Floods, one of the most common natural hazards globally, are challenging to anticipate and estimate accurately. This study aims to demonstrate the predictive ability of four ensemble algorithms for assessing flood risk. Bagging ensemble (BE), logistic model tree (LT), kernel support vector machine (k-SVM), and k-nearest neighbour (KNN) are the four algorithms used in this study for flood zoning in Jeddah City, Saudi Arabia. The 141 flood locations have been identified in the research area based on the interpretation of aerial photos, historical data, Google Earth, and field surveys. For this purpose, 14 continuous factors and different categorical are identified to examine their effect on flooding in the study area. The dependency analysis (DA) was used to analyse the strength of the predictors. The study comprises two different input variables combination (C1 and C2) based on the features sensitivity selection. The under-the-receiver operating characteristic curve (AUC) and root mean square error (RMSE) were utilised to determine the accuracy of a good forecast. The validation findings showed that BE-C1 performed best in terms of precision, accuracy, AUC, and specificity, as well as the lowest error (RMSE). The performance skills of the overall models proved reliable with a range of AUC (89–97%). The study can also be beneficial in flash flood forecasts and warning activity developed by the Jeddah flood disaster in Saudi Arabia.

Seawater intrusion (SWI) is the main threat to fresh groundwater (GW) resources in coastal regions worldwide. Early identification and delineation of such threats can help decision-makers plan for suitable management measures to protect water resources for coastal communities. This study assesses seawater intrusion (SWI) and GW salinization of the shallow and deep coastal aquifers in the Al-Qatif area, in the eastern region of Saudi Arabia. Field hydrogeological and hydrochemical investigations coupled with laboratory-based hydrochemical and isotopic analyses (¹⁸O and ²H) were used in this integrated study. Hydrochemical facies diagrams, ionic ratio diagrams, and spatial distribution maps of GW physical and chemical parameters (EC, TDS, Cl⁻, Br⁻), and seawater fraction (f_sw) were generated to depict the lateral extent of SWI. Hydrochemical facies diagrams were mainly used for GW salinization source identification. The results show that the shallow GW is of brackish and saline types with EC, TDS, Cl⁻, Br⁻ concentration, and an increasing f_sw trend seaward, indicating more influence of SWI on shallow GW wells located close to the shoreline. On the contrary, deep GW shows low f_sw and EC, TDS, Cl⁻, and Br⁻, indicating less influence of SWI on GW chemistry. Moreover, the shallow GW is enriched in ¹⁸O and ²H isotopes compared with the deep GW, which reveals mixing with recent water. In conclusion, the reduction in GW abstraction in the central part of the study area raised the average GW level by three meters. Therefore, to protect the deep GW from SWI and salinity pollution, it is recommended to implement such management practices in the entire region. In addition, continuous monitoring of deep GW is recommended to provide decision-makers with sufficient data to plan for the protection of coastal freshwater resources.

The aim of this study is to build a flood simulation model for the city of Hafr Al-Batin catchment area. The model consists of a hydrologic model, a hydraulic model and pre- and post-processing tools. A geographic information system-based modelling interface was used to pre-process the terrain and rainfall data and generate input files for hydrologic and hydraulic models. Soil map data, land cover map, land use map and digital elevation model was used to delineate the physical watershed's characteristics. The runoff estimation was based on the widely known Soil Conservation Service curve number approach. The hydrologic/hydraulic model simulations simulated the runoff hydrograph corresponding to different design storms and helped to delineate the resulting flood inundation maps. The results indicate good agreement between the delineated inundation map and the hazard map developed by the municipality. They also show that the location of the city complicates the runoff response for small storms creating two distinct peaks. The results of this study can be utilized for planning purposes and in the design of flood control structures as the study has estimated the runoff corresponding to different design storms and used hydraulics and geospatial data in delineating the flood zones.

The city of Jeddah experienced a severe flood in 2020, resulting in loss of life and damage to property. In such scenarios, a flood forecasting model can play a crucial role in predicting flood events and minimizing their impact on communities. The proposed study aims to evaluate the performance of machine learning algorithms in predicting floods and non-flood regions, including Gradient Boosting, Extreme Gradient Boosting, AdaBoosting Gradient, Random Forest, and the Light Gradient Boosting Machine, using the dataset from Jeddah City, Saudi Arabia. This study identified fourteen continuous parameters and various classification variables to assess the correlation between these variables and flooding incidents in the analyzed region. The performance of the proposed algorithms was measured using classification matrices and regression matrices. The highest accuracy (86%) was achieved by the Random Forest classifier, and the lowest error rate (0.06) was found with the Gradient Boosting regressor machine. The performance of other algorithms was also exceptional compared to existing literature. The results of the study suggest that the application of these machine learning algorithms can significantly enhance flood prediction accuracy, enabling various industries and sectors to make more informed decisions.