with focus on the hydrosphere (e.g., on water quality and quantity, hydropeaking mitigation, environmental flow control), biosphere (e.g., improvement of riparian vegetation, fish habitat and migration), atmosphere (reduction of methane emissions and evaporation from reservoirs), lithosphere (better sediment management, reduction of seepages), and on the anthroposphere (e.g., reduction of pollution associated to combined sewer overflows, chemicals, plastics and microplastics). With reference to the abovementioned Earth spheres, the main DICC applications, case studies, challenges, Technology Readiness Level (TRL), benefits and limitations, and transversal benefits for energy generation and predictive Operation and Maintenance (O&M), are discussed. The priorities for the European Union are highlighted. Although the paper focuses primarly on hydropower, analogous considerations are valid for any artificial barrier, water reservoir and civil structure which interferes with freshwater systems.

Ecological flow in southern Europe: Status and trends in non-perennial rivers

The concept of environmental flows (E-Flows) describes the streamflow that is necessary to maintain river ecosystems. Although a large number of methods have been developed, a delay was recorded in implementing E-Flows in non-perennial rivers. The general aim of the paper was to analyse the criticalities and the current state of implementation of the E-Flows in non-perennial rivers of southern Europe. The specific objectives were to analyse (i) the European Union (EU) and national legislation on E-Flows, and (ii) the methodologies currently adopted for setting E-Flows in non-perennial rivers in the EU Member States (MSs) of the Mediterranean Region (Spain, Greece, Italy, Portugal, France, Cyprus, and Malta). From the analysis of national legislations, it is possible to acknowledge a step forward toward regulatory unification at the European level, on the subject of E-Flows and more generally toward the protection of aquatic ecosystems. The definition of E-Flows, for most countries, has abandoned the idea of a regime of constant and minimal flow, but it recognizes the importance of the biological, and chemical-physical aspects connected to it. From the analysis of the E-Flows implementation through the review of the case studies, one can surmise that in non-perennial rivers the E-Flows science is still an emerging discipline. The limited availability of hydrological, hydraulic, and biological data as well as the restricted economic resources allocated for managing non-perennial rivers are the main causes of the delay in the E-Flows implementation in MSs. The results of the present study may contribute in setting an E-Flow regime in non-perennial rivers.

River ecological flow early warning forecasting using baseflow separation and machine learning in the Jiaojiang River Basin, Southeast China

Ecological flow early warning is crucial for the rational management of watershed water resources. However, determining of accurate ecological flow threshold and choosing the appropriate forecasting model are challenging tasks. In this study, we initially developed a baseflow separation and Tennant method-based technique for calculating ecological river flow. Then an ecological flow early warning model was created using the machine learning technique based on distributed gradient enhancement framework (LightGBM). Finally, we utilized the framework of Shapley Additive Planning (SHAP) to explain how various hydrometeorological factors affect the variations in ecological flow conditions. The Jiaojiang River basin in southeast China is selected as the study area, and the hydrological stations in upstream of Baizhiao (BZA) and Shaduan (SD) are chosen for key analysis. The results of these applications show that the monthly baseflow frequency of the river ecological flow conditions of the two stations in the dry season is 20 % (7.49 m³/s) and 30 % (4.79 m³/s), respectively. The ecological flow level early warning forecasting accuracy is close to 90 % in the BZA and SD stations during dry and wet seasons. The variations of ecological flow are most affected by evaporation and base flow index. The results of this study can serve as a strong basis for the effective allocation and utilization of locally available water resources.

Habitat alteration assessment for the management of environmental flows in regulated basins

The management of environmental flows is of paramount importance in regulated water resources systems to preserve river ecosystems. This work proposes a methodology to assess habitat alteration in river basins altered by management activities. The methodology is based on the joint application of a basin management model (SIMGES, AQUATOOL) and a model to estimate habitat time series (CAUDECO). CAUDECO is based on the weighted useable areas of the species in their different vital stages that, in turn, depend on the flows in each river stretch and the biological periods of the species. The final output is an indicator of habitat alteration, which is defined ad hoc for this work to relate the habitat suitability under regulated and natural regimes. The methodology was applied to a case study in north-western Spain: the Órbigo River basin. The results in the current management scenario highlight that the ecological flows improve the habitat suitability of several species with respect to natural regime conditions. For instance, the mean values of the habitat time series in the Órbigo River for the brown trout and bermejuela under regulated conditions are 69.6% and 88%; whereas in natural regime they are equal to 55.1% and 72.9%, respectively. Based on these results, eight additional scenarios of ecological flows were tested and their effects on both habitat alteration and water demand reliability were quantified and discussed. It was found that increases in the ecological flows up to 30% do not affect the reliability of water demands and reduce habitat alteration (i.e., lead to values of the habitat alteration indicator closer to 1) for all species present in the river basin. These results highlight that the methodology and indicator of habitat alteration proposed in this paper are useful to support the management of regulated river basins, since they allow assessing the implications of ecological flows on both habitat suitability and reliability of water demands.

Analysis of the trade-off between hydroelectricity generation and ecological protection from the perspective of eco-efficiency in Southwest China

Driven by the global net-zero carbon emission goal, even though the impact of hydropower on river ecosystems cannot be ignored, hydropower scale and intensity will be expanded in Southwest China (SC). Therefore, the trade-off between hydroelectricity generation and ecological protection remains an issue requiring urgent attention at the moment. This paper proposes an eco-efficiency (EE) indicator system of hydropower adopting the water consumption of hydropower product (PWC), labor, and capital as inputs and the power generation, ecological flow deviation (EFD) as outputs and then explores the factors influencing the EE value of hydropower in SC. The results indicate that (1) The EE incorporates the impact of each plant on fish, provides decision support for hydropower development planning and serves as the foundation for eco-dispatch operations. (2) Hydropower generation affects fish reproduction in SC, and the EE value of the Wu River is relatively low. (3) The scale of power generation and degree of fish protection are two significant factors that can increase the EE value of hydropower. To compensate for plant inadequacies in these two aspects, equivalent changes in hydropower planning and eco-dispatch operations should be implemented.

E-flows to reduce the hydropeaking impacts on the Iberian barbel (Luciobarbus bocagei) habitat. An effectiveness assessment based on the COSH Tool application

Hydropower plant (HPP) operations, in response to variations in market energy demand and electricity production, can generate rapid and frequent fluctuations of discharge in rivers downstream. This phenomenon, termed hydropeaking, may negatively impact fish populations. The present study aims to investigate the effects of hydropeaking on the Iberian barbel (Luciobarbus bocagei) habitat conditions. A two-dimensional (2D) model was used to obtain the habitat suitability downstream of a HPP. The influence of the ecological flow (E-flow) regime on the habitat conditions and flow fluctuations owing to hydropeaking was assessed. COSH-Tool was applied to the sub-daily flow series to quantify and characterize the rapid fluctuations (with and without an E-flow regime) with the purpose of assessing the impacts on fish habitat. The monthly distribution of peaking events showed a marked seasonal pattern associated with the Mediterranean climate, with most of the rapid fluctuations concentrated during the wet season. A peaking event occurred within three days of the low flow period. Approximately 80% of the 10-year time series returned a zero value of discharge (no power production). The median of the rates of stage (water level change during an increase or decrease of flow divided by the time of that change) resulted in 30.7 and 28.3 cm/h when the E-flow regime was not considered, and the rate of change was 26.3 and 22.4 cm/h when the E-flow regime was considered respectively for rapid increases and decreases. The flow ratio (peak flow divided by base flow) obtained for the E-flow regime was 334.3. Results showed that the hydrologic parameters associated with hydropeaking are attenuated with the E-flow regime. In certain cases, the E-flow regime should be regarded as an alternative mitigation measure for rivers subjected to hydropeaking.

Water replenishment for ecological flow with an improved water resources allocation model

With rapid urbanization, there will be more conflict between human systems and the river ecological system, and therefore, ecological operations, practices and research must involve the ecological water replenishment of entire river basins with new modeling tools. In this study, based on a water resource allocation and simulation model (WAS), we establish an ecological flow-oriented water resource allocation and simulation framework (E-WAS) by comprehensively considering both ecological flow constraints and ecological flow targets. To control multiple types of water sources and dynamically allocate water resources to replenish ecological water in the river, virtual reservoirs and ecological units are added to the model network. With new water balance equations for virtual reservoirs and ecological units, the E-WAS can simulate the ecological replenishment process in a river basin and can provide a recommended water replenishment scheme that considers optimization principles. The E-WAS was applied in the Pingshan River Basin, Shenzhen, China. Fourteen ecological units and 38 water supply nodes are considered in the model. A water replenishment scheme that used water from 6 reservoirs and reclaimed water from 5 water sewage plants was selected. This scheme significantly increased the satisfactory degree of ecological water demand and efficiently supported the formulation of a control scheme for the water environment of a basin. The E-WAS framework is similar to model plug-ins but helps to avoid the large workload that is required for model redevelopment and can expand the functions of core models relatively quickly.

Comparison of environmental flow assessment methods with a case study on a runoff river-type hydropower plant using hydrological methods

This paper focuses on the environmental flow assessment (EFA) methods that maintain the river ecosystem and its integrity for hydropower plants (HPP) with their implementations on a run-off river type HPP. EFA is a crucial phenomenon in terms of electricity production and sustaining river integrity simultaneously. The novelty of this study is that it consists both a comparison of widely used preferred EFA methods and a detailed investigation of the river with pre and post-dam flow regimes. The research shows that by expanding the content and scope of the methods, their relative reliabilities increase. However, this situation requires much more expert, money, and time. Apart from most of the relevant literature, pre and post-dam situations are investigated with a flow duration curve (FDC). It is concluded that the dramatic difference between the flow characteristics of pre and post-dam situations affects long-term aquatic life. Furthermore, a case study is conducted using the selected hydrological flow assessment methods, Tennant and Tessman methods, and comparisons are made. The calculated flows are compared with monthly average flow values before dam construction, projected environmental flow data, and the current situation. Accordingly, Tennant's "good classification" is proposed to determine the environmental flow (EF) for the considered case study.

Investigating the impacts of cascade hydropower development on the natural flow regime in the Yangtze River, China

The Yangtze River is one of the largest and most important rivers in the world. Over the past several decades, the flow regime of the Yangtze River has been altered by human activities, particularly dam construction. Hydrological regimes will be further influenced due to more dams that have been planned and are being built in the upper reach of the Yangtze River (URYR). In this context, to assess the impacts of cascade dam development on the natural flows, four different scenarios of the reservoirs' combination are simulated with a hydrological model (the Soil and Water Assessment Tool) in the URYR. Flow regime changes were investigated using the eco-flow metrics and minimum/optimal ecological flow with the simulated daily river flows. The results indicate that eco-surplus in low flows and eco-deficit in high flows greatly increases due to reservoir operations when more reservoirs are put into service. The minimum ecological flow and the optimal ecological flow cannot be guaranteed from September to November, which is a crucial time for fish spawning. To maintain the natural regime while meeting the requirements for the river ecosystem, we propose that the lower and satisfactory operation limits are 11,680m³/s and 7235m³/s and 16,300m³/s and 9130m³/s, respectively. Optimizing cascade reservoir operational rules is needed to achieve a better balance between ecological and socio-economic demands in the Yangtze River Basin.