Given the exponential rise in global plastic production and its significant ecological and socio‐economic impacts, monitoring macroplastics in rivers has become a central focus of water management efforts. However, standardized monitoring methodologies are lagging behind the rate of plastic waste currently entering aquatic systems on a global scale. This translates into a shortage of spatially and temporally refined data on the macroplastic pollution circulating in inland waters. Recent advancements in remote sensing techniques, primarily satellites, UASs, fixed and handheld cameras combined with crowd‐sourced data and automated macroplastic detection using machine and deep learning, offer promising opportunities for versatile monitoring solutions. Thus, this paper reviews state‐of‐the‐art approaches and emerging methods for macroplastic identification in rivers to provide researchers with a comprehensive inventory of techniques and to encourage the scientific community to harmonize monitoring methods and define standard protocols. According to our investigation, addressing the challenges of remote sensing‐based river macroplastics monitoring mandates further efforts to enhance and integrate multiple platforms with an emphasis on long‐term monitoring.

The development of continuous river turbidity monitoring systems is essential since this is a critical water quality metric linked to the presence of organic and inorganic suspended matter. Current monitoring practices are mainly limited by low spatial and temporal resolutions and costs. This results in the huge challenge of providing extensive and timely water quality monitoring at the global scale. In this work, we propose an image analysis procedure for river turbidity assessment using different camera systems (i.e. fixed-trap camera, camera on board an uncrewed aerial vehicle and a multispectral camera). We explored multiple types of camera installation setups during a river turbidity event artificially re-created on site. The outcomes prove that processed digital-camera data can properly represent the turbidity trends. Specifically, the experimental activities revealed that single-band values were the most reliable proxy for turbidity monitoring in the short term, more so than band ratios and indexes. The best camera positioning, orientation and lens sensitivity, as well as daily and seasonal changes in lightning and river flow conditions, may affect the accuracy of the results. The reliability of this application will be tested under different hydrological and environmental conditions during our next field experiments. The final goal of the work is the implementation of this camera system to support existing techniques and to help in finding innovative solutions to water resource monitoring.

Using large image data sets has been the conventional strategy to improve object detection, but it increases annotation effort and training cost and does not guarantee robust transfer to new sites. Here we quantify the value of a small, diverse training set for floating macroplastic detection by jointly evaluating performance, computational cost, annotation effort, and cross‐site transferability. We compile four river‐camera data sets from Indonesia, The Netherlands, and Vietnam (training/internal validation) and Italy (external validation, single site and single day data from a long‐term camera monitoring system), harmonized into 13 litter classes and a five‐level tiering scheme (progressive class aggregation). We train YOLOv7 and YOLOv8 models and compare site‐specific data sets with a merged “Mixed” data set (999 images) spanning heterogeneous environmental conditions. Results show that data sets with more diverse backgrounds (Type II; e.g., The Netherlands) achieve higher performance per annotation than homogeneous data sets (Type I; e.g., Indonesia, Vietnam), whereas naïvely merging data sets can degrade internal validation unless accompanied by feature‐aware filtering. Class aggregation substantially increases overall detection skill, with gains consistent across data sets when moving from fine (Tier 4) to coarse (Tier 0) label spaces. Finally, internal validation does not reliably predict external‐site performance, underscoring the need for transferability‐aware data set design and evaluation. Overall, our findings emphasize that data diversity and curation , rather than data set size alone, are key levers to scale river plastic detection toward broader deployment.

Given the exponential rise in global plastic production and its significant ecological and socio-economic impacts, monitoring macroplastics in rivers has become a central focus of water management efforts. However, standardized monitoring methodologies have not kept pace with the increasing volume of plastic waste entering aquatic systems worldwide. This resulted in a critical shortage of spatially and temporally refined data on macroplastic pollution circulating in inland waters. Recent advancements in remote sensing technologies such as satellites, unmanned aerial systems (UASs) and camera systems coupled with crowd-sourced data and automated detection using machine and deep learning, offer promising opportunities for versatile monitoring solutions. Towards improving monitoring practices, we reviewed emerging remote sensing methods and tools to tackle macroplastic identification in riverine environments. Our investigation highlights that overcoming the challenges of remote sensing-based river macroplastics monitoring requires further efforts to integrate multiple platforms and prioritize long-term monitoring strategies. The RiverWatch project exemplifies these advancements by developing an innovative infrastructure for detecting buoyant plastics in rivers. Utilizing fixed cameras along river networks and mobile cameras, including those operated by citizens via smartphones, RiverWatch employs advanced computer vision algorithms to analyse collected data. Focused on the Sarno River, among the most polluted rivers in Italy, this project harnesses low-cost, adaptable technologies and empowers citizen science through the RiverWatch mobile app, enhancing both spatial and temporal monitoring resolution. The project aligns with the broader goals of offering scalable and harmonized monitoring solutions. Furthermore, it serves as an example of integrating emerging technologies into standardized methodologies, bridging the gap between research advancements and practical applications for global riverine systems.

Improving river monitoring techniques is critical given the concomitant impact of climate change, population growth, and pollution over the last years. Turbidity is one of the most significant metrics for water quality characteristics. In river basins, high turbidity values can be indicative of both organic and inorganic materials. Turbidity is often used as a proxy for transport of suspended particles and associated fluxes of hydrophobic pollutants in a wide range of hydrological conditions. However, it is demanding to estimate suspended sediment yields in rivers because of the high variability along stream of suspended sediment concentrations. Traditional methods, such as gravimetric analysis, are time-consuming, expensive, often discontinuous in space and time and influenced by human errors or instrumental limitations.Remote sensing techniques are a suitable alternative to point measurements. Satellite remote sensing allows to study the spatial and temporal variations of water status parameters, but it is limited by the spatial and temporal resolution of the satellites considered. Low range systems can help increase the resolution of the imagery used for this purpose. In particular, the use of optical cameras can significantly reduce the monitoring cost and exponentially increase the information on water bodies health and hydrological dynamics, offering a large amount of data distributed in time and space. Nonetheless, all optical sensing methods are strongly affected by many environmental constraints (light, good optical transmission, visibility, etc.), which make them currently not always suitable for regular long-term monitoring of turbidity in rivers. The main goal of the monitoring procedure identified in this work is to avoid all these constraints, by processing the camera image to use it as a real measurement data. In this work, an image processing procedure has been identified by exploiting the water surface reflectance properties to estimate water turbidity spectral indices related to red and green bands of the light visible spectrum (Miglino et al., 2022). This river monitoring system is under development in different cross sections of the Bode River, one of the best-instrumented catchments in Central Germany.managed by UFZ Helmholtz Centre for Environmental Research. They gather a wide range of environmental data including a long-term time series on water quantity and quality. Preliminary results highlighted interesting similarities between the chromatic variation of the water surface captured by the RGB camera and the real data.  Keywords: turbidity, sediment transport, image processing, spectral indices, remote sensing, camera, water quality assessment. References:Miglino, D., Jomaa, S., Rode, M., Isgro, F., & Manfreda, S. (2022). Monitoring Water Turbidity Using Remote Sensing Techniques. Environmental Sciences Proceedings, 21(1), 63.