Water Quality Assessment Using eDNA and LightGBM Weighting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current water quality assessment systems overlook emerging contaminants and lack a comprehensive framework that integrates biotic and abiotic factors, leading to subjective analysis and uncertain assessment results, particularly in aquatic ecosystems.
Innovation Solution
A method and system that integrates biotic and abiotic factors using environmental DNA technology, machine learning, and a LightGBM model to construct a comprehensive weight matrix for water quality assessment, incorporating biotic-abiotic response relationships and machine learning-based indicator weights.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional water quality assessment systems use only physical and chemical parameters, then the assessment framework is simple and easy to operate, but the assessment results lack comprehensiveness and accuracy in reflecting aquatic ecosystem quality
Solution Approach 1:
The patent merges biotic factors (algae, bacteria, fungi, archaea, zoobenthos, fish) with abiotic factors (physical and chemical parameters) into a unified water quality assessment system. This integration allows the system to comprehensively evaluate aquatic ecosystem quality by considering both biological communities and environmental conditions, thereby improving measurement precision while managing complexity through systematic organization.
Solution Approach 2:
The assessment system is segmented into distinct biotic and abiotic indicator categories, with biotic indicators covering multiple trophic levels and abiotic indicators covering physical and chemical properties. This segmentation allows for systematic management of complexity while maintaining comprehensive coverage of water quality aspects, enabling accurate assessment through organized evaluation of separate but interconnected factors.
2Reliability
If subjective analysis and determination are used for indicator weight assignment, then the assessment process is simple and quick, but the objectivity and accuracy of assessment results deteriorate
Solution Approach 1:
The patent employs fuzzy comprehensive assessment and artificial neural network models that incorporate feedback mechanisms to objectively determine indicator weights. These models continuously adjust weight assignments based on data patterns and relationships, reducing subjective bias while maintaining efficient assessment processes. The feedback loops enable the system to learn from data and produce more reliable, objective results without significant loss of productivity.
Solution Approach 2:
The patent replaces subjective mechanical decision-making with computational models including artificial neural networks and fuzzy logic systems. These automated mechanisms objectively calculate indicator weights based on data relationships, eliminating human bias while maintaining assessment efficiency. The substitution of human judgment with algorithmic processing ensures reliability and consistency in weight assignment.
3Measurement precision
If emerging contaminants are excluded from assessment indicators, then the assessment system remains simple and focused on conventional parameters, but the system fails to detect toxic risks from human activities
Solution Approach 1:
The patent adds a new dimension to water quality assessment by incorporating emerging contaminants alongside conventional physical and chemical parameters. This dimensional expansion enables the system to detect toxic risks from human activities that were previously invisible to conventional assessment frameworks. The integration of emerging contaminants creates a multi-dimensional indicator system that comprehensively captures both traditional and contemporary water quality issues.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Provides a comprehensive, accurate, and quick assessment of water quality by objectively quantifying indicator weights, reducing subjectivity and uncertainty, and enhancing the reliability of water quality safety evaluations in rivers, lakes, and reservoirs.
Implementation Method 1
constructing a biotic factor indicator library by an environmental DNA technology
Data Source
AI summary
Provided is a method and system for comprehensive water quality assessment by integrating biotic and abiotic factors. The method includes: acquiring abiotic factors of a water body to be tested; constructing a biotic factor indicator library by an environmental DNA technology; determining a biotic-abiotic response relationship-based abiotic factor weight matrix using the abiotic factors and the biotic factor indicator library; acquiring a machine learning-based abiotic factor weight matrix using the abiotic factors and a LightGBM model; determining an abiotic factor comprehensive weight matrix according to the biotic-abiotic response relationship-based abiotic factor weight matrix and the machine learning-based abiotic factor weight matrix; and conducting the comprehensive water quality assessment of the water body to be tested based on the abiotic factor comprehensive weight matrix and the abiotic factors to determine a comprehensive water quality assessment result of the water body to be tested.