首页 > 最新文献

VIETNAM JOURNAL OF EARTH SCIENCES最新文献

英文 中文
The late Pleistocene - Holocene sedimentary evolution in the Ba Lat River mouth area of the Red River Delta 红三角洲巴拉特河口区晚更新世-全新世沉积演化
IF 1.5 Q2 GEOSCIENCES, MULTIDISCIPLINARY Pub Date : 2023-06-07 DOI: 10.15625/2615-9783/18408
Dien Tran Ngoc, Ha Vu Van, Amelie Paszkowski, Quang Nguyen Minh, Dao Ngo Thi, Min Nguyen Thi, Tung Dang Xuan, Dung Nguyen Chi, Tuyen Vu Ngoc, Tung Nguyen Khanh, Huan Tran Ngoc
The Ba Lat estuary is part of the downstream stretch of the Red River Delta, the second-largest Delta in Vietnam and the 12th largest in the world. This study analyses GAT borehole sediments in the Ba Lat estuary area to assess environmental changes during the Late Pleistocene - Holocene period. This entailed detailed analyses of 70 m-deep borehole data from the Ba Lat estuary area, including structural analysis of 70 m-deep sediment core samples, 230 samples of grain size, 49 samples of Foraminifera, five samples of petrographic thin slices, and four samples of radiocarbon dating. The data reveal nine sedimentary facies, including river channel sand facies, floodplain clayey silt facies, tidal flat sandy-silty facies, bay clayey silt facies, pro-delta clayey silt facies, delta front sandy-silty clay facies, mouth bar sand facies, tidal flat sandy - silty clay facies, and delta plain silty clay facies. The combined nine sedimentary facies formed sequentially in time, representing the evolution of the sedimentary environment from the Late Pleistocene to the Holocene and the evolutionary process from the continental to the estuarine and Delta environment. The results also enable the geographic identification and delineation of the incised valley in the Red River Delta during the Late Pleistocene to Holocene period. The sedimentation rate in the incised valley varies from period to period. In the sedimentation phase of the incised valley, the average accretion rate reached 11.64 mm/year. In contrast, during the open sea regime (shallow sea near the coast), the accretion rate was observed to be very low, with a rate of 1.27 mm/year and the period of delta formation had the highest accretion rate, reaching 13.41 mm/year.
巴叻河口是红河三角洲下游河段的一部分,红河是越南第二大三角洲,也是世界第12大三角洲。本研究分析了Ba Lat河口地区GAT钻孔沉积物,以评估晚更新世-全新世时期的环境变化。这需要对巴拉特河口地区70米深的钻孔数据进行详细分析,包括对70米深沉积物岩芯样本、230个粒度样本、49个有孔虫样本、5个岩相薄片样本和4个放射性碳年代测定样本的结构分析。数据揭示了9个沉积相,包括河道砂相、泛滥平原粘土质粉土相、潮坪砂质粉土相和海湾粘土质粉砂相、前三角洲粘土质粉土相、三角洲前缘砂质粉质粘土相、河口坝砂相、潮滩砂质-粉质粘土相和三角洲平原粉质粘土。组合的9个沉积相在时间上依次形成,代表了晚更新世至全新世沉积环境的演变以及从大陆到河口和三角洲环境的演变过程。研究结果也为晚更新世至全新世红河三角洲下切河谷的地理识别和划界提供了依据。下切河谷的沉积速率随时期而变化。在下切河谷的沉积阶段,平均吸积速率达到11.64mm/年。相反,在公海(海岸附近的浅海),观测到吸积率非常低,为1.27毫米/年,三角洲形成时期的吸积率最高,达到13.41毫米/年。
{"title":"The late Pleistocene - Holocene sedimentary evolution in the Ba Lat River mouth area of the Red River Delta","authors":"Dien Tran Ngoc, Ha Vu Van, Amelie Paszkowski, Quang Nguyen Minh, Dao Ngo Thi, Min Nguyen Thi, Tung Dang Xuan, Dung Nguyen Chi, Tuyen Vu Ngoc, Tung Nguyen Khanh, Huan Tran Ngoc","doi":"10.15625/2615-9783/18408","DOIUrl":"https://doi.org/10.15625/2615-9783/18408","url":null,"abstract":"The Ba Lat estuary is part of the downstream stretch of the Red River Delta, the second-largest Delta in Vietnam and the 12th largest in the world. This study analyses GAT borehole sediments in the Ba Lat estuary area to assess environmental changes during the Late Pleistocene - Holocene period. This entailed detailed analyses of 70 m-deep borehole data from the Ba Lat estuary area, including structural analysis of 70 m-deep sediment core samples, 230 samples of grain size, 49 samples of Foraminifera, five samples of petrographic thin slices, and four samples of radiocarbon dating. \u0000The data reveal nine sedimentary facies, including river channel sand facies, floodplain clayey silt facies, tidal flat sandy-silty facies, bay clayey silt facies, pro-delta clayey silt facies, delta front sandy-silty clay facies, mouth bar sand facies, tidal flat sandy - silty clay facies, and delta plain silty clay facies. The combined nine sedimentary facies formed sequentially in time, representing the evolution of the sedimentary environment from the Late Pleistocene to the Holocene and the evolutionary process from the continental to the estuarine and Delta environment. \u0000The results also enable the geographic identification and delineation of the incised valley in the Red River Delta during the Late Pleistocene to Holocene period. The sedimentation rate in the incised valley varies from period to period. In the sedimentation phase of the incised valley, the average accretion rate reached 11.64 mm/year. In contrast, during the open sea regime (shallow sea near the coast), the accretion rate was observed to be very low, with a rate of 1.27 mm/year and the period of delta formation had the highest accretion rate, reaching 13.41 mm/year.","PeriodicalId":23639,"journal":{"name":"VIETNAM JOURNAL OF EARTH SCIENCES","volume":" ","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46052351","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}
引用次数: 0
Coastline and shoreline change assessment in sandy coasts based on machine learning models and high-resolution satellite images 基于机器学习模型和高分辨率卫星图像的沙质海岸线和海岸线变化评估
IF 1.5 Q2 GEOSCIENCES, MULTIDISCIPLINARY Pub Date : 2023-06-07 DOI: 10.15625/2615-9783/18407
Tuan Giang Linh, Bac Dang Kinh, Quang Bui Thanh
Changes to the coastline or shoreline arise from the water's dynamic interaction with the land surface, which is triggered by ocean currents, waves, and winds. Various methods have been proposed to identify and monitor coastlines and shorelines, but their outcomes are uncertain. This study proposes indicators for identifying coastlines and shorelines in the fields and on the remote sensing data. Different pixel- and object-based machine learning (ML) models were built to automatically interpret coastlines and shorelines from high-resolution remote sensing images and monitor coastal erosion in Vietnam. Two pixel-based models using Random Forest and SVM structures and eight object-based models using U-Net, and U-Net3+ structures were trained. All models were trained using the high-resolution images gathered using Google Earth Pro as input data. The U-Net achieves the most remarkable performance of 98% with a loss function of 0.16 when utilizing an input-image size of 512×512. Object-based models have shown higher performance in analyzing coastlines and shorelines with linear and continuous structures than pixel-based models. Additionally, the coastline is appropriate to evaluate coastal erosion induced by the effect of sea-level rise during storms. At the same time, the shoreline is suited to observe seasonal tidal fluctuations or the instantaneous movements of current waves. Under the pressure of tourist development, the coasts in Danang and Quang Nam provinces have been eroded in the last 10 years. River and ocean currents also cause erosion in the southern Cua Dai estuary. In the future, the trained U-Net model can be used to monitor the changes in coastlines and shorelines worldwide.
海岸线或海岸线的变化源于水流、波浪和风引发的水与陆地表面的动态相互作用。已经提出了各种方法来识别和监测海岸线和海岸线,但其结果尚不确定。这项研究提出了在实地和遥感数据上识别海岸线和海岸线的指标。建立了不同的基于像素和对象的机器学习(ML)模型,从高分辨率遥感图像中自动解释海岸线和海岸线,并监测越南的海岸侵蚀。训练了使用随机森林和SVM结构的两个基于像素的模型,以及使用U-Net和U-Net3+结构的八个基于对象的模型。所有模型都是使用谷歌地球专业版收集的高分辨率图像作为输入数据进行训练的。当使用512×512的输入图像大小时,U-Net实现了98%的最显著性能,损失函数为0.16。与基于像素的模型相比,基于对象的模型在分析海岸线和具有线性和连续结构的海岸线方面表现出更高的性能。此外,海岸线适合评估风暴期间海平面上升影响引起的海岸侵蚀。同时,海岸线适合观察季节性潮汐波动或当前波浪的瞬时运动。在旅游业发展的压力下,岘港省和广南省的海岸在过去10年中受到侵蚀。河流和洋流也造成了南部错岱河口的侵蚀。未来,经过训练的U-Net模型可用于监测全球海岸线和海岸线的变化。
{"title":"Coastline and shoreline change assessment in sandy coasts based on machine learning models and high-resolution satellite images","authors":"Tuan Giang Linh, Bac Dang Kinh, Quang Bui Thanh","doi":"10.15625/2615-9783/18407","DOIUrl":"https://doi.org/10.15625/2615-9783/18407","url":null,"abstract":"Changes to the coastline or shoreline arise from the water's dynamic interaction with the land surface, which is triggered by ocean currents, waves, and winds. Various methods have been proposed to identify and monitor coastlines and shorelines, but their outcomes are uncertain. This study proposes indicators for identifying coastlines and shorelines in the fields and on the remote sensing data. Different pixel- and object-based machine learning (ML) models were built to automatically interpret coastlines and shorelines from high-resolution remote sensing images and monitor coastal erosion in Vietnam. Two pixel-based models using Random Forest and SVM structures and eight object-based models using U-Net, and U-Net3+ structures were trained. All models were trained using the high-resolution images gathered using Google Earth Pro as input data. The U-Net achieves the most remarkable performance of 98% with a loss function of 0.16 when utilizing an input-image size of 512×512. \u0000Object-based models have shown higher performance in analyzing coastlines and shorelines with linear and continuous structures than pixel-based models. Additionally, the coastline is appropriate to evaluate coastal erosion induced by the effect of sea-level rise during storms. At the same time, the shoreline is suited to observe seasonal tidal fluctuations or the instantaneous movements of current waves. Under the pressure of tourist development, the coasts in Danang and Quang Nam provinces have been eroded in the last 10 years. River and ocean currents also cause erosion in the southern Cua Dai estuary. In the future, the trained U-Net model can be used to monitor the changes in coastlines and shorelines worldwide.","PeriodicalId":23639,"journal":{"name":"VIETNAM JOURNAL OF EARTH SCIENCES","volume":" ","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49558751","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}
引用次数: 0
Combination of 2D-Electrical Resistivity Imaging and Seismic Refraction Tomography methods for groundwater potential assessments: A case study of Khammouane province, Laos 二维电阻率成像与地震折射层析成像相结合的地下水潜力评价方法——以老挝Khammouane省为例
IF 1.5 Q2 GEOSCIENCES, MULTIDISCIPLINARY Pub Date : 2023-05-18 DOI: 10.15625/2615-9783/18348
Viengthong Xayavong, Minh Vu Duc, Sounthone Singsoupho, Duong Nguyen Anh, Prasad K.N.D., Tuan Vu Minh, Chung Do Anh
2D Electrical Resistivity Imaging (2D-ERI) and Seismic Refraction Tomography (SRT) are non-destructive techniques widely used for numerous geophysical investigations, namely, structural geology mapping, archaeological, engineering, and groundwater investigations. The present study aims to define potential groundwater zones in the Thakhek district of Khammouane Province, Laos, by 2D-ERI and SRT methods; due to the limitation of groundwater potential information, monitoring and evaluation activities regarding groundwater quantity and quality have not been conducted in this study area. The 2D-ERI measurement is based on the Wenner configuration with an electrode spacing of 10-160 m. In contrast, SRT uses a 6.5 kg sledgehammer for a seismic source with a 4 m geophone interval. The results indicate moderate resistivity values ranging from 18.8-71 Ohm-m, and seismic velocities ranging from 1220-2140 m/s were found at 12-30 m in the study region, illustrating the existence of a groundwater/aquifer at this depth. These results correlate well with drilling results from the borehole measurements in the Thakhek district, where the water levels were found at a depth of 12 m for borehole 1 and 15 m for borehole 2. The present study also demonstrates the correlation between 2D-ERI and SRT techniques. The adopted methods favor groundwater identification in the study region and other areas with similar geology formations.
二维电阻率成像(2D- eri)和地震折射层析成像(SRT)是一种非破坏性技术,广泛应用于许多地球物理调查,即构造地质填图、考古、工程和地下水调查。本研究旨在利用2D-ERI和SRT方法确定老挝Khammouane省Thakhek地区潜在的地下水带;由于地下水潜力信息有限,本研究区尚未开展地下水数量和质量的监测评价活动。2D-ERI测量基于Wenner配置,电极间距为10-160 m。相比之下,SRT对震源使用6.5 kg的大锤,检波器间隔为4 m。结果表明,研究区12 ~ 30 m的电阻率值为18.8 ~ 71 ω -m,地震速度为1220 ~ 2140 m/s,表明该深度存在地下水/含水层。这些结果与Thakhek地区钻孔测量的钻探结果相吻合,在该地区,钻孔1的水位为12米,钻孔2的水位为15米。本研究还证明了2D-ERI和SRT技术之间的相关性。所采用的方法有利于研究区及其他类似地质构造地区的地下水识别。
{"title":"Combination of 2D-Electrical Resistivity Imaging and Seismic Refraction Tomography methods for groundwater potential assessments: A case study of Khammouane province, Laos","authors":"Viengthong Xayavong, Minh Vu Duc, Sounthone Singsoupho, Duong Nguyen Anh, Prasad K.N.D., Tuan Vu Minh, Chung Do Anh","doi":"10.15625/2615-9783/18348","DOIUrl":"https://doi.org/10.15625/2615-9783/18348","url":null,"abstract":"2D Electrical Resistivity Imaging (2D-ERI) and Seismic Refraction Tomography (SRT) are non-destructive techniques widely used for numerous geophysical investigations, namely, structural geology mapping, archaeological, engineering, and groundwater investigations. The present study aims to define potential groundwater zones in the Thakhek district of Khammouane Province, Laos, by 2D-ERI and SRT methods; due to the limitation of groundwater potential information, monitoring and evaluation activities regarding groundwater quantity and quality have not been conducted in this study area. The 2D-ERI measurement is based on the Wenner configuration with an electrode spacing of 10-160 m. In contrast, SRT uses a 6.5 kg sledgehammer for a seismic source with a 4 m geophone interval. The results indicate moderate resistivity values ranging from 18.8-71 Ohm-m, and seismic velocities ranging from 1220-2140 m/s were found at 12-30 m in the study region, illustrating the existence of a groundwater/aquifer at this depth. These results correlate well with drilling results from the borehole measurements in the Thakhek district, where the water levels were found at a depth of 12 m for borehole 1 and 15 m for borehole 2. The present study also demonstrates the correlation between 2D-ERI and SRT techniques. The adopted methods favor groundwater identification in the study region and other areas with similar geology formations.","PeriodicalId":23639,"journal":{"name":"VIETNAM JOURNAL OF EARTH SCIENCES","volume":" ","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43820002","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}
引用次数: 2
A novel swarm intelligence optimized extreme learning machine for predicting soil shear strength: A case study at Hoa Vuong new urban project (Vietnam) 一种新的群体智能优化极限学习机用于预测土壤抗剪强度:以越南Hoa Vuong新城市项目为例
IF 1.5 Q2 GEOSCIENCES, MULTIDISCIPLINARY Pub Date : 2023-05-15 DOI: 10.15625/2615-9783/18338
Viet-Ha Nhu, Binh Thai Pham, Dieu Bui Tien
In geotechnical engineering, soil shear strength is one of the most important parameters used in the design and construction of construction projects. However, determining this parameter in the laboratory is costly and time-consuming. Therefore, the main objective of this work is to develop a new alternative machine learning approach based on extreme learning machine (ELM) and Particle Swarm Optimization (PSO), namely PSO-ELM, for the shear strength prediction of soil for the Hoa Vuong new urban project in Nam Dinh province, North Vietnam. For this purpose, twelve soil parameters were collected on data from a survey of 155 soil samples to construct and validate the proposed model. We assessed the model's performance using the root-mean-square error (RMSE), the mean absolute error (MAE), and the coefficient of determination (R2). We compared the model's capability with five benchmark models, support vector regression (SVR), Gaussian process (GP), multi-layer perceptron neural network (MLP-NN), radial basis function neural network (RBF-NN), and the fast-decision tree (Fast-DT). The results revealed that the proposed PSO-ELM model yielded the highest prediction performance and outperformed the five benchmark models. It suggests that PSO-ELM can be an alternative method in estimating the shear strength of soil that would help geotechnical engineers reduce the cost of construction.
在岩土工程中,土壤抗剪强度是建筑工程设计和施工中最重要的参数之一。然而,在实验室中确定这一参数既昂贵又耗时。因此,本工作的主要目标是开发一种基于极限学习机(ELM)和粒子群优化(PSO)的新的替代机器学习方法,即PSO-ELM,用于越南北部南定省Hoa Vuong新城市项目的土壤抗剪强度预测。为此,从155个土壤样本的调查数据中收集了12个土壤参数,以构建和验证所提出的模型。我们使用均方根误差(RMSE)、平均绝对误差(MAE)和决定系数(R2)评估了模型的性能。我们将该模型的能力与五个基准模型进行了比较,即支持向量回归(SVR)、高斯过程(GP)、多层感知器神经网络(MLP-NN)、径向基函数神经网络(RBF-NN)和快速决策树(fast DT)。结果表明,所提出的PSO-ELM模型产生了最高的预测性能,并且优于五个基准模型。这表明PSO-ELM可以作为估算土壤抗剪强度的一种替代方法,有助于岩土工程师降低施工成本。
{"title":"A novel swarm intelligence optimized extreme learning machine for predicting soil shear strength: A case study at Hoa Vuong new urban project (Vietnam)","authors":"Viet-Ha Nhu, Binh Thai Pham, Dieu Bui Tien","doi":"10.15625/2615-9783/18338","DOIUrl":"https://doi.org/10.15625/2615-9783/18338","url":null,"abstract":"In geotechnical engineering, soil shear strength is one of the most important parameters used in the design and construction of construction projects. However, determining this parameter in the laboratory is costly and time-consuming. Therefore, the main objective of this work is to develop a new alternative machine learning approach based on extreme learning machine (ELM) and Particle Swarm Optimization (PSO), namely PSO-ELM, for the shear strength prediction of soil for the Hoa Vuong new urban project in Nam Dinh province, North Vietnam. For this purpose, twelve soil parameters were collected on data from a survey of 155 soil samples to construct and validate the proposed model. We assessed the model's performance using the root-mean-square error (RMSE), the mean absolute error (MAE), and the coefficient of determination (R2). We compared the model's capability with five benchmark models, support vector regression (SVR), Gaussian process (GP), multi-layer perceptron neural network (MLP-NN), radial basis function neural network (RBF-NN), and the fast-decision tree (Fast-DT). The results revealed that the proposed PSO-ELM model yielded the highest prediction performance and outperformed the five benchmark models. It suggests that PSO-ELM can be an alternative method in estimating the shear strength of soil that would help geotechnical engineers reduce the cost of construction.","PeriodicalId":23639,"journal":{"name":"VIETNAM JOURNAL OF EARTH SCIENCES","volume":" ","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45062149","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}
引用次数: 0
Monitoring the storage volume of impounding reservoirs in inaccessible regions using multi-sensor satellite data: the case study of Tuyen Quang Reservoir (Vietnam) 利用多传感器卫星数据监测人迹罕至地区蓄水库的蓄水量——以越南阮光水库为例
IF 1.5 Q2 GEOSCIENCES, MULTIDISCIPLINARY Pub Date : 2023-04-27 DOI: 10.15625/2615-9783/18303
Thao Nguyen Thien Phuong, Thai Nguyen Duy, Ha Nguyen Thi Thu, Vinh Pham Quang, Thanh Dinh Xuan
Water stored by reservoirs is critical for irrigation, electricity generation, drinking water supply, recreation, fisheries, and flood control. Therefore, the reservoir's water storage volume (SW) must be measured and monitored frequently for better watershed management. Since SW data is often not publicly available, finding a method to quantify SW objectively and accurately but to facilitate local water management is necessary. This study proposes a method for monitoring water surface area and storage volume using multi-sensor satellite remote sensing data through the Tuyen Quang Reservoir case study in Northern Vietnam. Accordingly, the water surface area was first delineated from multi-temporal optical satellite images, such as Landsat series and Sentinel-2 images, using the Modified Normalized Difference Water Index and resampled into 30-m pixel resolution data. Using the Shuttle Radar Topography Mission Digital Elevation Model data, the water depth at each pixel was then calculated by the difference between its elevation and the reservoir shoreline's mean elevation. The results showed that the reservoir's water surface area increased rapidly during 2003-2007 (from 579 ha to 5,516 ha), fluctuated insignificantly in 2008-2020, and reached 7,196 ha in 2021. Consequently, SW was raised from 11.8 million m3 in 2003 to 1.68 billion m3 in 2021. Our estimations agree with the depth and SW of Tuyen Quang Reservoir published in 2019. Our proposed method could be an effective water resource management tool in developing countries where the number of impounding reservoirs increases dramatically yearly without the financial afford to build gauging stations.   
水库蓄水对灌溉、发电、饮用水供应、娱乐、渔业和防洪至关重要。因此,为了更好地管理流域,必须经常测量和监测水库的蓄水量(SW)。由于SW数据通常不公开,因此有必要找到一种方法来客观准确地量化SW,但有助于当地水资源管理。本研究通过越南北部的阮光水库案例研究,提出了一种利用多传感器卫星遥感数据监测水面面积和蓄水量的方法。因此,首先使用修正的归一化差分水指数从多时相光学卫星图像(如Landsat系列和Sentinel-2图像)中划定水面区域,并将其重新采样为30m像素分辨率的数据。使用航天飞机雷达地形任务数字高程模型数据,然后通过高程与水库海岸线平均高程之间的差值计算每个像素的水深。结果表明,2003-2007年,水库水面面积迅速增加(从579公顷增加到5516公顷),2008-2020年波动不大,2021年达到7196公顷。因此,SW从2003年的1180万立方米增加到2021年的16.8亿立方米。我们的估计与2019年公布的Tuyen Quang水库的深度和SW一致。在发展中国家,我们提出的方法可能是一种有效的水资源管理工具,因为这些国家的蓄水池数量每年都在急剧增加,而没有资金来建造测量站。
{"title":"Monitoring the storage volume of impounding reservoirs in inaccessible regions using multi-sensor satellite data: the case study of Tuyen Quang Reservoir (Vietnam)","authors":"Thao Nguyen Thien Phuong, Thai Nguyen Duy, Ha Nguyen Thi Thu, Vinh Pham Quang, Thanh Dinh Xuan","doi":"10.15625/2615-9783/18303","DOIUrl":"https://doi.org/10.15625/2615-9783/18303","url":null,"abstract":"Water stored by reservoirs is critical for irrigation, electricity generation, drinking water supply, recreation, fisheries, and flood control. Therefore, the reservoir's water storage volume (SW) must be measured and monitored frequently for better watershed management. Since SW data is often not publicly available, finding a method to quantify SW objectively and accurately but to facilitate local water management is necessary. This study proposes a method for monitoring water surface area and storage volume using multi-sensor satellite remote sensing data through the Tuyen Quang Reservoir case study in Northern Vietnam. Accordingly, the water surface area was first delineated from multi-temporal optical satellite images, such as Landsat series and Sentinel-2 images, using the Modified Normalized Difference Water Index and resampled into 30-m pixel resolution data. Using the Shuttle Radar Topography Mission Digital Elevation Model data, the water depth at each pixel was then calculated by the difference between its elevation and the reservoir shoreline's mean elevation. The results showed that the reservoir's water surface area increased rapidly during 2003-2007 (from 579 ha to 5,516 ha), fluctuated insignificantly in 2008-2020, and reached 7,196 ha in 2021. Consequently, SW was raised from 11.8 million m3 in 2003 to 1.68 billion m3 in 2021. Our estimations agree with the depth and SW of Tuyen Quang Reservoir published in 2019. Our proposed method could be an effective water resource management tool in developing countries where the number of impounding reservoirs increases dramatically yearly without the financial afford to build gauging stations.   ","PeriodicalId":23639,"journal":{"name":"VIETNAM JOURNAL OF EARTH SCIENCES","volume":" ","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49224654","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}
引用次数: 0
Rainfall extremes in Northern Vietnam: a comprehensive analysis of patterns and trends 越南北部极端降雨模式和趋势的综合分析
IF 1.5 Q2 GEOSCIENCES, MULTIDISCIPLINARY Pub Date : 2023-04-20 DOI: 10.15625/2615-9783/18284
Thanh- Ngo Duc
This study examines the characteristics and trends of extreme rainfall in Northern Vietnam from 1961 to 2018, using daily rainfall data collected from 37 meteorological stations. The study reveals that the average annual rainfall varies significantly across stations, ranging from 1140 mm to 4758 mm. The rainy season accounts for 73% to 92% of the total annual rainfall. Most stations show a declining trend in the annual total rainfall during wet days (PRCPTOT) and the number of wet days (WDAY), while rainfall intensity (SDII) has increased in most stations, particularly during the dry season. This can be attributed to an increase in PRCPTOT and a decrease in WDAY in the dry season. The study also finds a general decreasing trend in the annual maximum 1-day precipitation (RX1day) and consecutive 5-day precipitation (RX5day), as well as for the number of moderate (R16mm) and heavy (R50mm) rainfall days. However, most stations in Northern Vietnam demonstrate no trend in the annual maximum number of consecutive dry days (CDD) and the annual maximum number of consecutive wet days (CWD). Furthermore, the frequency of extreme rainfall events in Northern Vietnam exceeding the 5-year and 10-year return values of 1961-2018 has decreased in recent decades at many stations. Overall, the findings of this study provide insights into the changing patterns of extreme rainfall in Northern Vietnam, with significant implications for climate change adaptation and disaster risk reduction efforts in the region.
本研究利用从37个气象站收集的日降雨量数据,考察了1961年至2018年越南北部极端降雨的特征和趋势。研究表明,各站点的年平均降雨量差异很大,从1140毫米到4758毫米不等。雨季占全年总降雨量的73%到92%。大多数站点在丰水日的年总降雨量(PRCPTOT)和丰水日数(WDAY)呈下降趋势,而大多数站点的降雨强度(SDII)有所增加,尤其是在旱季。这可归因于旱季PRCPTOT的增加和WDAY的减少。研究还发现,年最大1天降雨量(RX1天)和连续5天降雨量(rx5天)以及中等(R16mm)和强(R50mm)降雨天数总体呈下降趋势。然而,越南北部的大多数站点在年最大连续干旱日数(CDD)和年最大连续潮湿日数(CWD)方面没有表现出趋势。此外,近几十年来,越南北部许多站点超过1961-2018年5年和10年一遇的极端降雨事件频率有所下降。总的来说,这项研究的发现为越南北部极端降雨的变化模式提供了见解,对该地区适应气候变化和减少灾害风险的工作具有重要意义。
{"title":"Rainfall extremes in Northern Vietnam: a comprehensive analysis of patterns and trends","authors":"Thanh- Ngo Duc","doi":"10.15625/2615-9783/18284","DOIUrl":"https://doi.org/10.15625/2615-9783/18284","url":null,"abstract":"This study examines the characteristics and trends of extreme rainfall in Northern Vietnam from 1961 to 2018, using daily rainfall data collected from 37 meteorological stations. The study reveals that the average annual rainfall varies significantly across stations, ranging from 1140 mm to 4758 mm. The rainy season accounts for 73% to 92% of the total annual rainfall. Most stations show a declining trend in the annual total rainfall during wet days (PRCPTOT) and the number of wet days (WDAY), while rainfall intensity (SDII) has increased in most stations, particularly during the dry season. This can be attributed to an increase in PRCPTOT and a decrease in WDAY in the dry season. The study also finds a general decreasing trend in the annual maximum 1-day precipitation (RX1day) and consecutive 5-day precipitation (RX5day), as well as for the number of moderate (R16mm) and heavy (R50mm) rainfall days. However, most stations in Northern Vietnam demonstrate no trend in the annual maximum number of consecutive dry days (CDD) and the annual maximum number of consecutive wet days (CWD). Furthermore, the frequency of extreme rainfall events in Northern Vietnam exceeding the 5-year and 10-year return values of 1961-2018 has decreased in recent decades at many stations. Overall, the findings of this study provide insights into the changing patterns of extreme rainfall in Northern Vietnam, with significant implications for climate change adaptation and disaster risk reduction efforts in the region.","PeriodicalId":23639,"journal":{"name":"VIETNAM JOURNAL OF EARTH SCIENCES","volume":" ","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43237814","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}
引用次数: 0
Paleoenvironmental potential of lacustrine sediments in the Central Highlands of Vietnam: a review on the state of research 越南中部高地湖泊沉积物的古环境潜力:研究现状综述
IF 1.5 Q2 GEOSCIENCES, MULTIDISCIPLINARY Pub Date : 2023-04-19 DOI: 10.15625/2615-9783/18281
H. Nguyễn-Văn, I. Unkel, D. Nguyễn-Thùy, Thái Nguyễn-Đình, Đỗ Trọng Quốc, Đặng Xuân Tùng, Nguyen Thi hong, Đinh Xuân Thành, Nguyễn Thị Ánh Nguyệt, Nguyen Hong Quan, Đào Trung Hoàn, Nguyễn Thị Huyền Trang, Phạm Lê Tuyết Nhung, Lê Nguyệt Anh, Vũ Văn Hà, A. Ojala, A. Schimmelmann, P. Sauer
Global warming enhances atmospheric moisture loading and will likely affect monsoon strength in Vietnam. Without a long written history in Vietnam, we need to rely on geoarchives such as lake sediments to reconstruct past monsoon variability and regional paleoenvironmental fluctuations and evaluate current climatic trends. Natural lakes in the Central Highlands of Vietnam have the potential to have recorded shifts of the monsoon belt over glacial/interglacial cycles. Since 2016, the EOS Geoscience Research Group at Vietnam National University, Hanoi (EOS group) has collaborated with international partners to collect and analyze Vietnamese lake sediments to reconstruct the Pleistocene-Holocene climate history. Numerous sediment cores have been retrieved from Biển Hồ, Ia Bang, Ea Tyn, Ea Sno and Lak lakes between 2016 and 2022. Of special importance is a 25 m long sediment core from Biển Hồ Lake (Gia Lai province) covering the last 57 ka, which the team retrieved in April 2021. Sediment cores were analyzed for geochemistry, sedimentology, magnetic susceptibility, and radiocarbon dating. This paper reviews the status of our currently available sedimentary records to assess the paleoenvironmental potential of lacustrine sediments in the Central Highlands of Vietnam. Current data suggest that the lakes in the Central Highlands provide reliable sedimentological and geochemical records and bear the potential to reconstruct the paleoenvironmental and paleoclimatic conditions in Vietnam across several glacial periods, with a high-resolution record at least in the Holocene. The records contribute to quantifying the effects of monsoon variability and assessing the changes in hydrological conditions before and after the onset of human land use by comparing different lakes in the region. Future fieldwork will focus on retrieving longer lake sediment sequences from the Central Highlands, possibly covering the full interglacial-glacial cycle (i.e. the last 125 ka, back to MIS-5e), and on the assessment of comparable lake archives in other parts of Vietnam where the timing and character of monsoon-related climatic variations may have differed.
全球变暖增加了大气中的水分负荷,并可能影响越南的季风强度。由于越南没有悠久的文字历史,我们需要依靠湖泊沉积物等地质档案来重建过去的季风变化和区域古环境波动,并评估当前的气候趋势。越南中部高地的天然湖泊有可能记录到季风带在冰川/间冰川周期中的变化。自2016年以来,河内越南国立大学EOS地球科学研究小组(EOS小组)与国际合作伙伴合作,收集和分析越南湖泊沉积物,以重建更新世-全新世气候史。从Bi中提取了大量沉积物岩心ển Hồ, 2016年至2022年间,Ia Bang、Ea Tyn、Ea Sno和Lak湖。特别重要的是Bi的一个25米长的沉积物岩芯ển Hồ 湖(贾莱省)覆盖了最后57卡,该团队于2021年4月取回了该卡。对沉积物岩心进行了地球化学、沉积学、磁化率和放射性碳测年分析。本文回顾了我们目前可用的沉积记录的现状,以评估越南中部高地湖泊沉积物的古环境潜力。目前的数据表明,中央高地的湖泊提供了可靠的沉积学和地球化学记录,有可能重建越南几个冰川期的古环境和古气候条件,至少在全新世有高分辨率的记录。这些记录有助于量化季风变化的影响,并通过比较该地区不同的湖泊来评估人类土地利用开始前后水文条件的变化。未来的实地调查将侧重于从中央高地检索更长的湖泊沉积物序列,可能涵盖整个间冰期冰川周期(即最后125 ka,回到MIS-5e),并评估越南其他地区的可比湖泊档案,在这些地区,季风相关气候变化的时间和特征可能有所不同。
{"title":"Paleoenvironmental potential of lacustrine sediments in the Central Highlands of Vietnam: a review on the state of research","authors":"H. Nguyễn-Văn, I. Unkel, D. Nguyễn-Thùy, Thái Nguyễn-Đình, Đỗ Trọng Quốc, Đặng Xuân Tùng, Nguyen Thi hong, Đinh Xuân Thành, Nguyễn Thị Ánh Nguyệt, Nguyen Hong Quan, Đào Trung Hoàn, Nguyễn Thị Huyền Trang, Phạm Lê Tuyết Nhung, Lê Nguyệt Anh, Vũ Văn Hà, A. Ojala, A. Schimmelmann, P. Sauer","doi":"10.15625/2615-9783/18281","DOIUrl":"https://doi.org/10.15625/2615-9783/18281","url":null,"abstract":"Global warming enhances atmospheric moisture loading and will likely affect monsoon strength in Vietnam. Without a long written history in Vietnam, we need to rely on geoarchives such as lake sediments to reconstruct past monsoon variability and regional paleoenvironmental fluctuations and evaluate current climatic trends. Natural lakes in the Central Highlands of Vietnam have the potential to have recorded shifts of the monsoon belt over glacial/interglacial cycles. Since 2016, the EOS Geoscience Research Group at Vietnam National University, Hanoi (EOS group) has collaborated with international partners to collect and analyze Vietnamese lake sediments to reconstruct the Pleistocene-Holocene climate history. Numerous sediment cores have been retrieved from Biển Hồ, Ia Bang, Ea Tyn, Ea Sno and Lak lakes between 2016 and 2022. Of special importance is a 25 m long sediment core from Biển Hồ Lake (Gia Lai province) covering the last 57 ka, which the team retrieved in April 2021. Sediment cores were analyzed for geochemistry, sedimentology, magnetic susceptibility, and radiocarbon dating. This paper reviews the status of our currently available sedimentary records to assess the paleoenvironmental potential of lacustrine sediments in the Central Highlands of Vietnam. Current data suggest that the lakes in the Central Highlands provide reliable sedimentological and geochemical records and bear the potential to reconstruct the paleoenvironmental and paleoclimatic conditions in Vietnam across several glacial periods, with a high-resolution record at least in the Holocene. The records contribute to quantifying the effects of monsoon variability and assessing the changes in hydrological conditions before and after the onset of human land use by comparing different lakes in the region. Future fieldwork will focus on retrieving longer lake sediment sequences from the Central Highlands, possibly covering the full interglacial-glacial cycle (i.e. the last 125 ka, back to MIS-5e), and on the assessment of comparable lake archives in other parts of Vietnam where the timing and character of monsoon-related climatic variations may have differed.","PeriodicalId":23639,"journal":{"name":"VIETNAM JOURNAL OF EARTH SCIENCES","volume":" ","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47316583","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}
引用次数: 1
Analysis of gravity data for extracting structural features of the northern region of the Central Indian Ridge 中印度脊北部构造特征提取的重力数据分析
IF 1.5 Q2 GEOSCIENCES, MULTIDISCIPLINARY Pub Date : 2023-03-30 DOI: 10.15625/2615-9783/18206
Luan Thanh Pham, K. Prasad
In this study, structural lineaments and fracture zones of the northern region of the Central Indian Ridge have been determined using gravity data from XGM2019e_2159 global gravity model. In this scope, firstly, the edge detection performances of the gradient amplitude of the tilt angle (THDR), theta map (TM), improved local phase (ILP), and improved logistic (IL) methods have been evaluated on synthetic examples. The results show that the IL method effectively avoids false edges and produces high-resolution edges. Then, the methods are applied to the gravity anomaly of the northern region of the Central Indian Ridge. It has been determined that the most prominent structural lineaments observed over the region are in the NE-SW and NW-SE directions. These trends match reasonably with the significant trends of the Tilt depth solutions that show a depth range of 2.2 km to 7 km for different geological structures. In addition, the obtained results are compatible with the known fracture zones of the study area. The findings help us to improve our understanding of the structure and tectonic framework of the study region.
在本研究中,使用XGM2019e_2159全球重力模型的重力数据确定了中印度洋脊北部地区的构造线理和断裂带。在此范围内,首先,在合成示例上评估了倾斜角的梯度幅度(THDR)、θ映射(TM)、改进的局部相位(ILP)和改进的逻辑(IL)方法的边缘检测性能。结果表明,IL方法有效地避免了伪边缘,产生了高分辨率的边缘。然后,将这些方法应用于中印度洋脊北部地区的重力异常。已经确定,在该地区观察到的最突出的结构线理位于NE-SW和NW-SE方向。这些趋势与倾斜深度解的显著趋势合理匹配,倾斜深度解显示不同地质结构的深度范围为2.2 km至7 km。此外,所获得的结果与研究区域的已知断裂带相一致。这些发现有助于我们更好地了解研究区域的结构和构造框架。
{"title":"Analysis of gravity data for extracting structural features of the northern region of the Central Indian Ridge","authors":"Luan Thanh Pham, K. Prasad","doi":"10.15625/2615-9783/18206","DOIUrl":"https://doi.org/10.15625/2615-9783/18206","url":null,"abstract":"In this study, structural lineaments and fracture zones of the northern region of the Central Indian Ridge have been determined using gravity data from XGM2019e_2159 global gravity model. In this scope, firstly, the edge detection performances of the gradient amplitude of the tilt angle (THDR), theta map (TM), improved local phase (ILP), and improved logistic (IL) methods have been evaluated on synthetic examples. The results show that the IL method effectively avoids false edges and produces high-resolution edges. Then, the methods are applied to the gravity anomaly of the northern region of the Central Indian Ridge. It has been determined that the most prominent structural lineaments observed over the region are in the NE-SW and NW-SE directions. These trends match reasonably with the significant trends of the Tilt depth solutions that show a depth range of 2.2 km to 7 km for different geological structures. In addition, the obtained results are compatible with the known fracture zones of the study area. The findings help us to improve our understanding of the structure and tectonic framework of the study region.","PeriodicalId":23639,"journal":{"name":"VIETNAM JOURNAL OF EARTH SCIENCES","volume":" ","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47021980","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}
引用次数: 7
Analysis of landslide kinematics integrating weather and geotechnical monitoring data at Tan Son slow moving landslide in Ha Giang province 结合天气和岩土工程监测数据对江省Tan Son缓慢移动滑坡的运动学分析
IF 1.5 Q2 GEOSCIENCES, MULTIDISCIPLINARY Pub Date : 2023-03-30 DOI: 10.15625/2615-9783/18204
Duc Dao Minh, Minh Vu Cao, Yen Hoang Hai, Loc Nguyen The, Duc Do Minh
Rainfall infiltration on the slope increases pore-water pressure in the soil/ rock mass and may cause landslides. Therefore, the precipitation, pore-water pressure and displacement show the kinematic variation of a landslide. In recent years, several approaches have been proposed to investigate the kinematic behavior. Among them, the combination of time series data and geotechnical model has demonstrated its effectiveness in stage classification of landslide kinematics. This paper aims to analyze and classify the stages of landslide kinematic variation with integrating weather and geotechnical monitoring data of Tan Son market landslides. The real-time monitoring station for Tan Son slow-moving landslides were equipped with fixed-in-place inclinometer probes and standard pore-water pressure sensors. The results show that landslide kinematics consist of three stages: stabilization, accumulation, and displacement. The displacement of the landslides was heterogeneous process. The velocity of the landslides significantly increased when the pore-water pressure ratio (ru) at the sliding surfaces > 0.53. While it is almost impossible to notice any displacement when the ratio r­u < 0.45. During the displacement state, the trend of inverse velocity variation gradually decreases to near zero hour/mm. In addition, early warnings of landslide can be released based on the kinematic stages and changes in inverse velocity in this study.
斜坡上的降雨渗透增加了土壤/岩体中的孔隙水压力,并可能导致滑坡。因此,降水、孔隙水压力和位移显示了滑坡的运动变化。近年来,已经提出了几种方法来研究运动学行为。其中,将时间序列数据与岩土模型相结合,证明了其在滑坡运动学阶段分类中的有效性。本文旨在结合Tan Son市场滑坡的天气和岩土监测数据,对滑坡运动变化的阶段进行分析和分类。Tan Son慢速滑坡实时监测站配备了固定式测斜探头和标准孔隙水压力传感器。研究结果表明,滑坡运动学分为稳定、堆积和位移三个阶段。滑坡的位移是一个非均匀的过程。当滑动面孔隙水压力比(ru)>0.53时,滑坡速度显著增加。而当比值r­u<0.45时,几乎不可能注意到任何位移。在位移状态下,速度反向变化的趋势逐渐减小到接近零时/mm。此外,本研究还可以根据滑坡的运动学阶段和逆速度变化发布滑坡预警。
{"title":"Analysis of landslide kinematics integrating weather and geotechnical monitoring data at Tan Son slow moving landslide in Ha Giang province","authors":"Duc Dao Minh, Minh Vu Cao, Yen Hoang Hai, Loc Nguyen The, Duc Do Minh","doi":"10.15625/2615-9783/18204","DOIUrl":"https://doi.org/10.15625/2615-9783/18204","url":null,"abstract":"Rainfall infiltration on the slope increases pore-water pressure in the soil/ rock mass and may cause landslides. Therefore, the precipitation, pore-water pressure and displacement show the kinematic variation of a landslide. In recent years, several approaches have been proposed to investigate the kinematic behavior. Among them, the combination of time series data and geotechnical model has demonstrated its effectiveness in stage classification of landslide kinematics. This paper aims to analyze and classify the stages of landslide kinematic variation with integrating weather and geotechnical monitoring data of Tan Son market landslides. The real-time monitoring station for Tan Son slow-moving landslides were equipped with fixed-in-place inclinometer probes and standard pore-water pressure sensors. The results show that landslide kinematics consist of three stages: stabilization, accumulation, and displacement. The displacement of the landslides was heterogeneous process. The velocity of the landslides significantly increased when the pore-water pressure ratio (ru) at the sliding surfaces > 0.53. While it is almost impossible to notice any displacement when the ratio r­u < 0.45. During the displacement state, the trend of inverse velocity variation gradually decreases to near zero hour/mm. In addition, early warnings of landslide can be released based on the kinematic stages and changes in inverse velocity in this study.","PeriodicalId":23639,"journal":{"name":"VIETNAM JOURNAL OF EARTH SCIENCES","volume":" ","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49559432","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}
引用次数: 0
Daily streamflow forecasting by machine learning in Tra Khuc river in Vietnam 越南Tra Khuc河的机器学习日流量预测
IF 1.5 Q2 GEOSCIENCES, MULTIDISCIPLINARY Pub Date : 2022-12-02 DOI: 10.15625/2615-9783/17914
Huu Duy Nguyen
Precise streamflow prediction is crucial in the optimization of the distribution of water resources. This study develops the machine learning models by integrating recurrent gate unit (GRU) with bacterial foraging optimization (BFO), gray wolf optimizer (GWO), and human group optimization (HGO) to forecast the streamflow in the Tra Khuc River, Vietnam. For this purpose, the time series of daily rainfall and river flow at Son Giang station from 2000 to 2020 were employed to forecast the streamflow. The statistical indices, namely the root mean square error, the mean absolute error, and the coefficient of determination (R²), was utilized to evaluate the performance of the proposed models. The results showed that the three optimization algorithms (HGO, GWO, and BFO) effectively enhanced the performance of the GRU model. Moreover, among the four models (GRU, GRU-HGO, GRU-GWO, and GRU-BFO), the GRU-GWO model outperformed the other models with R² = 0.883. GRU-HGO achieved R² = 0.879, and GRU-BFO achieved R²=0.878. The results of this study showed that GRU combined with optimization algorithms is a reliable modeling approach in short-term flow forecasting.
精确的流量预测是水资源优化配置的关键。本研究将循环门单元(GRU)与细菌觅食优化(BFO)、灰狼优化(GWO)和人类群体优化(HGO)相结合,建立了机器学习模型,用于预测越南特拉胡克河的流量。为此,利用2000 - 2020年孙江站日降雨量和河流量时间序列对河流流量进行预报。采用均方根误差、平均绝对误差和决定系数(R²)等统计指标评价模型的性能。结果表明,三种优化算法(HGO、GWO和BFO)有效地增强了GRU模型的性能。在GRU、GRU- hgo、GRU- gwo、GRU- bfo四种模型中,GRU- gwo模型的表现优于其他模型,R²= 0.883。GRU-HGO达到R²= 0.879,GRU-BFO达到R²=0.878。研究结果表明,GRU结合优化算法是一种可靠的短期流量预测建模方法。
{"title":"Daily streamflow forecasting by machine learning in Tra Khuc river in Vietnam","authors":"Huu Duy Nguyen","doi":"10.15625/2615-9783/17914","DOIUrl":"https://doi.org/10.15625/2615-9783/17914","url":null,"abstract":"Precise streamflow prediction is crucial in the optimization of the distribution of water resources. This study develops the machine learning models by integrating recurrent gate unit (GRU) with bacterial foraging optimization (BFO), gray wolf optimizer (GWO), and human group optimization (HGO) to forecast the streamflow in the Tra Khuc River, Vietnam. For this purpose, the time series of daily rainfall and river flow at Son Giang station from 2000 to 2020 were employed to forecast the streamflow. The statistical indices, namely the root mean square error, the mean absolute error, and the coefficient of determination (R²), was utilized to evaluate the performance of the proposed models. The results showed that the three optimization algorithms (HGO, GWO, and BFO) effectively enhanced the performance of the GRU model. \u0000Moreover, among the four models (GRU, GRU-HGO, GRU-GWO, and GRU-BFO), the GRU-GWO model outperformed the other models with R² = 0.883. GRU-HGO achieved R² = 0.879, and GRU-BFO achieved R²=0.878. The results of this study showed that GRU combined with optimization algorithms is a reliable modeling approach in short-term flow forecasting.","PeriodicalId":23639,"journal":{"name":"VIETNAM JOURNAL OF EARTH SCIENCES","volume":" ","pages":""},"PeriodicalIF":1.5,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47863185","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}
引用次数: 1
期刊
VIETNAM JOURNAL OF EARTH SCIENCES
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1