Objectives The construction of urban thermal environment network for resource-depleted cities can contribute to urban transformation and sustainable development. It is a crucial research area to construct a rational resistance surface for the flow and transmission of thermal environments.

Methods By utilizing multi-source data such as Landsat remote sensing images, digital elevation model, point of interest, road network, and water system, this paper integrates regression analysis theory and applies machine learning method to construct urban thermal environment resistance surfaces under three scenarios, including natural scenario, human activity scenario, and the combination scenario of natural and human activity. Based on these resistance surfaces, the spatial network of urban thermal environment in Fuxin City, Liaoning Province is identified.

Results The high-temperature area accounts for 18.22% of the total area, with the core high-temperature zone covering more than 70% of the high-temperature area. In nonlinear models for different scenarios, the contribution of multiple resistance factors to the thermal environment differs significantly, with the model under the combination scenario of natural and human activity showing the highest accuracy. The length of thermal corridors under the human activity scenario and the combination scenario of natural and human activity reaches 95.86 km and 94.34 km, respectively. The areas of pinch points and obstacle points are highest under the human activity scenario and the combination scenario of natural and human activity, respectively. And a synergistic variation trend is observed between the pinch point area and the mean resistance.

Conclusions By discussing the spatial network of thermal environments under different scenarios in resource-exhausted cities, this paper provides the constructive guidance for accurately mitigating urban thermal environments.