Hydrological Knowledge Research Articles

A hydrological knowledge-informed LSTM model for monthly streamflow reconstruction using distributed data: Application to typical rivers across the Tibetan plateau

Long-term streamflow data are essential for water resources planning and management, cascade reservoir scheduling, and understanding the response of water resources to climate change and human activities. Streamflow reconstructions can effectively “fill-in” missing runoff data gaps. However, considering the scarcity of observational monitoring stations and the limitations of distributed hydrological models, the reconstruction of long-term time series of runoff under varying surface and climatic conditions remains a challenge. Here, we propose a hydrological knowledge-informed Long Short-Term Memory (LSTM) model (Hydro-LSTM) for monthly streamflow reconstruction using open-access distributed data. Hydrological knowledge was derived from hydrological governing equations and parameters for each independent water cycle component. The Hydro-LSTM addresses the lack of physical consistency inherent in data-driven models, along with missing observations. The approach was applied to simulate monthly runoff of representative rivers in the Tibetan Plateau (TP) from 1980 to 2018. The results show that streamflow reconstructions for these eight stations yielded favorable levels of performance; trends in dynamic change and the range of runoff in the model training period and test period are consistent with the measured values. Values of NSE, CC, and KGE range between 0.715–0.968, 0.847–0.985, and 0.786–0.969, respectively. The influence of hydrological expertise and distributed data on the model is discussed. The introduction of hydrological knowledge makes the driving elements have hydrological significance, which improves the physical consistency and interpretability of the Hydro-LSTM model. The proposed Hydro-LSTM is expected to (1) achieve accurate and efficient reconstructions of long-term runoff time series using open-access distributed data and limited observations and (2) provide a new perspective for runoff reconstruction and prediction, with promising application prospects.

The history of hydrological studies on the Mekong floodplains – from colonial experiments to computational models

ABSTRACT This paper investigates the interwoven history of hydrological studies and water infrastructure development on the Mekong floodplains. On the basis of an extensive literature review, archival work, and key informant interviews, we unravel the making of an expert-led understanding of the Mekong floodplains – from the detailed reports written by colonial engineers during the French protectorate in the late 19th century to the development of the first computational models, developed in the 1960s on punch-cards and in Fortran. We show how these studies not only reflect the objectives of successive powers and their relationships to local communities but also shaped the landscape and hydrology of the Mekong floodplains and continue to do so through a variety of water infrastructure development projects. This serves as a call to conceive of hydrological knowledge as contingent rather than as a neutral depiction of physical processes that exists independently from the conditions of its production.

Enhancing runoff forecasting through the integration of satellite precipitation data and hydrological knowledge into machine learning models

Enhancing runoff forecasting through the integration of satellite precipitation data and hydrological knowledge into machine learning models

Hybrid hydrological modeling for large alpine basins: a semi-distributed approach

Abstract. Alpine basins are important water sources for human life, and reliable hydrological modeling can enhance the water resource management in alpine basins. Recently, hybrid hydrological models, coupling process-based models and deep learning (DL), have exhibited considerable promise in hydrological simulations. However, a notable limitation of existing hybrid models lies in their failure to incorporate spatial information within the basin and describe alpine hydrological processes, which restricts their applicability in hydrological modeling in large alpine basins. To address this issue, we develop a set of hybrid semi-distributed hydrological models by employing a process-based model as the backbone and utilizing embedded neural networks (ENNs) to parameterize and replace different internal modules. The proposed models are tested on three large alpine basins on the Tibetan Plateau. A climate perturbation method is further used to test the applicability of the hybrid models to analyze the hydrological sensitivities to climate change in large alpine basins. Results indicate that proposed hybrid hydrological models can perform well in predicting runoff processes and simulating runoff component contributions in large alpine basins. The optimal hybrid model with Nash–Sutcliffe efficiencies (NSEs) higher than 0.87 shows comparable performance to state-of-the-art DL models. The hybrid model also exhibits remarkable capability in simulating hydrological processes at ungauged sites within the basin, markedly surpassing traditional distributed models. In addition, the results also show reasonable patterns in the analysis of the hydrological sensitivities to climate change. Overall, this study provides a high-performance tool enriched with explicit hydrological knowledge for hydrological prediction and improves our understanding about the hydrological sensitivities to climate change in large alpine basins.

Integrating hydrological knowledge into deep learning for DEM super-resolution

Deep learning-based super-resolution methods have been successfully applied to digital elevation model (DEM) downscaling studies by designing structures and loss functions of the model. However, little attention has been paid to the design of super-resolution models that can maintain the hydrological characteristics of the DEM, which is important for hydrological studies. This study introduces a super-resolution model that integrates hydrologic knowledge (HKSRCGAN), with the aim to effectively maintain topographic features as well as the hydrologic connectivity of the DEM. The hydrological knowledge derived from surface flow direction and hydrological features are integrated into a deep learning algorithm to guide model training. The 30 m spatial resolution FABDEM is used to demonstrate the utility of the proposed method. Results show that the HKSRCGAN outperforms the bicubic interpolation, SRCNN, SRGAN, SRResNet and TfaSR methods in reducing topographic errors and maintaining hydrologic characteristics. In the test area, the entropy difference analysis shows that the DEM generated by HKSRCGAN is similar to the information contained in the reference DEM. Furthermore, super-resolution models integrating hydrological knowledge are valuable for modeling terrain primarily shaped by gravity and surface water flows. In the future, deep learning-based models integrating hydrologic knowledge are expected to be applied in DEM upscaling to maintain consistent hydrological characteristics.

Improving Discharge Predictions in Ungauged Basins: Harnessing the Power of Disaggregated Data Modeling and Machine Learning

AbstractCurrent machine learning methods for discharge prediction often employ aggregated basin‐wide hydrometeorological data (lumped modeling) for parametric and non‐parametric training. This approach may overlook the spatial heterogeneity of river systems and their impact on discharge patterns. We hypothesize that integrating spatiotemporal hydrologic knowledge into the data modeling process (distributed/disaggregated modeling) can improve the performance of discharge prediction models. To test this hypothesis, we designed experiments comparing the performance of identical Long Short‐Term Memory Recurrent Neural Network (LSTM‐RNN) models forced with either lumped or distributed features. We gather meteorological forcing and static attributes for the Mackenzie basin in Canada‐ a large and unique basin. Importantly, discharge performance is assessed out‐of‐sample with k‐fold replication across gauges. Training LSTMs with disaggregated data significantly improved model accuracy. Specifically, there was a 9.6% increase in the mean Nash‐Sutcliffe Efficiency and a 4.6% increase in the mean Kling‐Gupta Efficiency, indicating a better agreement between predicted and actual observations in terms of mean, variability, and correlation. These experiments and results demonstrate the importance of integrating topologically guided geomorphologic and hydrologic information (distributed modeling) in data‐driven discharge predictions.

A new flow path: eDNA connecting hydrology and biology

AbstractEnvironmental DNA (eDNA) has revolutionized ecological research, particularly for biodiversity assessment in various environments, most notably aquatic media. Environmental DNA analysis allows for non‐invasive and rapid species detection across multiple taxonomic groups within a single sample, making it especially useful for identifying rare or invasive species. Due to dynamic hydrological processes, eDNA samples from running waters may represent biodiversity from broad contributing areas, which is convenient from a biomonitoring perspective but also challenging, as hydrological knowledge is required for meaningful biological interpretation. Hydrologists could also benefit from eDNA to address unsolved questions, particularly concerning water movement through catchments. While naturally occurring abiotic tracers have advanced our understanding of water age distribution in catchments, for example, current geochemical tracers cannot fully elucidate the timing and flow paths of water through landscapes. Conversely, biological tracers, owing to their immense diversity and interactions with the environment, could offer more detailed information on the sources and flow paths of water to the stream. The informational capacity of eDNA as a tracer, however, is determined by the ability to interpret the complex biological heterogeneity at a study site, which arguably requires both biological and hydrological expertise. As eDNA data has become increasingly available as part of biomonitoring campaigns, we argue that accompanying eDNA surveys with hydrological observations could enhance our understanding of both biological and hydrological processes; we identify opportunities, challenges, and needs for further interdisciplinary collaboration; and we highlight eDNA's potential as a bridge between hydrology and biology, which could foster both domains.This article is categorized under: Science of Water > Hydrological Processes Science of Water > Methods Water and Life > Nature of Freshwater Ecosystems

A recipe for why and how to set up and sustain an experimental catchment

AbstractExperimental catchments are fundamental elements in hydrological sciences as they provide key data for putting forward and testing hypotheses, developing theories, constraining models, and making predictions. Significant progress in catchment hydrology stemmed from field measurements but increasing costs and risks associated with field work and the availability of big data based on remote sensing, machine learning, and a plethora of models, as well as observations deriving from previous and current sites, raises questions on whether running an experimental catchment still provides individual and community benefits as in the past. In this commentary, I highlight the advantages of keeping experimental catchments alive and propose a personal 10‐step “recipe” to set up a new experimental catchment and manage and sustain it in the long term. These suggestions can be useful both to young and less young researchers who are open to facing the challenge of measuring processes in the field and are willing to offer the scientific community new experimental evidence for advancing our current knowledge in catchment hydrology.

РАСЧЕТЫ ВЛЕКОМЫХ НАНОСОВ С УЧЕТОМ НАИБОЛЬШИХ РАСХОДОВ ВЗВЕШЕННЫХ НАНОСОВ (НА ПРИМЕРЕ РЕК БОЛЬШОГО КАВКАЗА АЗЕРБАЙДЖАНА)

The article analyzes the flow of entrained sediments and their ratio to the highest expenditure of suspended sediments. The study of entrained sediments in mountainous areas is a more difficult task than in lowland areas. In addition, the weak hydrological knowledge of mountainous areas, as well as the lack of observations on the flow of entrained sediments on small rivers, do not allow for full monitoring of entrained sediments. Therefore, the study and calculation of entrained sediments is of great scientific and practical importance. Rolling particles in the largest flow rates of suspended sediments are considered to be entrained, especially when they move during mudflows. It was revealed that the runoff of the entrained sediments has a sorting character in the removal cone according to the Erie law.

Regional Low Flow Hydrology: Model Development and Evaluation

AbstractLow flows result from the interplay of climatic variability and catchment storage dynamics, but it is unclear which of these variables is more relevant for explaining low flow spatial patterns. Here, we develop a new conceptual model that integrates process‐based hydrological knowledge with statistics and test it for 1,400 Brazilian catchments. Through comparative hydrology, we isolate the low flow generating mechanisms and estimate their components using linear model trees. The model explains 58% of the spatial variance in 7‐day minimum annual flows (Qmin) based on climate and catchment characteristics. The primary Qmin controls depend on the spatial scale of analysis. Catchment characteristics govern Qmin up to the continental scale (107 km2), where their relative importance matches that of climate. At subcontinental scales, catchment characteristics are twice as important as climate in predicting Qmin, suggesting that low flows are governed by the catchment's capacity to attenuate the climatic variability through water storage. Geological properties are the most important catchment characteristics, particularly bedrock type, lithology and topographic slope, determining streamflow recession rates in the dry season. Soil properties, primarily soil class and depth, are half as important as geology. Climate impacts Qmin mainly through mean annual rainfall minus evaporation, representing the potential groundwater recharge, while dry‐season length has the lowest impact. These results hold mainly for highly seasonal and snow‐free climates. Low flow hydrology that combines statistics with process understanding offers a promising framework for understanding regional low flow generating mechanisms and could support other estimation models than that presented here.

The hydraulic network of the pre-Hispanic city of Tiwanaku (Bolivia): New insights from the integration of canal morphology, hydrogeological and palaeoenvironmental data

Water management enabled the development of ancient societies allowing them to ensure agropastoral production and manufacturing activities. In the Andes, near the shore of Lake Titicaca, the city of Tiwanaku (Bolivia) is one of the largest pre-Hispanic urban centres in South America. Abrupt climate changes in the high-altitude Altiplano during the late Holocene likely forced the population to develop water management strategies. So far, knowledge concerning the existence of a water network around the city of Tiwanaku is limited to hypotheses derived from surface and aerial observations. In this study, geoscience techniques (morphology, geophysics, sedimentology and chronostratigraphy) helped to reconstruct the canals' morphology and their flow dynamics, along with their chronology of operation in a context of hydroclimatic change. Two ca. 30 m large canals bypassing the monumental core and supplied by a shallow water table and multiple tributaries, connected the agricultural and the urban areas. The structure and organization of the network testify to an elaborate knowledge of the local hydrology by the former builders of the city. It ensured water supply and flood management in relation to the extreme intra- and inter-annual variability of precipitations in the central Andes. The palaeogeographical and landscape reconstruction demonstrates that canals were set from natural features during the early Late Formative period (200 BCE to 200 CE) during a wet period likely for water resource management needs. During the Tiwanaku state (before 800 CE), the filling of the canal network with soil and sediment suggests a major change in its use, and possibly its partial abandonment, during a major restructuration of the site, in a period of increased regional precipitation.

Wetlands as integral parts of surface water–groundwater interactions in the Athabasca Oil Sands Area: Review and synthesis

Wetlands comprise unique water storage and conveyance mechanisms that maintain landscape integrity under the sub-humid climate in the Athabasca Oil Sands Area. In addition to their internal function, wetlands support a two-way hydrological connection to adjacent uplands and provide water for downstream water courses. Understanding the role of wetlands as integral parts of surface water (SW)–groundwater (GW) exchange can provide insights into the functioning of the hydrological system as a whole and contribute to thoughtful water management strategies and better coordination of monitoring efforts in the areas affected by oil sands (OS) activities. As such, this study summarizes the current state of hydrological knowledge on the role of wetlands in SW–GW interactions based on studies conducted within the Western Boreal Plains. In particular, the role of wetland soils and their properties in SW–GW interactions, the effects of wetlands on landscape hydrological connectivity and watershed runoff, and features of “wetland–aquifer” and “wetland–open waterbody” interactions were reviewed. Given that alterations of SW–GW interactions in wetlands can occur as a result of anthropogenic disturbances, the coordination of GW, SW, and wetland monitoring efforts and targeting areas where increased SW–GW exchange occurs would be beneficial for the economic and logistical efficiency of the OS monitoring network.

Integrating domain knowledge and graph convolutional neural networks to support river network selection

AbstractDeep learning is increasingly being used to improve the intelligence of map generalization. Vector‐based map generalization, utilizing deep learning, is an important avenue for research. However, there are three questions: (1) transforming vector data into a deep learning data paradigm; (2) overcoming the limitation of the number of samples; and (3) determining whether existing knowledge can accelerate deep learning. To address these questions, taking river network selection as an example, this study presents a framework integrating hydrological knowledge into graph convolutional neural networks (GCNNs). This framework consists of the following steps: constructing a dual graph of river networks (DG_RN), extracting domain knowledge as node attributes of DG_RN, developing an architecture of GCNNs for the selection, and designing a fine‐tuning rule to refine the GCNN results. Experiments show that our framework outperforms existing machine learning and traditional feature sorting methods using different datasets and achieves good morphological consistency after the selection. Furthermore, these results indicate that DG_RN meets the data paradigm of graph deep learning, and the framework integrating existing characteristics (i.e., Strahler coding, the number of tributaries, the distance between proximity rivers, and upstream drainage area) mitigates the dependence of GCNNs on plenty of samples and enhance its performance.

Enhancing process-based hydrological models with embedded neural networks: A hybrid approach

Deep learning (DL) models have demonstrated exceptional performance in hydrological modeling; however, they are limited by their inability to output untrained hydrological variables and lack of interpretability compared to process-based hydrological models. We propose a hybrid approach that combines the conceptual EXP-Hydro model with embedded neural networks (ENNs), replacing its internal modules while maintaining adherence to hydrological knowledge. The resulting hybrid model can predict untrained hydrological variables without requiring post-processing or pre-training procedures. We tested 15 hybrid models that replace different internal modules across 569 basins in the contiguous United States using the CAMELS dataset. Additional experiments were conducted to generalize hydrological relationships within ENNs and further use them to improve the EXP-Hydro model's performance. Results show that all hybrid scenarios outperform the ordinary EXP-Hydro model, with an optimal median Nash-Sutcliffe efficiency (NSE) of 0.701 in the evaluation period – comparable to state-of-the-art LSTM and conceptual hydrological model featuring an error-correcting post-processor. Reasonable patterns of runoff and snow-related processes are captured by ENNs in respective hybrid models. We further used the runoff (snow-related) pattern to improve the ordinary EXP-Hydro model with median NSE increasing from 0.496 to 0.567 (raising median NSE from 0.601 to 0.677 in snow-influenced region). Our study highlights the potential for using ENNs in enhancing process-based hydrological models' performance while maintaining interpretability within a novel hybrid framework.

Managing Complex Knowledge in Sustainable Planning: A Semantic-Based Model for Multiagent Water-Related Concepts

The concepts of green infrastructures, nature-based solutions and ecosystem services are today considered an integral part of the broader theme of the urban bioregion, with an intrinsic character of complexity. It is certainly difficult to structure bioregional processes in a balanced and sustainable way, able to keep local energy production and consumption cycles closed. It is a complex issue of knowledge bases, and problems are increased by the participatory dimension of environmental planning. In fact, when rational planning models have failed in the face of prominent individual needs and environmental complexity, a path has emerged towards the inclusion of multiple citizens’ and stakeholders’ knowledge. The cognitive structure of the plans has thus changed from systems of exclusively expert, formal knowledge to systems of diffused, multi-agent knowledge. This has involved richness but also significant problems in understanding and managing knowledge bases. In this complexity, there are some common peculiarities when it comes to socio-environmental systems. A common feature of the reference domains of ecosystem services, nature-based solutions and green infrastructures is the water resource. A management model of hydrological data, which are structurally relevant and cross-sectoral in environmental planning actions, could represent a flagship initiative. The used approach could be conveyed to more complex and extensive areas of the environmental domain in a perspective of sustainable planning. The present paper is part of a research work oriented toward handling complex environmental subjects, such as green infrastructures, nature-based solutions or ecosystem services, with a knowledge modelling approach. This approach is based on semantic extensions, elaborated form the concept of semantic web, to allow shared interpretations of knowledge coming from different languages and scientific domains. It is also based on using applied ontologies, elaborated from the concept of ontology-based classification, to support a structured organization of knowledge contents. The main research objective is therefore to investigate about a knowledge management system with semantic extensions, populated with hydrological knowledge contents, as well as to propose a preliminary functional architecture. A simple ontology of data is extracted, aiming at clarifying and improving inter-domain communication, so as to enhance a common semantic understanding in a complex environmental system.

COMPARISON OF INNOVATIVE TREND ANALYSIS METHODS FOR HYDROMETEOROLOGICAL PARAMETERS IN THE KARASU SUB-BASIN

Türkiye, which has a complex climate structure, is shown among the countries that will be most affected by climate change with the effect of global warming. These effects will differ in different regions due to their topographic structure, location, and orographic characteristics. Trend analyzes are used to determine the direction and magnitude of this variability. In this study, trend analysis was carried out by using hydrometeorological data obtained from streamflow and meteorology stations located in the Karasu Sub-Basin located in the Euphrates-Tigris Basin. Three innovative trend methods, namely the Şen-Innovative Trend Analysis, Onyutha Trend Test, Combination of Wilcoxon Test and Scatter Diagram trend tests, were used together with the classical Mann-Kendall method in the monthly scale analysis of hydrometeorological data of the 1979-2020 period. Both graphical and statistical trend analysis can be done with innovative methods. The results obtained in the study, in which trend analyses were evaluated at the α=0.05 significance level, reveal significant and insignificant decreasing trends in the parameters of mean streamflow, maximum precipitation, total precipitation, mean and minimum relative humidity. Significant and insignificant increasing trends were determined in the maximum, minimum, and mean temperature, maximum relative humidity, and mean wind speed data. The trends obtained in the methods used in general are consistent with each other. The findings of this study could lead to a better knowledge of the region's hydrology and contribute sustainable water management. The trend analysis methods used in the study are thought to be quite helpful in the analysis of hydro-meteorological time series.

Deep transfer learning based on transformer for flood forecasting in data-sparse basins

There exists a substantial disparity in the distribution of streamflow gauge and basin characteristic information, with a majority of flood observations being recorded from a limited number of well-monitored locations. Transferring hydrological knowledge from data-rich to data-sparse basins has been a persistent issue. While artificial intelligence methods, such as Long-Short-Term Memory Neural Networks (LSTMs) have been attempted for simulating across different basins, the problem of gradient vanishing still inevitably lead to difficulties in responding to new basin datasets. A novel solution is presented in the form of the Transfer Learning Framework based on Transformer (TL-Transformer), which can accurately predict flooding in data-sparse basins (targets) by using models from data-rich basins (sources) without requiring extensive basin attributes at the target location. The framework was demonstrated in the middle reaches of the Yellow River, and performance was evaluated using the Nash Sutcliffe efficiency coefficient, root mean square error, and bias. The results show that TL-Transformer outperforms other models, including TOPMODEL, MLP, TL-MLP, LSTM, TL-LSTM and Transformer in all target basin stations. Compared with those models that without transfer learning, TL-Transformer showed significantly improved performance, where NSE increased by 0.2 and reached above 0.75, RMSE and bias were also controlled within 60 and 20, respectively. Furthermore, pre-training on basins with hydrological similarities increases the benefits of Transfer Learning, and we explained this response phenomenon through the topographic index. These results suggest that deep learning can tap into the commonalities in hydrological data across basins to improve the accuracy of flood forecast applications in areas with limited observations.

Hydroecological approach for an experimental well field in the Yucatan karst

The experimental well field of FIUADY is a system of 50 m and up to 75 m deep wells. It was built with the purpose of confronting and consolidating the hydrological knowledge of groundwater in the karst plain of northern Yucatan. In this context, the objective of this work is to document the historical behavior of some variables of the physical-chemical and biological environment of the aquifer to sketch models of the habitat of the epikarst microbiota in the northern plain of the Yucatan peninsula. Hydrogeological conformation was documented through drilling debris analysis and underwater video recordings in the well. Measurements of temperature, electrical conductivity, pH and dissolved oxygen were made in October, November, January, February, March and April of different years. For statistical analyses, data were grouped into two periods: recharge (October and November) and discharge (January-April). The results include a schematic hydrogeological profile and statistical analyses of the variables. The minimum and maximum values observed are: temperature °C (26.64, 29.87), electrical conductivity µS/cm (465,46800), pH (6.14, 8.20) and dissolved oxygen mg/L (0.01, 7. 93). It is concluded that: a) in an area of a few square meters there are important variations in the hydrogeological characteristics; b) the hydrogeological behavior of the wells has to do with karstic horizons; their dimensions, connectivity, distribution, density and the way they influence different hydrological stresses; finally c) the presence of crustaceans in the wells and "anomalies" in the concentration of oxygen may have an explanation in biogeochemical processes of dark ecosystems.

An interpretable model for bridge scour risk assessment using explainable artificial intelligence and engineers’ expertise

A machine learning (ML) model would be difficult to apply in practice without knowing how the prediction is made. To address this issue, this paper uses XAI and engineers’ expertise to interpret an ML model for bridge scour risk prediction. By using data from the French National Railway Company (SNCF), an extreme gradient boosting (XGBoost) algorithm-based ML model was constructed at first. Later, XAI approaches were employed to have global and local explanations as well as explicit expressions for ML model interpretation. Meanwhile, a group of engineers from SNCF were asked to rank the input parameters based on their engineering judgment. In the end, feature importance obtained from XAI approaches and engineers’ survey was compared. It was found that for both XAI and engineers’ interpretations, observation of local scour around the bridge foundation is the most important feature for decision-making. The differences between XAI interpretations and human expertise emphasize the importance of knowledge in hydrology and hydromorphology for scour risk assessment, since currently engineers make decisions primarily based on observed damages (e.g., scour hole, crack). The results of this paper could make the ML model trustworthy by understanding how the prediction is made and provide valuable guidance for improving current inspection procedures.

A Weak-Coupling Flow-Power Forecasting Method for Small Hydropower Station Group

Due to the need for rural revitalization and renewable energy utilization, a large quantity of small hydropower stations is emerging, with weak-coupling flow-power features. However, a weak spatial coupling exists between the distribution of small hydropower station groups (SHSGs) and gaging stations since the small hydropower stations are usually located in remote areas lacking hydrographic facilities. That may cause weak or no coupling between the hydroregime and the power output of small hydropower plants in the target basin, thus hindering accurate power forecasting. To meet the need for short-term power generation prediction for SHSGs in intensive management areas, we propose a data-driven power-forecasting model which can mine the correlation information of weakly coupled basins while transferring hydrological knowledge to uncoupled basins. First, to make the task data domains before and after migration more similar, a similar watershed matching algorithm based on the nonlinear dimensionality reduction algorithm (Isomap) and the k -means++ algorithm is proposed; then a short-term interpretable runoff prediction model is pretrained, and features are extracted in the source basin using the temporal fusion transformer (TFT) network. After that, a heuristic ensemble fine-tuning model based on the k -fold cross-validation fine-tuning method and heuristic ensemble algorithm is proposed to transfer the public knowledge of the source basin to the uncoupled basin. Then, a TFT network is used to mine the weak-coupling relationship between the hydrological regime and the output power of an SHSG. Finally, the validity of the model is verified with an example from a European region. After considering the weakly coupled flow-power characteristics, the mean absolute percentage error (MAPE) of three SHSGs’ power prediction by the proposed method is on average 34.8% lower than that of the method without considering the hydrological information.