Search

This article presents a research approach to enhancing the quality of short-term power output forecasting models for photovoltaic plants using a Long Short-Term Memory (LSTM) recurrent neural network. Typically, time-related indicators are used as inputs for forecasting models of PV generators. However, this study proposes replacing the time-related inputs with clear sky solar irradiance at the specific location of the power plant. This feature represents the maximum potential solar radiation that can be received at that particular location on Earth. The Ineichen/Perez model is then employed to calculate the solar irradiance. To evaluate the effectiveness of this approach, the forecasting model incorporating this new input was trained and the results were compared with those obtained from previously published models. The results show a reduction in the Mean Absolute Percentage Error (MAPE) from 3.491% to 2.766%, indicating a 24% improvement. Additionally, the Root Mean Square Error (RMSE) decreased by approximately 0.991 MW, resulting in a 45% improvement. These results demonstrate that this approach is an effective solution for enhancing the accuracy of solar power output forecasting while reducing the number of input variables.

Renewable electricity for off-grid areas is widely seen as one of the top choices in supporting local economic development in most countries, and so is Vietnam. Over the years, many isolated networks using renewable energy sources have been deployed for off-grid areas in Vietnam. However, the use of these energy sources in Vietnam’s isolated networks is still facing many challenges due to its infancy here. The issues of reliability and vulnerability of these networks are not given the expected attention. Another challenge is that the issues of the operational security of these systems could also be negatively affected by the variable nature of renewable sources, including static and dynamic security. For this reason, this study aims to contribute to a better understanding of integrating renewable energy into isolated networks, and in this case, using solar power for the An-Binh Island grid in Vietnam. The findings from this study suggest that choosing the right structure of the power mix could contribute to improving the operational security of isolated networks. Moreover, several solutions to enhance the reliability of this grid are also proposed. The NEPLAN environment was selected for simulation and analysis for all the scenarios in this study.

Field measurement of the bed roughness of tropical tidal rivers is a long and expensive process. In this study, we quantified the roughness coefficient from the acoustic Doppler current profiler (ADCP) measurements considering flow characteristics along a 240 km length of the Vu Gia Thu Bon River system, in central Vietnam. Our approach entailed the application of the logarithmic velocity distribution trend of turbulent flows to determine the bottom roughness height. Then, we applied the equation suggested by Strickler (1923) to calculate the Manning roughness coefficient. The TELEMAC-2D hydraulic model was then used to simulate the effect of the roughness coefficient on the estimated water level. Despite its uncertainty, the estimated bed roughness was sufficient for the accurate calculation of the hydraulic variables. Compared to those in previous research, the statistical indicators showed good performance in the first simulation process during both the calibration and validation periods along the river system. [ABSTRACT FROM AUTHOR]

In this paper, we present a low-cost health assessment system for oil-immersed service transformers using a monitoring device to measure energy in real time. By assessing the important level of transformer components, three indicators, top oil temperature, vibration, and transformer load, were selected as main indicators to investigate the service transformer’s condition. An evaluation system using Fuzzy logic method is also presented in the paper to support monitor transformer health without adding the extra cost of installing expensive sensors. Different testing scenarios with different case studies were carried out on a simulated 50 kVA oil-immersed service transformer to express the feasibility and effectiveness of this low-cost, fast response health assessment system.

The evolution of delta and riverbank erosion within the river basin can significantly impact the environment, ecosystems, and lives of those residing along rivers. The Vietnamese Mekong Delta (VMD), counted among the world's largest deltas, has undergone significant morphological alterations via natural processes and human activities. This research aims to examine these morphological alterations and their impacts on local economic and social conditions in the VMD. This study utilized satellite data from 1988 to 2020, coupled with population density and land use/land cover (LULC) maps from 2002, 2008, and 2015. The findings reveal that the VMD experienced widespread erosion over the past three decades, covering an area of 66.8 km2 and affecting 48% of the riverbank length (682 km). In contrast to riverbanks, islets showed an accretion trend with an additional area of 13.3 km2, resulting in a decrease in river width over the years. Riverbank and islet erosion has had a profound impact on the LULC, population, and economy of the provinces along the VMD. From 2002 to 2020, eight different land use types were affected, with agricultural land being the most severely eroded, constituting over 86% of the total lost land area (3235.47 ha). The consequences of land loss due to erosion affected 31,273 people and resulted in substantial economic damages estimated at VND 19,409.90 billion (USD 799.50 million) across nine provinces along the VMD. Notably, even though built-up land represented a relatively small portion of the affected area (6.58%), it accounted for the majority of the economic damage at 70.6% (USD 564.45 million). This study underscores the crucial role of satellite imagery and GIS in monitoring long-term morphological changes and assessing their primary impacts. Such analysis is essential for formulating effective plans and strategies for the sustainable management of river environments. [ABSTRACT FROM AUTHOR]

Hydraulic infrastructures, such as reservoirs and water diversion channels, cause altered streamflow worldwide. Therefore, this study aimed to assess the coupled impacts of reservoir operations and water transfer on downstream streamflow over 42 years (1979–2020) for a tropical river in Vietnam, the Vu Gia Thu Bon (VGTB). We also quantified variations in the multi‐sub‐basin contributions to the water budget associated with hydraulic structure development. Therefore, a semi‐distributed hydrological model, SWAT (Soil and Water Assessment Tool), was developed for the entire VGTB basin considering two plausible scenarios: with a dam and without a dam. In this study, reservoirs substantially affected the streamflow during the 2011–2020 period when 12 cascading hydropower dams were constructed in the Vu Gia sub‐basins. The cascading reservoirs across the Vu Gia River reduced the annual average streamflow by 28.1% during this period, whereas their influence was augmented by 13.9% at reaches further downstream. In contrast, the local reservoir and flow diversions created on the Thu Bon River resulted in a 6.5% increase in streamflow. The upstream reservoir operation significantly increased streamflow at the midstream stations by 27.8% compared to the no‐dam period. The streamflow decreased in the dry season by 5.6% in the Vu Gia sub‐basins and increased by 61.7% in the Thu Bon sub‐basins. However, the impacts decreased in the wet season by 41.3% due to the operation of reservoirs, in which Dak Mi 4 had the most significant influence. It was found that the water diverted to the Thu Bon River was governed and reduced by the cascading hydropower dams. Therefore, the operation of 11 reservoirs has partially compensated for the lost water in the Vu Gia sub‐basins, to which the Dak Mi 4 plant has transferred 19.7 m3/s (14%). Our findings classify the impact of cascading dams and diversion structures and their interaction with climate change. [ABSTRACT FROM AUTHOR]

The Vu Gia Thu Bon (VGTB) basin constitutes the primary water supply in Central Vietnam. While climate change disturbs stream discharges and affects flood extremes, upstream dam development may intensify or mitigate such impacts. Therefore, this study provides a quantitative evaluation of long-term alterations in the flow regimes of the VGTB rivers from 1977 to 2020 resulting from the impacts of upstream anthropogenic developments. The datasets are divided into two periods, pre-2000 (1977–2000) and post-2000 (2001–2020), using different indices and analytical methods. The analyses show that since 2011, reservoir operations have reduced the maximum and high-flow discharges downstream in excess of climate change and land-use effects. However, due to the impact of water transfer by the Dak Mi 4 hydropower dam from the Vu Gia River to the Thu Bon River through a diversion channel, the minimum and low-flow discharges decreased in the pre-dam period and increased in the post-dam period. [ABSTRACT FROM AUTHOR]

In this study, six machine learning (ML) models, namely, random forest (RF), Gaussian process regression (GPR), support vector regression (SVR), decision tree (DT), least squares support vector machine (LSSVM), and multivariate adaptive regression spline (MARS) models, were employed to reconstruct the missing daily‐averaged discharge in a mega‐delta from 1980 to 2015 using upstream‐downstream multi‐station data. The performance and accuracy of each ML model were assessed and compared with the stage‐discharge rating curves (RCs) using four statistical indicators, Taylor diagrams, violin plots, scatter plots, time‐series plots, and heatmaps. Model input selection was performed using mutual information and correlation coefficient methods after three data pre‐processing steps: normalization, Fourier series fitting, and first‐order differencing. The results showed that the ML models are superior to their RC counterparts, and MARS and RF are the most reliable algorithms, although MARS achieves marginally better performance than RF. Compared to RC, MARS and RF reduced the root mean square error (RMSE) by 135% and 141% and the mean absolute error by 194% and 179%, respectively, using year‐round data. However, the performance of MARS and RF developed for the climbing (wet season) and recession (dry season) limbs separately worsened slightly compared to that developed using the year‐round data. Specifically, the RMSE of MARS and RF in the falling limb was 856 and 1,040 m3/s, respectively, while that obtained using the year‐round data was 768 and 789 m3/s, respectively. In this study, the DT model is not recommended, while the GPR and SVR models provide acceptable results. [ABSTRACT FROM AUTHOR]

This paper uses recurrent neural network (Long Short - Term Memory - LSTM network) to build a model to forecast short-term generation capacity of Phong Dien solar power plant, (48 MWp - 35 MWAC) located in Thua Thien Hue Province, Viet Nam, with input factors including meteorological parameters. The authors conducted experiments to find the optimal structure of the model corresponding to the conditions of the plant and the data collection. Through this model, meteorological forecast data sets from commercial suppliers were used to forecast the plant's output power. The comments about the result as well as the further study direction are analysed and suggested. [ABSTRACT FROM AUTHOR]

The hydrogeomorphology of the Vietnamese Mekong Delta (VMD) has been significantly altered by natural and anthropogenic drivers. In this study, the spatiotemporal changes of the flow regime were examined by analysing the long‐term daily, monthly, annual and extreme discharges and water levels from 1980 to 2018, supported by further investigation of the long‐term annual sediment load (from the 1960s to 2015), river bathymetric data (in 1998, 2014 and 2017) and daily salinity concentration (from the 1990s to 2015) using various statistical methods and a coupled numerical model. Then, the effects of riverbed incision on the hydrology were investigated. The results show that the dry season discharge (i.e., in March–June) of the Tien River increased by up to 23% from the predam period (1980–1992) to the postdam period (1993–2018) but that the dry season water level at My Thuan decreased by up to −46%. The annual mean and monthly water levels in June at Tan Chau and in January and June–October at My Thuan in the Tien River decreased statistically, even though the respective discharges increased significantly. These decreased water levels instead of the increased discharges were attributed to the accelerated riverbed incision upstream from My Thuan, which increased by more than three times, from a mean rate of −0.16 m/year (−16.7 Mm3/year) in 1998–2014 to −0.5 m/year (−52.5 Mm3/year) in 2014–2017. This accelerated riverbed incision was likely caused by the reduction in the sediment load of the VMD (from 166.7 Mt/year in the predam period to 57.6 Mt/year in the postdam period) and increase in sand mining (from 3.9 Mm3 in 2012 to 13.43 Mm3 in 2018). Collectively, the decreased dry season water level in the Tien River is likely one of the main causes of the enhanced salinity intrusion. [ABSTRACT FROM AUTHOR]

To improve knowledge of this matter, the potential application of two gridded meteorological products (GMPs), the China Meteorological Assimilation Driving Datasets for the SWAT model (CMADS) and Climate Forecast System Reanalysis (CFSR), are compared for the first time with data from ground-based meteorological stations over 6 years, from 2008 to 2013, over the Cau River basin (CRB), northern Vietnam. Statistical indicators and the Soil and Water Assessment Tool (SWAT) model are employed to investigate the hydrological performances of the GMPs against the data of 17 rain gauges distributed across the CRB. The results show that there are strong correlations between the temperature reanalysis products in both CMADS and CFSR and those obtained from the ground-based observations (the correlation coefficients range from 0.92 to 0.97). The CFSR data overestimate precipitation (percentage bias approximately 99%) at both daily and monthly scales, whereas the CMADS product performs better, with obvious differences (compared to the ground-based observations) in high-terrain areas. Regarding the simulated river flows, CFSR-SWAT produced "unsatisfactory", while CMADS-SWAT (R2 > 0.76 and NSE > 0.78) performs better than CFSR-SWAT on the monthly scale. This assessment of the applicative potential of GMPs, especially CMADS, may further provide an additional rapid alternative for water resource research and management in basins with similar hydro-meteorological conditions. [ABSTRACT FROM AUTHOR]

River bank (RB) erosion is a global issue affecting livelihoods and properties of millions of people. However, it has not received enough attention in the Vietnamese Mekong Delta (VMD), i.e., the world's third largest delta, compared to salinity intrusion and flooding. There have been several studies examining RB and coastal erosion in the VMD using remotely sensed satellite data, but the applied methodology was not adequately validated. Therefore, we developed a novel SRBED (Spectral RB Erosion Detection) method, in which the M-AMERL (Modified Automated Method for Extracting Rivers and Lakes) is proposed, and a new RB change detection algorithm using Landsat data. The results show that NDWI (Normalized Difference Water Index) and MNDWI (Modified Normalized Difference Water Index) using the M-AMERL algorithm (i.e., NDWIM-AMERL, MNDWIM-AMERL) perform better than other indices. Furthermore, the NDWIM-AMERL; SMA (i.e., NDWIM-AMERL using the SMA (Spectral Mixture Analysis) algorithm) is the best RB extraction method in the VMD. The NDWIM-AMERL; SMA performs better than the MNDWI, NDVI (Normalized Difference Vegetation Index), and WNDWI (Weighted Normalized Difference Water Index) indices by 35–41%, 70% and 30%, respectively. Moreover, the NDVI index is not recommended for assessing RB changes in the delta. Applying the developed SRBED method and RB change detection algorithm, we estimated a net erosion area of the RB of –1.5 km2 from 2008 to 2014 in the Tien River from Tan Chau to My Thuan, with a mean erosion width of –2.64 m and maximum erosion widths exceeding 60 m in places. Our advanced method can be applied in other river deltas having similar characteristics, and the results from our study are helpful in future studies in the VMD. [ABSTRACT FROM AUTHOR]

[Display omitted] • Top ten influencing factors of groundwater salinization were identified. • The CatBoost Regression model provides the highest accuracy salinity prediction. • In the Mekong Delta, groundwater pumping has a strong impact on salinization processes. • Forty-eight percentage of the population is in threshold salinity areas (>250 mg/L). • Immediate actions are needed to prevent groundwater salinization. Groundwater salinization is considered as a major environmental problem in worldwide coastal areas, influencing ecosystems and human health. However, an accurate prediction of salinity concentration in groundwater remains a challenge due to the complexity of groundwater salinization processes and its influencing factors. In this study, we evaluate state-of-the-art machine learning (ML) algorithms for predicting groundwater salinity and identify its influencing factors. We conducted a study for the coastal multi-layer aquifers of the Mekong River Delta (Vietnam), using a geodatabase of 216 groundwater samples and 14 conditioning factors. We compared the predictive performances of different ML techniques, i.e., the Random Forest Regression (RFR), the Extreme Gradient Boosting Regression (XGBR), the CatBoost Regression (CBR), and the Light Gradient Boosting Regression (LGBR) models. The model performance was assessed by using root-mean-square error (RMSE), coefficient of determination (R 2), the Akaike Information Criterion (AIC), and Bayesian Information Criterion (BIC). The results show that the CBR model has the highest performance with both training (R 2 = 0.999, RMSE = 29.90) and testing datasets (R 2 = 0.84, RMSE = 205.96, AIC = 720.60, and BIC = 751.04). Ten of the 14 influencing factors, including the distance to saline sources, the depth of screen well, the groundwater level, the vertical hydraulic conductivity, the operation time, the well density, the extraction capacity, the thickness of the aquitard, the distance to fault, and the horizontal hydraulic conductivity are the most important factors for groundwater salinity prediction. The results provide insights for policymakers in proposing remediation and management strategies for groundwater salinity issues in the context of excessive groundwater exploitation in coastal lowland regions. Since the human-induced influencing factors have significantly influenced groundwater salinization, urgent actions should be taken into consideration to ensure sustainable groundwater management in the coastal areas of the Mekong River Delta. [ABSTRACT FROM AUTHOR]