Using tree-based machine learning models to predict diverse compost maturity via one-hot encoding: Model deployment, experimental validation, and practical application

doi:10.1016/j.wasman.2025.114981

Using tree-based machine learning models to predict diverse compost maturity via one-hot encoding: Model deployment, experimental validation, and practical application

2025-07-07

0

PRE

AI

DOI：10.1016/j.wasman.2025.114981

Original

Original request for help

Save

Abstract

En 中文

• Data combined with diverse material and scale achieved R2 > 0.93 in tree algorithms. • Best model, AdaBoost, achieves R2 = 0.9720 for compost maturity (GI) prediction. • Key features of compost maturity analyzed via Gini Index and SHAP. • Stacking fusion model achieved R2 = 0.9733 with validation using real-world data. • Created an easy-to-use app for predicting compost maturity on desktop and mobile.

Using tree-based machine learning models to predict diverse compost maturity via one-hot encoding: Model deployment, experimental validation, and practical application

Abstract

Journal

Organization