This study aims to develop an integrated approach for mapping and monitoring land use/land cover (LULC) changes and to investigate the impacts of LULC changes and population growth on groundwater level and quality using Landsat images and hydrological information in a Geographic information system (GIS) environment. All Landsat images (1990, 2000, 2010, and 2018) were classified using a support vector machine (SVM) and spectral analysis mapper (SAM) classifiers. The result of validation metrics, including precision, recall, and F1, indicated that the SVM classier has a better performance than SAM. The obtained LULC maps have an overall accuracy of more than 90%. Each pair of enhanced LULC maps (1990–2000, 2000–2010, 2010–2018, and 1990–2018) were used as input data for an image difference algorithm to monitor LULC changes. Maps of change detection were then imported into a GIS environment and spatially correlated against the spatiotemporal maps of groundwater level and groundwater quality. The results also show that the approximate built-up area increased from 227.26 km² (1.39%) to 869.77 km² (7.41%), while vegetated areas (farmlands, parks and gardens) increased from about 76.70 km² (0.65%) to 290.70 km² (2.47%). The observed changes in LULC are highly linked to the depletion in groundwater level and quality across the study area from the Oman Mountains to the coastal areas.

Mangrove forests are acting as a green lung for the coastal cities of the United Arab Emirates, providing a habitat for wildlife, storing blue carbon in sediment and protecting shoreline. Thus, the first step toward conservation and a better understanding of the ecological setting of mangroves is mapping and monitoring mangrove extent over multiple spatial scales. This study aims to develop a novel low-cost remote sensing approach for spatiotemporal mapping and monitoring mangrove forest extent in the northern part of the United Arab Emirates. The approach was developed based on random forest (RF), Kernel logistic regression (KLR), and Naive Bayes Tree machine learning algorithms which use multitemporal Landsat images. Our results of accuracy metrics include accuracy, precision, and recall, F1 score revealed that RF outperformed the KLR and NB with an F1 score of more than 0.90. Each pair of produced mangrove maps (1990–2000, 2000–2010, 2010–2019, and 1990–2019) was used to image difference algorithm to monitor mangrove extent by applying a threshold ranges from +1 to −1. Our results are of great importance to the ecological and research community. The new maps presented in this study will be a good reference and a useful source for the coastal management organization.

In an arid region, flash floods (FF), as a response to climate changes, are the most hazardous causing massive destruction and losses to farms, human lives and infrastructure. A first step towards securing lives and infrastructure is the susceptibility mapping and predicting of occurrence sites of FF. Several studies have been applied using an ensemble machine learning model (EMLM) but measuring FF magnitude using a hybrid approach that integrates machine learning (MCL) and geohydrological models have not been widely applied. This study aims to modify a hybrid approach by testing three machine learning models. These are boosted regression tree (BRT), classification and regression trees (CART), and naive Bayes tree (NBT) for FF susceptibility mapping at the northern part of the United Arab Emirates (NUAE). This is followed by applying a group of accuracy metrics (precision, recall and F1 score) and the receiving operating characteristics (ROC) curve. The result demonstrated that the BRT has the highest performance for FF susceptibility mapping followed by the CART and NBT. After that, the produced FF map using the BRT was then modified by dividing it into seven basins, and a set of new FF conditioning parameters namely alluvial plain width, basin gradient and mean slope for each basin was calculated for measuring FF magnitude. The results showed that the mountainous and narrower basins (e.g., RAK, Masafi, Fujairah, and Rol Dadnah) have the highest probability occurrence of FF and FF magnitude, while the wider alluvial plains (e.g., Al Dhaid) have the lowest probability occurrence of FF and FF magnitude. The proposed approach is an effective approach to improve the susceptibility mapping of FF, landslides, land subsidence, and groundwater potentiality obtained using ensemble machine learning, which is used widely in the literature.

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.

Mapping of groundwater potential in remote arid and semi-arid regions underneath sand sheets over a very regional scale is a challenge and requires an accurate classifier. The Classification and Regression Trees (CART) model is a robust machine learning classifier used in groundwater potential mapping over a very regional scale. Ten essential groundwater conditioning factors (GWCFs) were constructed using remote sensing data. The spatial relationship between these conditioning factors and the observed groundwater wells locations was optimized and identified by using the chi-square method. A total of 185 groundwater well locations were randomly divided into 129 (70%) for training the model and 56 (30%) for validation. The model was applied for groundwater potential mapping by using optimal parameters values for additive trees were 186, the value for the learning rate was 0.1, and the maximum size of the tree was five. The validation result demonstrated that the area under the curve (AUC) of the CART was 0.920, which represents a predictive accuracy of 92%. The resulting map demonstrated that the depressions of Mondafan, Khujaymah and Wajid Mutaridah depression and the southern gulf salt basin (SGSB) near Saudi Arabia, Oman and the United Arab Emirates (UAE) borders reserve fresh fossil groundwater as indicated from the observed lakes and recovered paleolakes. The proposed model and the new maps are effective at enhancing the mapping of groundwater potential over a very regional scale obtained using machine learning algorithms, which are used rarely in the literature and can be applied to the Sahara and the Kalahari Desert.

Mangrove forests are an important indicator of blue carbon storage and biodiversity and provide several benefits to the environment. This study showed the first attempt to apply the canonical correlation forest (CCF) model to classify mangroves and monitor changes in the mangrove forests of the entire region. The CCF model obtained a satisfactory accuracy with an F1 score of more than 0.90. Compared to Sentinel-2, Landsat 8 exhibited good temporal resolution with relatively little mangrove details. The resultant mangrove maps (1990–2020) were used to monitor changes in mangrove forests by applying a threshold value ranging from +1 to −1. The results showed a significant increase in the UAE mangroves over the period from 1990 to 2020. To characterize soil in mangrove forests, a set of interpolated maps for calcium carbonate, salinity concentration, nitrogen, and organic matter content was constructed. The results showed that there is a positive relationship between mangrove distribution and the calcium carbonate, nitrogen, salinity, and organic matter concentrations in the soil of the mangrove forests. Our results are of great importance to the ecological and research community. The new maps presented in this study will be a good reference and a useful source for the coastal management organization.