We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
"SensNexus Spectral Dataset (SensNexusDat)"
AI summary Read the abstract
Scientists created a detailed spectral "fingerprint" library by testing coastal soil contaminated with common plastic particles (like those from bottles and packaging), using a light-based scanning method instead of slower lab tests. This dataset can help researchers build faster, cheaper tools to detect microplastic pollution in soil, which matters because microplastics in soil can enter our food and water supply, making early detection an important step in understanding and reducing our exposure to them.
"Diffuse reflectance spectroscopy in the visible, near-infrared, and short-wave infrared (Vis\u2013NIR\u2013SWIR) ranges has emerged as a promising approach for detecting and quantifying microplastic (MP) contamination in soils, offering rapid, non-destructive analysis. Despite growing interest, published spectral datasets in this domain remain scarce and are generally limited to pristine polymer pellets or environmentally collected materials measured independently from soil matrices, or to studies involving non-coastal and non-tropical soils. This gap constrains the development and validation of predictive models tailored to the spectral complexity of real-world contaminated environments. This dataset was specifically constructed to support the training and validation of chemometric and machine learning models for MP quantification in soil using Vis\u2013NIR\u2013SWIR spectroscopy. It provides high-resolution spectral data (350\u20132500 nm) from a Brazilian coastal soil artificially contaminated under controlled laboratory conditions with particles of four polymer types, polyethylene (PE), polyethylene terephthalate (PET), polypropylene (PP), and polyvinyl chloride (PVC), encompassing both pristine polymers, intended to support model training, and colored post-consumer plastics, intended to support model validation under more realistic spectral conditions. The dataset addresses an underrepresentation of coastal and tropical soil environments in the MP spectroscopy literature and enables comparative analyses between pure polymers and colored, additive-containing post-consumer materials. Its spectral coverage and high resolution make it suitable for chemometric modeling, spectral library development, machine learning applications, and cross-dataset interoperability studies, with potential applications in proximal and remote sensing-based MP detection, digital soil mapping, and coastal environmental monitoring."
More Papers Like This
2T2D spectroscopy and deep learning for soil MPs quantification
AI summary Read the abstract
Scientists have developed a new tool that combines a special light-scanning technique with artificial intelligence to detect and measure tiny plastic particles (microplastics) hiding in soil. This matters because microplastics in soil can end up in the crops we eat and the water we drink, so having a faster, more accurate way to track them helps researchers understand how much plastic pollution is entering our food supply. This dataset and code release makes the detection method available for other scientists to test and build on, which could speed up future research into microplastics and health risks.
2T2D spectroscopy and deep learning for soil MPs quantification
AI summary Read the abstract
Scientists have developed a computer tool that uses light-based scanning and artificial intelligence to accurately measure how much microplastic is hiding in soil samples. This matters because microplastics can enter our food supply through crops grown in contaminated soil, and having a faster, more reliable way to detect them helps researchers track this pollution and understand potential risks to human health. Note that this dataset and code paper focuses on the technical method itself, not on health outcomes from microplastic exposure.
Data_PET_2
AI summary Read the abstract
This dataset provides spectroscopy readings (a way of measuring materials using light) combined with computer analysis to help detect tiny plastic particles, called microplastics, in soil. Since microplastics in soil can end up in the food we eat and water we drink, better tools for finding them are an important step toward understanding and reducing our exposure to these particles.
2T2D spectroscopy and deep learning for soil MPs quantification
AI summary Read the abstract
Scientists have developed an AI-powered tool that can accurately measure how much microplastic (tiny plastic particles) is hiding in soil, using light-based scanning combined with deep learning. This matters because microplastics in soil can end up in the food we grow and eventually in our bodies, so having a fast, reliable way to detect and measure them is a key step toward understanding—and eventually reducing—our exposure to this pollution.
Data_PET_3_4
AI summary Read the abstract
This dataset supports research into a new method that combines a scanning technique with artificial intelligence to detect and measure tiny plastic particles (microplastics) hidden in soil. This matters because microplastics in soil can end up in the food we grow and eventually in our bodies, so having faster, more reliable ways to spot them is an important step toward understanding and reducing our exposure. Note that this particular entry is the raw data itself, not a study with health findings—it's the foundation other researchers can use to build and test detection tools.
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.