In this paper, an eco-efficiency analysis is conducted using the epsilon-based measure data envelopment analysis (EBM-DEA) model for Russian cities along the Northern Sea Route (NSR). The EBM-DEA model includes five input variables: population, capital, public investment, water supply, and energy supply and four output variables: gross regional product (GRP), greenhouse gas (GHG) emissions, solid waste, and water pollution. The pattern of eco-efficiency of 28 Russian cities along the NSR is empirically analyzed based on the associated real data across the years from 2010 to 2019. The empirical results obtained from the analysis show that St. Petersburg, Provideniya, Nadym, N. Urengoy, and Noyabrsk are eco-efficient throughout the 10 years. The results also indicate that the cities along the central section of the NSR are generally more eco-efficient than those along other sections, and the cities with higher level of GRPs per capita have relatively higher eco-efficiency with a few exceptions. The study provides deeper insights into the causes of disparity in eco-efficiency, and gives further implications on eco-efficiency improvement strategies. The contributions of this study lie in the fact that new variables are taken into account and new modeling techniques are employed for the assessment of the eco-efficiency of the Russian cities.

The Arctic Northeast Passage is of growing economic and strategic importance, while its harsh and highly variable navigation environment poses substantial challenges for vessel operation. Existing assessment approaches often rely on predefined structural assumptions or sacrifice interpretability for numerical performance. This study proposes a data-driven evolutionary belief rule base model that integrates an adaptive reference value field mechanism with differential evolution-based structural optimization for rule pruning and growth. The inputs are observed vessel-operational and environmental variables from the Oden and Tian En datasets, and the output targets are three-grade expert-consensus navigation safety risk distributions aggregated from 100 independent votes per sample. Under the repeated random-split evaluations, ARVF-DEBRB achieved the lowest mean MAE on Oden and errors comparable to the leading learned baselines; on Tian En, its mean errors were comparable to those of the strongest learned baselines while lower than those of several conventional and deep baselines. Complementary chronological rolling-window evaluations over three disjoint future test windows provided future-only evidence as follows: ARVF-DEBRB ranked second in RMSE and third in MAE on Oden, and first in RMSE and second in MAE on Tian En. The rolling factorial ablation obtained the lowest mean errors for the complete configuration on both datasets. These results indicate competitive predictive performance under the reported evaluation protocols, while preserving transparent IF-THEN reasoning semantics and a compact rule structure. The data-adaptive ARVF construction and DE-based rule-structure refinement provide a methodological basis for recalibrating the framework to new operational settings.