We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
An inversion model of microplastics abundance based on satellite remote sensing: a case study in the Bohai Sea
AI summary Read the abstract
Researchers developed a satellite-based model to estimate microplastic concentrations in China's Bohai Sea using remote sensing data. The model combined water color measurements from satellites with field sampling to predict microplastic distribution across a large area. The study suggests that remote sensing could become a practical tool for monitoring ocean microplastic pollution over wide regions without relying solely on labor-intensive field sampling.
Nowadays, microplastics (MPs) as emerging contaminants have posed great risks to marine ecosystems and human health. However, non-continuous field sampling data makes it difficult to meet the needs of scientific research and pollution control of marine MPs. Consequently, the development of rapid monitoring techniques for marine MPs to achieve efficient acquisition of data is increasingly essential. Remote sensing technology provides a convenient and effective tool for monitoring and mapping marine MPs pollution. Therefore, we established an inversion model based on multiple regression by combining the remote sensing data and the measured data to predict the MPs pollution status in the Bohai Sea. The feature variables of a model are crucial to the prediction, and we proposed three methods of variable selection, namely successive projections algorithm (SPA), band combination method, and remote sensing index method. By comparing accuracy evaluation metrics, an approach based on SPA was selected to analyze the abundance and spatio-temporal distribution of MPs in the Bohai Sea in 2022. The determination coefficient of the SPA model is 0.75, and the root mean square error is 0.38 items/m. The error of the model is within an acceptable range. It was found that the MPs abundance on the sea surface of the Bohai Sea varied significantly in different seasons and regions. This study indicates that satellite remote sensing technology has great potential in monitoring marine MPs.
More Papers Like This
RFAGB model: A new machine learning model for microplastic inversion based on remotely sensed data in Bohai Sea
AI summary Read the abstract
Researchers developed a new machine learning model that uses satellite remote sensing data to map microplastic pollution in China's Bohai Sea. The model showed significant improvements in accuracy over previous approaches, with a 23% better fit and 67% lower error rate. The study found that Laizhou Bay had the highest microplastic concentrations, suggesting that remote sensing technology could become a practical tool for regular, large-scale ocean pollution monitoring.
Estimating microplastic concentrations in surface water using satellite-based turbidity measurements: a case study on the New River, VA
AI summary Read the abstract
Researchers used satellite-derived turbidity measurements as a proxy for microplastic concentrations in the New River, Virginia, developing and validating a model that enables broader spatial and temporal monitoring of riverine microplastic pollution without intensive field sampling.
Detection and Dynamic Imaging of Ocean Microplastics from Space
AI summary Read the abstract
Researchers developed a remote sensing approach using satellite imagery to detect and dynamically image ocean microplastic concentrations, offering broader spatial coverage than traditional net trawling methods. This study demonstrates that optical signatures of floating plastic patches can be identified from space under certain sea and lighting conditions.
Spatio-temporal distribution of plastic and microplastic debris in the surface water of the Bohai Sea, China
AI summary Read the abstract
Researchers monitored plastic debris and microplastics in surface waters of the Bohai Sea across four seasons in 2016-2017, finding a mean density of 0.49 particles per square meter with seasonal and spatial variation across macro-, meso-, and micro-size fractions.
Evaluating Microplastic Pollution Along the Dubai Coast: An Empirical Model Combining On-Site Sampling and Sentinel-2 Remote Sensing Data
AI summary Read the abstract
Researchers collected coastal water samples from Dubai and combined laboratory spectral measurements with Sentinel-2 satellite imagery to build a model that estimates microplastic concentrations from space. The model achieved an R² of 87% and was used to map microplastic pollution trends along the Dubai coast from 2018 to 2021. This remote-sensing approach demonstrates a scalable method for monitoring coastal microplastic pollution over large areas without intensive fieldwork.
Research digests by email
When a large batch of papers lands in the Atlas, we read through it and send a short write-up of what stood out.