Hydrometeorological Parameters Research Articles

EDH-STNet: An Evaporation Duct Height Spatiotemporal Prediction Model Based on Swin-Unet Integrating Multiple Environmental Information Sources

Given the significant spatial non-uniformity of marine evaporation ducts, accurately predicting the regional distribution of evaporation duct height (EDH) is crucial for ensuring the stable operation of radio systems. While machine-learning-based EDH prediction models have been extensively developed, they fail to provide the EDH distribution over large-scale regions in practical applications. To address this limitation, we have developed a novel spatiotemporal prediction model for EDH that integrates multiple environmental information sources, termed the EDH Spatiotemporal Network (EDH-STNet). This model is based on the Swin-Unet architecture, employing an Encoder–Decoder framework that utilizes consecutive Swin-Transformers. This design effectively captures complex spatial correlations and temporal characteristics. The EDH-STNet model also incorporates nonlinear relationships between various hydrometeorological parameters (HMPs) and EDH. In contrast to existing models, it introduces multiple HMPs to enhance these relationships. By adopting a data-driven approach that integrates these HMPs as prior information, the accuracy and reliability of spatiotemporal predictions are significantly improved. Comprehensive testing and evaluation demonstrate that the EDH-STNet model, which merges an advanced deep learning algorithm with multiple HMPs, yields accurate predictions of EDH for both immediate and future timeframes. This development offers a novel solution to ensure the stable operation of radio systems.

A novel method to estimate the 3D chlorophyll a distribution in the South China Sea surface waters using hydrometeorological parameters

Chlorophyll a (Chl-a) is a key indicator of marine ecosystems, and certain hydro-meteorological parameters (HMPs) are highly correlated with its fluctuations. Here, relevant and accessible HMPs were used as inputs, combined with machine learning (ML) algorithms for estimating 3D Chl-a in the South China Sea (SCS). With the inputs of temperature, salinity, depth, wind speed, wind direction, sea surface pressure, and relative humidity, the LightGBM-based model performed well, achieving high R2 values of 0.985 and 0.789 in validation and testing sets, respectively. Based on a large number of in situ measurements, this model enables the estimation of the 3D distribution of summer Chl-a in the SCS over the past fifteen years using a 3D hydrographic dataset combined with surface meteorological parameters. The results show that the 3D distribution of the model estimated Chl-a is characterized similarly to the previous studies and can capture the effect of hydro-meteorological conditions on Chl-a distribution. The environmental variables affecting Chl-a were considered more comprehensively in this study, and the methodological framework has the potential to be applied to the low-cost monitoring of the remaining water quality parameters.

Inter- and intra-annual carbon isotope fluctuations in Pinus sylvestris L. tree rings whole wood and cellulose in north-eastern Lithuania

In temperate regions trees typically exhibit growth sensitivity to climatic conditions during the growth season. Annual tree ring growth increments correlate with a variety of environmental factors. As an index of water use efficiency, δ13C is a preferred proxy to allow accurate interpretation of environmental factors critical for the tree growth, including changes in climate patterns, variation in the ambient temperature and precipitation. We assumed that isotopic differences within individual tree rings are likely to produce seasonal isotope fluctuations in the chronology that might be interpreted as response to environmental impacts. To verify the assumption, we measured δ13C in annual tree rings of Pinus Sylvestris L. split into 13 intra-annual segments each and checked δ13C correlations with temperature, precipitation, the number of sunshine hours and relative air humidity. For the investigation, we chose a site in north-eastern Lithuania, Zarasai, located in boreal latitude and remote from industrial pollution sources. The methodology of the research was based on high coherence of δ13C chronologies measured in the whole wood and α-cellulose extracted by means of two different methods. The experiment produced strong δ13C correlations with hydrometeorological parameters, especially in the earlywood formed in June

Effects of Short‐Term Climate Variations on Young Water Fraction in a Small Pre‐Alpine Catchment

AbstractContinuous and extended observations of hydrometeorological parameters, alongside the analysis of the isotopic composition across diverse waters within catchments, can significantly enhance our understanding of the potential ramifications of climate change on the hydrological response. In this study, a comprehensive analysis of hydrometeorological and isotopic data was conducted over 10 hydrological years (October 2012–September 2022) within a small, forested catchment in the Italian pre‐Alps, aiming to investigate the impacts of short‐term climatic changes on the isotopic composition of waters and the young water fraction (Fyw). The results showed that the catchment experienced climate conditions with rapid warming and drying trends. Significant isotopic enrichments were observed in all sampled water sources, driven primarily by air temperature. Fyw was estimated to be 0.64 ± 0.06, 0.45 ± 0.07, and 0.16 ± 0.03 for stream water, soil water, and shallow groundwater based on the whole‐period sinusoidal fittings, respectively. Comparative analyses comprising different approaches for the estimation of Fyw showed that time‐windows scenarios and detrending corrections yielded smaller Fyw than approaches based on the whole‐period fitting and discharge‐sensitivity modeling. Such differences can be attributed to an uneven temporal distribution of stream water isotopic data, the difficulties in capturing high flows in a humid catchment characterized by a fast runoff response during rainfall‐runoff events, and the presence of isotopic trends. Our findings underscore the imperative of integrating interannual isotopic trends and adopting appropriate sampling strategy and methodological approaches to ensure a robust Fyw estimation.

Arctic and Barents Sea ice extent variability and trends in 1979–2022

The aim of the paper is to assess interannual and decadal variability of the Barents Sea and Arctic ice extent in various seasons for the period from 1979 to 2022.The material for the study was satellite data on the Barents Sea and Arctic ice extent, climate indices, oceanographic data obtained during surveys in the Barents Sea by PINRO and other available information on hydrometeorological conditions of the sea in 1979–2022.Methods of descriptive statistics as well as comparative, correlation, regression, harmonic and cluster analyses were applied.Results: The year-to-year changes in the Barents Sea and Arctic ice extent in various seasons are described for 1979–2022. The modern climate changes, manifested in substantial warming of air and water masses in the Arctic, resulted in a considerable ice extent reduction in the studied areas in recent decades. Well-marked negative trends took place in all months and seasons. The annual mean ice extent was decreasing at a rate of 532 thousand km2 per decade in the Arctic, and at a rate of 105 thousand km2 per decade in the Barents Sea. Over the past 40 years, the ice extent in the Arctic has decreased by 14%, and in the Barents Sea — by half (by 51%), while the ice-free period duration has increased in the Barents Sea from one to three months. Hydrometeorological parameters were identified that are most closely related to the ice extent in the Arctic (|r| ≥ 0.40) and Barents Sea (|r| ≥ 0.60). Reliable regression models were developed that explain 45.2 and 88.0% of its variability, respectively. The contribution of individual factors to the ice extent variability explained by regression equations was quantitatively assessed, and the leading role of air temperature was noted.Practical significance: The obtained results are useful for a better understanding of the climate processes occurring in the Arctic and Barents Sea in recent decades and can be used to assess the impact of climate changes on the main objects of Russian fishery in these areas.

Dynamics of small metazooplankton in relation with environmental factors: A 12-year study in the coastal zone of the Southwestern Crimea (the Black Sea)

Based on continuous 12-year (2010–2021) monitoring of the average summer abundance of small metazooplankton (SMZ) in the coastal zone of the Southwestern Crimea, the patterns of its interannual fluctuations were investigated. The total SMZ abundance during the study period varied from 37.8 to 176.0 thousand·m−3 in the open coastal area (on average, 104.0 ± 49.2 thousand·m−3) and from 90.3 to 556.8 thousand·m−3 at the bay mouth (on average, 264.5 ± 121.0 thousand·m−3). The crustacean fraction accounted for 85–91% of the total SMZ abundance. Principal component analysis (PCA) showed a noticeable contribution of 48 % of total temperatures and wind speed and different direction repeatability to the SMZ abundance variability. For native data, significant relationships were revealed between the abundance of individual SMZ fractions and hydrometeorological parameters: total temperatures of the warm period of the year (May–October), periodicity of the southern and southwestern, northern winds, calm conditions (events of the absence of wind), and the summer index of the North Atlantic Oscillation (NAO) with a 1-year lag. The application of fast Fourier transform (FFT) with a Hamming filter to the original series and periodograms analysis allowed revealing typical periods of variability in SMZ abundance and hydrometeorological parameters of the environment: 2–4-year and 5–6-year ones. At these scales, a higher number of significant relationships was established with the indicated hydrometeorological parameters, inter alia winter and summer NAO indices, than during the analysis of the original series. The total contribution of hydrometeorological and climatic factors to the variation in the abundance of SMZ increased to 78–79 %. This confirms the assumption that the relationship between SMZ and environmental parameters is characterized by its own features at different scales. Analysis of long-term SMZ different fractions tendencies for Summer 2010–2021, according to the Mann-Kendall criterion, did not show significant results.

Towards development of a roadway flood severity index

Flooding is among the costliest and deadliest weather disasters. Moreover, different types of flooding have significant impacts on the transportation network and infrastructure including flash, riverine, urban, coastal, and storm surge. The variety of flooding scenarios makes it challenging to quantify the impacts of flooding on transportation across spatial scales; however, such metrics would be beneficial both prior to and after the event. Pre-flood metrics can promote enhanced impact-based decision-support guidance and hazard communication, while post-flood metrics may include larger regional disruptions located away from the most inundated areas and their associated secondary societal impacts. This study developed a retrospective Roadway Flood-Severity Index (RFSI) from 1982 to 2020 capable of integrating geo-located hydrometeorological data and transportation mobility information across localized and multi-state, sub-national regions to (1) categorize larger-scale, flood-related transportation disruptions, (2) understand the origins of those disruptions, and (3) identify severity risk levels of individual road segments and broader regions of transportation disruption during flood events. The fundamental question is, as flooding events unfold, can past hydrometeorological inundation information be coupled with transportation system network and mobility data to identify the most vulnerable roadway segments and regions? The overall mobility impacts of flooding on transportation were highly variable and relatively uncommon throughout the study period. Given this variability in other mobility data (e.g., vehicle speeds), hydrometeorological parameters were used exclusively as model inputs and crowdsourced Waze flood reports were used as the target response variable. A logistic regression based RFSI was found to best align with the dataset providing a “no flood” or “flood” classification. Eventually, this retrospective analysis will be extended to provide predictive capability as well. The RFSI is intended to provide transportation agencies with a quantitative metric to classify, categorize, and communicate the potential impacts of flood events throughout the transportation network.

Hybrid Model for Multistep-Ahead Rainfall Forecast in Northeast India: A Comparative Study

Abstract Among all hydrometeorological parameters, rainfall strongly correlates with hydrometeorological disasters. The rainfall forecast process remains challenging due to the nonlinear, nonstationary nature and multiscale variability of rainfall. Moreover, the unique microclimate in different regions further complicates the forecasting process. This study proposes a hybrid model employing multivariate singular spectrum analysis (MSSA) and long short-term memory (LSTM) for multistep-ahead hourly rainfall forecasting in urban areas of northeast India. The model is trained and evaluated using high-resolution (12 km) hourly meteorological data from the Indian Monsoon Data Assimilation and Analysis (IMDAA) dataset for Guwahati (plain) and Aizawl (hilly) regions from 2015 to 2019. The hybrid model outperforms the single LSTM model in both plain and hilly regions, with an average percentage gain of 47.99% and 43.88% for symmetric mean absolute percentage error (SMAPE) and root-mean-square error (RMSE) in the case of the Guwahati dataset and 84.59% and 82.27% in the case of the Aizawl dataset, respectively. The performance of the LSTM model significantly improves as the zero values in the observed data are eliminated after reconstruction by MSSA. This enables the model to discern essential patterns and relationships in the data, which leads to more accurate forecasts. However, the hybrid model underestimates the rainfall, which can be tackled by hypertuning the parameters. The study highlights the importance of considering the interplay between rainfall and meteorological parameters for accurate rainfall forecasting in urban areas. The proposed MSSA–LSTM model can be used as a decision support tool for urban planning and disaster management. Significance Statement This study addresses a critical need in multistep-ahead hourly rainfall forecasting in urban areas, with a focus on the unique conditions of northeast India. Our research has identified the presence of red noise in the rainfall data, shedding light on the complexities of the underlying rainfall patterns. Furthermore, we delve into the intricate interplay between rainfall and meteorological parameters, providing valuable insights into the factors influencing rainfall dynamics. Notably, our study underscores the region-specific challenges in rainfall forecasting. While the hybrid model demonstrates reasonable accuracy in the plains, its performance in the hilly region falls short of expectations. This highlights the nuanced nature of rainfall prediction in areas with varying topography and emphasizes the need for tailored forecasting approaches.

Research on GNSS-IR soil moisture retrieval based on random forest algorithm

Abstract Soil moisture (SM) retrieval is of great significance in climate, agriculture, ecology, hydrology, and natural disaster monitoring, and it is one of the essential hydrometeorological parameters studied in the world at present. With the continuous development of the GNSS, a technique called GNSS-IR became widely used in ground SM inversion. Therefore, based on the frequency, amplitude and phase of signal-to-noise ratio residuals (δSNR), this study takes P037 and P043 stations set by UNAVCO in the United States as examples and develops the research of SM inversion from Random Forest Regression (RFR) prediction. The experimental results show that the retrieval accuracy of SM under different practical schemes can be in descending order: L1 + L2 dual frequency combination > L2 single frequency > L1 single frequency. It is confirmed that the experimental scheme based on the L1+L2 dual-frequency combination is beneficial to the inversion of SM. In the L1+L2 dual-frequency combination, the prediction set accuracy of the P037 station is as follows: R is 0.796, RMSE is 0.032 cm3cm-3, ME is 0.002 cm3cm-3. The prediction accuracy of the P043 station is as follows: R is 0.858, RMSE is 0.039 cm3cm-3, ME is -0.009 cm3cm-3. Among them, the RMSE of the L1+L2 dual-frequency combination of the two stations has an improvement effect of 13%-37% compared with their single-frequency, which has a noticeable improvement effect. The difference between the SM retrieved by GNSS-IR and the reference value of PBO-H2O is concentrated around 0, further showing the accuracy of SM retrieved by GNSS-IR technology. To sum up, this study considers that SM retrieval based on the RFR model has good reliability and accuracy, which makes GNSS-IR technology an efficient means for SM retrieval. With the continuous improvement of the GNSS system and technology, the application of GNSS-IR technology in SM will become broader.

Litter in French urban areas-Part 2: transport dynamic and fluxes in stormwater.

Urban areas constitute a major hotspot of litter, including plastic litter, that stormwater can wash off towards waterways. However, few studies quantified and characterized litter densities in urban areas and fluxes transported by stormwater networks. Moreover, little information is available on litter transport dynamics in stormwater, and on the factors driving this transport. This study aims at characterizing and quantifying litter amounts transported by stormwater of two nested French urban catchments (total surface area of 105ha). Litter densities relative to land uses and rain events were investigated in the same catchments as in a compagnon paper (Ledieu et al., 2024). The present study explores the impact of rain events on the transport of urban litter in stormwater. Litter collection and characterization combined with a capture/recapture experiment using tagged litter placed in stormwater inlets show total litter fluxes of 29kg/year, in which 14kg/year are plastics, exported at the stormwater outlet. These fluxes confirm that stormwater runoff is a considerable pathway from urban surfaces to waterways, especially regarding small plastic litter (< 2.5cm). Item transport dynamic is however not linear and only 0.3% of the urban litter appear remobilized. Litter transport dynamics depends on several factors (urban litter densities, hydrometeorological parameters, item composition and morphologies, and stormwater management systems) that should be considered in global models.

Long-term variation of hydro-meteorological parameters and their impact on groundwater of unconfined aquifer

Long-term variation of hydro-meteorological parameters and their impact on groundwater of unconfined aquifer

Correlation between Two Sunshine Parameters and Three Hydrometeorological Parameters

In designing the correct capacity of solar panels that will be used for any project, the designer should know the solar radiation in that area. Next, the UV index data is needed to know if that area is safe from ultraviolet (UV) radiation. Unfortunately, solar radiation and UV index data from many hydrometeorological stations are usually rare. Hence, there is a necessity to solve this scarcity. The study, using the correlation method, intends to make the connection between two sunshine parameters (solar radiation and the ultraviolet (UV) index) and three hydrometeorological parameters (air temperature, humidity, or pressure). If these variable couplings are known, we can find the data of solar radiation (or UV index) based on air temperature, humidity, or pressure, which are usually much easier to obtain than solar radiation or UV index. The results showed that the correlation between solar radiation (or UV index) and air temperature, humidity, and pressure was strong positive-linear, strong negative-linear, and no strong correlation, respectively. Because it has a positive correlation, the temperature data have a strong potential to replace solar radiation or UV index data.

Effect of wind–wave conditions on the distribution of the phytoplankton community in the coastal area of the southern Crimea in spring (Black Sea)

Based on the measurement data obtained during the 121th cruise of the RV Professor Vodyanitsky, regularities were established between spatial distribution of quantitative characteristics and phytoplankton species composition, chlorophyll a concentration, and hydrometeorological parameters of the environment on the southern Crimean coast in the spring 2022. Chlorophyll a concentration was compared with satellite observation data of high spatial resolution. In selected areas with different shelf depths, the features of the distribution of phytoplankton indicators under conditions of changing hydrometeorological parameters were studied. The mechanisms of vertical water exchange were described. In coastal waters of the Crimea (Foros–Novy Svet), with intense western wind contributing to Ekman upwelling and low water temperature is a consequence of the upwelling, rather high values of phytoplankton biomass and abundance and chlorophyll a concentration were recorded, which were accompanied by the highest values of oxygen content. In the area of Sudak–Feodosiya, with intense northeastern wind and waves and with quite high water temperature, low dissolved oxygen, low values of phytoplankton biomass and abundance and chlorophyll a concentration were registered. Apparently, in Sevastopol area, Ekman upwelling arises under the effect of northern and northwestern winds. In three regions, dinoflagellate microalgae prevailed in spring 2022 in phytoplankton biomass. Those accounted for 52, 66, 81 % of the total number of species identified in the regions: Foros–Novy Svet, Sudak–Feodosiya, near Sevastopol, respectively. Thus, the main mechanisms were analyzed, which drive spatial distribution of quantitative characteristics and species composition of the phytoplankton community in the Crimean coastal water area with different shelf depths in spring.

Dynamics of Peatland Fires in South Sumatra in 2019: Role of Groundwater Levels

During the dry season, extensive peatland fires in South Sumatra and another peatland in Indonesia result in environmental damage and pose health risks to humans. The Indonesian Government has implemented several measures to prevent the recurrence of these fires. One such measure involves the establishment of observation stations to monitor hydrometeorological parameters in different peatlands across Indonesia, including those in South Sumatra. To effectively control fires in South Sumatra’s peatland and minimize hotspot occurrences, it is essential to determine hydrometeorological parameters that can serve as fire control indicators. Therefore, this study aimed to investigate the relationship between groundwater levels and hotspot occurrences by analyzing groundwater level data collected from six Peat Restoration Agency stations in South Sumatra’s peatland, along with hotspot data obtained from Moderate Resolution Imaging Spectroradiometer satellite measurements. The findings reveal a significant correlation between groundwater levels and hotspots at the six stations. As the GWL increased, the number of hotspots tended to decrease, and vice versa. This means that GWL can be used as a controlling variable for hotspot emergence. To effectively minimize hotspot occurrences, it is recommended to maintain a minimum groundwater level of −0.45 ± 0.09 m in the peatland of South Sumatra.

The influence of the hydrometeorological factors on the CO2 fluxes from the oligotrophic bog surface.

The influence of the hydrometeorological factors on the CO2 fluxes from the oligotrophic bog surface.

Assessment of Groundwater Recharge Using WetSpass-M and MODFLOW Coupling in Jedeb Watershed, Upper Blue Nile Basin, Ethiopia

Currently, the demand for water is rising, and as a result, the groundwater is declining. Water supplies are not sufficient for agricultural productivity, environmental preservation, or ecosystem services, resulting in an unbalanced water budget in the basin. The goal of this paper is to assess the groundwater recharge in the Jedeb sub-basin using WetSpass-MODFLOW coupling. A spatially distributed water balance model is developed to simulate long-term average recharge depending on land cover, soil texture, topography, and hydro meteorological parameters. The groundwater model is iteratively connected to the recharge model in order to simulate recharge. This means that the depth of the groundwater affects the recharge estimate and vice versa. The average yearly evapotranspiration, surface runoff, and groundwater recharge were determined using WetSpass-M to be 574, 898, and 99 mm, respectively. Groundwater recharge accounted for 6.3% of precipitation, while actual evapotranspiration and surface runoff accounted for 36.4% and 57% of precipitation, respectively. In such seasonal variations, the groundwater level in the Jedeb Sub-basin was studied under various stress conditions (dry season, wet season, and annually). The groundwater level distribution varied from 2,052.3 to 3,063.06 m in the summer stress period (recharge). While in the winter stress period (recharge), the groundwater level varied from 2,051.41 to 3,061.92 m, and the groundwater level due to the annual stress period (recharge) varied from 2,053.76 to 3,064.5 m. With a correlation coefficient of .89, which is an acceptable fit between the simulated and observed heads in steady state for all stress periods (summer, winter, and annual recharge). The contribution of this study could be used as baseline information for regional water resource experts, policymakers, and researchers for further investigation.

Analyzing trends and change points in hydro-meteorological parameters and groundwater level in the Barak river basin in India

Climate change has a substantial influence on a range of meteorological factors and the global hydrological cycle. This paper presents an analysis of the annual rainfall (P), temperature (including maximum temperature: Tmax, minimum temperature: Tmin, and average temperature: Tavg), stream flow (Q) data from 6 gauging sites, and groundwater level (GL) data from 7 groundwater stations in and around the Barak River Basin in India from 1986 to 2020. To identify patterns in the time series, the simple linear regression (SLR) approach, the Mann-Kendall (MK) test, the Hamid Mann-Kendall (HMK) test and the Spearman's Rho (SRO) tests have been employed. Pettit test has been used to identify the change points in the time series. The results indicated an increase in the Tmax and the Tmin across the study area, while no clear patterns were found in the Tavg time series. Except for the ‘Hailakhandi’ station, the annual total rainfall series showed an increasing trend. Tmax and Tmin showed a directional change point between 1999 and 2005, and between 2001 and 2007, respectively, according to change point analysis. Except for two stations, overall declining trends in the annual stream flow were found. Moreover, a total of five out of seven groundwater stations indicated a rise in groundwater levels. The findings presented here offer valuable insights into the current condition of the Barak basin and emphasize the importance of implementing sustainable water management practices.

Study of the Impact of Climatic Changes in 1980–2021 on Railway Infrastructure in the Central and Western Russian Arctic Based on Advanced Electronic Atlas of Hydrometeorological Parameters (Version 2, 2023)

Arctic zone of the Russian Federation (AZRF) is the region of intensive economic development. In this regard, it is critical to give an adequate assessment of natural factors that may have a negative impact on the growing technological infrastructure. Rapid climate change effects show a significant influence on this activity, including the railway network development. Hence, the decision-making community requires relevant information on climatic variations that can put at hazard the construction and operation of railway facilities. This paper presents the analysis of climatic changes within the region of Central and Western Russian Arctic in 1980–2021. It was performed using the new electronic Atlas of climatic variations in main hydrometeorological parameters, created for the Russian Railways in 2023. This geoinformatic product includes about 400 digital maps reflecting the variability of seven climatic parameters over more than four decades within the studied region. These parameters are air temperature, total precipitation, wind speed, soil temperature, soil moisture content, air humidity, and snow cover thickness. The analysis of climatic maps and their comparison between selected periods showed spatial and temporal heterogeneity of climatic variations in this region. This justifies the feasibility of further research using additional analytical instruments, such as Hovmöller diagrams, time series graphs, etc. The implementation of advanced geoinformatic products in the practice of the Russian Railways will facilitate sustainable development of its infrastructure in rapidly altering climatic conditions.

Histograms of the Caspian Sea Hydrometeorological Parameters

The article analyzes histograms of the distribution of the main hydrometeorological parameters of the Caspian Sea for 1980–2021 – air temperature, atmospheric pressure, absolute humidity, atmospheric precipitation and wind speed according to the MERRA-2 atmospheric reanalysis. Histograms were constructed for the entire study region of the Caspian Sea (36◦–48◦N, 45.625◦–55◦E), as well as separately for land and sea areas. The extremeness criteria were calculated based on the normal distribution and the real histogram for all 5 main meteorological parameters. A comparison was made of histograms obtained from MERRA-2 data and from weather station at Derbent located on the coast of the Caspian Sea. Distributions of average monthly wind speed, integral water vapor content and water vapor content in clouds over the Caspian Sea were also constructed according to microwave radiometry (SMMR, SSM/I) data for the time interval 1980–2021.

Early Flood Monitoring and Forecasting System Using a Hybrid Machine Learning-Based Approach

The occurrence of flash floods in urban catchments within the Mediterranean climate zone has witnessed a substantial rise due to climate change, underscoring the urgent need for early-warning systems. This paper examines the implementation of an early flood monitoring and forecasting system (EMFS) to predict the critical overflow level of a small urban stream on Lesvos Island, Greece, which has a history of severe flash flood incidents requiring rapid response. The system is supported by a network of telemetric stations that measure meteorological and hydrometric parameters in real time, with a time step accuracy of 15 min. The collected data are fed into the physical Hydrologic Engineering Center’s Hydrologic Modeling System (HEC-HMS), which simulates the stream’s discharge. Considering the HEC-HMS’s estimated outflow and other hydro-meteorological parameters, the EMFS uses long short-term memory (LSTM) neural networks to enhance the accuracy of flood prediction. In particular, LSTMs are employed to analyze the real-time data from the telemetric stations and make multi-step predictions of the critical water level. Hydrological time series data are utilized to train and validate the LSTM models for short-term leading times of 15 min, 30 min, 45 min, and 1 h. By combining the predictions obtained by the HEC-HMS with those of the LSTMs, the EMFS can produce accurate flood forecasts. The results indicate that the proposed methodology yields trustworthy behavior in enhancing the overall resilience of the area against flash floods.