ML Regression Trees for Water Parameter Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for measuring water parameters in artificial water bodies, such as chlorine concentration and pH, are complex, costly, and require expensive equipment, leading to inaccurate readings due to equipment degradation and accessibility issues.
Innovation Solution
The use of machine learning-based multivariate regression trees trained with physical and spectral features, including ORP values, to estimate water parameters, allowing for accurate and cost-effective monitoring using simple, accessible test equipment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If expensive equipment is used for measuring water parameters, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent creates a digital model (regression tree) that copies the relationship between spectral features and water parameters from training data. This virtual model replaces expensive physical measurement equipment, allowing accurate parameter estimation through computational analysis of spectral data rather than direct physical measurement with complex instruments.
Solution Approach 2:
The patent replaces mechanical/physical measurement systems with an information-processing system. Instead of using complex physical sensors and equipment to directly measure water parameters, the system uses spectral imaging combined with machine learning algorithms to infer parameter values, substituting physical measurement mechanisms with computational methods.
2Device complexity
If simple test equipment is used for monitoring water parameters, then device complexity is reduced, but measurement precision deteriorates
Solution Approach 1:
The patent merges spectral imaging technology with machine learning algorithms to create an integrated system. The spectral camera captures complex spectral data, and the regression tree model processes this data to extract water parameter information. This combination allows simple hardware to achieve precise measurements through sophisticated data processing.
Solution Approach 2:
The patent performs preliminary training of the regression tree model using labeled spectral data and corresponding water parameter measurements. This pre-computed model captures the relationships between spectral features and parameters, enabling the simple test equipment to make accurate predictions without requiring complex real-time analysis capabilities during actual measurement.
3Productivity
If frequent monitoring is performed, then productivity is improved, but loss of time and resources increases
Solution Approach 1:
The patent implements an automated monitoring system where the spectral camera and regression tree model work together to automatically estimate water parameters without requiring manual intervention. The system processes spectral images and generates parameter estimates autonomously, enabling frequent monitoring without proportional increases in time investment for data collection and analysis.
Data Source
AI summary
A method of estimating a level of one or more water parameters using trained machine learning (ML) based regression trees, comprising receiving physical features and spectral features relating to one or more sample of waters, propagating the water sample(s) through a regression trees comprising a plurality of nodes arranged in a plurality of branches propagating from a root node to a plurality of leaf nodes, each of the plurality of nodes is associated with an ML model trained to estimate a level of one or more water parameters in water samples, identifying a certain leaf node to which the water sample(s) propagated based on the plurality of physical features, estimating a level of one or more of the water parameters in the water sample(s) by applying the ML model associated with the certain leaf node to the spectral features, and initiating action(s) based on the water parameter(s) estimated level.