UAV Multispectral Image-Based Urban River Water Quality Monitoring Using Stacked Ensemble Machine Learning Algorithms—A Case Study of the Zhanghe River, China

Machine learning for cyanobacteria inversion via remote sensing and AlgaeTorch in the Třeboň fishponds, Czech Republic

Cyanobacteria blooms in fishponds, driven by climate change and anthropogenic activities, have become a critical concern for aquatic ecosystems worldwide. The diversity in fishpond sizes and fish densities further complicates their monitoring. This study addresses the challenge of accurately predicting cyanobacteria concentrations in turbid waters via remote sensing, hindered by optical complexities and diminished light signals. A comprehensive dataset of 740 sampling points was compiled, encompassing water quality metrics (cyanobacteria levels, total chlorophyll, turbidity, total cell count) and spectral data obtained through AlgaeTorch, alongside Sentinel-2 reflectance data from three Třeboň fishponds (UNESCO Man and Biosphere Reserve) in the Czech Republic over 2022-2023. Partial Least Squares Regression (PLSR) and three machine learning algorithms, Random Forest (RF), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost), were developed based on seasonal and annual data volumes. The SVM algorithm demonstrated commendable performance on the one-year data validation dataset from the Svět fishpond for the prediction of cyanobacteria, reflected by the key performance indicators: R2 = 0.88, RMSE = 15.07 μg Chl-a/L, and RPD = 2.82. Meanwhile, SVM displayed steady results in the unified one-year validation dataset from Naděje, Svět, and Vizír fishponds, with metrics showing R2 = 0.56, RMSE = 39.03 μg Chl-a/L, RPD = 1.50. Thus, Sentinel data proved viable for seasonal cyanobacteria monitoring across different fishponds. Overall, this study presents a novel approach for enhancing the precision of cyanobacteria predictions and long-term ecological monitoring in fishponds, contributing significantly to the water quality management strategies in the Třeboň region.

UAV and satellite remote sensing for inland water quality assessments: a literature review

High spatial and temporal resolution data is crucial to comprehend the dynamics of water quality fully, support informed decision-making, and allow efficient management and protection of water resources. Traditional in situ water quality measurement techniques are both time-consuming and labor-intensive, resulting in databases with limited spatial and temporal frequency. To address these challenges, satellite-driven water quality assessment has emerged as an efficient and effective solution, offering comprehensive data on larger-scale water bodies. Numerous studies have utilized multispectral and hyperspectral remote sensing data from various sensors to assess water quality, yielding promising results. However, the recent popularity of unmanned aerial vehicle (UAV) remote sensing can be attributed to its high spatial and temporal resolution, flexibility, ability to capture data at different times of day, and relatively low cost compared to traditional platforms. This study presents a comprehensive review of the current state of the art in monitoring water quality in small inland water bodies using satellite and UAV remote sensing data. It encompasses an overview of atmospheric correction algorithms and the assessment of different water quality parameters. Furthermore, the review addresses the challenges associated with monitoring water quality in these bodies of water and emphasizes the potential of UAVs to overcome these challenges by providing accurate and reliable data.

Water quality analysis based on LSTM and BP optimization with a transfer learning model

In the urban water environmental management, a fast and effective method for water quality analysis should be established with the rapid urbanization. In this study, the Beijing's sub-center was chosen as a case study, and long short-term memory (LSTM) and back propagation (BP) models were built, then a transfer learning model was proposed and applied to optimize the two models on the base of the upstream and downstream relationships in the rivers. The results indicated that the proposed deep learning model could improve NSE by 7% and 9% for LSTM and BP at the Dongguan Bridge gauge, respectively. At the Xugezhuang gauge in the Liangshui River, NSE was improved by 11% and 17%, respectively. At the Yulinzhuang gauge, it was improved by 16% and 13%, respectively. Because the upstream and downstream relationships were considered in the learning model, the model performance was obviously better. In brief, this method would provide an idea for the effective water quality model construction in the ungauged basins or regions.

Multi-sensor and multi-platform retrieval of water chlorophyll a concentration in karst wetlands using transfer learning frameworks with ASD, UAV, and Planet CubeSate reflectance data

China has one of the widest distributions of carbonate rocks in the world. Karst wetland is a special and important ecosystem of carbonate rock regions. Chlorophyll-a (Chla) concentration is a key indicator of eutrophication, and could quantitatively evaluate water quality status of karst wetland. However, the spectral reflectance characteristics of the water bodies of karst wetland are not yet clear, resulting in remote sensing retrieval of Chla with great challenges. This study is a pioneer in utilizing field-based full-spectrum hyperspectral data to reveal the spectral response characteristics of karst wetland water body and determine the sensitive spectral bands of Chla. We further evaluated the Chla retrieval performance of multi-platform spectral data between Analytical Spectral Device (ASD), Unmanned aerial vehicle (UAV), and PlanetScope (Planet). We proposed two multi-sensor weighted integration strategies and two transfer learning frameworks for estimating water Chla from the largest karst wetland in China by combing a partial least square with adaptive ensemble algorithms. The results showed that: (1) In the range of 500-850 nm, the spectral reflectance of water bodies in the karst wetland was overall 0.001-0.105 higher than the inland water bodies, and the sensitive spectral ranges of water Chla focus on 603-778 nm; (2) UAV images outperformed ASD and Planet data, and produced the highest inversion accuracy (R2 = 0.670) for water Chla in karst wetland; (3) Multi-sensor weighted integration retrieval methods improved the Chla estimation accuracy (R2 = 0.716). Integration retrieval methods with the different weights produced the better Chla estimation accuracy than that of methods with the equal weights; (4) The transfer learning methods from ASD to UAV platform provided the better retrieval performance (the average R2 = 0.669) than that of methods from UAV to Planet platform. The transfer learning methods obtained the highest estimation accuracy of Chla (R2 = 0.814) when the ratio of the training and test data in the target domain was 7:3. The transfer learning methods produced the higher estimation accuracies with the distribution of the absolute residuals between predicted and measured values <20.957 mg/m3 compared to the multi-sensor weighted integration retrieval methods, which demonstrated that transfer learning is more suitable for estimating Chla in karst wetland water bodies using multi-platform and multi-sensor data. The results provide a scientific basis for the protection and sustainable development of karst wetlands.