To address the critical industry challenges of insufficient thermal safety and reliability in the stacking design of lithium-ion battery (LIB) modules, as well as the lack of accurate traceability methods for LIB fire accidents, this study takes commercial 18650-type lithium, nickel cobalt aluminum (NCA) LIBs as the research object. First, we systematically investigated the thermal runaway (TR) behavior of single cells under thermal and electrical abuse conditions, identified the significant discrepancies in TR behavior between the two abuse scenarios, quantitatively revealed a positive correlation between TR risk and state of charge (SOC), and determined that the core feature is that the maximum heat release occurs in the negative electrode of the battery. Subsequently, we quantitatively analyzed the influences of the initial TR trigger position and module stacking structure on the TR propagation characteristics within the module, and obtained the key conclusions that center-triggered TR exhibits a faster propagation rate and that the vertical stacking structure significantly aggravates the TR chain reaction. Finally, based on the TR process, this paper summarizes the burn mark characteristics caused by different triggers of thermal runaway in LIBs. The results of this study provide critical fundamental data for optimizing the thermal safety design of LIB modules, and offer a scientific basis for the formulation of LIB fire rescue schemes and the implementation of fire investigation.

Forest fire events in coastal eastern Guangdong are strongly associated with human activities and often occur as small-scale, short-lived early-stage fire events. Given uneven thermal monitoring infrastructure, a key challenge is leveraging data-rich local areas to identify high-susceptibility areas in data-sparse regions. Focusing on Shanwei City, this study used fire data from thermal imaging in the Shenzhen–Shanwei Special Cooperation Zone. By integrating biophysical covariates and anthropogenic factors, we developed a Randomized Iterative Sampling–Similarity Assessment–Model Selection (RISAMS) framework to optimize negative-sample selection and identify a robust classifier. Shapley Additive exPlanations (SHAP) was implemented in Python 3.13.5 using the SHAP package (version 0.48.0) and was used to interpret drivers of susceptibility. In the optimal iteration, mean covariate similarity between training samples and the Shanwei macro-environmental background reached 0.94, with a minimum of 0.72. The optimal Random Forest classifier achieved an AUC of 0.92 on the training set and 0.91 on the test set, with Cohen’s Kappa of 0.78 for both. High-susceptibility zones clustered along forest edges and wildland–urban interfaces in northern and central Shanwei. SHAP identified road density, elevation, and slope as the primary drivers, with a cumulative relative importance of 61.87%. This framework supports early-stage forest fire susceptibility mapping under uneven monitoring resources and improves early warning of early-stage fires in human-dominated humid coastal forests.