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 (
R
2
) and 3.06 μg/L (RMSE). Among various climatic parameters, a high correlation (
R
2
= 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.
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-NO
2
−
), nitrate (N-NO
3
−
), and phosphate (P-PO
4
3−
), 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 (BOD
5
). Field data measurement showed that water quality in the TAR was eutrophic with an up-trend of N-NO
3
−
and P-PO
4
3−
during the study period. The RF regression model was reliable for N-NO
2
−
, N-NO
3
−
, and P-PO
4
3−
prediction with a high
R
2
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.
Seagrass provides numerous valuable ecosystem services across a wide range of climatic regions. However, in terms of area and habitat, this resource is in decline globally and there is an urgent need ...for accurate mapping of extant meadows and biomass to support sustainable seagrass blue carbon conservation and management. This study develops a novel method for a binary mapping of seagrass distribution and estimating seagrass above-ground biomass (AGB) by applying a suite of advanced machine learning (ML) algorithms combined with and without a metaheuristic optimization approach (particle swarm optimization - PSO) to various combinations of multispectral (Sentinel-2) and synthetic aperture radar (Sentinel-1) remote sensing data. Our results reveal that the Sentinel-1 data has potential for the binary mapping of seagrass meadows using an extreme gradient boosting (XGB) model (scores of precision (P) = 0.82, recall (R) = 0.90, and F
1
= 0.86) but is less effective at estimating AGB. The optimal method for estimation of AGB used both Sentinel-1 and Sentinel-2 imagery, the XGB model, and PSO optimization (coefficient of determination (R
2
) = 0.75, root mean squared error (RMSE) = 0.35, Akaike information criteria (AIC) = 24.80, Bayesian information criteria (BIC) = 44.70). Our findings contribute novel and advanced methods for seagrass detection and improvement of AGB estimation, which are fast and reliable, use open-source data and software and should be easily applicable to intertidal zones across many regions of the world.
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 (R2), the Akaike Information Criterion (AIC), and Bayesian Information Criterion (BIC). The results show that the CBR model has the highest performance with both training (R2 = 0.999, RMSE = 29.90) and testing datasets (R2 = 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.
Seagrass has been acknowledged as a productive blue carbon ecosystem that is in significant decline across much of the world. A first step toward conservation is the mapping and monitoring of extant ...seagrass meadows. Several methods are currently in use, but mapping the resource from satellite images using machine learning is not widely applied, despite its successful use in various comparable applications. This research aimed to develop a novel approach for seagrass monitoring using state-of-the-art machine learning with data from Sentinel–2 imagery. We used Tauranga Harbor, New Zealand as a validation site for which extensive ground truth data are available to compare ensemble machine learning methods involving random forests (RF), rotation forests (RoF), and canonical correlation forests (CCF) with the more traditional maximum likelihood classifier (MLC) technique. Using a group of validation metrics including F1, precision, recall, accuracy, and the McNemar test, our results indicated that machine learning techniques outperformed the MLC with RoF as the best performer (F1 scores ranging from 0.75–0.91 for sparse and dense seagrass meadows, respectively). Our study is the first comparison of various ensemble-based methods for seagrass mapping of which we are aware, and promises to be an effective approach to enhance the accuracy of seagrass monitoring.
Seagrass provides a wide range of essential ecosystem services, supports climate change mitigation, and contributes to blue carbon sequestration. This resource, however, is undergoing significant ...declines across the globe, and there is an urgent need to develop change detection techniques appropriate to the scale of loss and applicable to the complex coastal marine environment. Our work aimed to develop remote-sensing-based techniques for detection of changes between 1990 and 2019 in the area of seagrass meadows in Tauranga Harbour, New Zealand. Four state-of-the-art machine-learning models, Random Forest (RF), Support Vector Machine (SVM), Extreme Gradient Boost (XGB), and CatBoost (CB), were evaluated for classification of seagrass cover (presence/absence) in a Landsat 8 image from 2019, using near-concurrent Ground-Truth Points (GTPs). We then used the most accurate one of these models, CB, with historic Landsat imagery supported by classified aerial photographs for an estimation of change in cover over time. The CB model produced the highest accuracies (precision, recall, F1 scores of 0.94, 0.96, and 0.95 respectively). We were able to use Landsat imagery to document the trajectory and spatial distribution of an approximately 50% reduction in seagrass area from 2237 ha to 1184 ha between the years 1990–2019. Our illustration of change detection of seagrass in Tauranga Harbour suggests that machine-learning techniques, coupled with historic satellite imagery, offers potential for evaluation of historic as well as ongoing seagrass dynamics.
This study investigates the effectiveness of gradient boosting decision trees techniques in estimating mangrove above-ground biomass (AGB) at the Can Gio biosphere reserve (Vietnam). For this ...purpose, we employed a novel gradient-boosting regression technique called the extreme gradient boosting regression (XGBR) algorithm implemented and verified a mangrove AGB model using data from a field survey of 121 sampling plots conducted during the dry season. The dataset fuses the data of the Sentinel-2 multispectral instrument (MSI) and the dual polarimetric (HH, HV) data of ALOS-2 PALSAR-2. The performance standards of the proposed model (root-mean-square error (RMSE) and coefficient of determination (R2)) were compared with those of other machine learning techniques, namely gradient boosting regression (GBR), support vector regression (SVR), Gaussian process regression (GPR), and random forests regression (RFR). The XGBR model obtained a promising result with R2 = 0.805, RMSE = 28.13 Mg ha−1, and the model yielded the highest predictive performance among the five machine learning models. In the XGBR model, the estimated mangrove AGB ranged from 11 to 293 Mg ha−1 (average = 106.93 Mg ha−1). This work demonstrates that XGBR with the combined Sentinel-2 and ALOS-2 PALSAR-2 data can accurately estimate the mangrove AGB in the Can Gio biosphere reserve. The general applicability of the XGBR model combined with multiple sourced optical and SAR data should be further tested and compared in a large-scale study of forest AGBs in different geographical and climatic ecosystems.
This study proposes a hybrid intelligence approach based on an extreme gradient boosting regression and genetic algorithm, namely, the XGBR-GA model, incorporating Sentinel-2, Sentinel-1, and ALOS-2 ...PALSAR-2 data to estimate the mangrove above-ground biomass (AGB), including small and shrub mangrove patches in the Red River Delta biosphere reserve across the northern coast of Vietnam. We used the novel extreme gradient boosting decision tree (XGBR) technique together with genetic algorithm (GA) optimization for feature selection to construct and verify a mangrove AGB model using data from a field survey of 105 sampling plots conducted in November and December of 2018 and incorporated the dual polarimetric (HH and HV) data of the ALOS-2 PALSAR-2 L-band and the Sentinel-2 multispectral data combined with Sentinel-1 (C-band VV and VH) data. We employed the root-mean-square error (RMSE) and coefficient of determination (R2) to evaluate the performance of the proposed model. The capability of the XGBR-GA model was assessed via a comparison with other machine-learning (ML) techniques, i.e., the CatBoost regression (CBR), gradient boosted regression tree (GBRT), support vector regression (SVR), and random forest regression (RFR) models. The XGBR-GA model yielded a promising result (R2 = 0.683, RMSE = 25.08 Mg·ha−1) and outperformed the four other ML models. The XGBR-GA model retrieved a mangrove AGB ranging from 17 Mg·ha−1 to 142 Mg·ha−1 (with an average of 72.47 Mg·ha−1). Therefore, multisource optical and synthetic aperture radar (SAR) combined with the XGBR-GA model can be used to estimate the mangrove AGB in North Vietnam. The effectiveness of the proposed method needs to be further tested and compared to other mangrove ecosystems in the tropics.
Blue carbon ecosystems (mangroves, seagrasses and saltmarshes) are highly productive coastal habitats, and are considered some of the most carbon-dense ecosystems on Earth. They are an important ...nature-based solution for both climate change mitigation and adaptation. Quantifying blue carbon stocks and assessing their dynamics at large scales through remote sensing remains challenging due to difficulties of cloud coverage, spectral, spatial and temporal limitations of multispectral sensors and speckle noise of synthetic aperture radar (SAR). Recent advances in airborne and space-borne multispectral and SAR imagery and Light Detection and Ranging (LiDAR) data, sensor platforms such as unmanned aerial vehicles (UAVs), combined with novel machine learning techniques have offered different users with a wide-range of spectral, spatial, and multi-temporal information for quantifying blue carbon from space. However, a large number of challenges are posed by various traits such as atmospheric correction, water penetration, and water column transparency issues in coastal environments, the multi-dimensionality and size of the multispectral and LiDAR data, the limitation of training samples, and backscattering mechanisms of SAR imagery in the acquisition process. As a result, existing methodologies face major difficulties in accurately estimating blue carbon stocks using these datasets. In this context, emerging and innovative machine learning and artificial intelligence methodologies are often required for robustness and reliability of blue carbon estimates, particularly those using open-source software for signal processing and regression tasks. This review provides an overview of Earth Observation data, machine learning and state-of-the-art deep learning techniques that are currently being used to quantify above-ground carbon, below-ground carbon, and soil carbon stocks of mangroves, seagrasses and saltmarshes ecosystems. Some key limitations and future directions for the potential use of data fusion combined with advanced machine learning, deep learning, and metaheuristic optimisation techniques for quantifying blue carbon stocks are also highlighted. In summary, the quantification of blue carbon using remote sensing and machine learning approaches holds great potential in contributing to global efforts towards mitigating climate change and protecting coastal ecosystems.
Estimation of carbon stock in seagrass meadows is in challenges of paucity of assessment and low accuracy of the estimates. In this study, we used a fusion of the synthetic aperture radar (SAR) ...Sentinel-1 (S-1), the multi-spectral Sentinel-2 (S-2), and coupled this with advanced machine learning (ML) models and meta-heuristic optimization to improve the estimation of total organic carbon (TOC) stock in the Zostera muelleri meadows in Tauranga Harbour, New Zealand. Five scenarios containing combinations of data, ML models (Random Forest, Extreme Gradient Boost, Rotation Forest, CatBoost) and optimization were developed and evaluated for TOC retrieval. Results indicate a fusion of S1, S2 images, a novel ML model CatBoost and the grey wolf optimization algorithm (the CB-GWO model) yielded the best prediction of seagrass TOC (R
2
, RMSE were 0.738 and 10.64 Mg C ha
−1
). Our results provide novel ideas of deriving a low-cost, scalable and reliable estimates of seagrass TOC globally.