Prediction of lake chlorophyll concentration using the BP neural network and Sentinel-2 images based on time features

A comprehensive review of various environmental factors' roles in remote sensing techniques for assessing surface water quality

The aim of this research was to evaluate the existing remote sensing (RS) products, various tools and techniques, and their limitations in retrieving the optically active (OA) Chlorophyll-a (CHL) concentration from transitional, coastal and inland waters. In recent decades, satellite RS technique has emerged as a vital tool for assessing surface water quality (WQ) in a cost-effective and timely manner. Initially used in the 1970s to study ocean color (OC), RS techniques have advanced significantly, enabling the retrieval of key WQ indicators like CHL, colored dissolved organic matter (CDOM), total suspended matter (TSM), turbidity (TURB), and more from satellite images. Among these indicators, CHL is particularly important as it directly signifies eutrophication. While RS technique has been reliable in estimating CHL concentrations in open waterbodies (case1 water) such as oceans, it's application in shallow, turbid waters (case2 water) like transitional, coastal and inland areas faces challenges. Interference from other OA-WQ indicators like CDOM and TSM, coupled with environmental factors such as atmospheric components, sun-glint, and adjacency effects (AE), complicate the accurate CHL estimation. To address these challenges, researchers have developed four categories of CHL retrieval algorithms: empirical, semi-empirical, hybrid and data-driven models. Empirical and data-driven methods are straightforward but require regional calibration for accuracy, whereas semi-empirical approaches, rooted in solid theoretical foundations, demand extensive ancillary optical measurements. To harness the potential of RS in WQ assessment fully, it is essential to optimize these algorithms regionally, tailoring them to the specific optical characteristics of diverse waterbodies. This optimization process is vital for integrating RS technique as a complementary data source alongside traditional monitoring approach. By addressing the impact of environmental factors and fine-tuning of CHL retrieval methods according to regional nuances, satellite RS technique can significantly enhance the reliability and effectiveness of surface WQ evaluation, thereby contributing to more informed and efficient water resource management strategies. This review emphasizes the impact of these factors, categorizes CHL retrieval algorithms into empirical, semi-empirical, hybrid and data-driven methods and applicability in terms of tools/models' reliability and challenges for the further advancement of this approaches for monitoring transitional, coastal and inland waters. To optimize the reliability of remotely sensed CHL data, regional configuration(s) of retrieving algorithms is vital. By addressing these challenges and tailoring methods to specific regions, integrating satellite RS into traditional monitoring approaches can significantly enhance surface WQ assessment.

Smartphone as an alternative to measure chlorophyll-a concentration in small waterbodies

Monitoring chlorophyll-a concentrations (Chl-a, μg·L-1) in aquatic ecosystems has attracted much attention due to its direct link to harmful algal blooms. However, there has been a lack of a cost-effective method for measuring Chl-a in small waterbodies. Inspired by the increase of smartphone photography, a Smartphone-based convolutional neural networks (CNN) framework (SCCA) was developed to estimate Chl-a in Aquatic ecosystem. To evaluate the performance of SCCA, 238 paired records (a smartphone image with a 12-color background and a measured Chl-a value) were collected from diverse aquatic ecosystems (e.g., rivers, lakes and ponds) across China in 2023. Our performance-evaluation results revealed a NS and R2 value of 0.90 and 0.94 in Chl-a estimation, demonstrating a satisfactory (NS = 0.84, R2 = 0.86) model fit in lower Chl-a (<30 μg L-1) conditions. SCCA had involved a realtime-update method with hyperparameter optimization technology. In comparison with the existing methods of measuring Chl-a, SCCA provides a useful screening tool for cost-effective measurement of Chl-a and has the potential for being an algal bloom screening means in small waterbodies, using Huajin River as a case study, especially under limited resources for water measurement. Overall, we highlight that the SCCA can be potentially integrated into a smartphone application in the future to diverse waterbodies in environmental management.

A method based on improved ant colony algorithm feature selection combined with GWO-SVR model for predicting chlorophyll-a concentration in Wuliangsu Lake

Chlorophyll-a (Chl-a) is an important parameter in water bodies. Due to the complexity of optics in water bodies, it is difficult to accurately predict Chl-a concentrations in water bodies by current traditional methods. In this paper, using Sentinel-2 remote sensing images as the data source combined with measured data, taking Wuliangsu Lake as the study area, a new intelligent algorithm is proposed for prediction of Chl-a concentration, which uses the adaptive ant colony exhaustive optimization algorithm (A-ACEO) for feature selection and the gray wolf optimization algorithm (GWO) to optimize support vector regression (SVR) to achieve Chl-a concentration prediction. The ant colony optimization algorithm is improved to select remote sensing feature bands for Chl-a concentration by introducing relevant optimization strategies. The GWO-SVR model is built by optimizing SVR using GWO with the selected feature bands as input and comparing it with the traditional SVR model. The results show that the usage of feature bands selected by the presented A-ACEO algorithm as inputs can effectively reduce complexity and improve the prediction performance of the model, under the condition of the same model, which can provide valuable references for monitoring the Chl-a concentration in Wuliangsu Lake.