Rapid urbanization in semi-arid regions subjects metropolitan rivers to a distinctive form of hydrologic-physical impairment-herein designated as Type 4 degradation-characterized by connectiv-ity fragmentation, baseflow depletion, and physical habitat homogenization, in which groundwater over-extraction elevates zero-flow days and concrete chan-nelization eliminates substrate heterogeneity. Conven-tional assessment protocols, developed predominantly for humid-region perennial streams, inadequately capture the multidimensional connectivity dynam-ics critical to water-limited systems. To address this diagnostic gap, this study developed a hybrid Random Forest-Deep Neural Network (RF-DNN) framework that integrates objective feature selection with non-linear modeling capacity and couples SHAP-based interpretability for mechanistic inference. A compre-hensive indicator system encompassing 26 metrics across hydrology, hydrochemistry, physical habitat, biological organization, and socioeconomic pressure was constructed and evaluated using 96 observations collected from 24 monitoring sites across Xi'an's Ba, Chan, Feng, and Hei Rivers over 2 years. Under leave-one-river-out (LORO) cross-validation, the frame-work achieved a relative deviation of 7.6 +/- 1.3%, Cohen's kappa of 0.76 +/- 0.05, and ecological validity rho of 0.79 +/- 0.07, outperforming AHP-Fuzzy (15.2 +/- 2.8%) and AHP-TOPSIS (17.1 +/- 3.3%) methods as well as stand-alone XGBoost, SVM, Full-RF, and Full-DNN models (all paired-test p < 0.05). SHAP analysis identified urbanization rate (mean |SHAP|= 0.068), ammonia nitrogen (0.032), population density (0.028), and flow velocity (0.022) as dominant pre-dictors of health variation, and revealed critical eco-logical transition zones-bootstrap-validated at 45% impervious cover (95% CI 38-52%) and 0.8 mg/L NH3-N (95% CI 0.65-0.94 mg/L), with synergistic toxicity amplification of approximately 42% under co-occurring oxygen depletion (DO < 4.0 mg/L). Spatial assessment revealed a systematic longitudinal gradient (Hei > Feng > Chan > Ba), with the down-stream urban reaches of Ba River exhibiting a mean dry-season RHI of only 0.2482, while wet-season improvements produced grade-level transitions at 10 of 24 sites (41.67%). The framework advances mech-anistic diagnosis for semi-arid urban watersheds and supports evidence-based prioritization of flow real-location, coupled NH3-N/DO management, and ripar-ian habitat reconstruction for restoration planning. Highlights
A diagnostic framework was developed for type 4 hydrologic-physical impairment in semi-arid urban rivers.
An RF-DNN hybrid architecture coupled objec-tive feature selection with nonlinear ecological modeling.
SHAP analysis identified key predictors and boot-strap-validated critical ecological thresholds.
Three testable hypotheses regarding connectiv-ity, threshold dynamics, and intervention leverage were evaluated.
A multi-dimensional indicator system integrated hydrology, hydrochemistry, habitat, biota, and society.