Water Science and Technology, Artificial Intelligence, Waste Management and Disposal
39
Scopus Publications
Scopus Publications
Evaluation of fractal theory and LARS-WG downscaling model in precipitation and temperature forecasting via a climate change approach Mehdi Komasi, Bahareh Doorbashizadeh Journal of Water and Climate Change, 2025 In recent years, the disruption of the global climate balance due to the increase in greenhouse gases has introduced complexity in predicting hydrological processes. This research presents the changes in precipitation and temperature for the next 30 years (2024–2054) compared with the base period of 2002–2020, utilizing the HadCM3 and CanESM5 downscaling models from the CMIP6 models under the SSP1-2.6, SSP2-4.5, and SSP5-8.5 scenarios. Additionally, it examines the application of fractal theory to the Silakhor Plain. The results obtained from the climate models indicate that the prediction accuracies of the HadCM3 and CanESM5 models under the mentioned scenarios are very close to each other. In the best-case scenario, the optimistic scenario (SSP1-2.6) of the HadCM3 model, the average root mean square error values for the climatic parameters of precipitation and minimum and maximum temperatures are 0.39 mm, 1.26 °C, and 1.48 °C, respectively. The fractal model for the precipitation parameter falls within the range of strong stability (0.65–0.75). Similarly, the fractal model for the minimum and maximum temperatures is located in a very strong stability range (0.80–1.00), indicating that the time series has a long-term memory and an increasing trend.
Investigating Groundwater Level Fluctuations using Group Method of Data Handling and Empirical Bayesian Kriging Models (Case study: Silakhor plain) Mehdi Komasi, Hesam Goudarzi Numerical Methods in Civil Engineering, 2025 Groundwater level fluctuations and the lack of reliable methods for estimating them are major contributors to land subsidence. Data mining has increasingly applied artificial intelligence (AI) techniques in recent years to predict time series variations, including groundwater level changes. In this study, a temporal–spatial hybrid model was developed by integrating the Group Method of Data Handling (GMDH) with Empirical Bayesian Kriging (EBK) to predict monthly groundwater levels. The GMDH model was employed to extrapolate temporal variations one month ahead, while the EBK model interpolated spatial variations to generate regional groundwater level maps. The Silakhor Plain in Iran was chosen as the subject of the case study. The model was built using monthly data from 11 groundwater stations that were collected between 2003 and 2013. The hybrid model employed groundwater level observations and precipitation records as inputs. Results indicated that the GMDH-EBK model provided reliable and accurate predictions, with strong correlations in both training and testing phases. The model achieved coefficients of determination of 0.95, 0.91, 0.85, and 0.79 for the Hamyaneh, Chaghadon, Sugar Factory, and Valyan wells, respectively. Overall, the proposed methodology represents a significant advancement in regional groundwater modelling and offers a promising approach to supporting sustainable water resource management.
Optimizing pore pressure prediction in earth dams through the integration of panel data and intelligent models Behrang Beiranvand, Taher Rajaee, Mehdi Komasi Discover Applied Sciences, 2025 Modern dam safety management requires comprehensive instrumentation systems to monitor structural behavior and process critical data. Such systems play a vital role in identifying both immediate anomalies and gradual trends that may indicate potential safety hazards. This study presents an innovative spatiotemporal modeling approach that leverages data from properly functioning instruments to reconstruct missing measurements through panel data analysis. The research focuses on developing a robust pore pressure prediction system for Eyvashan Dam by integrating multiple artificial intelligence techniques—including Feed-Forward Neural Networks (FFNN), Support Vector Regression (SVR), Group Method of Data Handling (GMDH), and Ensemble Artificial Neural Networks (EANN)—with Fuzzy C-Means Clustering (FCM) methodology. The proposed framework was evaluated across three distinct operational scenarios, analyzing clustered measurement points to generate accurate pore pressure forecasts. Key findings demonstrate that combining data from a target piezometer with two neighboring instruments significantly enhances monitoring accuracy across all AI models tested. Comparative analysis revealed the EANN model to be particularly effective, establishing it as a reliable tool for pore pressure zone identification and monitoring in earth-fill dam structures. These results highlight the potential of integrated AI approaches to improve dam safety assessment, especially in situations with partial instrumentation failures or data gaps.
Presenting the AI models in predicting the settlement of earth dams using the results of spatiotemporal clustering and k-means algorithm Behrang Beiranvand, Taher Rajaee, Mehdi Komasi Scientific Reports, 2024 In this work, the results of instrumentation over 8 years, including the phases of construction, first impounding, and operation, have been used to analyze the location of the Eyvashan Dam settlement. Mohr–Coulomb behavioral model and numerical model of Plaxis 2D software were used to verify the monitoring results. The results demonstrated that settlement of the dam has increased in the dam's core since the beginning of construction, and they eventually stabilized during the operation phase. After the completion of the construction phase, the maximum settlement of the dam core was recorded as 809 mm, which is equivalent to 1.2% of the height of the dam at the middle level. Also, an approach to interpreting the settlement behavior of earth dams has been presented that is based on spatiotemporal clustering. Also, RF, MARS, and GMDH models were created based on a proposed scenario to predict settlement using points located in a cluster. Therefore, the settlement location of the studied dam was determined using the results of the k-means clustering algorithm in the aforementioned AI models. The high accuracy of the results of the proposed method confirms the proper performance of using AI models in predicting and diagnosing the settlement of earthen dams using the results of k-means spatiotemporal clustering algorithm. The evaluation of the models shows that the ENN model is a more suitable and efficient tool in this field and can be useful in monitoring the settlement of earth dams.
Optimizing the Design of Nickel and Composite Pressure Vessels Hassan Kamran, Mehdi Komasi, Behrang Beiranvand Computational Engineering and Physical Modeling, 2024 In this work, the replacement of nickel and composite materials instead of metal vessels in the oil industry has been investigated. The modeling is based on finite elements, and the capabilities of Abaqus finite element software have been used to consider the vessel's behavior against lateral forces and hydrostatic forces. In this regard, considering the high resistance of this material, the stresses and displacements experienced by the vessel against various forces have been investigated. Also, the behavioral comparison between the vessel made of nickel and composite and the metal vessel in this research is of interest. The results show that this type of vessel has a high resistance to lateral forces and a high potential to resist various mechanical forces. Static stresses in vessel optimization have been reduced by using nickel material and 400 Psi composite. Also, it has been reduced by 750 psi and 1.5 in against the stresses of the lateral forces of the wind and the displacement of the vessel against the force of the earthquake. Finally, displacement against wind force is optimized by 3 in, which shows the proper performance of the vessel.
Comparison of K-means and FCM algorithms to optimize spatiotemporal pore pressure prediction of earth dams Behrang Beiranvand, Taher Rajaee, Mehdi Komasi Results in Engineering, 2024 • This research shows that the prediction of the pore pressure zoning of earth dams using FCM and k-means algorithms in terms of the formation of homogeneous areas and acceptable estimates can be a suitable method for zoning and analyzing the pore pressure of dams. • By comparing the results of the clustering algorithms, it was found that the FCM algorithm has more suitable results than the k-means clustering algorithm due to the uncertainties in determining the boundaries of the classes. • The proposed method can reduce the collinearity between observations and provide a more accurate analysis of monitored points in spatial and temporal conditions. To identify the behavior and health monitoring of dams, it is necessary to correctly interpret the results of instrumentation in different phases of construction, impounding, and operation. Therefore, the approach based on spatiotemporal prediction is presented to improve the interpretation of pore pressure behavior of Eyvashan Earth Dam. In this research, using the results of other existing healthy piezometers, a spatiotemporal distribution model is proposed using panel data, which can be effective for predicting and reconstructing missing data. The optimal spatiotemporal clustering of pore pressure changes monitoring with K-Means and Fuzzy C-means (FCM) algorithms will enable the monitoring of points of the dam where instrumentations are not designed and installed or defective instrumentations. In predicting the pore pressure of dams, the input data is classified based on the pore pressure monitoring data, but with the use of clustering algorithms, the classification after the cluster analysis steps will lead to the proper resolution of the pore pressure clustering. According to the validation results of each of the clustering algorithms, the FCM clustering algorithm has more suitable results than the K-Means algorithm in determining the pore pressure clusters. In general, FCM clustering and K-Means algorithms are suitable and efficient tools in the field of more accurate monitoring of earth dams, and by using the proposed method, the detection of unusual areas of pore pressure and the related safety diagnosis is facilitated.
Spatiotemporal clustering of dam settlement monitoring using instrumentation data (case study: Eyvashan Earth Dam) Behrang Beiranvand, Taher Rajaee, Mehdi Komasi Results in Engineering, 2024 The integrity of monitoring data is important for studying the amount and location of deformation in earth dams. In this research, the meeting of the Eyvashan Earth Dam was analyzed using the results of precision instruments over a period of eight years during three periods of construction, first impoundment, and exploitation. To verify the accuracy of the results, the numerical model of the largest section of the dam was constructed with Plaxis software and analyzed according to the Mohr–Coulomb behavior model. The results showed that since the beginning of construction, the occurrence of settlements in the core of the dam has been increasing, and with the passage of time, settlements reach a constant value in the operation phase. The maximum settlement of the dam core at the end of the construction stage was 809 mm, which was equal to 1.2% of the dam height in the middle level. Additionally, an approach based on spatiotemporal clustering has been presented to improve the interpretability of the settlement behavior of earth dams. Clustering analysis of spatiotemporal data is used as a measure to determine the similarity of settlements and to select relevant data. Therefore, k-means clustering algorithms and two-step clustering were used to determine the displacement of earth dams. By comparing the correlation results, the proposed method of detecting settlement areas using a spatiotemporal clustering model can be considered a reliable method for monitoring the settlement of earth dams.
