Empirical parameter settings in steam-based soil disinfestation for Panax notoginseng (a valuable medicinal plant) often hinder the simultaneous optimization of pathogen control and energy efficiency. To address this limitation, this study aims to develop a parameter regulation framework that integrates multi-output regression with scenario-oriented intelligent decision-making. Initially, a comprehensive dataset comprising critical parameters—steam pressure (Psteam), soil compaction (Csoil), and heating time (theat)—was established. A random search (RS) hyperparameter optimization scheme was employed to comparatively evaluate the multi-output predictive performance of Random Forest (RF), Support Vector Regression (SVR), and Multilayer Perceptron (MLP) for the joint estimation of soil temperature (Tsoil) and root-rot pathogen kill rate (Killrate). Subsequently, by integrating total energy consumption (Etotal) and operating electricity cost models, a constrained search algorithm was implemented to develop three objective-oriented decision modes: “maximize Killrate”, “minimize Celectricity”, and “maximize Efficiency”. Results demonstrate that the RS-optimized SVR yielded superior multi-output performance, achieving R2 of 0.968 for Tsoil (MAE = 2.44 °C) and 0.808 for Killrate (MAE = 7.85%). Compared to conventional empirical configurations, the proposed decision modes exhibited significant advantages across diverse scenarios. In the “maximize Killrate” mode, dynamic extensions of theat facilitated theoretical complete inactivation even under challenging heating conditions, effectively eliminating disinfection “blind spots” inherent in fixed-duration strategies. Under the “minimize Celectricity” mode, precise regulation of Psteam reduced operational electricity costs by 18.2% while satisfying the constraint of Killrate ≥ 95%. Furthermore, the “maximize Efficiency” mode identified an optimal operating point at Csoil = 64 kPa (Psteam = 0.4 MPa, theat = 13 min), thereby mitigating performance degradation associated with excessive tillage or high media rigidity and achieving an optimized cost–benefit ratio. By synthesizing high-fidelity multi-output regression with a flexible multi-mode decision-making framework, this study provides an intelligent solution for soil disinfestation in protected agriculture, facilitating the coordinated optimization of phytosanitary efficacy, energy expenditure, and economic viability.
Jia et al. (Sun,) studied this question.