We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Enhanced spatiotemporal mapping of urban wetland microplastics: An interpretable CNN-GRU approach using satellite imagery and limited samples
Summary
Researchers built an interpretable CNN-GRU deep learning model combining satellite remote sensing with limited in-situ measurements to map microplastic distribution in urban wetlands with enhanced spatiotemporal resolution, enabling more comprehensive monitoring with less field sampling.
Comprehensive investigation of microplastics (MPs) in urban surface waters aids in managing and understanding this emerging contaminant that threatens ecosystems and human health. This work constructed an interpretable CNN-GRU model integrating Satellite Remote Sensing (SRS) data with limited in-situ samples to analyze spatiotemporal distribution characteristics of MPs pollution in wetlands of the Chebei drainage basin, Guangzhou, China. The proposed model exhibited superior predictive performance for MP concentrations, achieving a mean predicted concentration of 44.71 items/L with excellent accuracy (R = 0.9526) and low errors (MAE = 2.93, RMSE = 4.17) on independent test dataset. Through SHapley Additive exPlanations (SHAP) analysis, the near-infrared band was identified as the most notable predictor, showing consistent positive contributions to model outputs. Furthermore, Remote Sensing Index (RSI) analysis established a notable correlation between MPs abundance and algal content in urban wetlands. The strong sensitivity of near-infrared bands to algal content suggests that algal biomass may serve as a reliable proxy for assessing MPs accumulation levels in these ecosystems. Spatiotemporal analysis revealed notably greater MPs accumulation in wetlands than reservoirs, with seasonal peaks observed during summer months. This work demonstrates the feasibility of SRS-based MPs spatiotemporal mapping with limited samples in urban wetlands, and the SHAP method enhanced the credibility and interpretability of predictions. Notably, the model's reliability depends on the correlation between MPs and algal content, which may vary across different aquatic ecosystems. These findings provide a practical case study for applying interpretable deep learning to urban wetland MPs monitoring, with insights that can be referenced for similar regions.
Sign in to start a discussion.
More Papers Like This
Mapping the plastic legacy: Geospatial predictions of a microplastic inventory in a complex estuarine system using machine learning
Researchers applied machine learning techniques to develop geospatial predictions of microplastic inventory in a complex estuarine system, overcoming the limitations of coarse ocean basin models by accounting for the intricate geomorphological and hydrodynamic conditions that govern sediment-associated microplastic distribution.
Spatiotemporal Forecasting and Environmental Driver Modeling of Marine Microplastic Pollution: an Interpretable Deep Learning Approach for Sustainable Ocean Policy
Researchers developed an interpretable deep learning model integrating historical microplastic sampling data, seasonal patterns, and large-scale ocean-atmosphere climate indices to forecast spatiotemporal marine microplastic distribution, identifying climate drivers and offering a policy-relevant tool for ocean pollution management.
Mapping the Plastic Legacy: Geospatial Predictions of a Microplastic Inventory in a Complex Estuarine System Using Machine Learning
Researchers applied machine learning geospatial modelling to predict microplastic distribution across a complex estuarine system, using sediment samples as a training dataset to generate spatial inventory maps of microplastic accumulation. The model leveraged the estuary's role as a land-sea interface and plastic accumulation bottleneck to produce high-resolution predictions of microplastic hotspots for monitoring and management purposes.
Riverine Microplastic Quantification: A Novel Approach Integrating Satellite Images, Neural Network, and Suspended Sediment Data as a Proxy
Researchers developed satellite-based models using neural network algorithms to estimate riverine microplastic concentrations, using suspended sediment concentration as a proxy, offering a cost-effective approach for broad-scale freshwater microplastic monitoring.
Microplastic deposits prediction on Urban Sandy Beaches: Integrating Remote Sensing, GNSS Positioning, µ-Raman Spectroscopy, and Machine Learning Models
Researchers integrated remote sensing, GNSS altimetric surveys, micro-Raman spectroscopy, and machine learning models to predict microplastic deposition patterns on urban sandy beaches along the central Sao Paulo coastline, finding MP concentrations ranging from 6 to 35 MPs/m2.