Estimating the quantity of seepage through the foundation and body of a dam using proper health and safety monitoring is critical to the effective management of disaster risk in a reservoir downstream of the dam. In this study, a deep learning model was constructed to predict the extent of seepage through Pakistan’s Tarbela dam, the world’s second largest clay and rock dam. The dataset included hydro-climatological, geophysical, and engineering characteristics for peak-to-peak water inflows into the dam from 2014 to 2020. In addition, the data are time series, recurring neural networks (RNN), and long short-term memory (LSTM) as time series algorithms. The RNN–LSTM model has an average mean square error of 0.12, and a model performance of 0.9451, with minimal losses and high accuracy, resulting in the best-predicted dam seepage result. Damage was projected using a deep learning system that addressed the limitations of the model, the difficulties of calculating human activity schedules, and the need for a different set of input data to make good predictions.

This study presents the first comprehensive evaluation of the performance of three globally high‐resolution remotely sensed products in replicating the main characteristics of rainfall over the Middle East, with special emphasis on extreme wet events. Specifically, we employed daily observational data from a network of rain gauges (N = 217), spanning the retrospective period 1998–2013 and covering six countries in the Middle East (i.e., Egypt, Iraq, Jordan, Libya, Saudi Arabia, and Syria), against data derived from three global satellite‐based precipitation products: the Version 7 TRMM (Tropical Rainfall Measuring Mission) Multi‐satellite Precipitation Analysis 3B42 product (TRMM‐3B42), the Climate Prediction Center MORPHing technique (CMORPH), and the Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks (PERSIANN). Alongside a range of conventional statistical error measures (e.g., bias, normalized root‐mean‐square error [nRMSE] and Spearman's rho correlation coefficient), this study also gives priority to evaluate the skill of these products in reproducing characteristics of extreme wet events (e.g., frequency, intensity, duration, onset, anomaly). Results demonstrate that TRMM‐3B42 generally performs well in estimating rainfall totals during the rainy season (ONDJFMA), with a mean bias of 0.05 mm, nRMSE of 0.15 mm, and Spearman's rho of 0.74 for the whole Middle East. In contrast, PERSIANN‐CDR and CMORPH‐BLD underestimate the observed rainfall. Importantly, TRMM‐3B42 outperforms other products in reproducing the frequency and intensity of the most extreme wet events, while PERSIANN‐CDR and CMORPH‐BLD fail to reproduce these key characteristics. Notably, all products perform poorly in reproducing the climatology of the anomalous wet events in the region, indicating that careful scrutiny must be warranted before using these products, particularly for hydrological modelling. Considering the daily resolution of these remotely sensed precipitation products and their reasonable spatial resolution (0.25 × 0.25°) in comparison to available in situ data over the Middle East, results of this work provide a solid scientific reference for national stakeholders and policy makers to decide on the most useful product for their specific applications (e.g., hydrological modelling, streamflow forecasts, water resources management, and hydrometeorological hazard assessment and mitigation).

For better stability, safety and water resource management in a dam, it is important to evaluate the amount of seepage from the dam body. This research is focused on machine learning approach to predict the amount of seepage from Pakistan’s Earth and rock fill Tarbela Dam during 2003 to 2015. The data of temperature, rainfall, water inflow, sediment inflow, reservoir level collected during 2003 to 2015 served as input while the seepage from dam during this period was the output. Artificial Neural Network (ANN), Random Forest (RF), Support Vector Machine (SVM), and CatBoost (CB), have been used to model the input-output relationship. The algorithms used to predict the dam seepage reported a high R² scores between actual and predicted values of average seepage, suggesting their reliability in predicting the seepage in the Tarbela Dam. Moreover, the CatBoost algorithm outperformed, by achieving an R² score of 0.978 in training, 0.805 in validation, and 0.773 in testing phase. Similarly, RMSE was 0.025 in training, 0.076 in validation, and 0.111 in testing phase. Furthermore, to understand the sensitivity of each parameter on the output (average seepage), Shapley Additive Explanations (SHAP), a model explanation algorithm, was used to understand the affect of each parameter on the output. A comparison of SHAP used for all the machine learning models is also presented. According to SHAP summary plots, reservoir level was reported as the most significant parameter, affecting the average seepage in Tarbela Dam. Moreover, a direct relationship was observed between reservoir level and average seepage. It was concluded that the machine learning models are reliable in predicting and understanding the dam seepage in the Tarbela Dam. These Machine Learning models address the limitations of humans in data collecting and analysis which is highly prone to errors, hence arriving at misleading information that can lead to dam failure.

The over-exploitation of groundwater resources is a significant concern due to the potential risks associated with the depletion of this valuable freshwater source. Future planning must consider changes in groundwater availability and urban expansion which are critical for understanding urban growth patterns. This study aims to investigate the impact of land cover change on groundwater depletion. Further, the Land surface temperature (LST) analysis has been performed to find the spatial spread of urbanization and its impact on surface temperature. The Gravity Recovery and Climate Experiment (GRACE) data for groundwater storage monitoring and Landsat data for land cover and LST mapping have been used. The GRACE-based Groundwater Storage (GWS) anomaly has been correlated with Tropical Rainfall Measuring Mission (TRMM)-based precipitation data. The GWS is further cross validated with the groundwater monitoring stations in the study area and the correlation of 0.7 is found. The time series analysis of GWS and the land cover maps with a decadal interval from 1990 to 2020 has been developed to find the impact of groundwater change due to urbanization. The results demonstrate a rapid increase in groundwater depletion and urbanization rates over the past decade. The LST spatial pattern is increasing similarly with the study area’s urban expansion, indicating the temperature rise due to urbanization. The study highlights the limitation of effective policies to regulate groundwater extraction in urban areas and the importance of proper planning to ensure the long-term sustainability of freshwater resources.

A substantial interpretation of electromagnetic induction (EMI) measurements requires quantifying optimal model parameters and uncertainty of a nonlinear inverse problem. For this purpose, an adaptive Bayesian Markov chain Monte Carlo (MCMC) algorithm is used to assess multi-orientation and multi-offset EMI measurements in an agriculture field with non-saline and saline soil. In MCMC the posterior distribution is computed using Bayes' rule. The electromagnetic forward model based on the full solution of Maxwell's equations was used to simulate the apparent electrical conductivity measured with the configurations of EMI instrument, the CMD Mini-Explorer. Uncertainty in the parameters for the three-layered earth model are investigated by using synthetic data. Our results show that in the scenario of non-saline soil, the parameters of layer thickness as compared to layers electrical conductivity are not very informative and are therefore difficult to resolve. Application of the proposed MCMC-based inversion to field measurements in a drip irrigation system demonstrates that the parameters of the model can be well estimated for the saline soil as compared to the non-saline soil, and provides useful insight about parameter uncertainty for the assessment of the model outputs.