Identifying the impact of land use land cover change on streamflow and nitrate load following modeling approach: a case study in the upstream Dong Nai River basin, Vietnam.

Tri An Reservoir is a vital source of water for agriculture, industry, hydropower, and public usage in Southern Vietnam. Due to human activities, water eutrophication has become a serious problem in recent decades. This study investigated for the first time the impact of land use and land cover (LULC) change on streamflow and nitrate load from the upstream Dong Nai River basin, which is the largest watershed of the reservoir. The study utilized several LULC scenarios, including LULC 2000, 2010, and 2020. The SWAT model was applied to model the watershed during the period 1997-2009. Results showed that the hydrological model performed satisfactorily based on the Nash-Sutcliffe efficiency (NSE) coefficient, the root mean square error observations standard deviation ratio (RSR), and the percent bias (PBIAS). The average simulated values of monthly streamflow and nitrate load were 453.7, 450.0, 446.7 m3/s and 17,699.43, 17,869.13, 17,590.81 tonnes for the LULC 2000, 2010, and 2020 scenarios, respectively. There were no significant differences in streamflow and nitrate load at the basin level under the different LULC scenarios. However, when looking at the subbasin level, there were differences in nitrate load among the scenarios. This suggests that the impacts of LULC on nitrate load may be more pronounced at smaller scales. Overall, our finding underscores the importance of modeling techniques in predicting the impacts of LULC change on streamflow and water quality, which can ultimately aid in the sustainable management of water resources.

Comparing the performance of machine learning algorithms for remote and in situ estimations of chlorophyll-a content: A case study in the Tri An Reservoir, Vietnam.

Chlorophyll-a (Chl-a) is one of the most important indicators of the trophic status of inland waters, and its continued monitoring is essential. Recently, the operated Sentinel-2 MSI satellite offers high spatial resolution images for remote water quality monitoring. In this study, we tested the performance of the three well-known machine learning (ML) (random forest [RF], support vector machine [SVM], and Gaussian process [GP]) and the two novel ML (extreme gradient boost (XGB) and CatBoost [CB]) models for estimation a wide range of Chl-a concentration (10.1-798.7 µg/L) using the Sentinel-2 MSI data and in situ water quality measurement in the Tri An Reservoir (TAR), Vietnam. GP indicated the most reliable model for predicting Chl-a from water quality parameters (R2 = 0.85, root-mean-square error [RMSE] = 56.65 µg/L, Akaike's information criterion [AIC] = 575.10, and Bayesian information criterion [BIC] = 595.24). Regarding input model as water surface reflectance, CB was the superior model for Chl-a retrieval (R2 = 0.84, RMSE = 46.28 µg/L, AIC = 229.18, and BIC = 238.50). Our results indicated that GP and CB are the two best models for the prediction of Chl-a in TAR. Overall, the Sentinel-2 MSI coupled with ML algorithms is a reliable, inexpensive, and accurate instrument for monitoring Chl-a in inland waters. PRACTITIONER POINTS: Machine learning algorithms were used for both remote sensing data and in situ water quality measurements. The performance of five well-known machine learning models was tested Gaussian process was the most reliable model for predicting Chl-a from water quality parameters CatBoost was the best model for Chl-a retrieval from water surface reflectance.

Estimation of nitrogen and phosphorus concentrations from water quality surrogates using machine learning in the Tri An Reservoir, Vietnam.

Surface water eutrophication due to excessive nutrients has become a major environmental problem around the world in the past few decades. Among these nutrients, nitrogen and phosphorus are two of the most important harmful cyanobacterial bloom (HCB) drivers. A reliable prediction of these parameters, therefore, is necessary for the management of rivers, lakes, and reservoirs. The aim of this study is to test the suitability of the powerful machine learning (ML) algorithm, random forest (RF), to provide information on water quality parameters for the Tri An Reservoir (TAR). Three species of nitrogen and phosphorus, including nitrite (N-NO2-), nitrate (N-NO3-), and phosphate (P-PO43-), were empirically estimated using the field observation dataset (2009-2014) of six surrogates of total suspended solids (TSS), total dissolved solids (TDS), turbidity, electrical conductivity (EC), chemical oxygen demand (COD), and biochemical oxygen demand (BOD5). Field data measurement showed that water quality in the TAR was eutrophic with an up-trend of N-NO3- and P-PO43- during the study period. The RF regression model was reliable for N-NO2-, N-NO3-, and P-PO43- prediction with a high R2 of 0.812-0.844 for the training phase (2009-2012) and 0.888-0.903 for the validation phase (2013-2014). The results of land use and land cover change (LUCC) revealed that deforestation and shifting agriculture in the upper region of the basin were the major factors increasing nutrient loading in the TAR. Among the meteorological parameters, rainfall pattern was found to be one of the most influential factors in eutrophication, followed by average sunshine hour. Our results are expected to provide an advanced assessment tool for predicting nutrient loading and for giving an early warning of HCB in the TAR.

Inland harmful cyanobacterial bloom prediction in the eutrophic Tri An Reservoir using satellite band ratio and machine learning approaches.

In recent years, Tri An, a drinking water reservoir for millions of people in southern Vietnam, has been affected by harmful cyanobacterial blooms (HCBs), raising concerns about public health. It is, therefore, crucial to gain insights into the outbreak mechanism of HCBs and understand the spatiotemporal variations of chlorophyll-a (Chl-a) in this highly turbid and productive water. This study aims to evaluate the predictable performance of both approaches using satellite band ratio and machine learning for Chl-a concentration retrieval-a proxy of HCBs. The monthly water quality samples collected from 2016 to 2018 and 23 cloud free Sentinel-2A/B scenes were used to develop Chl-a retrieval models. For the band ratio approach, a strong linear relationship with in situ Chl-a was found for two-band algorithm of Green-NIR. The band ratio-based model accounts for 72% of variation in Chl-a concentration from 2016 to 2018 datasets with an RMSE of 5.95 µg/L. For the machine learning approach, Gaussian process regression (GPR) yielded superior results for Chl-a prediction from water quality parameters with the values of 0.79 (R2) and 3.06 µg/L (RMSE). Among various climatic parameters, a high correlation (R2 = 0.54) between the monthly total precipitation and Chl-a concentration was found. Our analysis also found nitrogen-rich water and TSS in the rainy season as the driving factors of observed HCBs in the eutrophic Tri An Reservoir (TAR), which offer important solutions to the management of HCBs in the future.