River Depth Research Articles

Machine Learning for the Sustainable Management of Depth Prediction and Load Optimization in River Convoys: An Amazon Basin Case Study

The seasonal fluctuation of river depths is a critical factor in designing cargo capacity for river convoys and logistics processes used for grain transportation in northern Brazil. Water level variations directly impact the load capacities of pusher convoys navigating the Amazon rivers. This paper presents a machine learning model based on a multilayer perceptron artificial neural network developed with the aim of estimating the cargo capacities of river convoys one year in advance, which is essential for determining load capacities during dry periods. The prediction model was applied to the Tapajós River in the Amazon Basin, Brazil, where grain transportation is significant and relies on inland waterways. Navigability conditions were evaluated in terms of depth and geometric parameters. The results of this case study were satisfactory, validating the computational tool and enabling the assessment of capacity losses during dry periods and the identification of navigation bottlenecks. The main contributions of this work include optimizing river logistics, reducing costs, minimizing environmental impacts, and promoting the sustainable management of water resources in the Amazon. Conclusions drawn from the study indicate that the developed model is highly effective, with an R2 of 0.954 and RMSE of 0.095, demonstrating its potential to significantly enhance river convoy operations and support sustainable development in the region.

A hybrid deep learning approach to predict hourly riverine nitrate concentrations using routine monitored data

With high-frequency data of nitrate (NO3–N) concentrations in waters becoming increasingly important for understanding of watershed system behaviors and ecosystem managements, the accurate and economic acquisition of high-frequency NO3–N concentration data has become a key point. This study attempted to use coupled deep learning neural networks and routine monitored data to predict hourly NO3–N concentrations in a river. The hourly NO3–N concentration at the outlet of the Oyster River watershed in New Hampshire, USA, was predicted through neural networks with a hybrid model architecture coupling the Convolutional Neural Networks and the Long Short-Term Memory model (CNN-LSTM). The routine monitored data (the river depth, water temperature, air temperature, precipitation, specific conductivity, pH and dissolved oxygen concentrations) for model training were collected from a nested high-frequency monitoring network, while the high-frequency NO3–N concentration data obtained at the outlet were not included as inputs. The whole dataset was separated into training, validation, and testing processes according to the ratio of 5:3:2, respectively. The hybrid CNN-LSTM model with different input lengths (1d, 3d, 7d, 15d, 30d) displayed comparable even better performance than other studies with lower frequencies, showing mean values of the Nash-Sutcliffe Efficiency 0.60–0.83. Models with shorter input lengths demonstrated both the higher modeling accuracy and stability. The water level, water temperature and pH values at monitoring sites were main controlling factors for forecasting performances. This study provided a new insight of using deep learning networks with a coupled architecture and routine monitored data for high-frequency riverine NO3–N concentration forecasting and suggestions about strategies about variable and input length selection during preprocessing of input data.

Livelihood adaptation to changes in River Ekulu depth, channel width and riverbank vegetation cover type by household breadwinners in selected communities in Enugu, Nigeria

Nigeria and most other developing countries need to explore using socio-ecological approaches to address some ecosystem challenges. Changes in river depth, channel width and riverbank vegetation cover type of River Ekulu in Enugu, Nigeria, their causes and effects on biodiversity and livelihood adaptation by household breadwinners, who depended on the river for livelihood activities, were investigated. Snowball sampling technique was adopted. Causes of changes in the river depth, channel width and riverbank vegetation cover type and their effects on biodiversity and livelihood adaptation were obtained from literature with Google Forms administered to purposively selected experts. Factor component analysis was used to select the significant ones. Aerial images of the river were captured with a drone. Questionnaire was used to elicit information from the target household breadwinners to corroborate the images or otherwise, the causes and the effects of the changes on biodiversity and livelihood adaptation. Data were analyzed to test seven null hypotheses bordering on the objectives of the study. Results showed that the observed changes led to adverse effect on biodiversity and the attendant imperative livelihood adaptation. Factors causing the changes in the river depth, width and riverbank vegetation cover type were climate change (factor weight, fw, 0.44–0.54) and increase in population density (fw 0.46–0.63). Recommendations include conscientisation of government and riverine neighbourhood dwellers on the observed ecological changes, their causes and effects, and ways-forward on policies and practices.

Meteotsunamis in the Tamsui River estuary, Taiwan

This study presents meteotsunami evolution and statistics in the Tamsui River estuarine system from 12 years observations. In the tide-dominated estuary, a strong correlation is observed between high tidal levels and the upstream propagation of meteotsunami waves. Such long waves travel the Tamsui River at an average speed of 6 m/s, while their speed slightly decreases to 4 m/s in the upstream rivers. The propagation changes are likely due to the contraction channel and shallow depth of the upstream rivers. During the upstream propagation, low-frequency waves (an average period of 44.5 min) have the significantly low reduction of wave height compared to high-frequency waves (an average period of 21.5 min). Findings suggest that low-frequency waves are capable of propagating over longer distances within the river estuary than high-frequency waves. In terms of long-term statistical analysis in 2014–2020, meteotsunamis predominantly occur in late winter and early spring. These events are primarily triggered by cluster and frontal convective storms, which are predominant atmospheric forcings responsible for initiating meteotsunami waves. These convective storms are often associated with incoming cold surges or cold fronts crossing the Taiwan Strait, which has implications on the role of pressure and wind disturbances, as well as the resonance mechanism in meteotsunami initiation. Furthermore, the study assesses the probability of meteotsunami occurrences, revealing that an annual prediction of wave height can reach up to 0.3 m. This finding raises concerns regarding potential hazards in Taipei City, where the population exceeds 6.8 million people. Of particular concern is the vulnerability of the Keelung River, which flows through the city center. In summary, the potential hazards posed by meteotsunamis in the Tamsui River estuary underscore the importance of risk management and preparedness measures.

Basin-analogy for calculating spring flood volumes at insufficiency of meteorological data (Tuba river as a case study)

Relevance. The necessity in provision of insufficient data on streamflow formation factors when predicting floods in the poorly explored and unstudied basins. For this purpose, in hydrological calculations and forecasts the method of hydrological analogy is applicable. Aim. To study probable application of the hydrological analogy method in calculations of spring flood volumes of a mountain river. The analysis was carried out by the example of the basins of the Tuba river and its tributaries (rivers Amyl, Kazyr and Kizir), as well as neighboring catchments (rivers Abakan and Syda). Methods. Integrated geographical-hydrometeorological analysis, correlation and regression analysis, and the hydrological analogy method. Results. We calculated total winter precipitation in the Amyl basin by means of (traditionally used in hydrology) elevation dependences, estimated average annual precipitation in the Tuba basin using modern glaciation data, and built a stochastic predictive model of flood runoff volume on the Amyl river (settl. Kachulka) based on the relationship between precipitation for the previous winter and flood periods. The influence of liquid (flood) precipitation on the forecast quality was analyzed. A comparative analysis of other Tuba tributaries (Kazyr, Kizir), including neighboring basins (rivers Abakan and Syda) in terms of their application as basins-analogies was performed. For instance, a feasible use of the Amyl basin as an analogy for forecasting flood runoff depth of the Tuba river (vill. Bugurtak) was analyzed. Conclusions. The correlation analysis of flood volumes of the Tuba, its main tributaries and neighboring rivers suggests that as an analogy the application of basins with similar conditions for precipitation formation (slope orientation relative to the direction of the prevailing moisture-bearing air masses) and average catchment elevation is currently favored. The Amyl basin use as the Tuba analogy is expedient for a medium-term forecast of melt runoff volumes (excluding liquid (flood) precipitation).

Metabolism Regimes in Regulated Rivers of the Illinois River Basin, USA

Metabolism estimates organic carbon accumulation by primary productivity and removal by respiration. In rivers it is relevant to assessing trophic status and threats to river health such as hypoxia as well as greenhouse gas fluxes. We estimated metabolism in 17 rivers of the Illinois River basin (IRB) for a total of 15,176 days, or an average of 2.5 years per site. Daily estimates of gross primary productivity (GPP), ecosystem respiration (ER), net ecosystem productivity (NEP), and the air-water gas exchange rate constant (K600) are reported, along with ancillary data such as river temperature and saturated dissolved oxygen concentration, barometric pressure, and river depth and discharge. Workflows for metabolism estimation and quality assurance are described including a new method for estimating river depth. IRB rivers are dominantly heterotrophic; however, autotrophy was common in river locations coinciding with reported harmful algal blooms (HABs) events. Metabolism of these regulated Midwestern U.S. rivers can help assess the causes and consequences of excessive algal blooms in rivers and their role in river ecological health.

Understanding the impact of population dynamics on water use utilizing multi-source big data

Abstract Population movement, such as commuting, can affect water supply pressure and efficiency in modern cities. However, there is a gap in the research concerning the relationship between water use and population mobility, which is of great significance for urban sustainable development. In this study, we analyzed the spatial–temporal dynamics of the population and its underlying mechanisms, using multi-source geospatial big data, including Baidu heat maps (BHMs), land use parcels, and point of interest. Combined with water consumption, sewage volume, and river depth data, the impact of population dynamics on water use was investigated. The results showed that there were obvious differences in population dynamics between weekdays and weekends with a ratio of 1.11 for the total population. Spatially, the population concentration was mainly observed in areas associated with enterprises, industries, shopping, and leisure activities during the daytime, while at nighttime, it primarily centered around residential areas. Moreover, the population showed a significant impact on water use, resulting in co-periods of 24 h and 7 days, and the water consumption as well as the wastewater production were observed to be proportional to the population density. This study can offer valuable implications for urban water resource allocation strategies.

A framework for parameter estimation, sensitivity analysis, and uncertainty analysis for holistic hydrologic modeling using SWAT+

Abstract. Parameter sensitivity analysis plays a critical role in efficiently determining main parameters, enhancing the effectiveness of the estimation of parameters and uncertainty quantification in hydrologic modeling. In this paper, we demonstrate an uncertainty and sensitivity analysis technique for the holistic Soil and Water Assessment Tool (SWAT+) model coupled with new gwflow module, spatially distributed, physically based groundwater flow modeling. The main calculated groundwater inflows and outflows include boundary exchange, pumping, saturation excess flow, groundwater–surface water exchange, recharge, groundwater–lake exchange and tile drainage outflow. We present the method for four watersheds located in different areas of the United States for 16 years (2000–2015), emphasizing regions of extensive tile drainage (Winnebago River, Minnesota, Iowa), intensive surface–groundwater interactions (Nanticoke River, Delaware, Maryland), groundwater pumping for irrigation (Cache River, Missouri, Arkansas) and mountain snowmelt (Arkansas Headwaters, Colorado). The main parameters of the coupled SWAT+gwflow model are estimated utilizing the parameter estimation software PEST. The monthly streamflow of holistic SWAT+gwflow is evaluated based on the Nash–Sutcliffe efficiency index (NSE), percentage bias (PBIAS), determination coefficient (R2) and Kling–Gupta efficiency coefficient (KGE), whereas groundwater head is evaluated using mean absolute error (MAE). The Morris method is employed to identify the key parameters influencing hydrological fluxes. Furthermore, the iterative ensemble smoother (iES) is utilized as a technique for uncertainty quantification (UQ) and parameter estimation (PE) and to decrease the computational cost owing to the large number of parameters. Depending on the watershed, key identified selected parameters include aquifer specific yield, aquifer hydraulic conductivity, recharge delay, streambed thickness, streambed hydraulic conductivity, area of groundwater inflow to tile, depth of tiles below ground surface, hydraulic conductivity of the drain perimeter, river depth (for groundwater flow processes), runoff curve number (for surface runoff processes), plant uptake compensation factor, soil evaporation compensation factor (for potential and actual evapotranspiration processes), soil available water capacity and percolation coefficient (for soil water processes). The presence of gwflow parameters permits the recognition of all key parameters in the surface and/or subsurface flow processes, with results substantially differing if the base SWAT+ models are utilized.

Inundation Mapping and Flood Frequency Analysis using HEC-RAS Hydraulic Model and EasyFit Software

Conducting a flood frequency analysis and mapping of the inundated area in rivers are important for river flow modeling. The main purpose of this research is to estimate the peak flow, model the inundated area using HEC-RAS, and conduct an analytical hierarchy process for the upper Baro Akobo basin in Ethiopia. The inundation area and river depth for 25, 50 and 100 years are considered while contemplating several factors which contribute to flooding. The downstream of the basin has experienced numerous floods that occurred in 2006, 2007, 2010, 2011, and 2012. Flood frequency analysis with stream flow data from 1990–2009 at the Baro-Gambella gauging station was carried out to estimate the expected peak floods of the watershed. The analysis was conducted using the Gumbel, Normal, and Log Pearson Type III distribution methods. The peak floods with return periods of 25, 50, and 100 years with a minimum statistical value calculated using the Normal distribution method resulted in 1739.586 m3/s, 1820.872 m3/s, and 1893.974 m3/s, respectively. The HEC-RAS model results indicated that the flood inundation areas under different land use changes for 25-, 50-, and 100-year return periods were 446.2 km2 (annual crop cover), 404.4 km2 (built area cover), 323.3 km2 (flooded vegetation), and 93.58 km2 (forest area), respectively, whereas the inundation depth ranged from 0–2.6 m, 0–2.9 m, and 0–3.2 m depth at the upstream and downstream of the river, respectively. The outcome of this study could be used to reduce temporal and permanent flood risk.

A new metric for sunlight exposure in rivers, lakes, and oceans

AbstractVertical motion is an important driver of sunlight exposure in aquatic environments, shaping the growth and fate of materials and organisms. We derive a simple model accounting for turbulent depth fluctuations of particles to predict the depth that contributes the most sunlight exposure (effective depth) as well as the single depth that, if measured at one place over time, produces the same total sunlight exposure as a moving particle (functional depth). Field measurements of light and depth in rivers using neutrally buoyant drifters and buoys validate our model. Effective depth varied from 0.1 to 1.5 m below the water surface and was ~ 30% of the overall water depth on average. Functional depth varied from 0.67 to 2.3 m and was ~ 50% of the overall water depth on average. Functional and effective depth are physically based concepts incorporating turbulent motion, spatial variability, and water clarity offering new approaches to characterize light exposure in aquatic environments.

Quantifying the variation of Scaly-sided merganser’ population and their divergent response to changes in hydrological connectivity of rivers in a high-latitude water tower

The Scaly-sided Merganser (SSME) is a globally endangered waterbird species, primarily inhabiting rivers. In recognition of its precarious status, it was added to the International Union for Conservation of Nature’s (IUCN) Red List of Threatened Species in 2002. The SSME is highly sensitive to ecological environmental changes driven by changes in hydrological connectivity, particularly within riverine habitats. Changbai Mountain, a high-latitude water tower in the Northeast Asia, is considered one of the most optimal breeding grounds for the SSME worldwide. Its extensive water system and dense primary forest create an environment particularly well-suited for this species. Over the past 40 years, rivers within Changbai Mountain have experienced phases of hydropower development and ecological restoration. These activities have dramatically altered the hydrological connectivity of the area. However, the response of SSME to these changes in aquatic ecology, driven by shifts in hydrological connectivity, remains uncertain. We employed the AutoRegressive Integrated Moving Average (ARIMA) model to analyze changes in the population size of the SSME. Furthermore, the GeoDetector model was used to understand the impact of ecological changes on the maximum population size (MPS) and distribution of SSME in the context of alterations in hydrological connectivity. Our findings reveal that the restoration of hydrological connectivity, a method of ecological restoration, exerts a bidirectional influence on both the distribution and the MPS of SSME. Our findings can be summarized as follows. Firstly, there was a general trend of increase in both the distribution points and population size of the SSME. Secondly, the contribution of driving factors to the MPS of SSME was ranked in the following order: temperature > Connectivity Status Index (CSI) > river width > fish abundance > river depth > velocity > altitude > forest type. Thirdly, the impacts on the distribution and MPS of SSME were not due to a single factor, but rather a complex interplay of multiple factors. Finally, the construction of small hydropower stations significantly disrupted the hydrological connectivity of rivers, thereby altering the natural habitat of the SSME. The reduction in fish population, resulting from the loss of hydrological connectivity, adversely affected the MPS. Conversely, an increase in water temperature due to loss of hydrological connectivity positively impacted the MPS. However, these effects displayed heterogeneity across different rivers. Our study suggests that the construction of gravel dams may be a suitable approach in certain sections of the river, with a recommended height limit of 1.5 m. This research provides valuable insights for managers, offering a sustainable foundation for future energy planning and ecological restoration efforts.

Damming consequences: Quantifying the effects on channel geometry and floodplain inundation

Dams have a profound effect on floodplain inundation and channel geometry. Still, few studies have analyzed detailed channel geometry changes, especially as they affect downstream floodplain inundation on large rivers. This research compared the Apalachicola River depths and floodplain inundation downstream of the Jim Woodruff Dam between early and late post-dam periods. We used hydrographic data for 1960 and 2010 collected by the U.S. Army Corps of Engineers. A ≤1.2 point/m2 LiDAR point cloud covering the entire floodplain was fused with the hydrographic data. After a forward and inverse transformation between coordinate systems, the combined data was converted into a riverbed digital elevation model (DEM). River geometric properties were calculated (Area, channel width, mean depth, thalweg elevation, and width-to-mean-depth ratio) for 1960 and 2010. Daily discharge and stage data (1928–2020) were collected for Chattahoochee and Blountstown gauge stations. Eleven flows, between the 10th and 99th percentile extracted from the daily flow duration curve for early and late post-dam periods, were used in a 2D hydrodynamic model, Hydrologic Engineering Center's River Analysis System (HEC-RAS) to simulate floodplain inundation. The result reveals that the riverbed degraded by about 1.5 m near the dam. Geometric changes between early and late post-dam periods include upper reaches deepening and narrowing (mean depth changed from ∼6.0 to ∼7.3 m with a consistent width), while the lower reach exhibited shallowing and widening (mean depth went from ∼6.0 m to ∼5.0 m). The channel area generally increased between the periods. Inundation depth was reduced by ∼1.0 m, for most flow categories, and decreased by 15 % from 1960 to 2010 for similar flows between the periods, particularly for the upper and middle reaches. Floodplain inundation extent deacreased by about 24.1 % for flow of ∼513 m3/s. The inundation decreases was partly due to alteration in geometric properties. This study highlights the need for comprehensive river morphology assessments to address human-induced degradation, changing inundation patterns, and their global implications in similar riverine ecosystems.

Flow Measurement Methods in Small Tributaries of the Teles Pires River, Southern of the Amazon Hydrological Region

The intensification of conflicts associated with the use of water in the transition region of the Cerrado and Amazon biomes caused by population and economic growth, combined with the interest in generating energy from hydroelectric plants, raise the need to quantify the surface water availability of rivers contributing with different drainage areas. The present study estimated and compared in loco measurements of liquid flow (QL) and the depth of rivers in the Teles Pires river basin by reference methods (MLN-7 hydrometric windlass and metal rod/winch) and by Acoustic Current Profiler by Doppler Effect (ADCP RiverRay), in this last method the uncertainty estimate of the total measurement time by ADCP was evaluated. Field measurements were carried out at monthly intervals between March 2020 and October 2021, seeking to represent the water seasonality and depth and QL variations in the cross-sections of the Caiabi 1 and 2, Celeste, Preto and Renato rivers. The evaluated rivers had a net flow between 3.48 and 60.78 m3 s−1 by the windlass and between 2.66 and 54.30 m3 s−1 by the ADCP, while the depths obtained were from 0.17 to 6.34 m by the rod/winch and from 0.65 to 6.20 m by the ADCP. The methods resulted in similar measurements of net flow and depth in each of the cross-sections, and the statistical performance of the linear regression model was satisfactory with a Willmott concordance index of 0.9977 and 0.9819 for estimates of QL and of the depth of the cross-sections, respectively. The ADCP accurately measured the net discharge and depth in shallow (up to 6.5 m) cross-sections of the Teles Pires River relative to the reference method. Determining the total measurement time and pairs of transects to obtain accurate QL by ADCP depends on the hydraulic characteristics of the watercourses.

Three-Dimensional Numerical Simulation of the Water Flow Effect on a Temporary Pier with Three Columns in Series

In order to ensure the safety of temporary piers during bridge construction, it is necessary to analyze the water flow effects on temporary piers during flood periods. Based on the practical engineering of a new bridge in Jiangxi province, a three-dimensional numerical model was established using the Reynolds Time Average Navier–Stokes equation (RANS) and SST k-ω turbulence model to simulate the flow force on three-column temporary piers in series. The stress state of the temporary pier was obtained under different flow velocities and submergence depths. The distribution characteristics of the flow field around the temporary pier and the flow force characteristics acting on the temporary pier were analyzed and compared with the monitoring measurement data and the Morison equation calculation data. The results indicate that the local flow was accelerated on both sides of the temporary pier, but the local acceleration effect along the river flow direction was weakened. The flow velocity of the water around the temporary pier decreases with the increasing of river depth. The pressure on the outer surface of the temporary pier is basically negative pressure, except for the positive pressure on the upstream side. The absolute value of the negative pressure on both sides is much greater than the positive pressure on the upstream side. As the submergence depth and flow velocity increase, the pressure in each area gradually increases. The pressure distribution of the upstream pier is basically symmetrical, while the pressure distribution of the middle and downstream piers is asymmetric due to the influence of the vortex shedding from the front pier, resulting in a change in the water flow incidence point. The turbulence intensity in each region of the flow field shows a trend of first increasing and then decreasing with the depth of the water flow. The drag coefficient and lateral force coefficient of the temporary pier are basically not affected by the inflow velocity, but the resistance and lateral force increase with the increase in submergence depth and inflow velocity.

Investigation of labyrinth weirs discharge coefficient with the same length

One of the approaches to reduce flood depth in dams and rivers is the application labyrinth weirs instead of simple linear weirs. Labyrinth weirs have a longer length than linear weirs; therefore, the flood will pass through it with a lower depth. In this study, two types of triangular and semicircular labyrinth weirs were experimentally investigated. Experiments were performed in a flume with a width of 0.8 m and a flow discharge of up to 70 L/s. Eight weir models with a thickness of 4 mm were made, of which four models are triangular weirs and four models are semicircular weirs. Weirs were used in two types, one-cycle and two-cycle. The height of the weirs is 15 cm and the ratio of the weir length to the flume width (L/W) is equal to 1.57. The results showed that the increase in the total water head ratio (HT/P) decreases the discharge coefficient in all models, which is due to the increase in the Nappe interference and the local submergence. Also, increasing the number of cycles in labyrinth weirs has reduced its efficiency. The reason for this decrease is the impact of the issuing jets at the junction of the cycles and the flow disturbance over the weir. The comparison between triangular and circular weirs showed the better efficiency of triangular weirs. In addition, the results showed that the placement of the top of the cycle towards the upstream will cause a better performance in the weir. It seems that the low angle of the weir wall in the downstream with the channel wall causes the Nappe flow to collide with the channel wall and consequent local submergence will ultimately reduce the discharge coefficient.

Evaluation of small hydropower turbines installed downstream of Nile River branches (Egypt)

The current study proposes a new strategy for using small hydroelectric turbines in downstream river branches with the least amount of construction and the lowest cost by comparing two different methods of installing the turbines, the first by installing the turbines at the river's bottom and the second by installing the turbines on floating boats. The methodology of this article is based on predicting the distribution of velocities through the watercourse using experimental data collected at various points in the river's depth, and then predicting the resulting electrical power for different sizes of turbines, as well as estimating the number of turbines for each row and the number of rows along the river. Therefore, Investigate the proposed systems. The proposed small hydropower system's economic viability and environmental impact are investigated in this article. According to the nature of the waterway, the best diameter of a turbine that can be used is 1.5 m based on water velocities and river depths. The proposed power plant generated 25.8 kW per single turbine row, with an estimated cost of produced power (0.035 USD/kWh) of approximately 20 turbines installed per row. Compared to other renewable energy sources, the proposed hydropower system is cost-effective and environmentally friendly, as generating electricity with the proposed small hydropower plant could reduce annual carbon dioxide emissions by 368 tones of CO2 per single turbine row.

A novel AI-based approach for modelling the fate, transportation and prediction of chromium in rivers and agricultural crops: A case study in Iran

Chromium (Cr) pollution caused by the discharge of industrial wastewater into rivers poses a significant threat to the environment, aquatic and human life, as well as agricultural crops irrigated by these rivers. This paper employs artificial intelligence (AI) to introduce a new framework for modeling the fate, transport, and estimation of Cr from its point of discharge into the river until it is absorbed by agricultural products. The framework is demonstrated through its application to the case study River, which serves as the primary water resource for tomato production irrigation in Mashhad city, Iran. Measurements of Cr concentration are taken at three different river depths and in tomato leaves from agricultural lands irrigated by the river, allowing for the identification of bioaccumulation effects. By employing boundary conditions and smart algorithms, various aspects of control systems are evaluated. The concentration of Cr in crops exhibits an accumulative trend, reaching up to 1.29 µg/g by the time of harvest. Using data collected from the case study and exploring different scenarios, AI models are developed to estimate the Cr concentration in tomato leaves. The tested AI models include linear regression (LR), neural network (NN) classifier, and NN regressor, yielding goodness-of-fit values (R2) of 0.931, 0.874, and 0.946, respectively. These results indicate that the NN regressor is the most accurate model, followed by the LR, for estimating Cr levels in tomato leaves.

Spatially consistent physical characteristics of UK rivers: 1‐km data

AbstractThe physical river characteristics datasets described here provide spatially consistent information to support hydrological and inundation modelling at a 1 km × 1 km resolution across the United Kingdom, on the British National Grid. The datasets of physical river characteristics provide gridded datasets (outflow drainage directions, catchment areas, widths of bankfull rivers and depths of bankfull rivers) and a comma‐separated table of NRFA (National River Flow Archive) gauging station locations. These datasets are derived from a range of sources: outflow drainage directions, catchment area and bankfull river widths are derived from existing higher resolution datasets, whereas bankfull river depths were harder to source and instead are derived from sparse historical measurements. The new gridded datasets provide a derived value for each UK land cell on the British National Grid (BNG). The comma‐separated NRFA gauging station locations table provides the most appropriate locations of 1,499 river flow gauging stations on the 1 km resolution grids, together with the approximate error in the 1 km × 1 km gridded delineation of the upstream catchment area. This article explains how UK‐wide 1‐km grids of these variables were estimated, their format and how to use them. The data are available from the Environmental Information Data Centre (EIDC).

The Impact of Hydrological Changes on Fish Assemblages in the Zachery Marshes of Southern Iraq

The present study was implemented in the Zachery Marsh as part of the middle marshes north of Bashar Province from January to December 2022 to investigate the impact of the seasons’ oscillation between drought and flooding on fish assemblage abundance, size spectrum, and ecological indices. Three stations were selected to collect samples of fish. The specimens were monthly gathered with different fishing tools, including fixed gillnets, cast nets, and electrofishing. The water temperature ranged from 12.32 to 34.03 °C, the salinity varied from 1.75 PSU to 2.89 PSU, and the pH fluctuated between 7.47 and 8.43. The rate of change in water depth in the low flat regions fluctuated from 27 cm in September to 76 cm in April. The mean water depth in rivers, small pits, and canals varied from 45 cm in October to the highest, 121 cm in March. In the seasonal regions, the average depth ranged from zero in July, August, September, and October to 40 cm in April. The current study documented 18 fish species belonging to 16 genera and 9 families from Zachery Marsh, all of them affiliated with the Osteichthyes class. Cyprinidae was the most abundant family, including six species. The species Planiliza abu, the most abundant species, formed 28.44%, Carassius gibelio constituted 20.27%, and Orechromis aureus represented 18.52%. The dominance index (D3) of the three dominant species was 67.23%. The size spectrum of the most commercial species was determined. The diversity index value ranged from 1.64 in August to 2.08 in June, the evenness index varied between 0.69 in May and 0.91 in December, and the richness index values fluctuated from 1.47 in August to 2.28 in June. Resident species represented 88.02%, seasonal species formed 6.08%, and the occasional fish species counted for 5.90%. The present study concludes that the fluctuation between drought and flooding has a critical role in the composition of fish assemblages, particularly in seasonal marshes that are subjected to extreme conditions. The fish evolve several reproductive strategies in these difficult conditions in order to survive and continue.

Potential of Using Machine Learning Regression Techniques to Utilize Sentinel Images for Bathymetry Mapping of Nile River

This paper investigates the potential of using the Sentinel-2 images for deriving bathymetric maps for the Nile River in Egypt. Regression analysis technique with the aid of in situ measurements were used. Exploring the effects of the size of calibration data, and water depth is another aim of this paper. Linear and machine learning regression techniques (Fine Decision Tree (FDT), and Random Forest (RF) Algorithms) are investigated. The study area is about 23 km between Assiut and Delta barrages. Around 82,000 depth points, are available. Regression models are developed using the depth data and the corresponding digital values of the 13 Sentinel-2 imagery bands. The linear regression model was not applicable (R2 = 0.02). The FDT, and RF models, have (R2 = 0.86) when half of the depth points were used for calibration, and the RMSE of the testing data (the other half of the depth points) equaled to 2.86 and 2.09 m, respectively. When fewer points were used for calibration, the R2 = 0.83 and 0.84, and RMSE = 2.65 and 2.19 m, for FDT and RF, respectively. When only the shallow water areas were considered, the RMSE reached 1.51 and 1.30 m for the FDT and RF, respectively. The VNIR bans of Sentinel-2 images are not enough to estimate the water depth of the Nile river. Collecting in situ measurements for small areas, is adequate for estimating the water depth and produces bathymetry maps for the Nile River in Egypt, and larger in situ measurements are not required.