Browsing by Author "Abdo, Hazem Ghassan"

Now showing 1 - 5 of 5

Estimation of Drought Trends and Comparison Between SPI and SPEI with Prediction Using Machine Learning Models in Rangpur, Bangladesh
(Taylor & Francis Group, 2023-09-09) Akter, Mst. Labony; Rahman, Md. Naimur; Azim, Syed Anowerul; Rony, Md. Rakib Hasan; Sohel, Md. Salman; Abdo, Hazem Ghassan
This study investigates drought trends, SPI-SPEI comparisons, and predictions in Rangpur, Bangladesh, from 1979 to 2020. We employed Modified Mann-Kendall for trend analysis, SPI and SPEI for drought assessment, and Pearson Correlation Coefficient and Simple Linear Regression for evaluating SPI and SPEI relationships. Additionally, we utilized ANN, SVM, and RF for prediction. The study revealed notable negative trends in seasonal and annual drought, with the highest z statistics observed for SPI 06 (-2.75), SPI 09 (-4.50), SPI 12 (5.60), SPI 24 (-8.40), SPEI 06 (-5.13), SPEI 09 (-6.82), SPEI 12 (-8.04), and SPEI 24 (-11.20). Strong correlations were identified across all SPI and SPEI indices, with coefficients peaking at 97%, 98%, 98%, and 97% for 06, 09, 12, and 24-month periods, respectively. The comparative assessment favored SPEI over SPI, highlighting its superiority and accuracy. The ANN prediction model showed significant results for short-term and seasonal drought forecasts, projecting SPEI 03 and SPEI 06 increases of 0.02 and 0.24, respectively. However, long-term drought estimation exhibited insignificant performance across all predictive models. This emphasizes the need for developing essential predictive tools for future drought variability.
Flood mapping based on novel ensemble modeling involving the deep learning, Harris Hawk optimization algorithm and stacking based machine learning
(2024-03-14) Costache, Romulus; Pal, Subodh Chandra; B. Pande, Chaitanya; Md. Towfiqul Islam, Abu Reza; Alshehri, Fahad; Abdo, Hazem Ghassan
Among the various natural disasters that take place around the world, flood is considered to be the most extensive. There have been several floods in Buzău river basin, and as a result of this, the area has been chosen as the study area. For the purpose of this research, we applied deep learning and machine learning benchmarks in order to prepare flood potential maps at the basin scale. In this regard 12 flood predictors, 205 flood and 205 non-flood locations were used as input data into the following 3 complex models: Deep Learning Neural Network-Harris Hawk Optimization-Index of Entropy (DLNN-HHO-IOE), Multilayer Perceptron-Harris Hawk Optimization-Index of Entropy (MLP-HHO-IOE) and Stacking ensemble-Harris Hawk Optimization-Index of Entropy (Stacking-HHO-IOE). The flood sample was divided into training (70%) and validating (30%) sample, meanwhile the prediction ability of flood conditioning factors was tested through the Correlation-based Feature Selection method. ROC Curve and statistical metrics were involved in the results validation. The modeling process through the stated algorithms showed that the most important flood predictors are represented by: slope (importance ≈ 20%), distance from river (importance ≈ 17.5%), land use (importance ≈ 12%) and TPI (importance ≈ 10%). The importance values were used to compute the flood susceptibility, while Natural Breaks method was used to classify the results. The high and very high flood susceptibility is spread on approximately 35–40% of the study zone. The ROC Curve, in terms of Success, Rate shows that the highest performance was achieved FPIDLNN-HHO-IOE (AUC = 0.97), followed by FPIStacking-HHO-IOE (AUC = 0.966) and FPIMLP-HHO-IOE (AUC = 0.953), while the Prediction Rate indicates the FPIStacking-HHO-IOE as being the most performant model with an AUC of 0.977, followed by FPIDLNN-HHO-IOE (AUC = 0.97) and FPIMLP-HHO-IOE (AUC = 0.924).
Microplastics contamination through a mighty estuarine island: Distribution, influencing factors, and risk assessment
(2024-12-20) Arefin, Shahoriar; Md. Towfiqul Islam, Abu Reza; Hasan, Mehedi; Mubin, Al-Nure; Alinur Rahman, Md.; Ali, Mir Mohammad; Siddique, Md Abu Bakar; Abdo, Hazem Ghassan; Idris, Abubakr M.; Pal, Subodh chandra; Malafaia, Guilherme; Senapathi, Venkatramanan
The global concern over microplastic (MP) contamination in diverse ecosystems is well-established, yet Nijhum Dwip Island (NDI), known for its ecological diversity, has not undergone a comprehensive study addressing the extent of MP pollution. This research aims to evaluate the spatial distribution, influencing factors, and ecological risks of MPs in both sediment and surface water surrounding NDI, situated in the Northern Bay of Bengal. A meticulous collection of 40 sediment and 40 tidal water samples from various sites facilitated a detailed analysis. The mean abundance of MPs in sediment was 138.39 ± 34.15 pieces/kg, while in water, it was 72.83 ± 30.76 pieces/m³. Various shapes observed on NDI included films, fragments, fibers, and foams, with fragments dominating in sediment (64.05 %) and water (61.51 %). Analysis of FTIR spectra identified two primary polymer types, namely polyethylene (PE) at 57 % and polypropylene (PP) at 40 %. The results indicated elevated pollution levels on NDI, with sediment and water pollution load index measuring 1.32 and 2.01, respectively, signifying significant MP contamination in both compartments. Given the island's rare biodiversity, the vicinity of wastewater sewages, anthropogenic activities, and atmospheric deposition, could be behind MP contamination in water and sediments. No strong correlation between MP and physiochemical properties in water and PCA biplots showed their similar distribution, whereas MP abundances in sediment were significantly correlated with pH and organic matter (p<0.05), signifying a pivotal role in transporting MPs in the aquatic environment. Two canonical variables were identified as important by canonical correlation analysis, demonstrating the interdependence of MP contamination at the sample sites. This research contributes to better insights into the occurrence of MP in the rare islands, which are ecosystems that have been hardly examined for this type of pollution, and it can report sustainable interventions to lessen MP inputs to the Bay of Bengal.
Microplastics contamination through a mighty estuarine island: Distribution, influencing factors, and risk assessment
(Regional Studies in Marine Science, Elsevier, 2024-12-20) Arefin, Shahoriar; Islam, Abu Reza Md. Towfiqul; Hasan, Mehedi; Mubin, Al-Nure; Rahman, Md. Alinur; Ali, Mir Mohammad; Siddique, Md Abu Bakar; Abdo, Hazem Ghassan; Idris, Abubakr M.; Pal, Subodh chandra; Malafaia, Guilherme; Senapathi, Venkatramanan
The global concern over microplastic (MP) contamination in diverse ecosystems is well-established, yet Nijhum Dwip Island (NDI), known for its ecological diversity, has not undergone a comprehensive study addressing the extent of MP pollution. This research aims to evaluate the spatial distribution, influencing factors, and ecological risks of MPs in both sediment and surface water surrounding NDI, situated in the Northern Bay of Bengal. A meticulous collection of 40 sediment and 40 tidal water samples from various sites facilitated a detailed analysis. The mean abundance of MPs in sediment was 138.39 ± 34.15 pieces/kg, while in water, it was 72.83 ± 30.76 pieces/m³. Various shapes observed on NDI included films, fragments, fibers, and foams, with fragments dominating in sediment (64.05 %) and water (61.51 %). Analysis of FTIR spectra identified two primary polymer types, namely polyethylene (PE) at 57 % and polypropylene (PP) at 40 %. The results indicated elevated pollution levels on NDI, with sediment and water pollution load index measuring 1.32 and 2.01, respectively, signifying significant MP contamination in both compartments. Given the island's rare biodiversity, the vicinity of wastewater sewages, anthropogenic activities, and atmospheric deposition, could be behind MP contamination in water and sediments. No strong correlation between MP and physiochemical properties in water and PCA biplots showed their similar distribution, whereas MP abundances in sediment were significantly correlated with pH and organic matter (p<0.05), signifying a pivotal role in transporting MPs in the aquatic environment. Two canonical variables were identified as important by canonical correlation analysis, demonstrating the interdependence of MP contamination at the sample sites. This research contributes to better insights into the occurrence of MP in the rare islands, which are ecosystems that have been hardly examined for this type of pollution, and it can report sustainable interventions to lessen MP inputs to the Bay of Bengal.
Using fuzzy and machine learning iterative optimized models to generate the flood susceptibility maps: case study of Prahova River basin, Romania
(Daffodil International University, 2023-11-21) Costache, Romulus; Abdo, Hazem Ghassan; Mishra, Arun Pratap; Pal, Subodh Chandra; Islam, Abu Reza Md. Towfiqul; Pande, Chaitanya B.
In this work, the vulnerability to flooding in the Prahova River basin was calculated and analyzed using advanced methods and techniques. Thus, 2 hybrid models represented by Iterative Classifier Optimizer – Multiclass Alternating Decision Tree – Certainty Factor (ICO-LADT-CF) and Fuzzy-Analytical Hierarchy Process – Certainty Factor (FAHP-CF) were generated, which had as input data the values of 10 flood predictors and a number of 158 points where historical floods occurred. In the first step, the Certainty Factor values were calculated, which were then used in the Fuzzy-Analytical Hierarchy Process and Multiclass Alternating Decision Tree models. It should be mentioned that the Multiclass Alternating Decision Tree model was optimized with the help of the Iterative Classifier Optimizer. In the case of both ensemble models the slope angle was the most important flood conditioning factor. Moreover, according to Certainty Factor modelling the 8 classes/categories achieved the maximum value of 1. Next, the susceptibility to floods on the surface of the study area was derived. On average, about 20% of the study area has areas with high and medium susceptibility to flash floods. After evaluating the quality of the models through Receiver Operating Characteristics (ROC) Curve, the following results emerged: Success Rate for Flood Potential Index (FPI) Iterative Classifier Optimizer – Multiclass Alternating Decision Tree – Certainty Factor (ICO-LADT-CF) (Area Under Curve = 0.985) and Flood Potential Index (FPI) Fuzzy-Analytical Hierarchy Process – Certainty Factor (FAHP-CF) (Area Under Curve = 0.967); Prediction Rate for Flood Potential Index (FPI) Iterative Classifier Optimizer – Multiclass Alternating Decision Tree – Certainty Factor (ICO-LADT-CF) (Area Under Curve = 0.952) and Flood Potential Index Fuzzy-Analytical Hierarchy Process – Certainty Factor (FAHP-CF) (Area Under Curve = 0.913). At the same time, the accuracies of the models were: Training dataset − 0.943 (Iterative Classifier Optimizer – Multiclass Alternating Decision Tree – Certainty Factor) and 0.931 (Fuzzy-Analytical Hierarchy Process – Certainty Factor); Validating dataset − 0.935 (Iterative Classifier Optimizer – Multiclass Alternating Decision Tree – Certainty Factor) and 0.926 (Fuzzy-Analytical Hierarchy Process – Certainty Factor). As main conclusion, it can be mentioned that the 2 ensemble models outperform the previous machine learning models applied on the same study area before.