Nitrate Accumulation and Other Components of the Groundwater in Relation to Cropping System in an Aquifer in Southwestern Spain

Inappropriate farming techniques and 4 years of drought (1992–1995) produced conditions for high nitrate concentration in an aquifer located in the Province of Seville (Southwest Spain). The objectives of this study were to study groundwater components and to determine the relationship between the cropping system and nitrate concentrations in groundwater. From October 1994 to May 1996, 16 groundwater samples were obtained from a network of 35 sample points. Groundwater concentrations were analysed by multivariate statistical techniques (factor and cluster analysis). Two factors were found: firstly, agricultural pollution and secondly, salinization (from natural mineralization of groundwater and from anthropogenic effects). High levels of NO_3– were closely associated with intensive cotton (Gossypium herbaceum L.) and potato production (Solanum tuberosum L.). The salinization factor includes electrical conductivity, Cl_–, Na₊, Ca_{2 +}, Mg_{2 +}, SO_{42 –} and HCO_3–. Our study permits the impact of crops on groundwater to be determined. In comparison to the other crops, cotton (Gossypium herbaceum L.) and potato (Solanum tuberosum L.) made the greatest contribution to nitrate pollution and salinization. Use of the groundwater for human consumption in drought periods could represent a public health risk. Alternative farming techniques for these crops such as monitored fractional fertilization and controlled irrigation are recommended.     

IMPACT OF CHANGING HYDROLOGY ON NUTRIENT UPTAKE IN HIGH ARCTIC RIVERS

Despite the importance of river nutrient retention in regulating downstream water quality and the potential alterations to nutrient fluxes associated with climate‐induced changes in Arctic hydrology, current understanding of nutrient cycling in Arctic river systems is limited. This study adopted an experimental approach to quantify conceptual water source contributions (meltwater, groundwater), environmental conditions and uptake of NO₃^?, NH₄⁺, PO₄^3? and acetate at 12 headwater rivers in Svalbard and so determine the role of changing hydrology on nutrient uptake in these Arctic river systems. Most rivers exhibited low demand for NO₃^? and PO₄^3?, but demand for NH₄⁺ and acetate was more variable and in several rivers comparable with that measured in sub‐Arctic regions. The proportion of meltwater contributing to river flow was not significantly related to nutrient uptake. However, NH₄⁺ uptake was associated positively with algal biomass, water temperature and transient storage area, whereas acetate uptake was associated positively with more stable river channels. Mean demand for NH₄⁺ increased when added with acetate, suggesting NH₄⁺ retention may be facilitated by labile dissolved organic carbon availability in these rivers. Consequently, nutrient export from Arctic river systems could be influenced in future by changes in hydrological and environmental process interactions associated with forecasted climate warming. Copyright © 2013 John Wiley & Sons, Ltd.     

Suitability of Water Quality Indices for Application in Lakes in the Mediterranean

Water quality indices (WQIs) are efficient and powerful tools for evaluating, organising and communicating information on the overall quality of surface water bodies. The use of these indices may be very helpful in evaluating the water quality of aquatic systems in relation to the EU Water Framework Directive (WFD). In this study, two well-known water quality indices have been selected for evaluation: the CCME (Canadian Council of Ministers of the Environment) and NSF (National Sanitation Foundation). These WQIs were applied in the Polyphytos reservoir-Aliakmon river in Greece where monthly water quality data were available for the period June 2004 to May 2005. The available dataset included values of the following parameters: water depth, water temperature, dissolved oxygen, electrical conductivity, pH, transparency (Secchi disk depth), BOD₅, COD, total phosphorus (TP), chlorophyll-a (Chl-a), ammonium (NH₄ ⁺), nitrite (NO₂ ^?) and nitrate (NO₃ ^?), and total Κjeldahl nitrogen (TKN). The application of the two WQIs was made using specialised, freely available software-tools. A comparison of their performance and a qualitative judgement on their suitability on expressing the quality of a surface water body is presented. The classification results were compared with those obtained by the WFD-ECOFRAME approach of the EU. Based on the applicability and drawbacks of the examined indices, useful conclusions were derived and discussed. Among others, it is concluded that the NSF-WQI is a more robust index and produces a classification nearer that of the WFD-ECOFRAME approach when compared to the CCME-WQI.     

Quality Evaluation of Groundwater Resources using Geostatistical Methods (Case Study: Central Lorestan Plain,Iran)

In this research, based on the qualitative data of 40 wells, variations of water quality parameters of the Central Plain Aquifer were evaluated using kriging and IDW (Inverse Distance Weighting) methods. Owing to the normal distribution of the studied parameters (except Na⁺, SO₄^2?, and TH: total hardness), ordinary kriging was used for modeling. The analysis of the data trends indicated that all the variables were influenced by in two general trends, i.e., NW–SE and NE–SW. In fact, these trends were a result of the effect of the structural conditions on aquifer properties such as transmissivity and flow direction. Variogram analysis (based on C₀ near zero and C₀/σ² ratio between 0.0–0.5) showed that the Na⁺, TDS (total dissolved solids), Ca²⁺, and TH variables have a good spatial structure and the BOD (biochemical oxygen demand), COD (chemical oxygen demand), NO₃^?, and EC variables have poor spatial structure. The BOD, COD, NO₃^?, and EC (electrical conductivity) variables have the smallest range and isotropic distribution. On the other hand, the Ca²⁺, Mg²⁺, Na⁺, SO₄^2?, Cl^?, HCO₃^?, pH, TDS, TH and Alk (alkalinity) parameters are characterized by anisotropic distributions. The Na⁺, TDS, Ca²⁺, and TH variables have the largest range. The results showed that both the IDW and kriging methods have close estimates to one another. The pH variable decreases toward the outlet whereas the EC and TDS variables increase along the direction of water flow and toward the outlet. The distributions of the BOD and COD variables do not perfectly match with the aggregation of industrial activities in the central part as well as the agricultural activities in the southeastern and central parts of the aquifer. The distributions of the Ca²⁺, Mg²⁺, and Alk variables completely follow the geology condition and regional spread of carbonate formations. The Na⁺ concentration increases from the center toward the outlet. The concentration of the Cl^? variable is the highest in the central part of the plain due to the concentration of agricultural and industrial activities. The distribution of the SO₄^2? variable is influenced by a natural factor (lithology), especially in the southeastern parts and the outlet as well as artificial factors (agricultural and industrial activities) in the central and southeastern parts of the aquifer. The NO₃^? variable, which is directly influenced by agricultural and livestock-farming activities, has its maximum concentration in the southeastern areas.     

重庆老龙洞岩溶地下水化学特征及影响因素

为研究老龙洞地下河出口(G3)与表层岩溶泉(G1、G2)水化学特征差异及影响因素,利用统计方法对2012年月尺度的水化学数据进行分析。结果表明:研究区地下水水化学组成以Ca~(2+)、Mg~(2+)、HCO_3~-、SO_4~(2-)为主,水化学类型主要为Ca-HCO_3型;Ca~(2+)、Mg~(2+)、HCO_3~-浓度变异系数较小,主要来源于碳酸盐岩地层溶蚀,且以石灰岩溶解为主;硫酸与硝酸参与了碳酸盐岩的溶蚀,其中硫酸对碳酸盐岩溶蚀的影响更大;地下水中SO_4~(2-)、PO_4~(3-)、Na~+、K~+、Cl~-和NO_3~-浓度变异系数较大,主要受农业施肥、畜禽粪便、企业废水和生活污水等因素的影响;SO_4~(2-)、PO_4~(3-)、Na~+、K~+、Cl~-浓度表现为地下河高于表层岩溶泉,而NO_3~-浓度表现为地下河低于岩溶泉。     

A case study of regional catchment water quality modelling to identify pollution control requirements.

There are four ecologically important river catchments that contain candidate Special Areas of Conservation (cSACs) under the Habitats Directive in the Lake District National Park located in the North of England. These are the rivers Ehen, Kent, Derwent and Eden. For each cSAC, there are defined ecological criteria that include water quality targets to protect the designated species. Stretches of the riverine cSACs in each catchment are failing to meet these and other water quality targets. The Environment Agency commissioned a study of each catchment to provide the underpinning scientific knowledge to allow it to deliver its statutory obligations under the Habitats Directive. SIMCAT river water quality models were produced and used to predict the water quality impacts resulting from a number of water quality planning scenarios aimed at achieving full compliance with the Habitats Directive and other national and EEC water quality targets. The results indicated that further controls on effluent discharges will allow the majority of targets to be met but other sources of pollution will also need to be controlled. The outcome of the study also recognised that water quality improvements alone will not necessarily produce the required improvement to the ecological interest features in each cSAC.     

Nitrogen processing by biofilms along a lowland river continuum

While numerous studies have examined N dynamics along a river continuum, few have specifically examined the role of biofilms. Nitrogen dynamics and microbial community structure were determined on biofilms at six sites along a 120 km stretch of the lowland Ovens River, South Eastern Australia using artificial substrates. Terminal restriction fragment length polymorphism (T‐RFLP), chlorophyll a and protein analyses were used to assess biofilm microbial community composition. N dynamics was determined on the biofilms using the acetylene (C₂H₂) block technique and assessing changes in NH, NO_x and N₂O. Unlike microbial community structure, N dynamics were spatially heterogeneous. Nitrification, determined from the difference in accumulation of NH before and after addition of C₂H₂, occurred mostly in the upper sites with rates up to 1.4 × 10^?5 mol m^?2 h^?1. The highest rates of denitrification occurred in the mid‐reaches of the river (with rates up to 1 × 10^?5 mol m^?2 h^?1) but denitrification was not detected in the lower reaches. At the very most, only 50% of the observed uptake of NO_x by the biofilms following addition of C₂H₂ could be accounted for by denitrification. Copyright © 2005 John Wiley & Sons, Ltd.     

Study of water quality of springs in Petra region,Jordan: A three-year follow-up

Petra region area was located in south part of Jordan has grown and urbanized rapidly. This area depends on the groundwater as a water resources. This study was undertaken to assess the physical, chemical quality of spring water of Petra region during a 36-months survey (September 2002 to September 2005). The samples were analyzed for temperature, conductivity, dissolved oxygen, pH, major cations (Ca²⁺, Mg²⁺, K⁺, and Na⁺), major anions (Cl⁻, NO⁻ ₃, HCO⁻ ₃, SO²⁻ ₄, PO³⁻ ₄, F⁻) and trace metals (Fe²⁺, Al³⁺, Cu²⁺, Ni²⁺ Pb²⁺, Zn²⁺ and Mn²⁺). Water quality for available springs in the study area showed high salinity due to longer period of contact with rocks. The chemistry of spring water samples were alkaline earth waters with prevailing bicarbonate and alkaline earth waters with prevailing bicarbonate chloride. Some springs showed that elevated nitrate, sulfate contents which could be due to percolation from septic tanks, cesspools and irrigational activities. The infiltration of wastewater from cesspools and septic tanks into groundwater was considered the major source of water pollution. The results showed that there were considerable variations among the examined samples with respect to their physical and chemical parameters, which lie below the maximum permissible levels of the Jordanian and WHO drinking water standards. The results indicate that the trace metals of springs water of Petra region do not generally pose any health or environmental problems.     

Nutrient Regeneration by Zooplankton in Southern Lake Huron

Rates of nutrient regeneration by zooplankton (μmol/mg dry wt/hr) in southern Lake Huron from April to August 1975 ranged from undetectable to 2.6 for total phosphorus (TP), undetectable to 0.8 for total soluble phosphorus (TSP), undetectable to 0.12 for soluble reactive phosphorus (SRP), undetectable to 0.97 for ammonia (NH₃), undetectable to 3.8 for nitrate plus nitrite (NO₃ + NO₂), and undetectable to 2.9 for silica (SiO₂). Two diel experiments were conducted. Times of highest rates of regeneration varied for the different nutrients on these dates. Using the average concentration of zooplankton in the surface waters during this study, the calculated average concentration of nutrients regenerated by zooplankton was 0.012 μmol P/L/ hr for TP, 0.0046 μmol P/L/ hr for TSP, 0.0016 μmol P/L/ hr for SRP, 0.0146 μmol N/L/ hr for NH₃, 0.043 μmol N/L/ hr for NO₃ + NO₂, and 0.058 μmol Si/L/ hr for SiO₂. The contribution of nutrient regeneration by zooplankton to the turnover time of the various nutrients in the surface waters was calculated to be 212 hr for TP, 239 hr for TSP, 69 hr for SRP, 62 hr for NH₃, 505 hr for NO₃ + NO₂, and 531 hr for SiO₂. Although the turnover time for most of these nutrients is fairly slow, the nutrient pools for SRP and NH₃ are replenished in less than 70 hr by nutrient regeneration. Zooplankton therefore appear to play a significant role in the cycling of SRP and NH₃ in southern Lake Huron.     

Overview of USEPA/CLEAR Lake Erie Sediment Oxygen Demand Investigations During 1979

In situ hypolimnetic oxygen depletion measurements were conducted during four summer cruises in 1979 at two central basin stations in Lake Erie to evaluate the relative contribution of the sediments to the oxygen demand. Sediment oxygen demand (SOD) rates were determined by measuring the rate of oxygen decrease within a triangular benthic chamber; water column oxygen demand (WOD) rates were determined using 24-hour light and dark bottles placed in situ. Results indicated that the SOD contribution to the hypolimnetic oxygen depletion rate decreased throughout the summer from about 81% to only 30% with an initially high rate due to spring algal biomass sedimentation and lower rates in late summer due to depressed oxygen levels. The WOD rate contribution increased from 19% to 70% throughout the stratified period due to the decomposition of settling algal cells. Comparing the overall volumetric summer in situ rates (0.126 mg O₂/L/day) with cruise-interval depletion rates (0.365 mg O₂/L/day), the in situ rates were about 300% higher. This is attributed to unaccounted oxygen sources to the hypolimnion and because the in situ rates measure the gross WOD and SOD rather than measuring the net effects they exert.     

Storm effects on nitrogen flux and longitudinal variability in a river–reservoir system

Sustainable management of the nitrogen (N) cycle remains a considerable global challenge that has major implications for aquatic ecosystems. Dams play a critical yet often neglected role in addressing this challenge as they increase hydraulic residence time and denitrification potential. However, during storm events when the majority of N loading occurs, less is known about the effects dams have on N fate and transport processes. Here, we examined the flux of N species and phosphorus (P) and longitudinal profiles of nitrate (NO₃^?) along a sixth‐order river–reservoir system at baseflow and across the falling limb of a multiday, 1‐year storm hydrograph. During the storm event, the reservoir reduced total NO₃^? flux by 19.1% and P flux by 12.7%. On the contrary, ammonium (NH₄⁺) fluxes were 200% higher downstream of the dam in comparison with fluxes into the reservoir, indicating that there was a substantial net export of NH₄⁺ from the reservoir during the storm event. Longitudinally along the river to reservoir transition, a breakpoint of statistical significance was identified, highlighting the sharp contrast between NO₃^? concentrations within the river and reservoir. Results suggest that frequent storm events such as the one presented here can greatly alter N removal processes in river–reservoir systems. Overall, this study highlights the need to better understand the role that storm events play in river–reservoir N cycling dynamics.     

Modernizing the boiler installation for unit no. 3 at the Kashirskaya GRÉS to reduce nitrogen oxide emissions

The purpose of modernizing the Pp-1050-25-545 KGZh (P-50R) boiler is to reduce the emissions of nitrogen oxides (NO_x) to levels consistent with modern requirements. The following engineering steps were taken, with liquid slag removal from the boiler, to attain NO_x levels of 700–750 mg/m³ for operation with coal and 125 mg/m³ for operation with natural gas — three-stage combustion with natural gas as the reducing fuel (∼15% thermal) burning in the recirculating gases; and — use of low-emission coal-dust burners with dust feed at high concentrations, overflow burners, and tertiary draft nozzles to lower the amount of excess air in the active combustion zone. The NO_x level was further reduced to 570 g/m³ (just for operation with coal) by using a selective noncatalytic nitrogen oxide reduction system with injection of ammonia (NH₃) vapor into the boiler in a zone with temperatures of 950°C. __________ Translated from élektricheskie Stantsii, No. 1, pp. 2–8 (2008).     

改性凹凸棒土/纳米铁复合材料去除地下水NO_3~--N的研究

采用液相还原法制备改性凹凸棒土/纳米铁复合材料(简称复合材料),考察了该复合材料的稳定性及其作用下"三氮"(NO_3~--N、NH_4~+-N、NO_2~--N)的变化情况,阐明了地下水环境因素(DO、温度、光照)对复合材料去除NO_3~--N的影响。模拟地下水环境时,3种材料去除NO_3~--N的反应活性顺序为:复合材料纳米铁改性凹凸棒土,且复合材料作用下NH_4~+-N的转化率低,几乎无NO_2~--N生成。DO、温度对复合材料去除地下水NO_3~--N的影响较大;而光照和黑暗环境下,地下水中NO_3~--N的去除率及NH_4~+-N、NO_2~--N的生成量均无明显差异。研究成果旨在为NO_3~--N污染地下水工程修复提供理论依据和技术支撑。     

Combined analytical solution of overland flow and sediment transport

With reference to the kinematic wave theory coupled with the hypothesis of constant linear velocity for the rating curve, rising limb analytical solutions have been calculated for overland flow, over an Hortonian-infiltrating surface, and sediment discharge. These analytical solutions are certainly easier to use than the numerical integration of the basic equations and they may be used to obtain an initial evaluation of the parameters of more complex models generally devised for complicated cases.Notation a exponent of the Horton law [T^–1] - b exponent of the rill erosion equation - B inter-rill erosion coefficient [ML^–m–2T ^m–1] - c sediment concentration [ML^–3] - c _o reference sediment concentration [ML^–3] - E _I inter-rill erosion [ML^–2T^–1] - E _R rill erosion [ML^–2T^–1] - f _c final infiltration rate of the soil [LT^–1] - f _o initial infiltration rate of the soil [LT^–1] - h flow depth [L] - h _o reference flow depth [L] - i infiltration rate [LT^–1] - k rill erosion coefficient [ML^–1–b T^–1] - K integration constant - L() Laplace transformation - m exponent of the inter-rill erosion equation - n Manning's coefficient [L^–1/3T] - p rainfall intensity [LT^–1] - q water discharge per unit width [L²T^–1] - q _s sediment discharge per unit width [ML^–1T^–1] - t time [T] - t _p ponding time [T] - x distance along the flow direction [L] Greek Letters coefficient of the stage-discharge equation [L^2–T^–1] - exponent of the stage-discharge equation - rill erosion coefficient [L^–1]     

水质标识指数法在赣江尾闾段水质评价中的应用

赣江为鄱阳湖的重要补给水源,赣江水质对鄱阳湖生态有着重要影响。本文以电导率（EC）、浊度（TUR）、悬浮物（SS）、总磷（TP）、总氮（TN）、氨氮（NH₄-N）、硝态氮（NO₃-N）以及化学需氧量（COD）作为赣江水质评价指标,采用水质标识指数法对赣江尾闾段2015年10月30日、12月4日以及2016年1月12日、3月10日和5月30日5个时间点、3个支流、8个监测点的水质进行综合评价分析。分析结果表明：采用主要污染物水质标识指数法（PP-WQI）所得赣江下游北、中、南支流污染指数分别为3.84（COD）、3.53（COD）、3.84（COD/SS）,综合水质标识指数法（CWQI）所得污染指数分别为3.8077、3.5003、3.7465;水质介于Ⅲ类和Ⅳ类之间,属于轻度污染,主要污染物为COD、TN和SS。水质在空间上表现为中支较好,南支和北支较差,上游优于下游;在时间上表现为夏季（5月30日）最差,冬季最好（12月4日和1月12日）。     

Periphyton contribution to nitrogen dynamics in the discharge from a wastewater treatment plant

To evaluate the importance of periphyton to nitrogen dynamics in the discharge from wastewater treatment plants (WWTPs), we examined changes in total and inorganic nitrogen content downstream from a WWTP on the Kurose River in Hiroshima Prefecture, Japan. At 0.7 km downstream of the WWTP (point A), NH₄⁺?N was the dominant form of inorganic nitrogen, but concentrations decreased rapidly to 5 km downstream (point B). In contrast, no significant change in the [NO₂^?+ + NO₃^?]?N concentration was observed between the two points. Total nitrogen (TN) load decreased significantly between the two points, suggesting that sorption and/or denitrification occurred in the river channel. Potential rates of nitrogen sorption and transformation by periphyton were determined in a loboratory experiment in which changes in the nitrogen content of river water were examined in an acrylic chamber with periphyton. Nitrification and nitrogen removal occurred mainly in the periphyton. The contributions of periphyton activity to TN and NH₄⁺?N decrease in the field, as estimated from the results of the laboratory experiments, were 6–18% and 23–72%, respectively. These results suggest that periphyton plays an important role in decreasing NH₄⁺?N concentration in the discharge from wastewater treatment plants.     

Co-Kriging Estimation of Nitrate-Nitrogen Loads in an Agricultural River

Daily nitrate-nitrogen (NO₃-N) loads in the Raccoon River, Iowa, were estimated using Ordinary kriging (OK), Cokriging (CK), and a standard rating curve method (LOADEST) based on a dataset of 3451 measurements of NO₃-N concentration collected over 19 years. The CK estimation utilizes the temporal correlation of NO₃-N load with daily discharge and honors the measured points to improve estimation relative to regression based models. Loads were estimated using the observed concentrations and three subsets of the measured data that correspond to three frequencies (weekly, biweekly, and monthly). Results indicated that daily NO₃-N loads were best estimated by CK using measured loads with daily discharge. Daily load estimates produced by OK using weekly data matched well with measured values, but discrepancies emerged when samples were collected less frequently, e.g., biweekly and monthly. For the entire 19-year dataset, compared to measured loads, the estimated total NO₃-N load decreased using OK when samples were collected monthly, but increased using CK. Load estimation using the seven-parameter LOADEST model did not perform well for the Raccoon River because the correlation of NO₃-N concentration to river discharge was poor. For the site studied, weekly and biweekly sampling may be sufficient to estimate daily NO₃-N loads with CK when daily discharge data is available.     

Chronicles of hypoxia: Time-series buoy observations reveal annually recurring seasonal basin-wide hypoxia in Muskegon Lake – A Great Lakes estuary

We chronicled the seasonally recurring hypolimnetic hypoxia in Muskegon Lake – a Great Lakes estuary over 3?years, and examined its causes and consequences. Muskegon Lake is a mesotrophic drowned river mouth that drains Michigan's 2nd largest watershed into Lake Michigan. A buoy observatory tracked ecosystem changes in the Muskegon Lake Area of Concern (AOC), gathering vital time-series data on the lake's water quality from early summer through late fall from 2011 to 2013 (www.gvsu.edu/buoy). Observatory-based measurements of dissolved oxygen (DO) tracked the gradual development, intensification and breakdown of hypoxia (mild hypoxia <4?mg DO/L, and severe hypoxia <2?mg DO/L) below the ~6?m thermocline in the lake, occurring in synchrony with changes in temperature and phytoplankton biomass in the water column during July–October. Time-series data suggest that proximal causes of the observed seasonal hypolimnetic DO dynamics are stratified summer water-column, reduced wind-driven mixing, longer summer residence time, episodic intrusions of cold DO-rich nearshore Lake Michigan water, nutrient run off from watershed, and phytoplankton blooms. Additional basin-wide water-column profiling (2011–2012) and ship-based seasonal surveys (2003–2013) confirmed that bottom water hypoxia is an annually recurring lake-wide condition. Volumetric hypolimnetic oxygen demand was high (0.07–0.15?mg DO/Liter/day) and comparable to other temperate eutrophic lakes. Over 3?years of intense monitoring, ~9–24% of Muskegon Lake's volume experienced hypoxia for ~29–85?days/year – with the potential for hypolimnetic habitat degradation and sediment phosphorus release leading to further eutrophication. Thus, time-series observatories can provide penetrating insights into the inner workings of ecosystems and their external drivers.     

Eutrophication modelling of Amirkabir Reservoir (Iran) using an artificial neural network approach

The complicated non‐linear relationships between water quality and environmental parameters involved in predicting algal blooms necessitate a new approach, using data‐driven modelling. Accordingly, a multilayer perceptron (MLP) and time delay neural network (TDNN) were used to predict the eutrophication status of two monitoring stations in the Amirkabir Reservoir in Iran. Six scenarios for each monitoring station were performed to select a significant, independent input using 12 years of monthly data. The final inputs were temperature, turbidity, phosphate (PO₄), nitrate (NO₃), nitrite (NO₂), ammonium (NH₃), dissolved oxygen (DO) and electrical conductivity (EC). Applying an MLP neural network to the upstream monitoring station with 21–38 neurons in the first and second hidden layers, the minimum mean squared errors (MSE ) in training, validating and testing were 0.083, 0.81 and 1.95 cells/100 ml, respectively. Further, when the TDNN network was used with the same neuron numbers in the hidden layer for the similar monitoring station, the minimum MSE values for model training, validating and testing were 0.06, 0.72 and 1.76 cells/100 ml, respectively. For the Beylaghan monitoring station, using the MLP neural network with 29–23 neurons in the first and second hidden layer, the minimum MSE values gained in training, validating and testing were 0.181, 0.58 and 0.95 cells/100 ml, respectively. Using the TDNN network with the same neurons in the hidden layers of the MLP neural network for the station, the minimum MSE values for training, validating and testing were 0.152, 0.43 and 0.84 cells/100mL, respectively. Thus, TDNN exhibited a high accuracy and workability, compared to the MLP. Sensitivity analysis of the Amirkabir Reservoir dataset indicated increasing the value of nitrate is the first factor, followed by turbidity and NH₃, having the greatest impacts on eutrophication prediction.