Spatial and Temporal Variations of the Water Quality of the Tiflet River, Province of Khemisset, Morocco

An ensemble model for accurate prediction of key water quality parameters in river based on deep learning methods

Deep learning models provide a more powerful method for accurate and stable prediction of water quality in rivers, which is crucial for the intelligent management and control of the water environment. To increase the accuracy of predicting the water quality parameters and learn more about the impact of complex spatial information based on deep learning models, this study proposes two ensemble models TNX (with temporal attention) and STNX (with spatio-temporal attention) based on seasonal and trend decomposition (STL) method to predict water quality using geo-sensory time series data. Dissolved oxygen, total phosphorus, and ammonia nitrogen were predicted in short-step (1 h, and 2 h) and long-step (12 h, and 24 h) with seven water quality monitoring sites in a river. The ensemble model TNX improved the performance by 2.1%-6.1% and 4.3%-22.0% relative to the best baseline deep learning model for the short-step and long-step water quality prediction, and it can capture the variation pattern of water quality parameters by only predicting the trend component of raw data after STL decomposition. The STNX model, with spatio-temporal attention, obtained 0.5%-2.4% and 2.3%-5.7% higher performance compared to the TNX model for the short-step and long-step water quality prediction, and such improvement was more effective in mitigating the prediction shift patterns of long-step prediction. Moreover, the model interpretation results consistently demonstrated positive relationship patterns across all monitoring sites. However, the significance of seven specific monitoring sites diminished as the distance between the predicted and input monitoring sites increased. This study provides an ensemble modeling approach based on STL decomposition for improving short-step and long-step prediction of river water quality parameter, and understands the impact of complex spatial information on deep learning model.

Seasonal fluctuation of water quality and ecogenomic phylogeny of novel potential microbial pollution indicators of Veshaw River Kashmir-Western Himalaya

Nearly a billion people, especially in underdeveloped nations, need safe drinking water. Indian studies suggest that most drinking water sources have high coliform levels, and quality assurance is required. This study was conducted in rural parts of South Kashmir in the Western Himalaya from February 2019 to January 2020. Standard river water sampling was done from upstream to downstream of the river. This study examined the detection, molecular identification, and chemical water quality of coliform-contaminated drinking water, which sums up river water pollution. Water quality varied significantly, indicating downstream contamination. Sangam (downstream) had the highest coliform count, showing 72.2600 cfu per litre in summer, while Kongwaton (upstream), near the Veshaw River, had no coliform count in winter. In summer, Sangam (downstream) had the highest water quality metrics (pH 6.847, Electrical conductivity (EC) 71.620 dS/m, Biological oxygen demand (BOD) 1.120 mg/L, and Chemical oxygen demand (COD) 24.637 mg/L) in all seasons. The lowest winter water quality metrics in Kongwaton were pH 8.947, EC 253.680 dS/m, BOD 4.963 mg/L, and COD 51.440 mg/L. Coliforms in water suggest faecal contamination. This study examines the water quality attributes of drinking water and associated factors to determine river pollution. Total DNA was collected and sequenced for 16 S rDNA and metagenomics. Universal primers were used to amplify the bacterial 16 S rRNA. Using BLAST, the amplified 16 S rRNA gene sequence was matched to the NCBI database. A metagenomic study revealed 27 species with different relative abundance. These species include Escherichia coli, E. fergusonii, E. albertii, Klebsiella grimontii, and Shigella dysenteriae. This study is thought to be the first to discriminate against E. fergusonii, E. albertii, K. grimontii, and S. dysenteriae from E. coli and to report on E. fergusonii and E. albertii, K. grimontii, and S. dysenteriae in the river Veshaw water sources in Kulgam, Western Himalaya.

A Continuous Fixed Bed Adsorption Process for Fez City Urban Wastewater Using Almond Shell Powder: Experimental and Optimization Study

This study deals with the valorization of a biomaterial, almond shell, for the treatment of urban effluents of the city of Fez by a fixed bed column adsorption process. A parametric analysis of the process is carried out with conditions such as particle size, pH and height of the adsorbent bed to evaluate the optimal removal percent and obtain an optimal removal capacity of the adsorbent load. Characterization of the adsorbent prior to continuous adsorption was carried out by X-ray diffraction, Fourier-transform infrared spectrometry and scanning electron microscopy. The adsorption treatment seems to be influenced by certain parameters, such as the particle size of the biomaterial used, the height of the adsorption bed and the pH. The results suggest that this biomaterial can be used as a less expensive, available, biodegradable and very effective adsorbent to eliminate the load of urban waters on a small scale and why not on a large scale to replace chemicals in the treatment and to recover waste such as almond shell. The parameters measured reached maximum values varying between 82% for COD, 79% for EC and 71% for nitrite under well-defined operating conditions, with a particle size of 0.063 mm, a height column height of 7 cm and a pH of 6.5.