Search

Water demand forecasting plays an important role in the sustainable management of water resources, especially in countries facing water scarcity challenges, such as the United Arab Emirates (UAE). Al-Ain, the second-largest city within the Emirate of Abu Dhabi and the fourth largest in the UAE, faces the dual challenge of anticipated population growth and forthcoming development initiatives. These factors are set to exert added pressure on the city's water resources. Hence, Al-Ain City requires an immediate assessment of future water demands as a critical step toward achieving sustainable development. The main objective of this study is to conduct a systematic analysis of historical consumption patterns and other relevant factors to predict future water demand and to present a water demand forecasting model to project the water requirements of Al-Ain City up to the year 2030. The proposed "Linear Forecast Model" for Al-Ain City is developed using the IWR-MAIN software (Version 6.0), with its core code developed by the U.S. Army Corps of Engineers' Institute for Water Resources. The results of this model suggest that the total water demand is projected to increase by 45% by the year 2030. Among the sectors, the residential sector is expected to have the highest water demand, accounting for approximately 61% of the total water demand by 2030. The governmental and agricultural sectors are estimated to contribute 20% and 10% to the total demand, respectively, with the remaining 9% distributed across the other four sectors. [ABSTRACT FROM AUTHOR]

Groundwater is more prone to contamination due to its extensive usage. Different methods are applied to study vulnerability of groundwater including widely used DRASTIC method, SI and GOD. This study proposes a novel method of mapping groundwater vulnerability using machine learning algorithms. In this study, point extraction method was used to extract point values from a grid of 646 points of seven raster layer in the Al Khatim study area of United Arab Emirates. These extracted values were classified based on nitrate concentration threshold of 50 mg/L into two classes. Machine learning models were developed, using depth to water (D), recharge (R), aquifer media (A), soil media (S), topography (T), vadose zone (I) and hydraulic conductivity (C), on the basis of nitrate class. Classified 'groundwater vulnerability class values' were trained using 10-fold cross-validation, using four machine learning models which were Random Forest, Support Vector Machine, Naïve Bayes and C4. 5. Accuracy showed the model developed by Random Forest gained highest accuracy of 93%. Four groundwater vulnerability maps were developed from machine learning classifiers and was compared with base method of DRASTIC index. The efficiency, accuracy and validity of machine learning based models were evaluated based on Receiver Operating Characteristics (ROC) curve and Precision-Recall curve (PRC). The results proved that machine learning is an efficient tool to access, analyze and map groundwater vulnerability. [ABSTRACT FROM AUTHOR]

Floods are among the devastating types of disasters in terms of human life, social and financial losses. Authoritative data from flood gauges are scarce in arid regions because of the specific type of dry climate that dysfunctions these measuring devices. Hence, social media data could be a useful tool in this case, where a wealth of information is available online. This study investigates the reliability of flood related data quality collected from social media, particularly for an arid region where the usage of flow gauges is limited. The data (text, images and videos) of social media, related to a flood event, was analyzed using the Machine Learning approach. For this reason, digital data (758 images and 1413 video frames) was converted into numeric values through ResNet50 model using the VGG-16 architecture. Numeric data of images, videos and text was further classified using different Machine Learning algorithms. Receiver operating characteristics (ROC) curve and area under curve (AUC) methods were used to evaluate and compare the performance of the developed machine learning algorithms. This novel approach of studying the quality of social media data could be a reliable alternative in the absence of real-time flow gauges data. A flash flood that occurred in the United Arab Emirates (UAE) from March 7–11, 2016 was selected as the focus of this study. Random forest showed the highest accuracy of 80.18% among the five other classifiers for images and videos. Precipitation/rainfall data were used to validate social media data, which showed a significant relationship between rainfall and the number of posts. The validity of the machine learning models was assessed using the area under the curve, precision-recall curve, root mean square error, and kappa statistics to confirm the validity and accuracy of the model. The data quality of YouTube videos was found to have the highest accuracy followed by Facebook, Flickr, Twitter, and Instagram. These results showed that social media data could be used when gauge data is unavailable. [ABSTRACT FROM AUTHOR]

This paper presents an approach to susceptibility mapping land subsidenceand sinkholes in the Al Ain area, UAE. A frequency ratio model was utilized to spatially analyse the relationship between locations of land subsidence and sinkhole and conditioning factors (CFs) to land subsidence susceptibility map. The values of eight essential CFs were employed as inputs to a random forest (RF) model. The produced map was compared with land subsidence and sinkhole locations and verified using the receiver operating characteristics (ROC). The results indicated a positive relationship and showed that the area under the curve was 88.4%, for the RF model. Thus, application of the approach using different algorithms could improve the performance of the modelling and the accuracy of the produced maps. The results of this study not only permit a better understanding of the impact of human activity and excessive groundwater extraction on ground surface stability, but also assist in enhancing geohazard mitigation strategies. [ABSTRACT FROM AUTHOR]

Microgravity monitoring was performed at four water wells in Al-Ain City (Abu Dhabi Emirate, United Arab Emirates) to understand the hydrodynamic characteristics of the shallow groundwater aquifer. Measurements of microgravity and water level at Wells 1–4 started in March 2018 and ended in March 2019, omitting the month of June due to weather conditions. A combination of time-lapse measurements of microgravity and groundwater levels in the wells was used to estimate the changes in groundwater storage from April 2018 to March 2019. Spatiotemporal changes in microgravity at the four water wells showed amplitudes between − 343.5 and 978.1 µGal with respect to a local reference. Water levels changes ranged between 1.85 and 3.95 m in March 2019 relative to March 2018. The calculated average water storage changes based on microgravity (∆Sg) ranged from 0.28 to 1.58 m over the entire study period for a specific yield (Sy) ranging from 15 to 40%. The average volume storage changes (∆Sh) for the study period ranged from 0.3 to 1.6 million m3 (with 15% < Sy < 40%). The microgravity method is recommended for monitoring shallow groundwater aquifers where there are few piezometric wells. [ABSTRACT FROM AUTHOR]

The Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) DEM and LANDSAT images of spatial resolution 30 m were used to construct groundwater potential zones (GPZ) map by integrating geological fractures, drainage network, slope and relief, and convergence index maps of the study area. Weight and score of each map were developed according to their level of contribution toward groundwater accumulation and spatial distribution of groundwater wells. The area that has very high potential for groundwater is located at the foot of Oman Mountains and Al Dhaid Depression covering an area of about 59.33 km², which is 4.40% of the study area. Further hydrological map and data on hydraulic properties of shallow aquifer, as recorded from observation wells in the regions, have been used to validate the produced GPZ map. The validation result showed sufficient agreement between the produced GPZ map. [ABSTRACT FROM AUTHOR]

The hydrological setting and groundwater quality of Musandam Peninsula was studied to investigate the influence of geological structures on the groundwater accumulation and groundwater salinity. Five sets of modified morphometric maps were used to reduce errors and carry out the geological structures. The modification was modified by applying mean filter to the Digital Elevation Model (DEM) then applying Soble filter with 10% threshold and equalization enhancement. D8 and algorithms were used to reveal the drainage basins and drainage networks of the entire area. The algorithm determines into which neighbouring pixel any water in a central pixel will flow naturally. Flow direction in a DEM is calculated for every central pixel of input blocks of a 3 × 3 window, all the time comparing the value of the central pixel in the window with the value of its eight neighbours. The spatial association between geological structures and drainage networks was studied using 2D graph and rose diagrams. Flood basin model was applied to simulate the Arabian Gulf water intrusion into the coastal aquifer. The concentrations of solutes in groundwater samples collected from Wadi Al Bih well field and well locations were correlated with the geological structure trends and intersections. The results of the study reveal that the drainage basins, drainage network and groundwater quality are structurally controlled by subsurface geological structure displacements. [ABSTRACT FROM AUTHOR]