Suspended Sediment Concentration Estimation from Landsat Imagery along the Lower Missouri and Middle Mississippi Rivers Using an Extreme Learning Machine

Remotely sensed estimates of long-term biochemical oxygen demand over Hong Kong marine waters using machine learning enhanced by imbalanced label optimisation

In many coastal cities around the world, continuing water degradation threatens the living environment of humans and aquatic organisms. To assess and control the water pollution situation, this study estimated the Biochemical Oxygen Demand (BOD) concentration of Hong Kong's marine waters using remote sensing and an improved machine learning (ML) method. The scheme was derived from four ML algorithms (RBF, SVR, RF, XGB) and calibrated using a large amount (N > 1000) of in-situ BOD5 data. Based on labeled datasets with different preprocessing, i.e., the original BOD5, the log10(BOD5), and label distribution smoothing (LDS), three types of models were trained and evaluated. The results highlight the superior potential of the LDS-based model to improve BOD5 estimate by dealing with imbalanced training dataset. Additionally, XGB and RF outperformed RBF and SVR when the model was developed using log10(BOD5) or LDS(BOD5). Over two decades, the BOD5 concentration of Hong Kong marine waters in the autumn (Sep. to Nov.) shows a downward trend, with significant decreases in Deep Bay, Western Buffer, Victoria Harbour, Eastern Buffer, Junk Bay, Port Shelter, and the Tolo Harbour and Channel. Principal component analysis revealed that nutrient levels emerged as the predominant factor in Victoria Harbour and the interior of Deep Bay, while chlorophyll-related and physical parameters were dominant in Southern, Mirs Bay, Northwestern, and the outlet of Deep Bay. LDS provides a new perspective to improve ML-based water quality estimation by alleviating the imbalance in the labeled dataset. Overall, the remotely sensed BOD5 can offer insight into the spatial-temporal distribution of organic matter in Hong Kong coastal waters and valuable guidance for the pollution control.

Retrieval of suspended sediment concentration (SSC) in the Arabian Gulf water of arid region by Sentinel-2 data

Suspended sediment concentration (SSC) in water increases temperature and turbidity, limits the photosynthesis of aquatic plants, and reduces biologically available oxygen. It is important to study SSC in the coastal waters of the Arabian Gulf. Thus, this study mapped the SSC of coastal water between Al Arish and Al Ghariyah in northern Qatar using the spectral bands of the MultiSpectral Imager (MSI) of Sentinel-2 by calculating the Normalized Difference Suspended Sediment Index and Normalized Suspended Material Index. The results are studied using the Normalized Difference Turbidity Index and Modified Normalized Difference Water Index. The mapping of SSC in the water using NDSSI showed the presence of a high concentration of suspended sediments between Al Arish and Al Mafjar and a low concentration between Al Mafjar and Al Ghariyah. The mapping of NSMI showed values between 0.012 (clear water) and 0.430 (more suspended material) for the occurrence of suspended materials and supported the results of NDSSI. The study of turbidity using an NDTI image showed turbidity index values ranging from -0.44 (clear water) to 0.12 (high turbidity) and confirmed the occurrence and distribution of suspended sediments and materials in the water. The MNDWI image was able to discriminate clear water with bright pixels from silty sand and mud flats. The relationships between NDSSI, NSMI, and NDTI were correlated with in-situ measurements and studied to find suitable indices to map SSC. Regression analyses showed the strongest relationship between NSMI and NDTI (R2 = 0.95) next to NDSSI and NDTI, where NDTI had the strongest effect on NDSSI (R2 = 0.86). The satellite data results were evaluated by studying the physical parameters and spatial distribution of suspended sediments in the surface and bottom waters. In addition, the grain size distributions, mineral identification, and chemical element concentrations in the bottom sediment samples were studied.

Effects of spectral variability due to sediment and bottom characteristics on remote sensing for suspended sediment in shallow rivers

Advances in remote sensing techniques for water environments have led to acquisition of abundant data on suspended sediment concentration (SSC). However, confounding factors, such as particle sizes, mineral properties, and bottom materials, have not been fully studied, despite their substantial interference with the detection of intrinsic signals of suspended sediments. Therefore, we investigated the spectral variability arising from the sediment and bottom using laboratory and field-scale experiments. In the laboratory experiment, we focused on measuring spectral characteristics of suspended sediment according to particle size and sediment type. The laboratory experiment was conducted under conditions of completely mixed sediment and non-bottom reflectance using a specially designed rotating horizontal cylinder. To investigate the effects of different channel bottoms under sediment-laden flow conditions, we performed sediment tracer tests in field-scale channels comprising sand and vegetated bottoms. Based on experimental datasets, we performed spectral analysis and multiple endmember spectral mixture analysis (MESMA) to quantify the effect of spectral variability of sediment and bottom on the relationship between hyperspectral data and SSC. The results showed that optimal spectral bands were precisely estimated under non-bottom reflectance conditions, and the effective wavelengths depended on the sediment type. The fine sediments had a higher backscattering intensity compared to the coarse sediments, and the reflectance difference according to the particle size difference increased as the SSC increased. However, in the field-scale experiment, the bottom reflectance substantially decreased the R2 in the relationship between the hyperspectral data and SSC. Nevertheless, MESMA can quantify the contribution of suspended sediment and bottom signals as fractional images. Moreover, the suspended sediment fraction had a clear exponential relationship with SSC in all cases. We conclude that MESMA-driven sediment fractions could be an important alternative for estimating SSC in shallow rivers, as it quantifies the contributions of each factor and then minimizes the bottom effect.

Assessing temporal variability of lake turbidity and trophic state of European lakes using open data repositories

Water turbidity is one of the more important water quality parameters that is strictly linked with the productivity of the lake and is commonly used as an indicator of the trophic state. However, limited field data availability across wide geographic gradients may hinder the conduction of large scale longitudinal studies. In this study, time series of lake turbidity and trophic state index (TSI) between 2002 and 2012 were obtained from the Copernicus Lake Water products to create a large longitudinal dataset of lake variables for 22 European lakes. The dataset was combined with estimates of nutrient concentrations and surface water temperature obtained from the Hydrological Predictions for the Environment (HYPE) and ERA5-Land data repositories, that were used as environmental predictors. Hence, the validity of the lake water quality parameters was tested by a) exploring their spatial and temporal variability and b) identifying associations with the environmental predictors. For this purpose, seasonal Mann-Kendall tests were applied to find significant inter-annual trends of turbidity and TSI for each lake, and generalized additive models (GAMs) were employed to identify the main parameters that shape their temporal dynamics. Although we did not find significant inter-annual changes, our findings highlighted the strong influence of seasonality and surface water temperature in defining the temporal variability patterns in most of the lakes. In addition, the importance of nutrients varied among lakes as several lakes exhibited narrow nutrient gradients reflecting relatively stable nutrient conditions during the examined period. Other lake intrinsic factors, such as local climate and biotic interactions, are important drivers of shaping turbidity and nutrient dynamics. This study highlighted the usefulness of combining lake data from large repositories in conducting large scale spatial studies as a valuable asset for future lake research and management purposes.

Retrieval of Suspended Sediment Concentration from Bathymetric Bias of Airborne LiDAR

In addition to depth measurements, airborne LiDAR bathymetry (ALB) has shown usefulness in suspended sediment concentration (SSC) inversion. However, SSC retrieval using ALB based on waveform decomposition or near-water-surface penetration by green lasers requires access to full-waveform data or infrared laser data, which are not always available for users. Thus, in this study we propose a new SSC inversion method based on the depth bias of ALB. Artificial neural networks were used to build an empirical inversion model by connecting the depth bias and SSC. The proposed method was verified using an ALB dataset collected through Optech coastal zone mapping and imaging LiDAR systems. The results showed that the mean square error of the predicted SSC based on the empirical model of ALB depth bias was less than 2.564 mg/L in the experimental area. The proposed method was compared with the waveform decomposition and regression methods. The advantages and limits of the proposed method were analyzed and summarized. The proposed method can effectively retrieve SSC and only requires ALB-derived and sonar-derived water bottom points, eliminating the dependence on the use of green full-waveforms and infrared lasers. This study provides an alternative means of conducting SSC inversion using ALB.

Modeling of surface sediment concentration in the Doce River basin using satellite remote sensing

Surface sediment concentration (SSC) is linked to several problems related to water quality and its monitoring is costly because of the required fieldwork and laboratory analyses. Thus, sediment measurements are often sporadic, punctual, and performed during a short period. Orbital remote sensing allows the monitoring of SSC along the river channel permitting continuous and spatial information. This work had two objectives: (1) to model the surface concentration of sediments in the main channel of the Doce river using data from Multispectral Instrument (MSI)/Sentinel 2 and Operational Land Imager (OLI)/Landsat 8 satellite sensors; and (2) to compare different linear modeling approaches to select the best variables for SSC monitoring. For comparison with actual field data, we used mean SSC measurements in 14 sediment gauge stations from 2013 to 2020. Reflectance data of the MSI/Sentinel 2 and OLI/Landsat 8 satellites bands and spectral indices related to the monitoring of water resources were used as explanatory variables. Simple and multiple linear regression models (SLR and MLR), least absolute shrinkage and selection operator (LASSO), and Elastic Net regression were used to predict the SSC. The near-infrared band images from both MSI/Sentinel 2 and OLI/Landsat 8 satellites showed a strong linear relationship with the SSC. Multiple linear regression, LASSO and Elastic Net regressions showed good performance for SSC prediction. Sediment flow maps show an SSC reduction in the Doce river channel in recent years, indicating that part of the material from the Fundão tailings dam rupture may have been transported through sediment resuspension and transport processes.

Data reconstruction of daily MODIS chlorophyll-a concentration and spatio-temporal variations in the Northwestern Pacific

Sea surface chlorophyll-a concentration (Chl-a) is a key proxy for phytoplankton biomass. Spatio-temporal continuous Chl-a data are important to understand the mechanisms of chlorophyll occurrence and development and track phytoplankton changes. However, the greatest challenge in utilizing daily Chl-a data is massive missing pixels due to orbital position and cloud coverage. This study proposes the application of a spatial filling method using the machine learning-based Extreme Gradient Boosting (BST) to reconstruct missing pixels of daily MODIS Chl-a data from 2007 to 2018. The approach is applied to different trophic biogeographical subregions of the Northwestern Pacific where it has complex phytoplankton dynamics and frequent data missing. Various environmental variables are taken into consideration, including meteorological forcing, geographic and topographic features, and oceanic physical components. The BST-reconstructed Chl-a (BST Chl-a) is validated using in-situ Chl-a measurements, VIIRS and Himawari-8 Chl-a products. The results show that the BST model is highly adaptive in reconstructing Chl-a data, and it performs well in pelagic, offshore and coastal with the best performance in pelagic. BST Chl-a improves coverage without significant quality degradation compared to the original MODIS Chl-a. BST Chl-a agrees better with in-situ data than that of MODIS, with CC of 0.742, RMSE of 0.247, MAE of 0.202 and Bias of 0.089. Cross-satellite validation using VIIRS and Himawari-8 Chl-a also shows promising results with the CC of 0.861 and 0.765, respectively, suggesting the high accuracy of BST Chl-a. The inter-annual trend of BST Chl-a decreases in coastal and increases in offshore and pelagic. BST Chl-a images present similar spatial patterns to MODIS Chl-a under different missing rates, with gradual decreases from coastal to pelagic. It indicates that phytoplankton bloom patterns can be identified by daily BST Chl-a images.

MODIS-Landsat fusion-based single-band algorithms for TSS and turbidity estimation in an urban-waste-dominated river reach

Riverine ecosystem management along an urban stretch mostly depends on high-frequent (daily-scale) monitoring of water quality at finer spatial resolutions. However, with the decrease in the number of in-situ monitoring stations owing to their expensive maintenance cost, there is a need to develop the next-generation remote sensing (RS) tools as an alternate approach with better synoptic coverage of river water quality assessment. This study advocates three novel model variants to estimate the total suspended solids (TSS) concentration at daily-scale using the public-domain MODIS and Landsat satellite datasets. The MOD_T model variant uses the 1-day×250 m MODIS public domain datasets, and the FUS_T model is based on the 1-day×30 m MODIS-Landsat fusion datasets, whereas the CFUS_T model integrates the Frank Copula with the FUS_T model. These hierarchical model variants are assessed in the urban-waste-dominated lower Ganges, namely the Hooghly River and the Brahmani River, in eastern India using the measured in-situ TSS datasets at multiple monitoring stations from 2016 to 2019. The results reveal that the CFUS_T is the best TSS estimation model variant that performs with the average coefficient of determination of 0.88-0.93, mean absolute error of 0.17-0.19, and normal root mean square error of 0.05-0.09. Conclusively, the proposed CFUS_T and CFUS_TU stochastic models can be used as potential tools for TSS and turbidity assessment along the dynamic river systems, respectively.

The Numerical Investigation of the Performance of a Newly Designed Sediment Trap for Horizontal Transport Flux

Marine sediment transport is closely related to seafloor topography, material transport, marine engineering safety, etc. With a developed time-series vector observation device, the sediment capture and transport process can be observed. The structure of the capture tube and the internal filter screen can significantly affect the flow field during the actual observation, further influencing the sediment transport observation and particle capture process. This paper presents a numerical model for investigating the effect of device structure on seawater flow to study the processes of marine sediment transport observation and sediment particle capture. The model is based on the solution of both porous media and the Realizable k-ε turbulence in Fluent software. The flow velocity distribution inside and outside the capture tube with different screen pore sizes (0.300, 0.150, and 0.075 mm) is analyzed. To enhance the reliability of the numerical simulation, the simulation calculation results are compared with the test results and have good coincidence. Finally, by analyzing the motion law of sediment in the capture tube, the accurate capture of sediment particles is achieved, and the optimal capture efficiency of the sediment trap is obtained.

Prediction of Total Phosphorus Concentration in Macrophytic Lakes Using Chlorophyll-Sensitive Bands: A Case Study of Lake Baiyangdian

Total phosphorus (TP) is a significant indicator of water eutrophication. As a typical macrophytic lake, Lake Baiyangdian is of considerable importance to the North China Plain’s ecosystem. However, the lake’s eutrophication is severe, threatening the local ecological environment. The correlation between chlorophyll and TP provides a mechanism for TP prediction. In view of the absorption and reflection characteristics of the chlorophyll concentrations in inland water, we propose a method to predict TP concentration in a macrophytic lake with spectral characteristics dominated by chlorophyll. In this study, water spectra noise is removed by discrete wavelet transform (DWT), and chlorophyll-sensitive bands are selected by gray correlation analysis (GRA). To verify the effectiveness of the chlorophyll-sensitive bands for TP concentration prediction, three different machine learning (ML) algorithms were used to build prediction models, including partial least squares (PLS), random forest (RF) and adaptive boosting (AdaBoost). The results indicate that the PLS model performs well in terms of TP concentration prediction, with the least time consumption: the coefficient of determination (R2) and root mean square error (RMSE) are 0.821 and 0.028 mg/L in the training dataset, and 0.741 and 0.029 mg/L in the testing dataset, respectively. Compared with the empirical model, the method proposed herein considers the correlation between chlorophyll and TP concentration, as well as a higher accuracy. The results indicate that chlorophyll-sensitive bands are effective for predicting TP concentration.

Estimating Suspended Sediment Fluxes from the Largest Glacial Lake in Svalbard to Fjord System Using Sentinel-2 Data: Trebrevatnet Case Study

Glacier-fed hydrological systems in high latitude regions experience high seasonal variation in meltwater runoff. The peak in runoff usually coincides with the highest air temperatures which drive meltwater production. This process is often accompanied by the release of sediments from within the glacier system that are transported and suspended in high concentrations as they reach the proglacial realm. Sediment-laden meltwater is later transported to the marine environment and is expressed on the surface of fjords and coastal waters as sediment plumes. Direct monitoring of these processes requires complex and time-intensive fieldwork, meaning studies of these processes are rare. This paper demonstrates the seasonal dynamics of the Trebrevatnet lake complex and evolution of suspended sediment in the lake and sediment plumes in the adjacent Ekmanfjorden. We use the Normalized Difference Suspended Sediment Index (NDSSI) derived from multi-temporal Sentinel-2 images for the period between 2016–2021. We propose a new SSL index combining the areal extent of the sediment plume with the NDSSI for quantification of the sediment influx to the marine environment. The largest observed sediment plume was recorded on 30 July 2018 and extended to more than 40 km2 and a SSL index of 10.4. We identified the greatest sediment concentrations in the lake in the beginning of August, whereas the highest activity of the sediment plumes is concentrated at the end of July. The temporal pattern of these processes stays relatively stable throughout all ablation seasons studied. Sediment plumes observed with the use of optical satellite remote sensing data may be used as a proxy for meltwater runoff from the glacier-fed Trebrevatnet system. We have shown that remote-sensing-derived suspended sediment indexes can (after proper in situ calibration) serve for large scale quantification of sediment flux to fjord and coastal environments.

Newly Designed and Experimental Test of the Sediment Trap for Horizontal Transport Flux

The transport processes of marine suspended sediments are important to the material cycle and the shaping of seafloor topography. Existing sediment monitoring methods are limited in their use under high concentration conditions, and are not effective in monitoring and capturing sediment in 3D directions, and there is an inability to accurately explain sediment transport processes. To infer the transport process of suspended sediments, this study proposed a time-series vector in situ observation device. An accompanying time-series analytic method was developed for sediment transport fluxes. The correlation between the internal and external flow velocities of the capture tube was established through indoor tests, and then the applicability of the device was verified by the correlation between the theoretical capture quality and the actual capture quality, and the analytic formula of the flux was refined. The proposed observation technique can be used for in situ long-term observation and sampling of marine suspended sediments under conventional and even extreme sea conditions, achieving accurate time-series suspended sediment capture and high-resolution transport flux analysis. The technique thus provides a more effective means for scientific research into the dynamics of seafloor sedimentation, the mechanisms of ocean carbon sinks, and the processes of the carbon cycle.

Remote Sensing of Sediment Discharge in Rivers Using Sentinel-2 Images and Machine-Learning Algorithms

The spatio-temporal dynamism of sediment discharge (Qs) in rivers is influenced by various natural and anthropogenic factors. Unfortunately, most rivers are only monitored at a limited number of stations or not gauged at all. Therefore, this study aims to provide a remote-sensing-based alternative for Qs monitoring. The at-a-station hydraulic geometry (AHG) power–law method was compared to the at-many-stations hydraulic geometry (AMHG) method; in addition, a novel AHG machine-learning (ML) method was introduced to estimate water discharge at three gauging stations in the Tisza (Szeged and Algyő) and Maros (Makó) Rivers in Hungary. The surface reflectance of Sentinel-2 images was correlated to in situ suspended sediment concentration (SSC) by support vector machine (SVM), random forest (RF), artificial neural network (ANN), and combined algorithms. The best performing water discharge and SSC models were employed to estimate the Qs. Our novel AHG ML method gave the best estimations of water discharge (Szeged: R2 = 0.87; Algyő: R2 = 0.75; Makó: R2 = 0.61). Furthermore, the RF (R2 = 0.9) and combined models (R2 = 0.82) showed the best SSC estimations for the Maros and Tisza Rivers. The highest Qs were detected during floods; however, there is usually a clockwise hysteresis between the SSC and water discharge, especially in the Tisza River.

Burned Area Classification Based on Extreme Learning Machine and Sentinel-2 Images

Sentinel-2 satellite images allow high separability for mapping burned and unburned areas. This problem has been extensively addressed using machine-learning algorithms. However, these need a suitable dataset and entail considerable training time. Recently, extreme learning machines (ELM) have presented high precision in classification and regression problems but with low computational cost. This paper proposes evaluating ELM to map burned areas and compare them with other machine-learning algorithms broadly used. Several indices, metrics and training times were used to assess the performance of the algorithms. Considering the average of datasets, the best performance was obtained by random forest (DICE = 0.93; omission and commission = 0.08) and ELM (DICE = 0.90; omission and commission = 0.07). The training time for the best model was from ELM (1.45 s) and logistic regression (1.85 s). According to results, ELM was the best burned-area classification algorithm, considering precision and training time, evidencing great potential to map burned areas at global scales with medium-high spatial resolution images. This information is essential to fire-risk systems and burned-area records used to design prevention and fire-combat strategies, and it provides valuable knowledge on the effect of fires on the landscape and atmosphere.

A critical and intensive review on assessment of water quality parameters through geospatial techniques

Evaluation of water quality is a priority work nowadays. In order to monitor and map, the water quality for a wide range on different scales (spatial, temporal), the geospatial technique has the potential to minimize the field and laboratory work. The review has emphasized the advance of remote sensing for the effectiveness of spectral analysis, bio-optical estimation, empirical method, and application of machine learning for water quality assessment. The water quality parameters (turbidity, suspended particles, chlorophyll, etc.) and their retrieval techniques are described in a scientific manner. Available satellite, bands, resolution, and spectrum ranges for specific parameters are critically described in this review with challenges in remote sensing for water quality analysis, considering non-optical active parameters. The application of statistical programmes like linear (multiple regression analysis) and non-linear approaches is discussed for better assessment of water quality. Emphasis is given on comparison between different models to increase the accuracy level of remote sensing of water quality assessment. A direction is suggested for future development in the field of estimation of water pollution assessment through geospatial techniques.

Integration of Remote Sensing and Mexican Water Quality Monitoring System Using an Extreme Learning Machine

Remote Sensing, as a driver for water management decisions, needs further integration with monitoring water quality programs, especially in developing countries. Moreover, usage of remote sensing approaches has not been broadly applied in monitoring routines. Therefore, it is necessary to assess the efficacy of available sensors to complement the often limited field measurements from such programs and build models that support monitoring tasks. Here, we integrate field measurements (2013–2019) from the Mexican national water quality monitoring system (RNMCA) with data from Landsat-8 OLI, Sentinel-3 OLCI, and Sentinel-2 MSI to train an extreme learning machine (ELM), a support vector regression (SVR) and a linear regression (LR) for estimating Chlorophyll-a (Chl-a), Turbidity, Total Suspended Matter (TSM) and Secchi Disk Depth (SDD). Additionally, OLCI Level-2 Products for Chl-a and TSM are compared against the RNMCA data. We observed that OLCI Level-2 Products are poorly correlated with the RNMCA data and it is not feasible to rely only on them to support monitoring operations. However, OLCI atmospherically corrected data is useful to develop accurate models using an ELM, particularly for Turbidity (R² = 0.7). We conclude that remote sensing is useful to support monitoring systems tasks, and its progressive integration will improve the quality of water quality monitoring programs.

Determination of Water Depth in Ports Using Satellite Data Based on Machine Learning Algorithms

One of the fundamental maintenance tasks of ports is the periodic dredging of them. This is necessary to guarantee a minimum draft that will enable ships to access ports safely. The determination of bathymetries is the instrument that determines the need for dredging and permits an analysis of the behavior of the port bottom over time, in order to achieve adequate water depth. Satellite data processing to predict environmental parameters is used increasingly. Based on satellite data and using different machine learning algorithm techniques, this study has sought to estimate the seabed in ports, taking into account the fact that the port areas are strongly anthropized areas. The algorithms that were used were Support Vector Machine (SVM), Random Forest (RF) and the Multi-Adaptive Regression Splines (MARS). The study was carried out in the ports of Candás and Luarca in the Principality of Asturias. In order to validate the results obtained, data was acquired in situ by using a single beam provided. The results show that this type of methodology can be used to estimate coastal bathymetry. However, when deciding which system was best, priority was given to simplicity and robustness. The results of the SVM and RF algorithms outperform those of the MARS. RF performs better in Candás with a mean absolute error (MAE) of 0.27 cm, whereas SVM performs better in Luarca with a mean absolute error of 0.37 cm. It is suggested that this approach is suitable as a simpler and more cost-effective rough resolution alternative, for estimating the depth of turbid water in ports, than single-beam sonar, which is labor-intensive and polluting.

Consistency of Suspended Particulate Matter Concentration in Turbid Water Retrieved from Sentinel-2 MSI and Landsat-8 OLI Sensors

Research on the consistency of suspended particulate matter (SPM) concentration retrieved from multisource satellite sensors can serve as long-time monitoring of water quality. To explore the influence of the atmospheric correction (AC) algorithm and the retrieval model on the consistency of the SPM concentration values, Landsat 8 Operational Land Imager (OLI) and Sentinel 2 MultiSpectral Imager (MSI) images acquired on the same day are used to compare the remote sensing reflectance (Rrs) SPM retrieval values in two high-turbidity lakes. An SPM retrieval model for Shengjin Lake is established based on field measurements and applied to OLI and MSI images: two SPM concentration products are highly consistent (R2 = 0.93, Root Mean Squared Error (RMSE) = 20.67 mg/L, Mean Absolute Percentage Error (MAPE) = 6.59%), and the desired results are also obtained in Chaohu Lake. Among the four AC algorithms (Management Unit of the North Seas Mathematical Models (MUMM), Atmospheric Correction for OLI'lite'(ACOLITE), Second Simulation of Satellite Signal in the Solar Spectrum (6S), Landsat 8 Surface Reflectance Code & Sen2cor (LaSRC & Sen2cor)), the two Rrs products, as well as the final SPM concentration products retrieved from OLI and MSI images, have the best consistency when using the MUMM algorithm in SeaWIFS Data Analyst System (SeaDAS) software. The consistency of SPM concentration values retrieved from OLI and MSI images using the same model or same form of models is significantly better than that retrieved by applying the optimal models with different forms.

Spatiotemporal Dynamics of Suspended Sediments in the Negro River, Amazon Basin, from In Situ and Sentinel-2 Remote Sensing Data

Monitoring suspended sediments through remote sensing data in black-water rivers is a challenge. Herein, remote sensing reflectance (Rrs) from in situ measurements and Sentinel-2 Multi-Spectral Instrument (MSI) images were used to estimate the suspended sediment concentration (SSC) in the largest black-water river of the Amazon basin. The Negro River exhibits extremely low Rrs values (<0.005 sr−1 at visible and near-infrared bands) due to the elevated absorption of coloured dissolved organic matter (aCDOM at 440 nm > 7 m−1) caused by the high amount of dissolved organic carbon (DOC > 7 mg L−1) and low SSC (<5 mg L−1). Interannual variability of Rrs is primarily controlled by the input of suspended sediments from the Branco River, which is a clear water river that governs the changes in the apparent optical properties of the Negro River, even at distances that are greater than 90 km from its mouth. Better results were obtained using the Sentinel-2 MSI Red band (Band 4 at 665 nm) in order to estimate the SSC, with an R2 value greater than 0.85 and an error less than 20% in the adjusted models. The magnitudes of water reflectance in the Sentinel-2 MSI Red band were consistent with in situ Rrs measurements, indicating the large spatial variability of the lower SSC values (0 to 15 mg L−1) in a complex anabranching reach of the Negro River. The in situ and satellite data analysed in this study indicates sedimentation processes in the lower Negro River near the Amazon River. The results suggest that the radiometric characteristics of sensors, like sentinel-2 MSI, are suitable for monitoring the suspended sediment concentration in large tropical black-water rivers.

Development of a Multiple Linear Regression Model for Meteorological Drought Index Estimation Based on Landsat Satellite Imagery

Climate polarization due to global warming has increased the intensity of drought in some regions, and the need for drought estimation studies to help minimize damage is increasing. In this study, we constructed remote sensing and climate data for Boryeong, Chungcheongnam-do, Korea, and developed a model for drought index estimation by classifying data characteristics and applying multiple linear regression analysis. The drought indices estimated in this study include four types of standardized precipitation indices (SPI1, SPI3, SPI6, and SPI9) used as meteorological drought indices and calculated through cumulative precipitation. We then applied statistical analysis to the developed model and assessed its ability as a drought index estimation tool using remote sensing data. Our results showed that its adj.R2 value, achieved using cumulative precipitation for one month, was very low (approximately 0.003), while for the SPI3, SPI6, and SPI9 models, the adj.R2 values were significantly higher than the other models at 0.67, 0.64, and 0.56, respectively, when the same data were used.

Ensemble machine-learning-based framework for estimating total nitrogen concentration in water using drone-borne hyperspectral imagery of emergent plants: A case study in an arid oasis, NW China

In arid and semi-arid regions, water-quality problems are crucial to local social demand and human well-being. However, the conventional remote sensing-based direct detection of water quality parameters, especially using spectral reflectance of water, must satisfy certain preconditions (e.g., flat water surface and ideal radiation geometry). In this study, we hypothesized that drone-borne hyperspectral imagery of emergent plants could be better applied to retrieval total nitrogen (TN) concentration in water regardless of preconditions possibly due to the spectral responses of emergent plants on nitrogen removal and water purification. To test this hypothesis, a total of 200 groups of bootstrap samples were used to examine the relationship between the extracted TN concentrations from the drone-borne hyperspectral imagery of emergent plants and the experimentally measured TN concentrations in Ebinur Lake Oasis using four machine learning (ML) models (Partial Least Squares (PLS), Random Forest (RF), Extreme Learning Machine (ELM), and Gaussian Process (GP)). Through the introduction of the fractional order derivative (FOD), we build a decision-level fusion (DLF) model to minimize the regression results' biases of individual ML models. For individual ML model, GP performed the best. Still, the amount of uncertainty in individual ML models renders their performance to be subpar. The introduction of the DLF model greatly minimizes the regression results' biases. The DLF model allows to reduce potential uncertainties without sacrificing accuracy. In conclusion, the spectral response caused by nitrogen removal and water purification on emergent plants could be used to retrieve TN concentration in water with a DLF model framework. Our study offers a new perspective and a basic scientific support for water quality monitoring in arid regions.

Estimating River Sediment Discharge in the Upper Mississippi River Using Landsat Imagery

With the decline of operational river gauges monitoring sediments, a viable means of quantifying sediment transport is needed. In this study, we address this issue by applying relationships between hydraulic geometry of river channels, water discharge, water-leaving surface reflectance (SR), and suspended sediment concentration (SSC) to quantify sediment discharge with the aid of space-based observations. We examined 5490 Landsat scenes to estimate water discharge, SSC, and sediment discharge for the period from 1984 to 2017 at nine gauging sites along the Upper Mississippi River. We used recent advances in remote sensing of fluvial systems, such as automated river width extraction, Bayesian discharge inference with at-many-stations hydraulic geometry (AMHG), and SSC-SR regression models. With 621 Landsat scenes available from all the gauging sites, the results showed that the water discharge and SSC retrieval from Landsat imagery can yield reasonable sediment discharge estimates along the Upper Mississippi River. An overall relative bias of −25.4, mean absolute error (MAE) of 6.24 × 104 tonne/day, relative root mean square error (RRMSE) of 1.21, and Nash–Sutcliffe Efficiency (NSE) of 0.49 were obtained for the sediment discharge estimation. Based on these statistical metrics, we identified three of the nine gauging sites (St. Louis, MO; Chester, IL; and Thebes, IL), which were in the downstream portion of the river, to be the best locations for estimating water and sediment discharge using Landsat imagery.

Crop Monitoring Using Satellite/UAV Data Fusion and Machine Learning

Non-destructive crop monitoring over large areas with high efficiency is of great significance in precision agriculture and plant phenotyping, as well as decision making with regards to grain policy and food security. The goal of this research was to assess the potential of combining canopy spectral information with canopy structure features for crop monitoring using satellite/unmanned aerial vehicle (UAV) data fusion and machine learning. Worldview-2/3 satellite data were tasked synchronized with high-resolution RGB image collection using an inexpensive unmanned aerial vehicle (UAV) at a heterogeneous soybean (Glycine max (L.) Merr.) field. Canopy spectral information (i.e., vegetation indices) was extracted from Worldview-2/3 data, and canopy structure information (i.e., canopy height and canopy cover) was derived from UAV RGB imagery. Canopy spectral and structure information and their combination were used to predict soybean leaf area index (LAI), aboveground biomass (AGB), and leaf nitrogen concentration (N) using partial least squares regression (PLSR), random forest regression (RFR), support vector regression (SVR), and extreme learning regression (ELR) with a newly proposed activation function. The results revealed that: (1) UAV imagery-derived high-resolution and detailed canopy structure features, canopy height, and canopy coverage were significant indicators for crop growth monitoring, (2) integration of satellite imagery-based rich canopy spectral information with UAV-derived canopy structural features using machine learning improved soybean AGB, LAI, and leaf N estimation on using satellite or UAV data alone, (3) adding canopy structure information to spectral features reduced background soil effect and asymptotic saturation issue to some extent and led to better model performance, (4) the ELR model with the newly proposed activated function slightly outperformed PLSR, RFR, and SVR in the prediction of AGB and LAI, while RFR provided the best result for N estimation. This study introduced opportunities and limitations of satellite/UAV data fusion using machine learning in the context of crop monitoring.

A Method for Chlorophyll-a and Suspended Solids Prediction through Remote Sensing and Machine Learning

Total Suspended Solids (TSS) and chlorophyll-a concentration are two critical parameters to monitor water quality. Since directly collecting samples for laboratory analysis can be expensive, this paper presents a methodology to estimate this information through remote sensing and Machine Learning (ML) techniques. TSS and chlorophyll-a are optically active components, therefore enabling measurement by remote sensing. Two study cases in distinct water bodies are performed, and those cases use different spatial resolution data from Sentinel-2 spectral images and unmanned aerial vehicles together with laboratory analysis data. In consonance with the methodology, supervised ML algorithms are trained to predict the concentration of TSS and chlorophyll-a. The predictions are evaluated separately in both study areas, where both TSS and chlorophyll-a models achieved R-squared values above 0.8.

A Review of Earth Observation-Based Analyses for Major River Basins

Regardless of political boundaries, river basins are a functional unit of the Earth’s land surface and provide an abundance of resources for the environment and humans. They supply livelihoods supported by the typical characteristics of large river basins, such as the provision of freshwater, irrigation water, and transport opportunities. At the same time, they are impacted i.e., by human-induced environmental changes, boundary conflicts, and upstream–downstream inequalities. In the framework of water resource management, monitoring of river basins is therefore of high importance, in particular for researchers, stake-holders and decision-makers. However, land surface and surface water properties of many major river basins remain largely unmonitored at basin scale. Several inventories exist, yet consistent spatial databases describing the status of major river basins at global scale are lacking. Here, Earth observation (EO) is a potential source of spatial information providing large-scale data on the status of land surface properties. This review provides a comprehensive overview of existing research articles analyzing major river basins primarily using EO. Furthermore, this review proposes to exploit EO data together with relevant open global-scale geodata to establish a database and to enable consistent spatial analyses and evaluate past and current states of major river basins.

Quantitative Remote Sensing of Land Surface Variables: Progress and Perspective

The land is of particular importance to the human being, not only because it is our, as well as terrestrial biomes’, habitat, but the land surface also plays a unique role in the Earth system [...]

Evaluation of Regression Analysis and Neural Networks to Predict Total Suspended Solids in Water Bodies from Unmanned Aerial Vehicle Images

The concentration of suspended solids in water is one of the quality parameters that can be recovered using remote sensing data. This paper investigates the data obtained using a sensor coupled to an unmanned aerial vehicle (UAV) in order to estimate the concentration of suspended solids in a lake in southern Brazil based on the relation of spectral images and limnological data. The water samples underwent laboratory analysis to determine the concentration of total suspended solids (TSS). The images obtained using the UAV were orthorectified and georeferenced so that the values referring to the near, green, and blue infrared channels were collected at each sampling point to relate with the laboratory data. The prediction of the TSS concentration was performed using regression analysis and artificial neural networks. The obtained results were important for two main reasons. First, although regression methods have been used in remote sensing applications, they may not be adequate to capture the linear and/or non-linear relationships of interest. Second, results show that the integration of UAV in the mapping of water bodies together with the application of neural networks in the data analysis is a promising approach to predict TSS as well as their temporal and spatial variations.