High Flow Events Research Articles

Fungicides in English Rivers: Widening the Understanding of the Presence, Co-Occurrence and Implications for Risk Assessment

Fungicides are commonly found in freshwater; however, the understanding of their wider presence, co-occurrence, and potential risk remains limited. This study examined English national datasets to highlight knowledge gaps and identify improvements to monitoring and risk assessment. The analysis found that at least one fungicide was present in 91% of samples collected from English rivers over a 5-year period, with four fungicides detected at rates exceeding 50%. Co-occurrence occurs widely, with up to nine different fungicides detected within the same sample and four detected the most frequently, raising concerns for synergistic interactions. The semi-quantitative nature of much of the available data precludes a clear determination of the potential risk of detrimental effects on aquatic biota. Fully quantitative analysis is required, and ecotoxicity-based water quality standards need to be agreed upon. The monthly sampling regime reflected in the national datasets will infrequently capture high flow events and so is unlikely to fully represent fungicides transported to rivers via rainfall-driven processes. Several information gaps exist, including the risk posed by fungicides in sewage sludge applied to land and the extent to which fungicides in the aquatic and terrestrial environments contribute to antifungal resistance. Improvements in spatial and temporal information on fungicide use are needed.

Enhanced streamflow forecasting using hybrid modelling integrating glacio-hydrological outputs, deep learning and wavelet transformation

Understanding snow and ice melt dynamics is vital for flood risk assessment and effective water resource management in populated river basins sourced in inaccessible high-mountains. This study provides an AI-enabled hybrid approach integrating glacio-hydrological model outputs (GSM-SOCONT), with different machine learning and deep learning techniques framed as alternative ‘computational scenarios, leveraging both physical processes and data-driven insights for enhanced predictive capabilities. The standalone deep learning model (CNN-LSTM), relying solely on meteorological data, outperformed its counterpart machine learning and glacio-hydrological model equivalents. Hybrid models (CNN-LSTM1 to CNN-LSTM15) were trained using meteorological data augmented with glacio-hydrological model outputs representing ice and snow-melt contributions to streamflow. The hybrid model (CNN-LSTM14), using only glacier-derived features, performed best with high NSE (0.86), KGE (0.80), and R (0.93) values during calibration, and the highest NSE (0.83), KGE (0.88), R (0.91), and lowest RMSE (892) and MAE (544) during validation. Finally, a multi-scale analysis using different feature permutations was explored using wavelet transformation theory, integrating these into the final hybrid model (CNN-LSTM19), which significantly enhances predictive accuracy, particularly for high-flow events, as evidenced by improved NSE (from 0.83 to 0.97) and reduced RMSE (from 892 to 442) during validation. The comparative analysis illustrates how AI-enhanced hydrological models improve the accuracy of runoff forecasting and provide more reliable and actionable insights for managing water resources and mitigating flood risks - despite the paucity of direct measurements.

Individual movement behaviour and habitat use of a small-sized cypriniform (Telestes muticellus) in a mountain stream

Knowledge about the biology and ecology of species is fundamental for their management and conservation. Despite this, many fish species and life stages are understudied, and there is a great need for research efforts to understand their ecology. Italian riffle dace (Telestes muticellus; order Cypriniformes) is a small-sized (< 15 cm) stream fish native to the Italian peninsula. There is a scarcity of research on its ecology and behaviour. In this study, we explored the movement ecology of Telestes muticellus in a Mediterranean mountain stream in Northern Italy using passive integrated transponder (PIT) telemetry. Over 15 months, 267 fish were located 2–27 times. Most fish remained stationary, while a few roamed over several hundreds of meters. Fish covered a larger linear range during spring and autumn than during other seasons. T. muticellus showed a strong preference for pools, and this preference was strongest during summer. We observed no differences in habitat use and movements between day and night, and fish size had no major effect. Within pools, many T. muticellus displayed remarkably small home ranges (median 8 m2). Fish increased their linear ranges over a period of flood events, indicating that high-flow events may be important for the downstream and upstream dispersal of T. muticellus in small mountain streams.

Source-tracing of industrial and municipal wastewater effluent in river water via fluorescence fingerprinting.

Fluorescence fingerprinting is a technique to uniquely characterize water samples based on their distinct composition of dissolved organic matter (DOM) measured via 3D fluorescence spectroscopy. It is an effective tool for monitoring the chemical composition of various water systems. This study examines a river affected by several municipal and industrial wastewater treatment plant (WWTP) effluents and aims to source-tracing them via fluorescence fingerprints based on parallel factor analysis (PARAFAC) components. Additional principal component analysis (PCA) clusters the WWTP effluents according to similarity. The results yield seven PARAFAC components characterizing the WWTP effluents. Considering the ratios among the components, these distinct fluorescence fingerprints are attributable to the studied industrial sectors: leather industry, meat processing, electronics industry, and municipal wastewater treatment. Furthermore, the fluorescence signal of the receiving river is examined by PCA and assessment of flow-weighted fluorescence intensities for source-tracing the fingerprints of the WWTP effluents. An analysis of the contribution of each WWTP effluent shows that during low flow, the fluorescence signal in the river is dominated by WWTP emissions. In contrast, during high flow events, the impact of WWTP emissions is masked by diffuse emissions. The techniques presented in this study have the potential to define generalizable fluorescence fingerprints for WWTP effluents of various industrial sectors and source-trace them in the receiving river. This approach represents a step closer to implementing complex fluorescence monitoring tools in rivers, tracing the impact of municipal and industrial WWTP effluents on riverine OM.

Decentralized Satellite Constellation Replanning for Event Observation

Satellite observation planning is an active field of research that aims to improve the quantity and utility of observations by agile or taskable satellites. Most of the existing work focuses on observing static ground points with constant rewards, which is not sufficient to capture dynamic events on Earth’s surface. We introduce in this work a decentralized replanning method suitable for the observation of time-varying events by a constellation of homogeneous or heterogeneous satellites and compare it to an algorithm without replanning. We perform this comparison on a generalized scenario with varying parameters such as event duration and number of satellites. We also examine several realistic event scenarios, including lightning storms, fires, and high-flow events in rivers. We show that replanning outperforms no replanning in observing and re-observing events, with a median of 17% improvement in event observations. However, the magnitude of the improvement depends strongly on the event and constellation parameters, such as event duration and number of planes. A sensitivity analysis shows that replanning is most beneficial compared to no replanning in terms of generating more re-observations of events when there are more satellites per plane and when event durations are several hours. Ultimately, the proposed replanning strategies can greatly reduce our response time to—and increase our spatiotemporal sampling of—short-lived events and Earth system processes.

Ensemble Methods for Parameter Estimation of WRF‐Hydro

AbstractThe WRF‐Hydro hydrological model has been used in many applications in the past with some level of history matching in the majority of these studies. In this study, we use the iterative Ensemble Smoother (iES), a powerful parameter estimation methodology implemented in the open‐source PEST++ software. The iES provides an ensemble solution with an uncertainty bound instead of a single best estimate which has been the common approach in the previous WRF‐Hydro studies. We discuss the importance of accounting for observation noise which results in a wider spread in the model solution. We investigate the impact of constructing objective functions by differentially weighting the observations to tune the model response toward model outputs appropriate for a specific application. Results confirm the necessity of differentially weighting the observations before calculation of the objective function as the optimization algorithm struggles with calculating parameter updates with uniform weighting. We also show that we achieve better model performance in terms of verification metrics with higher emphasis on the high flow events, when the objective function is tuned toward an application where the extreme events are of importance. We then investigate the impact of estimating more parameters, in particular we estimate a larger number of snow parameters. Results show a large improvement in the model performance. In summary, our study demonstrates the efficacy of employing iES alongside differential weighting of observations, highlighting its potential to enhance hydrological model parameter estimation.

Compositional changes of dissolved organic matter during high flow events in headwater catchments along a gradient of climate and land use

Compositional changes of dissolved organic matter during high flow events in headwater catchments along a gradient of climate and land use

Spatio-temporal characteristics of heavy precipitation events observed over the last decade on the eastern French Mediterranean coastal area

Study regioneastern part of the French Mediterranean coastal area. Study focusThis work focuses on the heavy precipitation events that have affected the eastern part of the French Mediterranean coastal area over the last decade and the river discharges associated with these events. The aim is to make a throughout analysis of the spatio-temporal characteristics of heavy precipitation events, and to evaluate whether a high flow event is associated with them when looking at river discharges on affected catchments. New hydrological insights for the regionBased on radar-based precipitation grids, 158 heavy precipitation events (HPEs) affected the study area over the period 2007–2020. In addition, 65 % of HPEs were associated with a high flow event (HFE) on one or more gauged catchments. Results show that HPEs were more frequent during the beginning of summer and autumn. A large portion of autumn and winter HPEs were associated with a HFE. Looking at the spatio-temporal characteristics of the HPEs, their mean duration was 20 hours, with 42 % of the events lasting less than 6 hours. Some common characteristics among the HPEs that caused HFEs were identified: all HPEs lasting more than 30 hours and all HPEs with catchment precipitation accumulation above 150 mm were associated with a HFE.

New objective functions for streamflow calibrations to specific model applications

Most hydrological models require a calibration process, performed usually using objective functions that measure the differences between observed and simulated data. Objective functions are typically based on statistical metrics, such as the mean squared error (MSE), which penalizes extreme values in statistics, or mean absolute error (MAE), which assigns equal weight to each measure. Although the MSE is effective in capturing model prediction bias or variability, the calibration results with MSE-based objective functions tend to focus on high flow events at the expense of low flow errors. As different objective functions may emphasize different model response aspects, an appropriate objective function is critical to successful model calibration for model application suitability to a given task. The primary aim of this study is not to directly compare the MSE and MAE to determine which is more relevant to model performance. Instead, as an extended formulation for the Kling–Gupta efficiency (KGE), the new objective functions were designed to incorporate performance metrics based on both the MSE and MAE to evaluate model performance more comprehensively across different flow regimes. The case study has investigated the influence of the proposed objective functions on long-term daily streamflow simulations from a land surface model (LSM) over four study watersheds in the Republic of Korea. The proposed objective functions can help simulate streamflow for the specific purpose of model applications through trade-offs between the MSE- and MAE-based variability metrics in the constituent components. The proposed calibration method allows for a more balanced consideration of various flow regime aspects, compared with the results obtained using traditional objective functions.

Riverine 129I dynamics during high-flow events on the Abukuma River in Fukushima

This study presents the riverine 129I concentrations and fluxes during high-flow events. The river water samples obtained by a previous study were subjected to 129I analyses. River water samples were collected at the midstream of the Abukuma River for five and seven times during high-flow events in July 2018 and October 2018, respectively. Suspended solids and filtered water samples were measured for 129I/127I ratios using an accelerator mass spectrometer system and for 127I concentrations using ICP-MS. Aggregated mean values of dissolved 129I concentration and 129I concentrations in suspended solids were 0.11 μBq/L (n = 12) and 0.60 mBq/kg (n = 12), respectively. Corresponding values of 129I/127I ratios were in 2.2 × 10−9 (n = 12) and 3.7 × 10−9 (n = 12), respectively. These concentrations and ratios were comparable to those at the background level before the Fukushima Dai-ichi nuclear power plant accident. Positive correlations with dissolved 137Cs and Cl− concentrations suggested that the dissolved 129I concentration decreased due to dilution of the river water during the events. A positive correlation with total carbon content suggested that organic matter contents determine 129I concentrations in suspended solids. The total 129I fluxes during JUL18 and OCT18 were 9.9 × 103 and 2.2 × 104 Bq, respectively. Although dissolved 129I was predominant under low-flow conditions, the particulate 129I flux increased by one or two orders of magnitude during the peak water discharge phases. These results underline the importance of particulate 129I dynamics during high-flow events for quantitative evaluation of the 129I cycle.

Climate Change and the Ob River: A Reassessment of Major and Trace Element Fluxes to the Arctic Ocean

Over the past few decades, climate warming has driven alterations in both the discharge volume and biogeochemical composition of Arctic riverine fluxes. This study investigated the content of macro- and microelements in the lower reaches of the Ob River (western Siberia). Seasonal sampling was performed over a four-year period (2020–2023) during the main hydrological seasons (winter low water, spring-summer floods, and early fall low water) at three river stations. The results revealed significant seasonal variations in the elemental content of the Ob River water associated with changes in catchment inputs, physical and chemical conditions of the aquatic environment, and the amount and composition of incoming suspended sediment. During high water flow events in the Ob River, the concentration of suspended solids increased substantially. During the winter period when the Ob River was ice-covered, a two- to three-fold rise was observed in the concentration of Na, Mg, Ca, K, Si, and Mn. Having accounted for these seasonal variations in water chemistry, we were able to refine our estimates of elemental export to the Arctic Ocean. Compared to estimates from previous studies, we observed 2.3-fold higher dissolved loads of Mn, and the dissolved loads were higher by 2.1-fold for Zn, 1.6-fold for Fe, and 1.4-fold for Pb. The observed rise in elemental export is likely attributable to a confluence of factors, including permafrost thaw, enhanced water inflow from wetland catchments, and intensifying snowfall leading to increased flood runoff.

Streamflow in the United States: Characteristics, trends, regime shifts, and extremes

Long-term streamflow observations contain essential information for understanding hydrological changes and managing water resources. A continental-scale dataset or analysis of temporal streamflow change is still lacking across hydrologic gauges in the Conterminous United States (CONUS). Here, we compiled 70 years of streamflow records from 1951 to 2021 at ~ 8000 hydrologic stations across the CONUS and characterized temporal trends, regime shifts, and extreme events using a Bayesian time series analysis algorithm. We found that the occurrences of sudden streamflow changes (e.g., regime shifts and extreme events) have been increasing with time across the CONUS. In addition, we derived 181 streamflow indicators that are valuable for hydrological and biological applications, such as the duration and frequency of high or low streamflow events. The Mississippi River Basin, especially the middle and lower parts, was a hot spot of high-frequency high-flow events. Overall, we anticipate the dataset generated here offers valuable information for understanding and quantifying changes in water resources across the CONUS.

Wastewater discharges and urban land cover dominate urban hydrology signals across England and Wales

Urbanisation is an important driver of changes in streamflow. These changes are not uniform across catchments due to the diverse nature of water sources, storage, and pathways in urban river systems. While land cover data are typically used in urban hydrology analyses, other characteristics of urban systems (such as water management practices) are poorly quantified which means that urbanisation impacts on streamflow are often difficult to detect and quantify. Here, we assess urban impacts on streamflow dynamics for 711 catchments across England and Wales. We use the CAMELS-GB dataset, which is a large-sample hydrology dataset containing hydro-meteorological timeseries and catchment attributes characterising climate, geology, water management practices and land cover. We quantify urban impacts on a wide range of streamflow dynamics (flow magnitudes, variability, frequency, and duration) using random forest models. We demonstrate that wastewater discharges from sewage treatment plants and urban land cover dominate urban hydrology signals across England and Wales. Wastewater discharges increase low flows and reduce flashiness in urban catchments. In contrast, urban land cover increases flashiness and frequency of medium and high flow events. We highlight the need to move beyond land cover metrics and include other features of urban river systems in hydrological analyses to quantify current and future drivers of urban streamflow.

Assessment of longitudinal dispersion and flow resistance near floodplains through riparian woodlands

Riparian woodlands prevent bank erosions, recycle minerals, sustain biodiversity, act as flow resistance on floodplains, and filter pollutants. The emergent trees characterize woodlands with different spacing arrangements that dictate flow resistance and longitudinal dispersion of the pollutants in compound channel flow. The single- and multistage compound channels exist in urban and natural watercourses with riparian and transplanted trees on different stages of the floodplain. This study numerically validates the planting of vegetation in lines on single- and multistage floodplains using a wall-modeled large-eddy simulation model. Post-validation, the focus of the study was to assess the hydrodynamic behavior and mixing around the floodplain and main channel section of different tested configurations. The approximation of flow structures for the various configurations of tree plantations shows stronger vortices with significant characteristic length scales for floodplains closer to the main channel. The intensity of the secondary current is higher for denser planted trees at junctions of floodplains. For higher flow events, drag force contributions for staged floodplains with trees on both stages are 45–41%, and trees on the top stage contribute 27-22% to the total frictional force budget. The subsequent investigation shows that the in-line trees geometrical configuration and spacing arrangement on the floodplain dictates flow resistance and longitudinal dispersion of the pollutants and contamination in channel flow. The results show that the overall reduction in discharge for floodplains with tree planting is 19.8–36.2% for single-stage and 10.4–23.6% for multistage compound channels. The longitudinal dispersion coefficients for each multi-zone model predict a 61% and 41% dispersion reduction, respectively, in single- and multistage floodplains with planted trees. Floodplains with denser tree spacing have a maximum zonal discharge reduction of 45% for a single-stage and 27.2% and 28.0% for multistage channels. These findings strongly suggest that the planting parameters of spacing-to-diameter ratio and floodplain geometry play a pivotal role in floodplain management from the perspective of contaminant dispersion and flood risk reduction during high-flow events.

Fluvial Dynamics and Hydrological Variability in the Chiriquí Viejo River Basin, Panama: An Assessment of Hydro-Social Sustainability through Advanced Hydrometric Indexes

The objective of this study was to conduct a detailed analysis of the available flow series in the Chiriquí Viejo River basin in Panama. This paper examines the patterns of variation within these series and calculates various hydrological indexes indicative of the region’s hydrology. Utilizing advanced hydrological indexes within the Chiriquí Viejo River basin in Panama, which spans an area of 1376 km2 and supports an estimated population of 100,000 inhabitants, analytical methods were employed to compute indexes such as the Daily Flow Variation Index (QVAR), the Slope of the Flow Duration Curve (R2FDC), the Hydrological Regulation Index (IRH), and the average duration of low (DLQ75) and high (DHQ25) flow pulses. The results indicate moderate flow variability (QVAR of 0.72) and a Hydrological Regulation Index (IRH) of 2.32, signifying a moderate capacity for flow regulation. Notably, low flow events (DLQ75) lasted approximately 3.73 days, while high flow events (DHQ25) lasted around 4.08 days. The study highlights a significant capacity to respond to extreme events, with maximum annual flows reaching 80.25 m3/s and minimum flows dropping to 3.01 m3/s. Despite the significant contribution of the basin to hydroelectric power generation and other economic activities, there is an observed need for sustainable management that accommodates hydrological fluctuations and promotes resource conservation. The conclusions indicate that these findings are critical for future planning and conservation strategies in the region, emphasizing the importance of integrating multidisciplinary approaches for Hydro-Social Sustainability. This novel and holistic approach underscores the interdependence between hydrological dynamics, socio-economic activities, and environmental sustainability, aiming to ensure the long-term resilience of the Chiriquí Viejo basin and its communities.

Investigating the utility of satellite-based precipitation products for simulating extreme discharge events: an exhaustive model-driven approach for a tropical river basin in India.

Satellite-based precipitation estimates are a critical source of information for understanding and predicting hydrological processes at regional or global scales. Given the potential variability in the accuracy and reliability of these estimates, comprehensive performance assessments are essential before their application in specific hydrological contexts. In this study, six satellite-based precipitation products (SPPs), namely, CHIRPS, CMORPH, GSMaP, IMERG, MSWEP, and PERSIANN, were evaluated for their utility in hydrological modeling, specifically in simulating streamflow using the Variable Infiltration Capacity (VIC) model. The performance of the VIC model under varying flow conditions and timescales was assessed using statistical indicators, viz., R2, KGE, PBias, RMSE, and RSR. The findings of the study demonstrate the effectiveness of VIC model in simulating hydrological components and its applicability in evaluating the accuracy and reliability of SPPs. The SPPs were shown to be valuable for streamflow simulation at monthly and daily timescales, as confirmed by various performance measures. Moreover, the performance of SPPs for simulating extreme flow events (streamflow above 75%, 90%, and 95%) using the VIC model was assessed and a significant decrease in the performance was observed for high-flow events. Comparative analysis revealed the superiority of IMERG and CMORPH for streamflow simulation at daily timescale and high-flow conditions. In contrast, the performances of CHIRPS and PERSIANN were found to be poor. This study highlights the importance of thoroughly assessing the SPPs in modeling diverse flow conditions.

Short-term geomorphic adjustments of bars in the Elbe, a large regulated river in Czechia

Gravel and sandy bars constitute critical components of river channel morphology, yet their morphodynamics in large, heavily regulated rivers during periods without significant flows remain poorly understood. This study investigates changes in surface heterogeneity and sediment sizes through a two-year field monitoring program, focusing on the frontal, central, and distal sections of four bars along the Elbe River in Czechia. Despite the absence of high-flow events reaching at least a one-year recurrence interval, observable changes in surface heterogeneity and sediment sizes were noted across all bars. However, the changes did not follow a uniform pattern; individual bars and their sections exhibited varying degrees of surface sediment coarsening or fining, alongside increases or decreases in surface heterogeneity. These findings highlight the necessity for site-specific management strategies for individual bars within such human-impacted rivers, recognizing their value as ecological hotspots. Furthermore, the methodology presented in this study may serve as a blueprint for the cost-effective monitoring of bar dynamics in channelized river sections.

Inter‐basin comparison of wood flux using random forest modelling and repeated wood extractions in unmonitored catchments

AbstractPredicting wood flux (i.e., wood piece number per time interval) or discharge (metre cubes of wood per second) in rivers is crucial for adequate integrated river management that balances risk assessment and ecological improvement. To enhance our understanding of the transport mechanisms of wood and assess their effects in various geographical contexts, it is necessary to conduct inter‐basin comparative studies and preliminary modelling. The wood flux of two river basins was analysed using video monitoring and random forest predictions based on hydrological drivers. The wood flux dynamics of the Ain and Allier rivers were both compared and contrasted. Although there was shared wood transport hysteresis, hourly wood flux, relative critical flow discharges of wood transport and certain hydrological factors exhibited differences between the two river basins. As a next step, the two random forest models, which were trained previously, were applied to predict wood flux and then wood discharge in a third river (the Rhône), in order to estimate a wood volume export, which can be compared with the wood volumes extracted over a series of a few monthly periods in the Génissiat reservoir. By using the random forest modelling, it is possible to estimate the volume of wood on the Rhône river. Despite the absence of any training data, there is a noticeable correlation, however, the estimated volumes were significantly overestimated. To resolve this issue, a correction factor was applied, accounting for disparities in wood recruitment dynamics between the Rhône basin and the training river basins. It was found that high flow events are underestimated, emphasizing the importance of incorporating local annotations and additional parameters in training the random forest model. Accurately predicting wood flux is important for integrated watershed management, but field observations are still lacking for validation and process‐based understanding.

Systematic underestimation of polycyclic aromatic hydrocarbon aqueous concentrations in rivers

Polycyclic aromatic hydrocarbons (PAHs) are a widespread group of organic contaminants whose presence in water bodies is cause of severe concern. With few exceptions, the majority of PAHs is hydrophobic, presents a high adsorption affinity, and is thus primarily transported within river systems during high-flow events together with suspended particulate matter (SPM). Evidence exists of analytical challenges related to the incomplete extraction of PAHs adsorbed to solids and thus to a potential negative bias in the chemical analysis of PAHs in bulk water samples with high SPM content. Despite this, partly due to the elevated efforts required to collect representative samples containing sufficient SPM for the separate PAH analysis in this matrix, several investigations rely on the analysis of aqueous samples. This study tests the hypothesis that surveys based exclusively on bulk water may lead to a systematic underestimation of the real contamination level and transport of PAHs in rivers. Six high-turbidity events were examined in three Austrian rivers applying time-integrated sampling and simultaneously analyzing PAHs in total bulk water, filtered water, SPM, and supernatant. Despite an unavoidable degree of uncertainty in such challenging sampling scheme, the results indicate that measurements performed with best available standard methods in bulk water samples determined in average only about 40% of the theoretically expected total PAHs concentrations derived from the analyses in SPM. Such deviation has important implications for the reliable assessment of the compliance with environmental quality standards as well as for surveys aimed to estimate riverine loads, validate emission models, and understand the transport dynamics of PAHs in rivers. Whereas the first objective, e.g., in European countries, is alternatively achieved via monitoring in biota, the latter ones require efforts directed to complement monitoring campaigns with separate sampling of SPM, with monitoring of suspended solids transport to appropriately select and interpret the results of water samples and to improve the chemical analysis of PAHs in bulk water samples with high solids content.

High flow prediction model integrating physically and deep learning based approaches with quasi real-time watershed data assimilation

When operating a flood forecasting system, it is crucial to prioritize both promptness and accuracy, along with reflecting the latest watershed conditions. This study proposes a hybrid model for rainfall-induced high flow prediction that combines an instantaneous physically-based model and a deep learning-based rainfall loss model assimilating with quasi real-time watershed conditions. Its primary objective is to present immediate and reliable high flow predictions, ensuring stability in prediction procedures. The surface runoff component of the model is based on nonlinear instantaneous unit hydrograph (IUH) derived using a dynamic wave model, which considers the nonlinearity between the rainfall excess intensity and the time to peak and peak flow of the IUH. To account for rainfall loss, which can significantly influence rainfall-runoff quantity, Long Short-Term Memory (LSTM) model is employed to establish link between key rainfall loss parameters and the latest watershed conditions obtained from the Global Land Data Assimilation System (GLDAS). The application of the proposed model to 28 high flow events reveals several noteworthy outcomes. Firstly, unlike conventional models that depend on fixed parameter values specific to each event, the proposed model offers immediate, stable, and highly accurate high flow predictions without the need for manual calibration. Secondly, the prioritization of parameters reflecting watershed conditions varies between different watersheds and depends on the rainfall events. These findings indicate the necessity to estimate rainfall loss parameters individually for each rainfall-runoff event in each watershed, as no universal value exists for these parameters. Lastly, despite the limited number of test cases conducted in this study, the LSTM model achieved sufficiently accurate rainfall loss estimation for high flow prediction using only 50 datasets.