Pub Date : 2024-07-13DOI: 10.15625/2615-9783/21133
Ly Hai-Bang, Nguyen Hoang-Long, Phan Viet-Hung, Vincent Monchiet
The prediction of permeability in porous media is a critical aspect in various scientific and engineering applications. This paper presents a machine learning (ML) model based on the XGBoost algorithm for predicting the permeability of porous media using microstructure characteristics. The seahorse optimization algorithm was employed to fine-tune the hyperparameters of the XGBoost algorithm, resulting in a model with predictive solid capabilities. Regression analysis and residual errors indicated that the model achieved good prediction results on the training and testing datasets, with RMSE values of 0.0494 and 0.0826, respectively. A SHAP value sensitivity analysis revealed that the essential inputs were the size of the inclusions, with the quantiles representing the maximum size of the inclusions being the most significant variables affecting permeability. The findings of this study have important implications for the design and optimization of porous media, and the XGBoost algorithm-based ML model provides a fast and accurate tool for predicting the permeability of porous media based on microstructure characteristics.
{"title":"Hybrid approach for permeability prediction in porous media: combining FFT simulations with machine learning","authors":"Ly Hai-Bang, Nguyen Hoang-Long, Phan Viet-Hung, Vincent Monchiet","doi":"10.15625/2615-9783/21133","DOIUrl":"https://doi.org/10.15625/2615-9783/21133","url":null,"abstract":"The prediction of permeability in porous media is a critical aspect in various scientific and engineering applications. This paper presents a machine learning (ML) model based on the XGBoost algorithm for predicting the permeability of porous media using microstructure characteristics. The seahorse optimization algorithm was employed to fine-tune the hyperparameters of the XGBoost algorithm, resulting in a model with predictive solid capabilities. Regression analysis and residual errors indicated that the model achieved good prediction results on the training and testing datasets, with RMSE values of 0.0494 and 0.0826, respectively. A SHAP value sensitivity analysis revealed that the essential inputs were the size of the inclusions, with the quantiles representing the maximum size of the inclusions being the most significant variables affecting permeability. The findings of this study have important implications for the design and optimization of porous media, and the XGBoost algorithm-based ML model provides a fast and accurate tool for predicting the permeability of porous media based on microstructure characteristics.","PeriodicalId":23639,"journal":{"name":"VIETNAM JOURNAL OF EARTH SCIENCES","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141651681","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-02DOI: 10.15625/2615-9783/21075
N. Duong Thi, S. Huang B., T. Dinh Van, P. Lai H., T. Bui V., O. Sulinthone, T. Pham H., D. Pham N., H. Nguyen V., S. Duangpaseuth
In this study, the main active faults in the territory of Laos were identified by analyzing the spatial relationship between the distributions of neo-tectonic faults and earthquake epicenters. The map of neo-tectonic faults was built by integrating the results of neo-tectonic faults research using geological-geomorphological data together with the lineament map obtained from remote sensing analysis. Nontectonic lineaments were eliminated by correlating the spatial distribution of the lineament field with a topographic map, DEM, and geological-geomorphological data. The earthquake data, including 4416 events in Laos and its surroundings, were collected from different sources: the International Seismological Center (ISC), the earthquakes recorded by the local seismic network in Laos, the seismic data in Vietnam, and the earthquake catalog provided by the Thailand Meteorological Department (TMD). Among these, 820 events were located using the hypocenter method, and the local network recorded the data. The magnitude conversion was applied to get a unified scale Mw. The catalog of 1617 main shocks obtained after eliminating foreshocks and aftershocks using the declustering technique was used for a spatial correlation with the neotectonic fault distribution to identify active faults. A total of 14 main active fault zones in the Laos territory were defined. Most are also seismogenic faults with Mw ≥ 5.0 occurring along their trace. Considering the characteristics of seismic activity and the active and neotectonic faults, the territory of Laos can be divided into six seismotectonic zones according to the decreasing level of seismic activity: the Western, the Northeastern Samnua, the Phongsali, the South Truong Son, the North Truong Son, and the Khorat zones. Each zone is characterized by relative homogeneity in the seismic activity and the characteristics of active and neotectonic faults.
{"title":"Identification of the active faults and seismotectonic zonation of Laos territory","authors":"N. Duong Thi, S. Huang B., T. Dinh Van, P. Lai H., T. Bui V., O. Sulinthone, T. Pham H., D. Pham N., H. Nguyen V., S. Duangpaseuth","doi":"10.15625/2615-9783/21075","DOIUrl":"https://doi.org/10.15625/2615-9783/21075","url":null,"abstract":"In this study, the main active faults in the territory of Laos were identified by analyzing the spatial relationship between the distributions of neo-tectonic faults and earthquake epicenters. The map of neo-tectonic faults was built by integrating the results of neo-tectonic faults research using geological-geomorphological data together with the lineament map obtained from remote sensing analysis. Nontectonic lineaments were eliminated by correlating the spatial distribution of the lineament field with a topographic map, DEM, and geological-geomorphological data. The earthquake data, including 4416 events in Laos and its surroundings, were collected from different sources: the International Seismological Center (ISC), the earthquakes recorded by the local seismic network in Laos, the seismic data in Vietnam, and the earthquake catalog provided by the Thailand Meteorological Department (TMD). Among these, 820 events were located using the hypocenter method, and the local network recorded the data. The magnitude conversion was applied to get a unified scale Mw. The catalog of 1617 main shocks obtained after eliminating foreshocks and aftershocks using the declustering technique was used for a spatial correlation with the neotectonic fault distribution to identify active faults. A total of 14 main active fault zones in the Laos territory were defined. Most are also seismogenic faults with Mw ≥ 5.0 occurring along their trace. Considering the characteristics of seismic activity and the active and neotectonic faults, the territory of Laos can be divided into six seismotectonic zones according to the decreasing level of seismic activity: the Western, the Northeastern Samnua, the Phongsali, the South Truong Son, the North Truong Son, and the Khorat zones. Each zone is characterized by relative homogeneity in the seismic activity and the characteristics of active and neotectonic faults.","PeriodicalId":23639,"journal":{"name":"VIETNAM JOURNAL OF EARTH SCIENCES","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141685384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-02DOI: 10.15625/2615-9783/21067
Hanh Nguyen Duc, Giang Nguyen Tien, Hoa Nguyen Xuan, Vinh Tran Ngoc, Duy Nguyen Huu
This study evaluates the efficacy of five machine learning algorithms Support Vector Regression (SVR), Decision Tree (DT), Random Forest (RF), Light Gradient Boosting Machine Regressor (LGBM), and Linear Regression (LR) in predicting water levels in the Vietnamese Mekong Delta's tidal river system, a complex nonlinear hydrological phenomenon. Using daily maximum, minimum, and mean water level data from the Cao Lanh gauging station on the Tien River (2000-2020), models were developed to forecast water levels one, three, five, and seven days in advance. Performance was assessed using Nash-Sutcliffe Efficiency, coefficient of determination, Root Mean Square Error, and Mean Absolute Error. Results indicate that all models performed well, with SVR consistently outperforming others, followed by RF, DT, and LGBM. The study demonstrates the viability of machine learning in water level prediction using solely historical water level data, potentially enhancing flood warning systems, water resource management, and agricultural planning. These findings contribute to the growing knowledge of machine learning applications in hydrology and can inform sustainable water resource management strategies in delta regions.
{"title":"Multi-step-ahead prediction of water levels using machine learning: A comparative analysis in the Vietnamese Mekong Delta","authors":"Hanh Nguyen Duc, Giang Nguyen Tien, Hoa Nguyen Xuan, Vinh Tran Ngoc, Duy Nguyen Huu","doi":"10.15625/2615-9783/21067","DOIUrl":"https://doi.org/10.15625/2615-9783/21067","url":null,"abstract":"This study evaluates the efficacy of five machine learning algorithms Support Vector Regression (SVR), Decision Tree (DT), Random Forest (RF), Light Gradient Boosting Machine Regressor (LGBM), and Linear Regression (LR) in predicting water levels in the Vietnamese Mekong Delta's tidal river system, a complex nonlinear hydrological phenomenon. Using daily maximum, minimum, and mean water level data from the Cao Lanh gauging station on the Tien River (2000-2020), models were developed to forecast water levels one, three, five, and seven days in advance. Performance was assessed using Nash-Sutcliffe Efficiency, coefficient of determination, Root Mean Square Error, and Mean Absolute Error. Results indicate that all models performed well, with SVR consistently outperforming others, followed by RF, DT, and LGBM. The study demonstrates the viability of machine learning in water level prediction using solely historical water level data, potentially enhancing flood warning systems, water resource management, and agricultural planning. These findings contribute to the growing knowledge of machine learning applications in hydrology and can inform sustainable water resource management strategies in delta regions.","PeriodicalId":23639,"journal":{"name":"VIETNAM JOURNAL OF EARTH SCIENCES","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141687358","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-10DOI: 10.15625/2615-9783/20925
Cuong Tran Thien, Duc Do Xuan, Tuan Do Huu, Thinh Nguyen An, Hien Van Dao, Minh Tran
The Son La hydropower reservoir (S.L.R.) is the largest water reservoir in Vietnam. Da River water has been treated for drinking and domestic purposes; water quality management is essential for the safety of ecosystems and human health. This study was conducted to determine changes in water quality indicators [pH, dissolved Oxygen (D.O.), total suspended solids (T.S.S.), chemical oxygen demand (C.O.D.), ammonium (NH4+), nitrite (NO2-), and coliform] in the Da River in 2010 and the Son La hydropower reservoir during 2014-2023. The results of mean annual values of Da river water quality and Son La hydropower reservoir were, specifically: pH (7.8; 7.4), D.O. (4.3; 6.2), T.S.S. (112; 5), C.O.D. (15; 8.7), NH4+ (0.17; 0.3), NO2- (0.009; 0.04), and coliform (1,723; 747). Water quality parameters significantly varied between rive and reservoir water: D.O., T.S.S., C.O.D., and Coliform. pH, T.S.S., and C.O.D. slightly decreased; however, Dissolved oxygen (D.O.), NH4+, NO2-, and coliform demonstrated an increasing trend during 2014-2023. The impact of the Son La Dam (S.L.D.) on water quality was relatively straightforward: increasing the concentration of dissolved oxygen and the self-cleaning ability of pollutants. Periodic water impoundment was divided (April to August) into a low water level of 175 m, impoundment (January to March), a median water level of 190m, and a high water level of 215 m (September to December) to period. However, the impact of the staged impoundment on water quality, especially in 2014-2023, remains unclear, except D.O., T.S.S., NH4+, NO2- and Coliform exceeded limits or were lower is not significant for living water under the Vietnam regulation, specifically: D.O. (5.36, 5.52; ≥ 6), T.S.S. (25.13; ≤ 25), NH4+ (0.3331; 0.3), NO2- (0.0504; 0.05), coliform (1,018.5; ≤ 1,000). Results from the current study provide valuable information for reservoir and river water pollution source management and reduce potential risks to exposed ecosystems, livelihoods, and human health.
{"title":"Temporal and spatial variation in water quality in the Son La hydropower Reservoir, Northwestern Vietnam","authors":"Cuong Tran Thien, Duc Do Xuan, Tuan Do Huu, Thinh Nguyen An, Hien Van Dao, Minh Tran","doi":"10.15625/2615-9783/20925","DOIUrl":"https://doi.org/10.15625/2615-9783/20925","url":null,"abstract":"The Son La hydropower reservoir (S.L.R.) is the largest water reservoir in Vietnam. Da River water has been treated for drinking and domestic purposes; water quality management is essential for the safety of ecosystems and human health. This study was conducted to determine changes in water quality indicators [pH, dissolved Oxygen (D.O.), total suspended solids (T.S.S.), chemical oxygen demand (C.O.D.), ammonium (NH4+), nitrite (NO2-), and coliform] in the Da River in 2010 and the Son La hydropower reservoir during 2014-2023. The results of mean annual values of Da river water quality and Son La hydropower reservoir were, specifically: pH (7.8; 7.4), D.O. (4.3; 6.2), T.S.S. (112; 5), C.O.D. (15; 8.7), NH4+ (0.17; 0.3), NO2- (0.009; 0.04), and coliform (1,723; 747). Water quality parameters significantly varied between rive and reservoir water: D.O., T.S.S., C.O.D., and Coliform. pH, T.S.S., and C.O.D. slightly decreased; however, Dissolved oxygen (D.O.), NH4+, NO2-, and coliform demonstrated an increasing trend during 2014-2023. The impact of the Son La Dam (S.L.D.) on water quality was relatively straightforward: increasing the concentration of dissolved oxygen and the self-cleaning ability of pollutants. Periodic water impoundment was divided (April to August) into a low water level of 175 m, impoundment (January to March), a median water level of 190m, and a high water level of 215 m (September to December) to period. However, the impact of the staged impoundment on water quality, especially in 2014-2023, remains unclear, except D.O., T.S.S., NH4+, NO2- and Coliform exceeded limits or were lower is not significant for living water under the Vietnam regulation, specifically: D.O. (5.36, 5.52; ≥ 6), T.S.S. (25.13; ≤ 25), NH4+ (0.3331; 0.3), NO2- (0.0504; 0.05), coliform (1,018.5; ≤ 1,000). Results from the current study provide valuable information for reservoir and river water pollution source management and reduce potential risks to exposed ecosystems, livelihoods, and human health.","PeriodicalId":23639,"journal":{"name":"VIETNAM JOURNAL OF EARTH SCIENCES","volume":null,"pages":null},"PeriodicalIF":1.5,"publicationDate":"2024-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141364691","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-10DOI: 10.15625/2615-9783/20766
Huong Thi Thanh Ngo, Quynh- Anh Thi Bui, Vi Nguyen Van, Thuy Nguyen Thi Bich
California Bearing Ratio (CBR) is used to assess bearing capacity, deformation characteristics of roadbed soil, and base layer material in pavement structure. In general, CBR is often determined by laboratory or in-situ tests. However, it is time- and cost-consuming to conduct this experiment because this test requires cumbersome equipment such as a compressor. In this study, two Artificial Intelligence models are developed, including a simple model (Decision Tree Regression, DT) and a hybrid model (AdaBoost - Decision Tree, AB-DT). Using 214 data samples from Van Don - Mong Cai expressway, Vietnam, 10 input variables of the model were considered namely particle composition (content of gravel (X1), coarse sand (X2), fine sand (X3), silt clay (X4), organic (X5)), Atterberg limits (Liquid limit (X6), Plastic limit (X7), Plastic index (X8)), and compaction curve (optimum water content (X9) and maximum dry density (X10)). The developed models were evaluated by using a variety of statistical indicators, including coefficient of determination (R2), Root mean square error (RMSE), and Mean absolute error (MAE). The results show that AB-DT model has higher accuracy than the DT model. Moreover, the SHAP value analysis shows that the variable X10 influences the CBR value the most. Thus, it implies that applying the AB-DT model to effectively predict the CBR of the roadbed soil saves time and money for experiments.
{"title":"Application of hybrid modeling to predict California bearing ratio of soil","authors":"Huong Thi Thanh Ngo, Quynh- Anh Thi Bui, Vi Nguyen Van, Thuy Nguyen Thi Bich","doi":"10.15625/2615-9783/20766","DOIUrl":"https://doi.org/10.15625/2615-9783/20766","url":null,"abstract":"California Bearing Ratio (CBR) is used to assess bearing capacity, deformation characteristics of roadbed soil, and base layer material in pavement structure. In general, CBR is often determined by laboratory or in-situ tests. However, it is time- and cost-consuming to conduct this experiment because this test requires cumbersome equipment such as a compressor. In this study, two Artificial Intelligence models are developed, including a simple model (Decision Tree Regression, DT) and a hybrid model (AdaBoost - Decision Tree, AB-DT). Using 214 data samples from Van Don - Mong Cai expressway, Vietnam, 10 input variables of the model were considered namely particle composition (content of gravel (X1), coarse sand (X2), fine sand (X3), silt clay (X4), organic (X5)), Atterberg limits (Liquid limit (X6), Plastic limit (X7), Plastic index (X8)), and compaction curve (optimum water content (X9) and maximum dry density (X10)). The developed models were evaluated by using a variety of statistical indicators, including coefficient of determination (R2), Root mean square error (RMSE), and Mean absolute error (MAE). The results show that AB-DT model has higher accuracy than the DT model. Moreover, the SHAP value analysis shows that the variable X10 influences the CBR value the most. Thus, it implies that applying the AB-DT model to effectively predict the CBR of the roadbed soil saves time and money for experiments.","PeriodicalId":23639,"journal":{"name":"VIETNAM JOURNAL OF EARTH SCIENCES","volume":null,"pages":null},"PeriodicalIF":1.5,"publicationDate":"2024-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140990199","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-03DOI: 10.15625/2615-9783/20716
Giang Nguyen Cong, Chien Nguyen Quyet, Khac Dang Vu
In recent decades, Vietnam has gradually become a critical global rice producer. During that production process, residual straw becomes an environmental pollutant due to open burning, raising greenhouse gas emissions. This study combines the optical images of the Sentinel-2 satellite and the radar images of the Sentinel-1 satellite to estimate the dry biomass of rice and to determine gas emissions due to rice straw burning over the fields in Quoc Oai district, Hanoi city for urban environmental management purposes. Sentinel-2 images have been classified into the land covers, thereby identifying the areas of rice cultivation and the areas of burned straw. Meanwhile, the Sentinel-1 radar image has been used to calculate the dry biomass of rice due to its ability to penetrate clouds, an obstacle to optical images in tropical regions. Furthermore, a field trip during harvesting season allows us to measure aboveground dry biomass. Then, the analysis shows a high correlation between the backscatter V.V. and V.H. of the radar image and the in-situ dry biomass (R=0.923 and R2=0.852), with a relatively low average error (RMSE = 6.58 kg/100 m2). By linear regression method, the study found the total rice dry biomass of 28728.5 tons, which was obtained after the Summer rice crop 2020 for the whole Quoc Oai district, of which 2037.91 tons of rice straw have been burned, releasing a large amount of greenhouse gas emission with 2398.6 tons of CO2, 189.5 tons of CO, 18.8673 tons of PM10 dust, 17.2087 tons of PM2.5 dust and some other gases. The identical procedure has also been applied to the western region of Hanoi city center to estimate the amount of gas emissions. This study has proven the effectiveness of an approach and contributed to supporting urban managers in proposing appropriate policies to monitor and protect the environment.
{"title":"Estimation of greenhouse gas emission due to open burning of rice straw using Sentinel data","authors":"Giang Nguyen Cong, Chien Nguyen Quyet, Khac Dang Vu","doi":"10.15625/2615-9783/20716","DOIUrl":"https://doi.org/10.15625/2615-9783/20716","url":null,"abstract":"In recent decades, Vietnam has gradually become a critical global rice producer. During that production process, residual straw becomes an environmental pollutant due to open burning, raising greenhouse gas emissions. This study combines the optical images of the Sentinel-2 satellite and the radar images of the Sentinel-1 satellite to estimate the dry biomass of rice and to determine gas emissions due to rice straw burning over the fields in Quoc Oai district, Hanoi city for urban environmental management purposes. Sentinel-2 images have been classified into the land covers, thereby identifying the areas of rice cultivation and the areas of burned straw. Meanwhile, the Sentinel-1 radar image has been used to calculate the dry biomass of rice due to its ability to penetrate clouds, an obstacle to optical images in tropical regions. \u0000Furthermore, a field trip during harvesting season allows us to measure aboveground dry biomass. Then, the analysis shows a high correlation between the backscatter V.V. and V.H. of the radar image and the in-situ dry biomass (R=0.923 and R2=0.852), with a relatively low average error (RMSE = 6.58 kg/100 m2). By linear regression method, the study found the total rice dry biomass of 28728.5 tons, which was obtained after the Summer rice crop 2020 for the whole Quoc Oai district, of which 2037.91 tons of rice straw have been burned, releasing a large amount of greenhouse gas emission with 2398.6 tons of CO2, 189.5 tons of CO, 18.8673 tons of PM10 dust, 17.2087 tons of PM2.5 dust and some other gases. The identical procedure has also been applied to the western region of Hanoi city center to estimate the amount of gas emissions. This study has proven the effectiveness of an approach and contributed to supporting urban managers in proposing appropriate policies to monitor and protect the environment.","PeriodicalId":23639,"journal":{"name":"VIETNAM JOURNAL OF EARTH SCIENCES","volume":null,"pages":null},"PeriodicalIF":1.5,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141015650","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-03DOI: 10.15625/2615-9783/20714
Thao Nguyen Thien Phuong, Ha Nguyen Thi Thu, Vinh Pham Quang, Hien Tran Thi, Thanh Dinh Xuan
Monitoring chlorophyll-a concentration (Chla) in inland waters is vital for environmental assessment. This study develops an empirical multivariate linear regression (MLR) model to directly estimate Chla in Quan Son Reservoir using Sentinel-2B (S2B) Level 2A images. Regression analysis of a 68-point in-situ Chla dataset measured in Quan Son Reservoir between 2021 and 2023, in conjunction with the corresponding S2B reflectance data, reveals a significant correlation between Chla and a combination of the blue (B2), green (B3), and red (B4) bands (coefficient of determination, R² = 0.95). The Chla estimation model is validated using a 30-point in-situ dataset collected on various dates (R² = 0.87; the root-mean-squared error RMSE < 5%). Subsequently, the model is applied to ten S2B images acquired from 2021 to 2023, revealing Chla's spatio-temporal distribution across the reservoir. Two key trends emerge: (1) Chla is lower during winter (November and December) than in summer and early autumn (July and September), and (2) The distribution of Chla undergoes noticeable spatial changes, particularly in July, with elevated levels observed in areas characterized by tourist hotspots. This approach shows promise for monitoring Chla in similar inland waters.
{"title":"A multivariate linear regression model for estimating chlorophyll-a concentration in Quan Son Reservoir (Hanoi, Vietnam) using Sentinel-2B Imagery","authors":"Thao Nguyen Thien Phuong, Ha Nguyen Thi Thu, Vinh Pham Quang, Hien Tran Thi, Thanh Dinh Xuan","doi":"10.15625/2615-9783/20714","DOIUrl":"https://doi.org/10.15625/2615-9783/20714","url":null,"abstract":"Monitoring chlorophyll-a concentration (Chla) in inland waters is vital for environmental assessment. This study develops an empirical multivariate linear regression (MLR) model to directly estimate Chla in Quan Son Reservoir using Sentinel-2B (S2B) Level 2A images. Regression analysis of a 68-point in-situ Chla dataset measured in Quan Son Reservoir between 2021 and 2023, in conjunction with the corresponding S2B reflectance data, reveals a significant correlation between Chla and a combination of the blue (B2), green (B3), and red (B4) bands (coefficient of determination, R² = 0.95). The Chla estimation model is validated using a 30-point in-situ dataset collected on various dates (R² = 0.87; the root-mean-squared error RMSE < 5%). Subsequently, the model is applied to ten S2B images acquired from 2021 to 2023, revealing Chla's spatio-temporal distribution across the reservoir. Two key trends emerge: (1) Chla is lower during winter (November and December) than in summer and early autumn (July and September), and (2) The distribution of Chla undergoes noticeable spatial changes, particularly in July, with elevated levels observed in areas characterized by tourist hotspots. This approach shows promise for monitoring Chla in similar inland waters.","PeriodicalId":23639,"journal":{"name":"VIETNAM JOURNAL OF EARTH SCIENCES","volume":null,"pages":null},"PeriodicalIF":1.5,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141015022","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-02DOI: 10.15625/2615-9783/20706
Duy Nguyen Huu, Tung Vu Cong, P. Brețcan, A. Petrisor
Landslides are natural disasters most frequent in the mountain region of Vietnam, producing critical damage to human lives and assets. Therefore, precisely identifying the landslide occurrence probability within the region is essential in supporting decision-makers or developers in establishing effective strategies for reducing the damage. This study is aimed at developing a methodology based on machine learning, namely Xgboost (XGB), lightGBM, K-Nearest Neighbors (KNN), and Bagging (BA) for assessing the connection of land cover change to landslide susceptibility in Da Lat City, Vietnam. 202 landslide locations and 13 potential drivers became input data for the model. Various statistical indices, namely the root mean square error (RMSE), the area under the curve (AUC), and mean absolute error (MAE), were used to evaluate the proposed models. Our findings indicate that the Xgboost model was better than other models, as shown by the AUC value of 0.94, followed by LightGBM (AUC=0.91), KNN (AUC=0.87), and Bagging (AUC=0.81). In addition, urban areas increased during 2017-2023 from 25 km² to 30 km² in very high landslide susceptibility areas. Our approach can be applied to test the other regions in Vietnam. Our findings might represent a necessary tool for land use planning strategies to reduce damage from natural disasters and landslides.
{"title":"Assessing the relationship between landslide susceptibility and land cover change using machine learning","authors":"Duy Nguyen Huu, Tung Vu Cong, P. Brețcan, A. Petrisor","doi":"10.15625/2615-9783/20706","DOIUrl":"https://doi.org/10.15625/2615-9783/20706","url":null,"abstract":"Landslides are natural disasters most frequent in the mountain region of Vietnam, producing critical damage to human lives and assets. Therefore, precisely identifying the landslide occurrence probability within the region is essential in supporting decision-makers or developers in establishing effective strategies for reducing the damage. This study is aimed at developing a methodology based on machine learning, namely Xgboost (XGB), lightGBM, K-Nearest Neighbors (KNN), and Bagging (BA) for assessing the connection of land cover change to landslide susceptibility in Da Lat City, Vietnam. 202 landslide locations and 13 potential drivers became input data for the model. Various statistical indices, namely the root mean square error (RMSE), the area under the curve (AUC), and mean absolute error (MAE), were used to evaluate the proposed models. Our findings indicate that the Xgboost model was better than other models, as shown by the AUC value of 0.94, followed by LightGBM (AUC=0.91), KNN (AUC=0.87), and Bagging (AUC=0.81). In addition, urban areas increased during 2017-2023 from 25 km² to 30 km² in very high landslide susceptibility areas. Our approach can be applied to test the other regions in Vietnam. Our findings might represent a necessary tool for land use planning strategies to reduce damage from natural disasters and landslides.","PeriodicalId":23639,"journal":{"name":"VIETNAM JOURNAL OF EARTH SCIENCES","volume":null,"pages":null},"PeriodicalIF":1.5,"publicationDate":"2024-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141021717","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-22DOI: 10.15625/2615-9783/20639
Binh Pham Duc
This work investigates the efficacy of L-band and C-band Synthetic Aperture Radar (SAR) sensors onboard ALOS-2 and Sentinel-1 satellites, as compared to optical sensors onboard Sentinel-2 satellite, for mapping open water of the Tri An reservoir, one of the largest artificial reservoirs in South Vietnam, during the 2016-2023 period. The Google Earth Engine (GEE) was the primary computing platform to pre-process all satellite observations. The Otsu threshold algorithm was employed to generate water/non-water maps derived from the VH- and HH-polarized backscatter coefficient data acquired by Sentinel-1 and ALOS-2 satellites and from the Modified Normalized Difference Water Index (MNDWI) data acquired by Sentinel-2 satellite, respectively. The findings reveal the stability of Tri An reservoir’s surface water extent from 2017 to 2022, followed by a significant decline of nearly 70% during the dry season of 2023 to approximately 100 km2. This substantial decrease can be explained by the impact of a robust El Niño phase occurring in the region simultaneously. Overall, there is a high consistency between results derived from SAR and optical sensors, but the correlation between Sentinel-1 and Sentinel-2 (R = 0.9774) was higher than that between ALOS-2 and Sentinel-2 (R = 0.9145). During the drought period, both C-band and L-band SAR sensors overestimate the reservoir’s surface water extent due to the similarity in their backscatter coefficient between water and dry flat soil surfaces. This misclassification is more pronounced in ALOS-2 data than Sentinel-1 data, suggesting that the C-band sensor is more suitable than the L-band sensor for mapping the lake’s open water areas.
这项工作研究了 ALOS-2 号卫星和哨兵-1 号卫星上的 L 波段和 C 波段合成孔径雷达(SAR)传感器与哨兵-2 号卫星上的光学传感器相比,在 2016-2023 年期间对越南南部最大的人工水库之一 Tri An 水库的开放水域进行测绘的功效。谷歌地球引擎(GEE)是预处理所有卫星观测数据的主要计算平台。利用大津阈值算法,分别从哨兵-1 号卫星和 ALOS-2 号卫星获取的 VH 偏振和 HH 偏振后向散射系数数据以及哨兵-2 号卫星获取的修正归一化差异水指数(MNDWI)数据生成水/非水地图。研究结果表明,2017 年至 2022 年,三安水库的地表水面积保持稳定,随后在 2023 年旱季大幅下降近 70%,降至约 100 平方公里。这一大幅下降的原因是该地区同时出现了强劲的厄尔尼诺现象。总体而言,合成孔径雷达和光学传感器得出的结果具有很高的一致性,但哨兵-1 和哨兵-2 之间的相关性(R = 0.9774)高于 ALOS-2 和哨兵-2 之间的相关性(R = 0.9145)。在干旱期间,C 波段和 L 波段合成孔径雷达传感器都高估了水库的地表水范围,原因是它们在水面和干燥平坦的土壤表面之间的后向散射系数相似。与哨兵 1 号数据相比,ALOS-2 数据的这种误判更为明显,这表明 C 波段传感器比 L 波段传感器更适合绘制湖泊的开放水域。
{"title":"Comparison of Synthetic Aperture Radar Sentinel-1 and ALOS-2 observations for lake monitoring","authors":"Binh Pham Duc","doi":"10.15625/2615-9783/20639","DOIUrl":"https://doi.org/10.15625/2615-9783/20639","url":null,"abstract":"This work investigates the efficacy of L-band and C-band Synthetic Aperture Radar (SAR) sensors onboard ALOS-2 and Sentinel-1 satellites, as compared to optical sensors onboard Sentinel-2 satellite, for mapping open water of the Tri An reservoir, one of the largest artificial reservoirs in South Vietnam, during the 2016-2023 period. The Google Earth Engine (GEE) was the primary computing platform to pre-process all satellite observations. The Otsu threshold algorithm was employed to generate water/non-water maps derived from the VH- and HH-polarized backscatter coefficient data acquired by Sentinel-1 and ALOS-2 satellites and from the Modified Normalized Difference Water Index (MNDWI) data acquired by Sentinel-2 satellite, respectively. The findings reveal the stability of Tri An reservoir’s surface water extent from 2017 to 2022, followed by a significant decline of nearly 70% during the dry season of 2023 to approximately 100 km2. This substantial decrease can be explained by the impact of a robust El Niño phase occurring in the region simultaneously. Overall, there is a high consistency between results derived from SAR and optical sensors, but the correlation between Sentinel-1 and Sentinel-2 (R = 0.9774) was higher than that between ALOS-2 and Sentinel-2 (R = 0.9145). During the drought period, both C-band and L-band SAR sensors overestimate the reservoir’s surface water extent due to the similarity in their backscatter coefficient between water and dry flat soil surfaces. This misclassification is more pronounced in ALOS-2 data than Sentinel-1 data, suggesting that the C-band sensor is more suitable than the L-band sensor for mapping the lake’s open water areas.","PeriodicalId":23639,"journal":{"name":"VIETNAM JOURNAL OF EARTH SCIENCES","volume":null,"pages":null},"PeriodicalIF":1.5,"publicationDate":"2024-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140673749","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-21DOI: 10.15625/2615-9783/20400
Thanh Bui Nhi, Phong Tran Van, Diep Nguyen Van, Trinh Phan Trong
Studying the present strain rate is significant in determining the characteristics and origin of geological anomalies in the region. Tectonic strain occurs under the influence of various factors, especially tectonic forces, and only a few cases of deformation occur at speeds observable by humans. This research uses velocity data from GNSS measurements in Quang Nam - Quang Ngai and surrounding regions to assess present tectonic strain. The combination of methods used in this study includes calculating the ITRF Earth-fixed frame to minimize errors, the method of relative velocity calculation to compare the speed variations between station positions, and the deformation calculation method using the QOCA software developed by NASA's Jet Propulsion Laboratory (JPL). The calculated results show that the coastal areas of the study have relatively low strain rates with the principal strain rate <15 nano-strain/year, the magnitude of deformation is always less than 7.5 nano-strain/year, and the area is conducive to the development of dominant reverse faulting.
{"title":"The present strain rate of Quang Nam - Quang Ngai and the surrounding region","authors":"Thanh Bui Nhi, Phong Tran Van, Diep Nguyen Van, Trinh Phan Trong","doi":"10.15625/2615-9783/20400","DOIUrl":"https://doi.org/10.15625/2615-9783/20400","url":null,"abstract":"Studying the present strain rate is significant in determining the characteristics and origin of geological anomalies in the region. Tectonic strain occurs under the influence of various factors, especially tectonic forces, and only a few cases of deformation occur at speeds observable by humans. This research uses velocity data from GNSS measurements in Quang Nam - Quang Ngai and surrounding regions to assess present tectonic strain. The combination of methods used in this study includes calculating the ITRF Earth-fixed frame to minimize errors, the method of relative velocity calculation to compare the speed variations between station positions, and the deformation calculation method using the QOCA software developed by NASA's Jet Propulsion Laboratory (JPL). The calculated results show that the coastal areas of the study have relatively low strain rates with the principal strain rate <15 nano-strain/year, the magnitude of deformation is always less than 7.5 nano-strain/year, and the area is conducive to the development of dominant reverse faulting.","PeriodicalId":23639,"journal":{"name":"VIETNAM JOURNAL OF EARTH SCIENCES","volume":null,"pages":null},"PeriodicalIF":1.5,"publicationDate":"2024-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140222213","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}