Drought trends projection under future climate change scenarios for Iran region.

The study highlights the potential characteristics of droughts under future climate change scenarios. For this purpose, the changes in Standardized Precipitation Evapotranspiration Index (SPEI) under the A1B, A2, and B1 climate change scenarios in Iran were assessed. The daily weather data of 30 synoptic stations from 1992 to 2010 were analyzed. The HadCM3 statistical model in the LARS-WG was used to predict the future weather conditions between 2011 and 2112, for three 34-year periods; 2011-2045, 2046-2079, and 2080-2112. In regard to the findings, the upward trend of the potential evapotranspiration in parallel with the downward trend of the precipitation in the next 102 years in three scenarios to the base timescale was transparent. The frequency of the SPEI in the base month indicated that 17.02% of the studied months faced the drought. Considering the scenarios of climate change for three 34-year periods (i.e., 2011-2045, 2046-2079, and 2080-2112) the average percentages of potential drought occurrences for all the stations in the next three periods will be 8.89, 16.58, and 27.27 respectively under the B1 scenario. While the predicted values under the A1B scenario are 7.63, 12.66, and 35.08%respectively. The relevant findings under the A2 scenario are 6.73, 10.16, 40.8%. As a consequence, water shortage would be more serious in the third period of study under all three scenarios. The percentage of drought occurrence in the future years under the A2, B1, and A1B will be 19.23%, 17.74%, and 18.84%, respectively which confirms the worst condition under the A2 scenario. For all stations, the number of months with moderate drought was substantially more than severe and extreme droughts. Considering the A2 scenario as a high emission scenario, the analysis of SPEI frequency illustrated that the proportion of dry periods in regions with humid and cool climate is more than hot and warm climates; however, the duration of dry periods in warmer climates is longer than colder climates. Moreover, the temporal distribution of precipitation and potential evapotranspiration indicated that in a large number of stations, there is a significant difference between them in the middle months of the year, which justifies the importance of prudent water management in warm months.

Modelling monthly pan evaporation utilising Random Forest and deep learning algorithms.

Evaporation is the primary aspect causing water loss in the hydrological cycle; therefore, water loss must be precisely measured. Evaporation is an intricate nonlinear process occurring as a result of several climatic aspects. The purpose of this research is to assess the feasibility of using Random Forest (RF) and two deep learning techniques, namely convolutional neural network (CNN), and deep neural network (DNN) to accurately estimate monthly pan evaporation rates. Month-based weather data gathered from four Malaysian weather stations during the 2000-2019 timeframe was used to train and evaluate the models. Several input attributes (predictor variables) were investigated to select the most suitable variables for machine learning models. Every approach was tested with several models, each with a different set of model aspects and input parameter combinations. The formulated ML approaches were benchmarked against two commonly used empirical methods: Stephens & Stewart and Thornthwaite. Model outcomes were assessed using standard statistical measures to determine their effectiveness in predicting evaporation. The results indicated that the three ML models developed in the study performed better than empirical models and could significantly improve the precision of monthly Ep estimates even with the identical input sets. The performance assessment metrics also show that the formulated CNN approach was acceptable for modelling monthly water loss due to evaporation with a higher degree of accuracy than other ML frameworks explored in this study. In addition, the CNN framework outperformed other AI techniques evaluated for the same areas using identical data inputs. The investigation's findings in relation to the various performance criteria show that the proposed CNN model is capable of capturing the highly non-linearity of evaporation and could be regarded as an effective tool to predict evaporation.

Application of long short-term memory neural network technique for predicting monthly pan evaporation.

Evaporation is a key element for water resource management, hydrological modelling, and irrigation system designing. Monthly evaporation (Ep) was projected by deploying three machine learning (ML) models included Extreme Gradient Boosting, ElasticNet Linear Regression, and Long Short-Term Memory; and two empirical techniques namely Stephens-Stewart and Thornthwaite. The aim of this study is to develop a reliable generalised model to predict evaporation throughout Malaysia. In this context, monthly meteorological statistics from two weather stations in Malaysia were utilised for training and testing the models on the basis of climatic aspects such as maximum temperature, mean temperature, minimum temperature, wind speed, relative humidity, and solar radiation for the period of 2000-2019. For every approach, multiple models were formulated by utilising various combinations of input parameters and other model factors. The performance of models was assessed by utilising standard statistical measures. The outcomes indicated that the three machine learning models formulated outclassed empirical models and could considerably enhance the precision of monthly Ep estimate even with the same combinations of inputs. In addition, the performance assessment showed that Long Short-Term Memory Neural Network (LSTM) offered the most precise monthly Ep estimations from all the studied models for both stations. The LSTM-10 model performance measures were (R2 = 0.970, MAE = 0.135, MSE = 0.027, RMSE = 0.166, RAE = 0.173, RSE = 0.029) for Alor Setar and (R2 = 0.986, MAE = 0.058, MSE = 0.005, RMSE = 0.074, RAE = 0.120, RSE = 0.013) for Kota Bharu.

Application of M5 model tree optimized with Excel Solver Platform for water quality parameter estimation.

The high cost and time for determining water quality parameters justify the importance of application of mathematical models in discovering connection among them. This paper presents a data mining technique and its improved version in estimating water quality parameters. For this purpose, the surface and ground water quality data from Hamedan (Iran) between 2006 and 2015 were analyzed using M5 model tree and its modified version optimized with Excel Solver Platform (ESP). The values of electrical conductivity (EC), total dissolved solids (TDS), sodium adsorption ratio (SAR), and total hardness (TH) were considered as target variables, whereas pH, concentrations of sodium (Na), chlorine (Cl), bicarbonate (HCO3), sulfate (SO4), magnesium (Mg), calcium (Ca), and potassium (K) were as inputs. The results showed that in both the sources, pH was the least influential parameter on EC, TDS, SAR, and TH. It was found that among the objective parameters, the accuracy of models in estimating TH was higher than the other parameters, whereas SAR was a complex variable. The comparison of performances of the M5 and the M5-ESP models illustrated that the application of the ESP significantly decreased the normal root mean error (NRMSE) of the M5 model; the mean NRMSEs were decreased by 18.95% and 20.29% in estimating groundwater and surface water quality parameters, respectively. Moreover, ability of both the M5 and the M5-ESP models in computing objective parameters of the groundwater was found to be better than the surface water.

Environmental and geotechnical suitability of recycling waste materials from plasterboard manufacturing.

This paper presents the geotechnical and environmental suitability of recycling gypsum-based waste material produced from plasterboard manufacturing. Most of the current plasterboard manufacturing industries are dumping these wastes to landfills. Among the major impediments to recycling such waste are environmental concerns around using such recycled material, as well as proper and suitable places to use it. To investigate these, such a waste from an Australian plasterboard manufacturing company was collected and a series of geotechnical properties were tested to evaluate the materials' suitability for any engineering construction. It was found that the tested gypsum-based plasterboard materials are suitable to use as road subgrade, pipe bedding and pipe backfill material. To ascertain the environmental safety of using such material in regards to manual handling as well as contaminants' leaching into the surrounding environment, materials were thoroughly tested for more than a hundred different contaminants. Tests were conducted to evaluate both the contaminants' concentrations in the sample as well as the leaching behaviour of those contaminants. It was found that concentrations of the tested contaminants were either below the individual detection limit or the safe limit defined by the local regulatory authority.

Spatio-temporal analysis of urban growth and its impact on floods in Ajman City, UAE.

The negative consequences of urbanisation have been recently recognised despite the social and economic benefits it provides to the community. Effects of urbanisation include increases in surface runoff, frequency and magnitude of floods and urban water harvesting capacity. Accordingly, this study utilised multi-spectral and multi-resolution satellite images combined with field data to conduct a quantitative assessment of the impact of urbanisation on urban flooding for the period of 1975-2015 in Ajman City, United Arab Emirates (UAE). Results showed that urban areas in the city have increased by approximately 12-fold over the period 1975-2015, whilst the population increased by approximately 16-fold. Owing to a substantial increase in urbanisation (as impervious areas expanded), minimum precipitation to generate runoff in built areas dropped from approximately 16.37 mm in 1975 to approximately 13.3 mm in 2015, which caused a substantial increase in the surface runoff. To visualise the flooding potential, urban flooding maps were generated using a well-established decision analysis technique called Analytical Hierarchy Process. The latter adopted three thematic factors, namely excess rain, elevation and slope. Flooding potential was then found to have increased substantially, specifically in the downtown area. Finally, this study is expected to contribute highly to flood protection and sustainable urban storm water management in Ajman City.

Development of groundwater vulnerability zones in a data-scarce eogenetic karst area using Head-Guided Zonation and particle-tracking simulation methods.

Delineation of groundwater vulnerability zones based on a valid groundwater model is crucial towards an accurate design of management strategies. However, limited data often restrain the development of a robust groundwater model. This study presents a methodology to develop groundwater vulnerability zones in a data-scarce area. The Head-Guided Zonation (HGZ) method was applied on the recharge area of Oemau Spring in Rote Island, Indonesia, which is under potential risk of contamination from rapid land use changes. In this method the model domain is divided into zones of piecewise constant into which the values of subsurface properties are assigned in the parameterisation step. Using reverse particle-tracking simulation on the calibrated and validated groundwater model, the simulation results (travel time and pathline trajectory) were combined with the potential groundwater contamination risk from human activities (land use type and current practice) to develop three vulnerability zones. The corresponding preventive management strategies were proposed to protect the spring from contamination and to ensure provision of safe and good quality water from the spring.

Possible environmental impacts of recycled glass used as a pavement base material.

In theory, glass diverted or recovered from the municipal solid waste (MSW) stream can be used as feedstock (glass cullet) in the production of new glass containers. However, post-consumer glass typically contains a mixture of clear and coloured material and is often contaminated with other wastes; characteristics that are impediments to the production of new containers. Sorting and cleaning of glass diverted from MSW to make it feasible for use in bottle industries are also time consuming and costly tasks. There is, however, the potential to use recycled glass as a sub-base material for road pavement construction. Geotechnical investigations to date suggest that use of recycled glass as a roadway sub-base could be cost-effective, and thus preclude the need for expensive sorting. There is, however, the necessessity to further investigate the potential short- and long-term toxicity, health hazards, and/or environmental pollution associated with use of mixed glass cullet as an aggregate, considering conditions during stockpiled storage and after placement. The results of laboratory tests on recycled glass regarding its potential to release pollutants to the environment via leaching are presented herein. Five random samples of crushed glasses were collected from a recycling company in Melbourne, Australia. The parameters tested for each sample were total organic matter, heavy metals, sulfates, chlorides, conductivity, pH and surfactant levels. It wais found that in most cases, the contamination levels were within the State of Victoria's Environmental Protection Agency-specified limits for manual handling, thus indicating that recycled glass could probably be safely used in pavement sub-bases.

Modelling multi-species algal bloom in a lake and inter-algal competitions.

A numerical model was developed to simulate water quality and algal species composition in a deep lake. As artificial destratification is widely used in the lakes, a destratification (bubble plume) model was incorporated with the ecological model to simulate the dynamic responses of different species under artificial mixing. The ecological model predicts concentrations of PO(4)-P, NH(4)-N, NO(3)-N, DO and pH throughout the water column, all of which have a significant influence on the growth of different algal species. The model has been calibrated using data from Uokiri Lake (Japan) for two different species (Diatom and Cyanobacteria) with and without artificial mixing. The calibrated model was used to simulate different conditions of artificial mixing within the lake over a period of five months. The simulation results show that artificial mixing favors non-motile heavier species, such as Diatom, while preventing the growth of Blue-green algae. It is also demonstrated that intermittent operation of the artificial mixing is better for water quality amelioration than continuous operation.