We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Papers
20 resultsShowing papers similar to VIRS based detection in combination with machine learning for mapping soil pollution
ClearConvolutional neural network for soil microplastic contamination screening using infrared spectroscopy
Researchers trained a convolutional neural network on visible-near-infrared spectra to classify soil samples by degree of microplastic contamination, using concentrations from industrial areas around metropolitan Sydney as a baseline. The model accurately identified uncontaminated samples and improved classification of highly contaminated samples as the number of contamination classes increased, with transfer learning further enhancing performance.
Efficient screening of microplastics in soils using hyperspectral imaging in the short-wave infrared range coupled with machine learning – A laboratory-based experiment
Researchers tested short-wave infrared hyperspectral imaging combined with machine learning to detect three types of microplastics in soil, finding it could identify elevated contamination but was not sensitive enough for typical environmental background levels. The technique shows most promise for screening heavily polluted sites like landfills and industrial areas.
High-Precision Mapping of Soil Organic Matter Based on UAV Imagery Using Machine Learning Algorithms
UAV-based multispectral imaging combined with random forest machine learning achieved high-precision soil organic matter mapping with R2 of 0.91, outperforming SVM, elastic net, and other algorithms, with results showing a negative correlation between SOM content and elevation.
Microplastic Analysis in Soil Using Ultra-High-Resolution UV–Vis–NIR Spectroscopy and Chemometric Modeling
Researchers tested a new method using UV-visible-near infrared spectroscopy combined with machine learning to identify microplastics in soil samples. They found the technique could rapidly and accurately distinguish between different plastic polymers and natural soil particles. The study offers a promising alternative to current labor-intensive identification methods, potentially making large-scale microplastic soil monitoring more practical.
Soil Nitrogen Content Detection Based on Near-Infrared Spectroscopy
Researchers developed a near-infrared spectroscopy method combined with random forest regression to rapidly measure soil nitrogen content from 143 soil samples collected near a river in Hubei, China. The model achieved high accuracy and provided a faster, non-destructive alternative to conventional soil nitrogen analysis.
Rapid detection of microplastics in plastic-covered soils using FT-NIR and ATR-FTIR spectral data fusion
Researchers developed a rapid, non-destructive method to detect microplastics in agricultural soils by combining two infrared spectroscopy techniques (FT-NIR and ATR-FTIR) with machine-learning models. The fused spectral approach substantially outperformed either technique alone, detecting microplastics down to around 7 parts per million. Fast, accurate soil screening tools are critical for understanding and managing the growing microplastic contamination in farmland.
Accurate detection of low concentrations of microplastics in soils via short-wave infrared hyperspectral imaging
Researchers combined short-wave infrared hyperspectral imaging with machine learning algorithms to detect low concentrations of polyamide and polyethylene microplastics in soil samples, achieving accurate classification with implications for fast, non-destructive screening of agricultural land for plastic contamination.
Application of Near-infrared Spectroscopy and Multiple Spectral Algorithms to Explore the Effect of Soil Particle Sizes on Soil Nitrogen Detection
Researchers applied near-infrared spectroscopy with machine learning algorithms to rapidly measure soil nitrogen content. While focused on agricultural management rather than microplastics, spectroscopic methods like near-infrared are also used for detecting microplastics in soil samples.
Predicting soil microplastic concentration using vis-NIR spectroscopy
Researchers used visible and near-infrared (vis-NIR) spectroscopy to predict microplastic concentrations in soil samples, developing calibration models that could estimate contamination levels directly from spectral measurements without extensive sample preparation. The approach offers potential for faster and more scalable monitoring of microplastic pollution in agricultural and natural soils.
Comparison of learning models to predict LDPE, PET, and ABS concentrations in beach sediment based on spectral reflectance
Researchers compared machine learning models to predict concentrations of LDPE, PET, and ABS microplastics in beach sediments using visible-near-infrared spectral reflectance, demonstrating that spectroscopic methods can efficiently estimate microplastic pollution in understudied terrestrial and coastal environments.
Toward high-precision analysis of soil micro-and nanoplastics: A review of spectroscopy and machine learning approaches
Researchers reviewed multiple spectroscopy techniques — including infrared, Raman, and hyperspectral imaging — combined with machine learning as faster, cheaper alternatives to traditional methods for detecting microplastics and nanoplastics in soil. While promising, key challenges remain including poor detection of nanoplastics, limited real-world validation, and detection limits that often miss environmentally relevant concentrations.
Rapid detection of colored and colorless macro- and micro-plastics in complex environment via near-infrared spectroscopy and machine learning.
Researchers developed a near-infrared spectroscopy method combined with machine learning classifiers -- including PLS-DA, random forest, and XGBoost -- to rapidly identify both colored and colorless plastic fragments across different polymer types, thicknesses, and environmental backgrounds. The approach improved detection of colorless plastics that are typically underestimated in environmental surveys, with random forest achieving the highest classification accuracy.
Identification of potentially contaminated areas of soil microplastic based on machine learning: A case study in Taihu Lake region, China
Researchers applied machine learning models — including random forest and support vector regression — to predict the spatial distribution of soil microplastic pollution in China's Taihu Lake region, finding that soil texture, population density, and proximity to known plastic sources were the dominant drivers, with nearly half of urban soils showing serious contamination.
Heavy metal concentrations in the soil near illegal landfills in the vicinity of agricultural areas—artificial neural network approach
Researchers used artificial neural network models to predict heavy metal contamination in soils near illegal landfills close to agricultural areas. The study found that illegal landfilling significantly impacts surrounding soil quality and proposes these predictive models as effective tools for environmental risk management and decision-making.
Soil Microplastics Spectrum Based on Visible Near-Infrared Spectroscopy
Researchers developed a visible near-infrared spectroscopy method for quantifying microplastics in soil, finding that spectral reflectance decreases with increasing microplastic content and that a regression model combining normalisation with first-derivative transformation achieved the best predictive accuracy with R-squared values of 0.75 and 0.77 for calibration and validation sets.
Innovative approach for determining polypropylene microplastics pollution in calcareous soils: Vis-NIR spectroscopy
Researchers demonstrated that visible and near-infrared (Vis-NIR) spectroscopy combined with statistical modeling can accurately detect and quantify polypropylene microplastics in agricultural calcareous soils, with a model accuracy of R² = 0.91. This is promising because it could enable rapid, low-cost field screening of soil microplastic contamination without expensive laboratory analysis.
Enhancing Agricultural Sustainability Through Robotic-IoT Systems for Real-Time Monitoring Soil Contamination
Researchers developed an IoT-based robotic system integrating portable NIR spectroscopy sensors and machine learning, including a Random Forest algorithm, to monitor soil quality and detect microplastic contamination in real time, achieving 96% accuracy in microplastic detection and 91% accuracy in broader pollutant analysis.
Vis-NIR Spectroscopy for Soil Organic Carbon Assessment: A Meta-Analysis
This meta-analysis of 134 studies found that Vis-NIR spectroscopy models for predicting soil organic carbon content vary significantly in accuracy depending on preprocessing methods, spectral range, and modeling approaches. The research identifies best practices for remote soil carbon assessment, which is relevant to monitoring soil health in areas affected by microplastic contamination.
Tall Trees and Small Plastics. Using Random Forest Classification to Identify Microplastic Pollution in Surface Soil Samples
Researchers used machine learning (random forest classification) to identify and distinguish twenty types of plastic particles in soil samples from agricultural land. Developing accurate, automated detection methods for microplastics in soil is essential for large-scale environmental monitoring.
Spatial prediction of physical and chemical properties of soil using optical satellite imagery: a state-of-the-art hybridization of deep learning algorithm
Not relevant to microplastics — this study uses deep learning models combining satellite imagery and topographic data to predict soil chemical properties (pH, organic carbon, phosphorus, potassium) across a region of Iran, with no connection to microplastic pollution.