Hospitals, clinics, and laboratories generate a variety of biomedical waste, including syringes, blood-soaked bandages, and even tissue samples. When not handled properly, it can pose significant environmental and public health challenges. Traditional methods such as incineration and landfilling often lead to secondary pollution. With the increasing volume of biomedical waste, identifying new and effective solutions for managing it is a pressing environmental concern. A new study for the Journal of Hazardous, Toxic, and Radioactive Waste explores chemical heat energy processes to convert biomedical waste into valuable materials and energy-dense products such as bio-oil, syngas, and biochar. Optimizing the yield and quality of these products, however, presents a scientific and engineering challenge due to the wide variety of biomedical waste.
To address the challenges, researchers Subbaiyan Naveen, Madesh Kumar, Aruna Jayalakshmi Sekar, Jayaseelan Arun, Punniyakotti Varadharajan Gopirajan, Sathish Kumar Palaniappan, and Suchart Siengchin propose and evaluate hybrid machine learning models, specifically XGBoost and LightGBM, for predicting product distributions from thermochemical processes. The authors of “Sustainable Valorization of Biomedical Waste: Predictive Modeling of Thermochemical Product Distribution Using Hybrid Machine-Learning Models” applied hybrid ML techniques to biomedical waste pyrolysis, systematically developing a practical framework for predictive analysis and process optimization and combining literature-derived data with lab-scale experimental results for validation. Learn more about the decision support system they developed and how it can help optimize waste treatment decisions and further sustainable biomedical waste management strategies at https://ascelibrary.org/doi/10.1061/JHTRBP.HZENG-1643. The abstract is below.
Abstract
This research concentrates on modeling product distributions in the thermochemical process of biomedical waste processing using a hybrid machine learning model (ensemble of XGBoost and LightGBM). This study focuses on accurately predicting and optimizing the production of hydrothermal, gasification, and pyrolysis products (e.g., bio-oil, syngas, and biochar) using process parameters such as temperature, heating rate, pressure, and pH. Modeling of process parameter–product yield interactions via a hybrid ML framework is carried out. A training dataset was prepared using experimental values along with published data to analyze the parameters in detail. Training datasets were used to form a Pearson correlation matrix that has positive and negative coefficients. A DSS was developed to support the optimization of operating parameters to improve the product yield. A dataset of 180 points was compiled (150 from literature + 30 independent laboratory hydrothermal experiments). The proposed hybrid model achieved a classification accuracy of 94 percent (macro-F1: 0.94) for process selection and regression performance of MAE = 4.6 percent [3.3–6.0], RMSE = 5.9 percent [4.3–7.5], and R2 = 0.78 [0.62–0.88] on the external test set. The study also shows that the feature importance and sensitivity analyses ranked the temperature, catalyst concentration, and residence time as the dominant factors that are influencing the yields. Key factors received priority rankings to generate predictions that were evaluated on other dataset samples. Hybrid ML models can be more suited for highly parameter-oriented processes such as pyrolysis of biomedical waste.
Explore the testing and successful results in detail in the ASCE Library: https://ascelibrary.org/doi/10.1061/JHTRBP.HZENG-1643.
