We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Modeling the temporal evolution of plastic film microplastics in soil using a backpropagation neural network
AI summary Read the abstract
A backpropagation neural network model accurately predicted the temporal evolution of PE and biodegradable PBAT microplastics in soil, finding PBAT microplastics changed more rapidly in abundance, size, and shape than PE microplastics over the incubation period.
Plastic films are a crucial aspect of agricultural production in China, as well as a key source of microplastics in farmland. However, research into the environmental behavior of microplastics derived from polyethylene (PE) and biodegradable plastic films such as polybutylene adipate-co-terephthalate (PBAT) is limited by inadequate knowledge of their evolution and fate in soil. Therefore, we conducted controlled soil incubation experiments using new and aged microplastics derived from prepared PE and PBAT plastic films to determine their temporal evolution characteristics in soil. The results indicated that PBAT microplastics exhibited more pronounced changes in abundance, size, and shape over time than PE microplastics. Notably, the magnitude and timing of changes in newly introduced PBAT microplastics were consistently delayed relative to those of aged microplastics. Specifically, the abundance of aged PBAT microplastics initially increased then decreased, whereas their size continuously decreased, ultimately reaching 21.9 % and 47.5 % of the initial values, respectively. Furthermore, we constructed a novel backpropagation neural network model based on our morphological and spectral data, which effectively identified the incubation duration of PE and PBAT microplastics, with recognition accuracies of 98.1 % and 84.6 %, respectively. These findings offer a novel perspective for assessing the environmental persistence and fate of plastic film microplastics.
More Papers Like This
Predicament of biodegradation of microplastics in water by MLP-ANN
AI summary Read the abstract
Researchers tested whether Bacillus bacteria could biodegrade microplastic particles under controlled laboratory conditions and used machine learning neural networks to model and predict degradation rates. The study found measurable bacterial degradation of microplastics, though rates were slow. Combining biological and computational approaches offers a pathway for developing more efficient microbial strategies to address the persistent microplastic pollution problem.
A generative physics-informed machine learning model for soil microplastic accumulation dynamics
AI summary Read the abstract
Researchers developed a physics-informed machine learning model to simulate and predict microplastic accumulation dynamics in soils, combining experimental data with mechanistic equations to overcome the limitations of heterogeneous field conditions. The integrated model outperformed purely data-driven approaches in predicting MP transport and retention in soil.
Machine learning prediction and interpretation of the impact of microplastics on soil properties
AI summary Read the abstract
Researchers applied machine learning models to predict how microplastics affect soil properties, finding that microplastic release into soils is 4 to 23 times higher than into oceans. The models identified key factors influencing soil changes, including microplastic type, size, and concentration, as well as soil texture. The study suggests that machine learning can help address the complexity of soil-microplastic interactions and improve predictions of environmental impacts.
Degradation of biodegradable plastic films in soil: microplastics formation and soil microbial community dynamics
AI summary Read the abstract
Scientists tracked what happens when biodegradable PBAT plastic films break down in soil over 180 days and found they release microplastics that peaked before declining. Fungi broke the films into smaller pieces while bacteria consumed the fragments, suggesting that even plastics marketed as biodegradable generate microplastics during their breakdown, though soil microbes can eventually help clean them up.
Machine learning-driven analysis of soil microplastic distribution in the Bang Pakong Watershed, Thailand
AI summary Read the abstract
Researchers used machine learning techniques to analyze the distribution and influencing factors of soil microplastic contamination in the Bang Pakong Watershed in Thailand. The study identified key environmental and land-use variables that predict microplastic occurrence, providing a data-driven approach for understanding how microplastics distribute across agricultural and urban landscapes.
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.