We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
A Low-Cost Detection Method for Nitrite Content in a Mariculture Water Environment Based on an Improved Residual Network
Summary
This paper is not about microplastic pollution. It describes a low-cost method for detecting nitrite levels in aquaculture water using chemical reagents and a neural network for image recognition, aimed at helping small-scale fish farmers in China monitor water quality more affordably.
Nitrite content is one of the key indicators for measuring the quality of mariculture water and has a crucial impact on the benefits of aquaculture. Most of China’s fisheries are small-scale domestic aquaculture. For economic reasons, farmers generally use chemical colorimetry or rely on life experience (such as whether the water bodies have become turbid or whether aquatic organisms have abnormal or died) to determine the nitrite content in water; however, both methods can easily lead to misjudgment and cause losses. Another more accurate method is spectrophotometry, but the spectrophotometer used is more expensive. This article aims to propose a low-cost and high-precision nitrite detection method. The new method we propose is to first perform a color development reaction using chemical detection reagents, and then use an improved residual network instead of human eyes to determine the nitrite concentration in the water sample. The advantages of this method are the fast response of the chemical reagents and the high accuracy of the machine vision recognition. Our network can achieve an accuracy of 98.3% on the test set. The experimental results indicate that this method can be applied to practical mariculture.
Sign in to start a discussion.
More Papers Like This
A Machine Learning Approach To Microplastic Detection And Quantification In Aquatic Environments
This study developed a machine learning approach for detecting and quantifying microplastics in aquatic environments, demonstrating that automated image analysis can improve throughput and accuracy compared to manual microscopic counting for environmental monitoring applications.
Identification of Microplastics in Aquatic Environments Using Oxidative Treatment and Automated Image Analysis
Researchers developed a cost-effective and replicable method for detecting microplastics in freshwater environments using oxidative treatment to digest organic matter from water samples, enabling cleaner isolation and more accurate identification of MP particles without requiring expensive instrumentation.
Predicting Aquaculture Water Quality Using Machine Learning Approaches
Researchers compared four machine learning approaches for predicting water quality parameters in industrial aquaculture systems, finding that back propagation and radial basis function neural networks outperformed support vector machine models for most parameters. The models achieved sufficient accuracy to support real-time management decisions without continuous in-situ monitoring.
From microplastics to pixels: Testing the robustness of two machine learning approaches for automated, Nile red-based marine microplastic identification.
Researchers tested the robustness of two automated machine learning approaches combined with Nile red fluorescent staining for marine microplastic identification, specifically evaluating performance on environmentally weathered particles that challenge the reliability of methods developed using pristine laboratory plastics.
Deep Learning-Based Image Recognition System for Automated Microplastic Detection and Water Pollution Monitoring
This study developed a deep learning image recognition system to automate the detection and classification of microplastics from microscopy images of water samples. The system achieved high accuracy across particle types and sizes, offering a scalable and less labor-intensive alternative to manual microscopy for large-scale water pollution monitoring.