Daily and Monthly Suspended Sediment Load Predictions Using Wavelet Based Artificial Intelligence Approaches

In the current study, the efficiency of Wavelet-based Least Square Support Vector Machine(WLSSVM) model was examined for prediction of daily and monthly Suspended Sediment Load(SSL) of the Mississippi River. For this purpose, in the first step, SSL was predicted via ad hoc LSSVM and Artificial Neural Network(ANN) models; then,streamflow and SSL data were decomposed into subsignals via wavelet, and these decomposed sub-time series were imposed to LSSVM and ANN to simulate discharge-SSL relationship. Finally, the ability of WLSSVM was compared with other models in multistep-ahead SSL predictions. The results showed that in daily SSL prediction, LSSVM has better outcomes with Determination Coefficient(DC)=0.92 than ad hoc ANN with DC=0.88. However unlike daily SSL, in monthly modeling, ANN has a bit accurate upshot.WLSSVM and wavelet-based ANN(WANN) models showed same consequences in daily and different in monthly SSL predictions, and adding wavelet led to more accuracy of LSSVM and ANN. Furthermore,conjunction of wavelet to LSSVM and ANN evaluated via multi-step-ahead SSL predictions and, e.g.,DC LSSVM=0.4 was increased to the DC WLSSVM=0.71 in 7-day ahead SSL prediction. In addition, WLSSVM outperformed WANN by increment of time horizon prediction.

Application of different clustering approaches to hydroclimatological catchment regionalization in mountainous regions, a case study in Utah State

With respect to the different hydrological responses of catchments, even the adjacent ones, in mountainous regions, there are a great number of motivations for classifying them into homogeneous clusters. These motivations include prediction in ungauged basins(PUB), model parameterization, understanding the potential impact of environmental changes, transferring information from gauged catchments to the ungauged ones. The present study investigated the similarity of catchments through the hydro-climatological pure time-series of a 14-year period from 2001 to 2015. Data sets encompass more than 13,000 month-station streamflow, rainfall, and temperature data obtained from 27 catchments in Utah State as one of the eight mountainous states of the USA. The identification, analysis, and interpretation of homogeneous catchments were investigated by applying the four approaches ofclustering, K-means, Ward, and SOM(Self-Organized Map) and a newly proposed Wavelet-Entropy-based(WE-SOM) clustering method. By using two clustering evaluation criteria, 3, 5, and 6 clusters were determined as the best numbers of clusters, depending on the method employed, where each cluster represents different hydro-climatological behaviors. Despite the absence of geographic characteristics in input data matrix, the results indicated a regionalization in agreement with topographic characteristics. Considering the dependency of the hydrological behavior of catchments on the physiographic field aspects and characteristics, WE-SOM method demonstrated a more acceptable performance, compared to the other three conventional clustering methods, by providing more clusters. WE-SOM appears to be a promising approach in catchment clustering. It preserves the topological structure of data which can, as a result, be proofed in a greater number of clusters by dividing data into higher numbers of distinct clusters withsimilar altitudes of catchments in each cluster. The results showed the aptitude of wavelets to quantify the time-based variability of temperature, rainfall and streamflow, in the way contributing to the regionalization of diverse catchments.

Hybrid denoising-jittering data processing approach to enhance sediment load prediction of muddy rivers

Successful modeling of hydroenvironmental processes widely relies on quantity and quality of accessible data,and noisy data can affect the modeling performance.On the other hand in training phase of any Artificial Intelligence(AI) based model,each training data set is usually a limited sample of possible patterns of the process and hence,might not show the behavior of whole population.Accordingly,in the present paper,wavelet-based denoising method was used to smooth hydrological time series.Thereafter,small normally distributed noises with the mean of zero and various standard deviations were generated and added to the smooth time series to form different denoised-jittered data sets.Finally,the obtained pre-processed data were imposed into Artificial Neural Network(ANN) and Adaptive Neuro-Fuzzy Inference System(ANFIS)models for daily runoff-sediment modeling of the Minnesota River.To evaluate the modeling performance,the outcomes were compared with results of multi linear regression(MLR) and Auto Regressive Integrated Moving Average(ARIMA)models.The comparison showed that the proposed data processing approach which serves both denoising and jittering techniques could enhance the performance of ANN and ANFIS based runoffsediment modeling of the case study up to 34%and 25%in the verification phase,respectively.

Assessment of water quality suitability for agriculture in a potentially leachate-contaminated region

Dump sites pose a significant threat to groundwater resources due to the possibility of leachate leakage into the aquifer.This study investigated the impact of leachate on groundwater quality in the southwest region of Zanjan City,Iran,where groundwater is utilized for drinking,agricultural,and industrial purposes.We analyzed 18 parameters of dump site leachate,including physicochemical,heavy metals,and bacterial properties,alongside 13 groundwater samples.Sampling was conducted twice,in November 2020 and June 2021,within a five-kilometer radius of the Zanjan dump site.We utilized the Leachate Pollution Index(LPI)to evaluate potential groundwater contamination by leachate leakage from nearby dumpsite.Additionally,due to the predominant agricultural activities in the study area,various indices were employed to assess groundwater quality for agricultural purposes,such as Sodium Adsorption Ratio(SAR),Soluble Sodium Index(SSI),Kelly Ratio(KR),and Permeability Index(PI).Our analysis revealed no observed contamination related to leachate in the study area according to the LPI results.However,with the persistent pollution threat,implementing sanitary measures at the dump site is crucial to prevent potential impacts on groundwater quality.Moreover,the assessment of groundwater quality adequacy for irrigation yielded satisfactory results for SAR,KR,and PI indices.However,during both the dry(November 2020)and wet seasons(June 2021),the SSP index indicated that 80%of the samples were not classified as excellent,suggesting groundwater may not be suitable for agriculture.Overal,our qualitative study highlights the significant impact of the dry season on groundwater quality in the study area,attributed to elevated concentration levels of the investigated parameters within groundwater sources during the dry season.