Related Experiment Video
Updated: Aug 17, 2025
06:52
Lab-Scale Model to Evaluate Odor and Gas Concentrations Emitted by Deep Bedded Pack Manure
Published on: July 19, 2018
6.4K
Prediction for odor gas generation from domestic waste based on machine learning
Yuanyan Jiang1, Jiawei Huang1, Wei Luo2
1State Key Laboratory of Coal Mine Disaster Dynamics and Control, Chongqing University, Chongqing 400044, China; College of Environment and Ecology, Chongqing University, Chongqing 400044, China.
Waste Management (New York, N.Y.)
|December 12, 2022
Summary
Predicting domestic waste odor gases is crucial for treatment. Machine learning models, particularly Random Forest, accurately forecast odor production using waste factors like weight and temperature.
Area of Science:
- Environmental Science
- Chemical Engineering
- Data Science
Background:
- Domestic waste generates volatile organic compounds (VOCs), leading to unpleasant odors.
- Effective treatment of odor gases requires accurate prediction of their production from waste.
Purpose of the Study:
- To predict domestic waste odor gases using machine learning.
- To evaluate the performance of different machine learning models for odor prediction.
Main Methods:
- Utilized four domestic waste factors: weight, wet composition, temperature, and fermentation time.
- Developed and evaluated Random Forest, XGBoost, and LightGBM models using 512 odor intensity values.
- Employed supervised machine learning for regression prediction of odor gases.
Main Results:
- The Random Forest model achieved the highest prediction accuracy with an R² value of 0.8958.
- Evaluated prediction performance across three distinct machine learning algorithms.
- Discussed Random Forest model predictions in the context of microbial fermentation of domestic waste.
Conclusions:
- Machine learning, specifically Random Forest, offers a highly accurate method for predicting domestic waste odor gas production.
- This study enhances understanding of odor generation from domestic waste.
- Demonstrated the practical application of machine learning in addressing odor pollution from waste.
