Rapid earthquake damage assessment via hybrid LSTM-RNN with a quantum-inspired classification head based on Autonomous Perceptron Model APM

Rapid post-event assessment of earthquake damage is essential for resilient emergency response and risk mitigation. We present a multi-scenario deep learning framework that uses stacked LSTM and a hybrid LSTM-RNN to (i) forecast structural response variables (displacement [Formula: see text], velocity [Formula: see text], acceleration [Formula: see text], and Damage Index [Formula: see text]), (ii) classify damage status, (iii) conditionally estimate the weight factor [Formula: see text] for damaged cases ([Formula: see text]), and (iv) identify features most associated with negligible damage via GridSearchCV. In addition, we benchmark a quantum-inspired Activation-based Probabilistic Machine (APM) classifier head attached to the shared sequence encoder to probe whether compact state encodings and Hadamard-style interactions can improve damage discriminability under the same leakage-safe pipeline. Models were trained on 40-step windows for 100 epochs with Adam, using linear heads for regression and Softmax for classification (APM and standard heads share the global training schedule). Across sequence-regression tasks, the LSTM-RNN consistently outperformed stacked LSTM: [Formula: see text] improved from 98.37 to 99.42% for [Formula: see text], 89.57 to 97.58% for [Formula: see text], 97.69 to 99.8% for [Formula: see text], and 99.68 to 99.97% for [Formula: see text]. For [Formula: see text], error metrics were markedly lower with LSTM-RNN (MAE 0.0031 vs. 0.0132, RMSE 0.0047 vs. 0.0163, MAPE 1.51 vs. 5.25, MedAE 0.0022 vs. 0.0118), indicating tighter tracking of the damage signal. The conditional [Formula: see text] estimation and feature-ranking scenario offers practical levers for risk-informed prioritization, while the APM head provides a compact, quantum-inspired alternative for damage classification within the same framework. Overall, the results support sequence models, particularly LSTM-RNNs, as an effective basis for rapid, data-driven earthquake damage modeling and decision support, with quantum-inspired heads as a complementary option.