We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Hybrid TinyML Sensor Detection for Microplastics
AI summary Read the abstract
A low-cost embedded system using an ESP32 microcontroller, LED light source, and light-dependent resistor combined with TinyML models successfully identified polyethylene and polypropylene microplastics in liquid samples through optical light-intensity variation. This portable, field-deployable sensor design represents a significant step toward accessible microplastic monitoring outside specialized laboratory settings.
Microplastics are small plastic pieces that are now found in liquids like water and oil. Testing for them becomes difficult outside laboratories because most methods need costly equipment and controlled conditions. This study addresses this issue by examining a simple embedded sensing approach for microplastic monitoring. This proposed system is a simple, budget-friendly device that utilizes an ESP32 microcontroller, an everyday LED as a light source, and an LDR to measure changes in light for processing and potential connectivity. The entire setup is designed for cost-effective monitoring and data handling capabilities. When a liquid sample is placed in the sensing path, variations in light intensity caused by suspended particles are observed. These signals are processed directly on the device. Lightweight machine learning models are applied to identify frequently used polymer types, including Polyethylene and Polypropylene. All computation is carried out locally on the embedded system, and the output is displayed immediately without the use of cloud services or laboratory instruments. The experimental results indicate that the system can operate with low power consumption and is suitable for simple field testing. The work shows that compact TinyML-enabled optical sensing can be explored as a practical option for microplastic monitoring in resource-constrained environment.
More Papers Like This
Efficient Detection of Microplastics on Edge Devices With Tailored Compiler for TinyML Applications
AI summary Read the abstract
Two AI models (MLP and GRU) were designed for microplastic detection in water from scattered optical signals and optimized via neural architecture search, then compiled with a custom TinyML compiler for deployment on resource-constrained edge devices—enabling low-power, distributed microplastic monitoring.
Proof of Concept: A TinyML-Based Image Classifier for Detecting Microplastics and Waste in Simulated Marine Environments
AI summary Read the abstract
Researchers developed a proof-of-concept image classifier using Tiny Machine Learning (TinyML) implemented on an ESP32-CAM module to detect microplastics and cardboard waste in simulated marine environments, training a MobileNetV1-based transfer learning model on 229 images with 96x96 pixel scaling and normalization for low-cost autonomous monitoring applications.
Smart Portable Sensor System for Microplastic Detection in Water
AI summary Read the abstract
Researchers built a low-cost portable device that uses a light sensor to detect microplastics in water, showing results on a small screen and indicator lights. In tests with water samples containing different contamination levels, the device responded quickly and accurately classified the level of contamination.
A Portable Optical Sensor for Microplastic Detection: Development and Calibration
AI summary Read the abstract
Researchers built a portable, low-cost optical sensor prototype designed to detect microplastics by shining multiple wavelengths of light through water samples. The device measures how different plastic particles absorb and scatter light, producing color spectra that can help identify microplastics. The sensor offers an affordable field-deployable option for environmental monitoring, with potential future improvements using machine learning for automated identification.
An IoT Based Low-Cost Optical System for Early Detection of Microplastics in Water Sources
AI summary Read the abstract
Researchers developed a low-cost device that can detect tiny plastic particles (microplastics) in drinking water using simple LED lights and sensors, which could make testing much cheaper and easier than current lab methods. This matters because microplastics are found in water supplies worldwide and may pose health risks, but expensive testing equipment has made it hard to monitor water quality regularly. The study shows this simpler technology could work, potentially helping communities better track plastic pollution in their water sources.
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.