Browsing by Author "Costache, Romulus"

Now showing 1 - 9 of 9

A review of recent advances and future prospects in calculation of reference evapotranspiration in Bangladesh using soft computing models
(Scopus, 2024) Alam, Md Mahfuz; Akter, Mst. Yeasmin; Reza, Abu; Islam, Md Towfiqul; Mallick, Javed; Kabir, Zobaidul; Chu, Ronghao; Arabameri, Alireza; Pal, Subodh Chandra; Masud, Md Abdullah Al; Costache, Romulus; Senapathi, Venkatramanan
Evapotranspiration (ETo) is a complex and non-linear hydrological process with a significant impact on efficient water resource planning and long-term management. The Penman-Monteith (PM) equation method, developed by the Food and Agriculture Organization of the United Nations (FAO), represents an advancement over earlier approaches for estimating ETo. Eto though reliable, faces limitations due to the requirement for climatological data not always available at specific locations. To address this, researchers have explored soft computing (SC) models as alternatives to conventional methods, known for their exceptional accuracy across disciplines. This critical review aims to enhance understanding of cutting-edge SC frameworks for ETo estimation, highlighting advancements in evolutionary models, hybrid and ensemble approaches, and optimization strategies. Recent applications of SC in various climatic zones in Bangladesh are evaluated, with the order of preference being ANFIS > Bi-LSTM > RT > DENFIS > SVR-PSOGWO > PSO–HFS due to their consistently high accuracy (RMSE and ). This review introduces a benchmark for incorporating evolutionary computation algorithms (EC) into ETo modeling. Each subsection addresses the strengths and weaknesses of known SC models, offering valuable insights. The review serves as a valuable resource for experienced water resource engineers and hydrologists, both domestically and internationally, providing comprehensive SC modeling studies for ETo forecasting. Furthermore, it provides an improved water resources monitoring and management plans.
Evaluation of Groundwater Contamination and Associated Human Health Risk in a Water-Scarce Hard Rock-Dominated Region of India
(Elsevier, 2023-11-15) Biswas, Tanmoy; Pal, Subodh Chandra; Ruidas, Dipankar; Saha, Asish; Shit, Manisa; Islam, Abu Reza Md. Towfiqul; Islam, Aznarul; Costache, Romulus
Groundwater is the most precious resource on the earth's surface, providing fresh drinking water for human beings and supplying water for plants to survive. The shortage, unavailability, and pollution of fresh drinking water is an emerging issue in almost every part of the world. To this end, the present study intends to evaluate the quality of groundwater and the associated health hazard risk of the Bankura district. To conduct the present study, 55 groundwater samples were collected across the Bankura district with intensive field investigation in the dry season, 2021 to assess the groundwater quality and associated health risks. For this study, we have selected 15 groundwater causative parameters to seek the NO3−, F− and Fe heavy metal groundwater quality (GWQ) status and impact of GWQ on human health by utilizing the degree of contamination (CD), GWQI and human health hazard index. Gibbs's diagram confirmed that the source of the groundwater pollutants is more geogenic than anthropogenic inputs for the Bankura district. The study's findings indicate that the GWQ of 25% area of the Bankura district is poor and unsafe for drinking purposes. In comparison, 15% of the groundwater contains good quality and is safe for drinking, and various pollutants moderately contaminate the remaining areas. The human health hazard index exhibited the same pattern as the GWQI map of the Bankura district. This unique finding of the present study will be helpful for the decision-makers, local well-being authorities and disaster management team to manage and mitigate the issue of GWQ of Bankura district and surroundings more sustainably.
Flood Hazard Potential Evaluation Using Decision Tree State-of-the-Art Models
(John Wiley & Sons, 2023-07-25) Costache, Romulus; Arabameri, Alireza; Costache, Iulia; Crăciun, Anca; Islam, Abu Reza Md. Towfiqul; Abba, Sani Isah; Sahana, Mehebub; Pandey, Manish; Tin, Tran Trung; Pham, Binh Thai
Floods occur frequently in Romania and throughout the world and are one of the most devastating natural disasters that impact people's lives. Therefore, in order to reduce the potential damages, an accurate identification of surfaces susceptible to flood phenomena is mandatory. In this regard, the quantitative calculation of flood susceptibility has become a very popular practice in the scientific research. With the development of modern computerized methods such as geographic information system and machine learning models, and as a result of the possibility of combining them, the determination of areas susceptible to floods has become increasingly accurate, and the algorithms used are increasingly varied. Some of the most used and highly accurate machine learning algorithms are the decision tree models. Therefore, in the present study focusing on flood susceptibility zonation mapping in the Trotus River basin, the following algorithms were applied: forest by penalizing attribute—weights of evidence (forest-PA-WOE), best first decision tree—WOE, alternating decision tree—WOE, and logistic regression—WOE. The best performant, characterized by a maximum accuracy of 0.981, proved to be forest-PA-WOE, whereas in terms of flood exposure, an area of over 16.22% of the Trotus basin is exposed to high and very high floods susceptibility. The performances applied models in the present work are higher than the models applied in the previous studies in the same study area. Moreover, it should be noted that the accuracy of the models is similar with the accuracies of the decision tree models achieved in the studies focused on other areas across the world. Therefore, we can state that the models applied in the present research can be successfully used in by the researchers in other case studies. The findings of this research may substantially map the flood risk areas and further aid watershed managers in limiting and remediating flood damage in the data-scarce regions. Moreover, the results of this study can be a very useful for the hazard management and planning authorities.
Flood hazard potential evaluation using decision tree state-of-the-art models
(2023-06-25) Costache, Romulus; Arabameri, Alireza; Costache, Iulia; Crăciun, Anca; Md. Towfiqul Islam, Abu Reza; Abba, Sani Isah; Sahana, Mehebub; Pandey, Manish; Tin, Tran Trung; Pham, Binh Thai
Floods occur frequently in Romania and throughout the world and are one of the most devastating natural disasters that impact people's lives. Therefore, in order to reduce the potential damages, an accurate identification of surfaces susceptible to flood phenomena is mandatory. In this regard, the quantitative calculation of flood susceptibility has become a very popular practice in the scientific research. With the development of modern computerized methods such as geographic information system and machine learning models, and as a result of the possibility of combining them, the determination of areas susceptible to floods has become increasingly accurate, and the algorithms used are increasingly varied. Some of the most used and highly accurate machine learning algorithms are the decision tree models. Therefore, in the present study focusing on flood susceptibility zonation mapping in the Trotus River basin, the following algorithms were applied: forest by penalizing attribute—weights of evidence (forest-PA-WOE), best first decision tree—WOE, alternating decision tree—WOE, and logistic regression—WOE. The best performant, characterized by a maximum accuracy of 0.981, proved to be forest-PA-WOE, whereas in terms of flood exposure, an area of over 16.22% of the Trotus basin is exposed to high and very high floods susceptibility. The performances applied models in the present work are higher than the models applied in the previous studies in the same study area. Moreover, it should be noted that the accuracy of the models is similar with the accuracies of the decision tree models achieved in the studies focused on other areas across the world. Therefore, we can state that the models applied in the present research can be successfully used in by the researchers in other case studies. The findings of this research may substantially map the flood risk areas and further aid watershed managers in limiting and remediating flood damage in the data-scarce regions. Moreover, the results of this study can be a very useful for the hazard management and planning authorities.
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).
Land Use and Climate Change-Induced Soil Erosion Mapping in a Sub-Tropical Environment
(Informa UK Limited, trading as Taylor & Francis Group., 2023-10-27) Pal, Subodh Chandra; Chakrabortty, Rabin; Islam, Abu Reza Md. Towfiqul; Roy, Paramita; Chowdhuri, Indrajit; Saha, Asish; Islam, Aznarul; Costache, Romulus; Alam, Edris
One of the most important aspects of the ‘sub-tropical’ monsoon-influenced environment is the issue of ‘soil erosion’ and its related ‘land degradation’. On the other hand, the climate in this area has become quite extreme. According to this viewpoint, it is important to research a future ‘soil erosion’ scenario in front of the probable effects of climate change and land use change. For the objective of assessing the extent of soil erosion in this area, this study took into account both the USLE and the RUSLE. Compared to the USLE that has been validated, RUSLE has a comparatively greater quantitative efficiency. In RUSLE, the ‘very high’ (>20) and ‘high’ (15–20) ‘soil erosion’ zones tend to be associated with the ‘north-western, western, south-western, and southern’ regions of the river basin. The ‘soil erosion’ that will occur in the future has been estimated by taking into account the projected rainfall, land use and land cover (LULC). ‘Soil erosion’ has increased from the previous time to the projected time. Predicted R factor values for SSP 585 range from 399.92 to 493.72. In addition, a growing erosion tendency associated with increased shared socio-economic pathways (SSPs) has been found.
Pollution Trends and Ecological Risks of Heavy Metal(loid)s in Coastal Zones of Bangladesh
(Elsevier, 2023-06-04) Jannat, Jannatun Nahar; Mia, Md. Yousuf; Jion, Most. Mastura Munia Farjana; Islam, Md. Saiful; Ali, Mir Mohammad; Siddique, Md. Abu Bakar; Rakib, Md. Refat Jahan; Ibrahim, Sobhy M.; Pal, Subodh Chandra; Costache, Romulus; Islam, Abu Reza Md Towfiqul
Heavy metal(loid)s inputs contribute to human and environmental stresses in the coastal zones of Bangladesh. Several studies have been conducted on metal(loid)s pollution in sediment, soil, and water in the coastal zones. However, they are sporadic, and no attempt has been made in coastal zones from the standpoint of chemometric review. The current work aims to provide a chemometric assessment of the pollution trend of metal(loid)s, namely arsenic (As), chromium (Cr), cadmium (Cd), lead (Pb), copper (Cu), zinc (Zn), and nickel (Ni) in sediments, soils, and water across the coastal zones from 2015 to 2022. The findings showed that 45.7, 15.2, and 39.1 % of studies on heavy metal(loid)s were concentrated in the eastern, central, and western zones of coastal Bangladesh. The obtained data were further modeled using chemometric approaches, such as the contamination factor, pollution load index, geoaccumulation index, degree of contamination, Nemerow's pollution index, and ecological risk index. The results revealed that metal(loid)s, primarily Cd, have severely polluted the sediments (contamination factor, CF = 5.20) and soils (CF = 9.35) of coastal regions. Water was moderately polluted (Nemerow's pollution index, =5.22 ± 6.26) in the coastal area. The eastern zone was the most polluted compared to other zones, except for a few observations in the central zone. The overall ecological risks posed by metal(loid)s highlighted the significant ecological risk in sediments (ecological risk index, RI = 123.50) and soils (RI = 238.93) along the eastern coast. The coastal zone may have higher pollution levels due to the proximity of industrial effluent, residential sewage discharge, agricultural activities, sea transport, metallurgical industries, shipbreaking and recycling operations, and seaport activities, which are the major sources of metal(loid)s. This study will provide useful information to the relevant authorities and serve as the foundation for future management and policy decisions to reduce metal(loid) pollution in the coastal zones of southern Bangladesh.
Receptor Model-Based Source-Specific Health Risks of Toxic Metal(loid)s in Coal Basin-Induced Agricultural Soil in Northwest Bangladesh
(Springer Nature, 2023-08-30) Habib, Md. Ahosan; Islam, Abu Reza Md. Towfiqul; Varol, Memet; Phoungthong, Khamphe; Khan, Rahat; Islam, Md. Saiful; Hasanuzzaman, Md.; Mia, Md. Yousuf; Costache, Romulus; Pal, Subodh Chandra
Toxic metal(loid)s (TMLs) in agricultural soils cause detrimental effects on ecosystem and human health. Therefore, source-specific health risk apportionment is very crucial for the prevention and control of TMLs in agricultural soils. In this study, 149 surface soil samples were taken from a coal mining region in northwest Bangladesh and analyzed for 12 TMLs (Pb, Cd, Ni, Cr, Mn, Fe, Co, Zn, Cu, As, Se, and Hg). Positive matrix factorization (PMF) and absolute principal component score-multiple linear regression (APCS-MLR) receptor models were employed to quantify the pollution sources of soil TMLs. Both models identified five possible sources of pollution: agrochemical practice, industrial emissions, coal-power-plant, geogenic source, and atmospheric deposition, while the contribution rates of each source were calculated as 28.2%, 17.2%, 19.3%, 19% and 16.3% in APCS-MLR, 22.2%, 13.4%, 24.3%, 15.1% and 25.1% in PMF, respectively. Agrochemical practice was the major source of non-carcinogenic risk (NCR) (adults: 32.37%, children: 31.54%), while atmospheric deposition was the highest source of carcinogenic risk (CR) (adults: 48.83%, children: 50.11%). NCR and CR values for adults were slightly higher than for children. However, the trends in NCR and CR between children and adults were similar. As a result, among the sources of pollution, agrochemical practices and atmospheric deposition have been identified as the primary sources of soil TMLs, so prevention and control strategies should be applied primarily for these pollution sources in order to protect human health.
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.