River Network Research Articles

Technical note: Surface fields for global environmental modelling

Abstract. Climate change has resulted in more frequent occurrences of extreme events, such as flooding and heavy snowfall, which can have a significant impact on densely populated or industrialised areas. Numerical models are used to simulate and predict these extreme events, enabling informed decision-making and planning to minimise human casualties and to protect costly infrastructure. LISFLOOD is an integrated hydrological model underpinning the European Flood Awareness System and Global Flood Awareness System (EFAS and GloFAS, respectively), developed by the Copernicus Emergency Management Service (CEMS). The CEMS_SurfaceFields_2022 dataset is a new set of high-resolution surface fields at 1 and 3 arcmin resolution (approximately 2 and 6 km at the Equator, respectively) based on a wide variety of high-resolution and up-to-date data sources. The 1 arcmin fields cover Europe, while the surface fields at 3 arcmin cover the global land surface (excluding Antarctica). The dataset encompasses (i) catchment morphology and river networks, (ii) land use, (iii) vegetation cover type and properties, (iv) soil properties, (v) lake information, and (vi) water demand. This paper details the complete workflow used to generate the CEMS_SurfaceFields_2022 fields, including the data sources and methodology. Whilst created together with upgrades to the open source LISFLOOD code, the CEMS_SurfaceFields_2022 fields can be used independently for a wide range of applications, including as input to hydrological, Earth system, or environmental models or for carrying out general analyses across spatial scales, ranging from global and regional levels to local levels (especially useful for regions outside Europe), expected to improve the accuracy, detail and realism of applications.

Delineation of Intermittent Rivers and Ephemeral Streams Using a Hybrid Method

Intermittent rivers and ephemeral streams are crucial for the water cycle and ecosystem services, yet they are often neglected by managers and researchers, especially in headwater areas. This oversight has caused a lack of comprehensive basemaps for these vital river systems. In headwater regions, water bodies are typically sparse and disconnected, with narrow and less distinct channels. Therefore, we propose a novel hybrid method that integrates topographic data and remote sensing imagery to delineate river networks. Our method reestablishes connectivity among sparsely distributed water bodies through topographic pairs, enhances less distinct channel features using the gamma function, and converts topographic and water indices data into a weighted graph to determine optimal channels with the A* algorithm. The topographic and water indices data are derived from the Multi-Error-Removed Improved-Terrain DEM (MERIT DEM) and an average composite of the Modified Normalized Difference Water Index (MNDWI), respectively. In the upper Lancang-Mekong River basin, our method outperformed five publicly available DEM datasets, achieving over 91% positional accuracy within a 30 m buffer. This hybrid method enhances positional accuracy and effectively connects sparse water bodies in headwater areas, offering promising applications for delineating intermittent rivers and ephemeral streams and providing baseline information for these river systems.

Carbon emissions from inland waters may be underestimated: Evidence from European river networks fragmented by drying

AbstractRiver networks contribute disproportionately to the global carbon cycle. However, global estimates of carbon emissions from inland waters are based on perennial rivers, even though more than half of the world's river length is prone to drying. We quantified CO2 and CH4 emissions from flowing water and dry riverbeds across six European drying river networks (DRNs, 120 reaches) and three seasons and identified drivers of emissions using local and regional variables. Drivers of emissions from flowing water differed between perennial and non‐perennial reaches, both CO2 and CH4 emissions were controlled partly by the annual drying severity, reflecting a drying legacy effect. Upscaled CO2 emissions for the six DRNs at the annual scale revealed that dry riverbeds contributed up to 77% of the annual emissions, calling for an urgent need to include non‐perennial rivers in global estimates of greenhouse gas emissions.

Longitudinal distribution of fish fauna and characteristics of indicator species in the East Seto Inland Ecological Region within the Japanese Archipelago

Understanding biota distribution patterns is essential for ecosystem conservation and restoration. In addition to biogeography, the distribution patterns of aquatic organisms that inhabit rivers vary longitudinally along river networks. Although longitudinal changes in distribution patterns in aquatic organisms along river networks have been studied in single river basins, it is crucial to understand these patterns at a regional ecological scale for broad-scale ecosystem conservation. This study aimed to elucidate the longitudinal distribution patterns of fish fauna and their correlation with environmental factors in several watersheds within the East Setouchi Ecological Region, renowned for its rich freshwater fish diversity in the Japanese archipelago. Data were obtained for 118 species across 10 watersheds and 85 sites, and the surveyed sites were classified into four longitudinal groups based on the similarity of the fish fauna. The lowest group comprised river estuaries, abundant in brackish-water fish, comprising primarily Gobiidae species. In lower watershed areas with low agricultural land and forest cover but high urbanization, all fish species selected as indicators were non-native. Upstream areas with a high percentage of agricultural land featured a mix of native Cyprinidae and non-native species such as Micropterus salmoides and Rhodeus ocellatus ocellatus. The most upstream groups, marked by significantly greater elevations and bed slopes, exclusively comprised native species as indicator species. Analyzing the longitudinal distribution patterns of fish fauna at multiple sites within the same ecological region enabled us to choose endemic fish species as indicators and identify important species for conservation. Additionally, the selection of sites characterized by significant urbanization and strong anthropogenic influences, along with the selection of non-native species as indicators, underscores the urgency of conserving native organisms in these areas, calling for continuous monitoring.

Assessing the impact of rainfall on water quality in a coastal urban river utilizing the environmental fluid dynamics code

The Haihe River, flowing through Tianjin City, grapples with pollution challenges, notably high levels of nitrogen (N) and phosphorus (P) leading to eutrophication and unpleasant odors, particularly aggravated by rainfall. This study used Environmental Fluid Dynamics Code to comprehensively analyze the water environment under three scenarios: low flow year, normal flow year, and high flow year. The investigation delves into N and P concentrations, computes atmospheric deposition fluxes, and evaluates the loads and retention ratios of N and P in the urban river network of Tianjin City. Scenario analysis reveals distinct trends, with high flow years associated with elevated N and hydrodynamics levels, while low flow years exhibit contrasting patterns. Key findings include 1) wet deposition fluxes contributing 21% of NH4+-N and 9% of TP river loads, 2) continuous rainfall and runoff resulting in immediate or delayed increases in NH4+-N, TN, and TP concentrations in surface water, 3) an increase in average N:P mole ratios downstream along the Haihe River, and 4) N and P mean retention ratios were 48% and 63%, respectively. The study suggests that implementing sponge city construction and sustainable drainage systems may improve water quality by mitigating the direct discharge of rainfall runoff into the river.

Hydrodynamic and Sediment Transport Modeling at Lower Citarum and Cibeet River Confluence West Java

Flooding and changes in riverbed morphology often become issues near river confluences, as observed at the confluence of Citarum Hilir and Cibeet Rivers. This study aims to analyze the cross-sectional capacity and riverbed changes around the confluence of Citarum Hilir and Cibeet Rivers. This study utilizes 1D numerical modeling MIKE 11 with Hydrodynamic and Sediment Transport Modules. The hydrodynamic modeling inputs are river network and cross-sectional profiles. Hydrographs with return periods of 2, 5, 10, and 25 years are used as upstream boundaries, and a discharge curve is used as the downstream boundary of the model. The model is calibrated using water surface elevation measurements taken from September 13-16, 2021. The hydrodynamic modeling results indicate that Citarum Hilir and Cibeet Rivers cannot convey flood discharges with a 2-year return period. The sediment transport modeling results show no significant changes in the riverbed of Citarum Hilir before the confluence, but degradation of approximately 0.38 – 0.46 meters occurs after the confluence. Degradation happens in zones of maximum velocity where flow turbulence and shear stress increase, causing erosion of the Citarum Hilir riverbed. Degradation also occurs near the Cibeet River confluence due to flow acceleration at the outer bend of the river. Flooding and sediment transport are natural factors that can alter the morphology of river confluences, such as the confluence of Citarum Hilir and Cibeet Rivers.Keywords: Citarum river, Cibeet river, river confluence, hydrodinamic modeling, sedimen transport modeling

Quantifying pollution contributions across a reticular river network: Insights from water quantity composition analysis

Calculating pollution load contribution rate is an effective way to identify pollution sources, which is important in improving water quality management. Reticular river networks pose unique challenges in pollution load contribution rates calculation, as current methods are not applicable to river networks with uncertain flow direction or exhibit low computational efficiency. This study addresses this challenge by offering a new method that transforms the calculation of water quantity constituents in assessment sections into a conserved substance concentration problem. Applied to a typical reticular river network, Suzhou River Network in the Tai Lake Basin, China, total phosphorus pollution load contribution rates demonstrate significant spatial and temporal variations, and are closely associated with factors such as pollution load, rainfall, and water diversion. The developed method stands out for its simplicity and improved computational efficiency, making it particularly suitable for regions with indeterminate flow directions. Quantifying the contribution of pollution sources in reticular river networks to identify sources of pollution helps to improve the precision and pertinence of water pollution management programs.

Influences of carbonate weathering and hyporheic exchange on carbon fluxes in Pearl River Basin, China

Deciphering riverine dissolved carbon dynamics is pivotal for a comprehensive picture of the global carbon cycle. Through rigorous in-situ sampling across the Pearl River Basin (PRB), our investigation reveals the Pearl River networks function as a significant carbon source, with the annual carbon dioxide (CO2) emission of 2.57 ± 1.94 Tg C, which offsets 10 ± 8 % of the forest carbon sequestration or 65 ± 49 % carbon sink via chemical weathering in the PRB. Based on the mass balance of 222Rn, we initially reveal that the contributions of water flux from the hyporheic zone increased with the river orders (Hack Order) across both dry and wet seasons. Conversely, the evasion rates of dissolved CO2 (CO2*) and dissolved inorganic carbon (DIC) from the hyporheic zone into river channels exhibited a decline with the increasing river orders. The hyporheic exchange contributes 4 – 11 % of the lateral and vertical DIC losses, thereby is a key mechanism in the riverine carbon cycle. Furthermore, CO2* derived from the hyporheic zone was ∼4 times of riverine CO2 emissions and this CO2* flux from the hyporheic zone was buffered into carbonates/bicarbonates in river channels, due to the high riverine pH resulted from carbonate weathering in the basin. These results not only highlight the substantial role of carbonates and hyporheic processes in modulating riverine carbon fluxes but also signify their broader implications on understanding riverine carbon dynamics at both regional and global scales.

Dispersal capacity as assessed by distance-decay relationships is lower for aquatic shredder insects than aquatic non-shredder insects in a Neotropical river network

Dispersal capacity as assessed by distance-decay relationships is lower for aquatic shredder insects than aquatic non-shredder insects in a Neotropical river network

Influence of SMAP soil moisture retrieval assimilation on runoff estimation across South Asia

This study was designed to characterize and quantify the influence of surface soil moisture assimilation on estimated runoff (surface flow and baseflow) and hydraulically-routed streamflow across three large river basins in South Asia that are at risk of impending water stress. Soil Moisture Active Passive (SMAP) surface soil moisture retrievals were assimilated into the Noah-MP land surface model. The gridded runoff was hydraulically routed to obtain volumetric streamflow values for a river network using a runoff routing module (Hydrological Modeling and Analysis Platform, HyMAP). The open loop (OL, model-only) and data assimilated (DA, includes soil moisture retrieval assimilation) Noah-MP runoff estimates highlighted the improvements in estimated total runoff across irrigated areas. Soil moisture assimilation impacted baseflow more relative to surface runoff. The HyMAP-based OL and DA streamflow generally underestimated the streamflow at upstream stations and overestimated the streamflow at downstream stations within the Indus basin due to missing physics related to reservoir operations. For stations located in the Ganges–Brahmaputra basins, the OL and DA estimation performance varied. The OL and DA results showed that the assimilation of soil moisture retrievals improves gridded runoff and volumetric streamflow across irrigated areas. Considerable relative change in streamflow (>70% increase in magnitude relative to OL) is noted after assimilation across the highly irrigated lower Indus basin and high precipitation regions in Bangladesh. Improving the modeling system’s representativeness of ground conditions via inclusion of water management information could improve large-scale streamflow modeling across South Asia.

Unraveling the Impacts of River Network Connectivity on Ecological Quality Dynamics at a Basin Scale

The ecological quality of river basins is significantly influenced by the complex network of river structures and their connectivity. This study measured the temporal and spatial variability of ecological quality, as reflected by remote sensing ecological indices (RSEI), and examined their responses to river network connectivity (RNC). In total, 8 RNC indices, including river structure of river density (Dr), water surface ratio (Wr), edge-node ratio (β), and network connectivity (γ), and node importance indices of betweenness centrality (BC), PageRank (PG_R), out_degree centrality (Out_D), and in_closeness centrality (In_C), were generated at the subbasin scale. Our results highlighted the significance of RNC in influencing both the values and variability of RSEI, and the extent of this influence varied across different time periods. Specifically, three distinct clusters can be extracted from the temporal variability of RSEI, representing wet, near-normal, and dry years. The river structure index of γ significantly influenced the spatial patterns of subbasin RSEIs, particularly in wet years (R2 = 0.554), whereas β displayed a pronounced U-shape correlation with subbasin RSEIs in dry years (R2 = 0.512). Although node importance indices did not correlate directly with subbasin RSEI levels, as the river structure indices did, they significantly positively affected temporal variability of subbasin RSEIs (EI_SD_t). Higher values of PG_R, Out_D, and In_C were associated with increased subbasin RSEI variability. Based on these correlations, we developed RNC-based RSEI and EI_SD_t models with high adjusted coefficients of determination to facilitate the assessment of ecosystem quality. This study provides essential insights into ecosystem dynamics related to river connectivity within a basin and offers valuable guidance for effective watershed management and conservation efforts aimed at enhancing ecological resilience and sustainability.

Hydrologic connectivity and dynamics of solute transport in a mountain stream: Insights from a long-term tracer test and multiscale transport modeling informed by machine learning

The movement of solutes in a watershed is a complex process with multiple interactions and feedbacks across spatial and temporal scales. Modeling the dynamics of solute transport along diverse hydrologic pathways within watersheds – from hillslopes to stream channels and in and out of the hyporheic zones – is challenging but critically important, as these processes integrate and contribute to the biogeochemical functioning of the river corridor up to the river network scale. Here we use results from a long-term network-scale tracer test at the H.J. Andrews experimental forest in western Cascade Mountains, Oregon, USA to inform a multiscale framework for transport in stream corridors. The framework uses a Lagrangian-based subgrid model to represent the effects of hyporheic exchange flow and advective transport at stream network scales. The spatially and temporally resolved stream discharge needed for the transport model is imputed across the river system by an entity-aware long short-term memory network. Modeled concentrations show good agreements with the observations and exhibit power scaling laws indicative of a very wide range of timescales over which hyporheic exchange flow occurs. Our results demonstrate a data-informed modeling framework that links dynamical processes occurring at small scales to a network context to help understand how changes at reach scale cascade into network-scale effects, providing a useful tool for sustainable river basin management.

Prevention policies for the marine ecological environment in the South China Sea as a consequence of excessive plastic compound use in Vietnam.

Vietnam suffers from a distressing predicament: It ranks among the most heavily contaminated nations on earth. Its coastal and marine domains are plagued by an excess of plastic waste. Vietnam has consistently discharged a substantial amount of waste into the oceans, ranging from 0.28 to 0.73 million metric tons annually. Numerous areas have emerged as focal points of plastic pollution throughout its extensive seashore and marine areas. The escalating presence of marine litter poses an increasingly grave threat to the intricate equilibrium of Vietnam's marine ecosystems. This comprehensive policy study reveals that the mounting problem of ocean plastic pollution, characterized by the abundance of floating plastic debris, imperils both plant and animal life, placing various marine species such as seabirds, fish, turtles, and cetaceans at risk. The consumption of minuscule plastic particles and the harmful impact of chemical pollutants from plastic waste in the ocean not only endangers the vitality of marine life but also poses a substantial hazard to human well-being because plastic waste infiltrates the food chain. This research reveals that, despite the existence of numerous laws and policies-including the Law on Environmental Protection 2020, the Marine Plastic Waste Management Initiative for the Fisheries Sector 2020-2030, and the National Action Plan for Management of Marine Plastic Litter-a significant amount of plastic waste is infiltrating the river network and eventually infiltrating oceans as a result of improper monitoring and ineffective enforcement of these legislations. Relying primarily on existing data released by the government and other sources and a wide range of gray literature retrieved from reputable databases, this study aims to evaluate the role of Vietnam's legal framework for combating the critical issue of marine plastic pollution in the South China Sea. Integr Environ Assess Manag 2024;20:2088-2106. © 2024 SETAC.

Assessing the conjunction of environmental sustainability and tourism development along Chinese waterways

The complex interplay between tourism expansion and environmental conservation responsibilities necessitates the adoption of sustainable practices in aquatic ecosystems around the world. Still, existing scholarly investigations predominantly focus on the dynamics of individual rivers, resulting in considerable gaps in our comprehension of large river network systems. To redress these gaps, this study examines the potential effects of tourism development on the environmental sustainability of the Yangtze River and its tributaries in China. Furthermore, it evaluates government support and interventions aimed at strengthening environmental sustainability while proposing specific improvements. In 2023, a comprehensive survey involving 982 stakeholders provided invaluable insights into the multilayered nexus between tourism development and environmental sustainability. We analyzed carefully gathered data from a thoughtfully designed questionnaire using rigorous reliability assessments, correlation analyses, and regression techniques. Cronbach’s alpha coefficients ranging from 0.83 to 0.95 support the results, indicating robust reliability. The findings reveal predominantly positive correlations between governmental support and interventions and environmental sustainability, with visitor management showing the strongest correlation (r = 0.66**). Furthermore, regression analysis reveals that tourism development and governmental support and interventions contribute to both economic sustainability (R2 = 0.61 ∼ R2 = 0.77, ΔR2 = 16) and environmental conservation and management (R2 = 0.51 ∼ R2 = 0.62, ΔR2 = 11) in environmental sustainability. Thus, the study highlights the importance of governmental support and intervention in achieving environmental sustainability. Therefore, it advocates a coordinated approach to maximize policy formulation and implementation benefits. This study provides actionable insights for researchers, stakeholders, and policymakers alike to promote sustainable tourism practices.

Structural characteristics and spatiotemporal changes of a reticular river network based on complex network theory

eticular river networks, characterized by a dense pattern of rivers and loop structures, are primarily found in lower river delta plains and are being modified due to rapid population growth and urbanization. This change impacts the distribution of water resources and could result in more frequent and severe floods. Therefore, accurately characterizing the structure of river networks is crucial. In this study, the structure and its changes of a typical plain reticular river network in the Lixia River hinterland area (LRHA), China, were evaluated in the 1960s, 1970s, 1980s, 2009, and 2016 using complex network theory tools at global and local scales. First, we constructed a complex network model by generalizing river sources, outlets, and confluences as nodes and channels as edges. By comparing with the equivalent random networks, it is found that the river networks of LRHA have large clustering coefficients and short characteristic path lengths. These characteristics classify it as a small-world network within complex networks, which is notably efficient for water and material transportation. Second, at the global scale, the global efficiency in complex network theory considers the interconnectivity between nodes and assesses the potential paths between them, effectively reflecting the connectivity status of the river network. At the local scale, the betweenness centrality of a complex network can reflect the control ability of water and material transportation at river nodes. After the 1970s, constructing several new mainstem rivers gradually shifted nodes with high betweenness centrality towards the north–south flowing rivers. In addition, we used Moran’s I to quantify the spatial clustering of the network’s indicators and found that degree and betweenness centrality exhibited higher spatial clustering, with mean Moran’s I values of 0.398 and 0.300, respectively. Finally, we compared the structure of river networks in urban versus rural areas and the mainstem versus tributary streams. We found that urban river networks and mainstem rivers exhibit a higher degree of betweenness centrality, resulting in a greater capacity to regulate water and material cycles within the river network. According to the research findings, complex network theory has been proven to effectively evaluate the structure of reticular river networks at various scales. It enhances our comprehension of the river network’s structure and assists managers in gaining a deeper understanding of how the river network structure influences the distribution of water resources.

Hyper-resolution flood hazard mapping at the national scale

Abstract. Flood hazard mapping is currently in a transitional phase involving the use of data and methods that were traditionally in the domain of local studies in a regional or nationwide context. Challenges include the representation of local information such as hydrological particularities and small hydraulic structures, as well as computational and labour costs. This paper proposes a methodology of flood hazard mapping that merges the best of the two worlds (local and regional studies) based on experiences in Austria. The analysis steps include (a) quality control and correction of river network and catchment boundary data; (b) estimation of flood discharge peaks and volumes on the entire river network; (c) creation of a digital elevation model (DEM) that is consistent with all relevant flood information, including riverbed geometry; and (d) simulation of inundation patterns and velocities associated with a consistent flood return period across the entire river network. In each step, automatic methods are combined with manual interventions in order to maximise the efficiency and at the same time ensure estimation accuracy similar to that of local studies. The accuracy of the estimates is evaluated in each step. The study uses flood discharge records from 781 stations to estimate flood hazard patterns of a given return period at a resolution of 2 m over a total stream length of 38 000 km. It is argued that a combined local–regional methodology will advance flood mapping, making it even more useful in nationwide or global contexts.

The Role of Cultural Landscape in Shaping the Urban Spatial Context of Changzhou (1843–2021) from a Spatial Syntax Perspective

Changzhou is a city situated in the eastern region of China and serves as a pivotal juncture of the UNESCO World Cultural Heritage site, the Grand Canal of China. The study employed spatial syntax foreground and background network analysis to examine the cultural landscape characteristics and determinants of the urban spatial context in Changzhou, influenced by the Grand Canal, with a focus on rivers, streets, and social networks. The findings revealed that: (1) Foreground network construction: serving as the fundamental framework of urban space, street and river networks exhibited distinct functionalities in terms of structural configuration, functional organization, and potential impact. (2) Background network construction: social networks identified through spatial structure recognition demonstrated sustainable characteristics, as their layout was not directly correlated to the foreground network but contributed to the identification of the identity and the traits of social networks. (3) Dual network adaptability to contemporary urban space: it was imperative to redefine the role of river networks to augment their potential impact in shaping scenic leisure systems. This study provides novel insights into preserving and acknowledging the urban spatial context while offering valuable references for safeguarding regional cultural landscapes.

Watershed features shape spatial patterns of fish tissue mercury in a boreal river network

Freshwater mercury (Hg) contamination is a widespread environmental concern but how proximate sources and downstream transport shape Hg spatial patterns in riverine food webs is poorly understood. We measured total Hg (THg) in slimy sculpin (Cottus cognatus) across the Kuskokwim River, a large boreal river in western Alaska and home to subsistence fishing communities which rely on fish for primary nutrition. We used spatial stream network models (SSNMs) to quantify watershed and instream conditions influencing sculpin THg. Spatial covariates for local watershed geology and slope accounted for 55 % of observed variation in sculpin THg and evidence for downstream transport of Hg in sculpins was weak. Empirical semivariograms indicated these spatial covariates accounted for most spatial autocorrelation in observed THg. Watershed geology and slope explained up to 70 % of sculpin THg variation when SSNMs accounted for instream spatial dependence. Our results provide network-wide predictions for fish tissue THg based largely on publicly available geospatial data and open-source software for SSNMs, and demonstrate how these emerging models can be used to understand contaminant behavior in spatially complex aquatic ecosystems.

GIS-Based Methods for Identifying River Networks Types and Changing River Basins

GIS-Based Methods for Identifying River Networks Types and Changing River Basins

Multivariate Hydrological Modeling Based on Long Short-Term Memory Networks for Water Level Forecasting

In the Department of Chocó, flooding poses a recurrent and significant challenge due to heavy rainfall and the dense network of rivers characterizing the region. However, the lack of adequate infrastructure to prevent and predict floods exacerbates this situation. The absence of early warning systems, the scarcity of meteorological and hydrological monitoring stations, and deficiencies in urban planning contribute to the vulnerability of communities to these phenomena. It is imperative to invest in flood prediction and prevention infrastructure, including advanced monitoring systems, the development of hydrological prediction models, and the construction of hydraulic infrastructure, to reduce risk and protect vulnerable communities in Chocó. Additionally, raising public awareness of the associated risks and encouraging the adoption of mitigation and preparedness measures throughout the population are essential. This study introduces a novel approach for the multivariate prediction of hydrological variables, specifically focusing on water level forecasts for two hydrological stations along the Atrato River in Colombia. The model, utilizing a specialized type of recurrent neural network (RNN) called the long short-term memory (LSTM) network, integrates data from hydrological variables, such as the flow, precipitation, and level. With a model architecture featuring four inputs and two outputs, where flow and precipitation serve as inputs and the level serves as the output for each station, the LSTM model is adept at capturing the complex dynamics and cross-correlations among these variables. Validation involves comparing the LSTM model’s performance with linear and nonlinear Autoregressive with Exogenous Input (NARX) models, considering factors such as the estimation error and computational time. Furthermore, this study explores different scenarios for water level prediction, aiming to utilize the proposed approach as an effective flood early warning system.