The rapid urbanization process, marked by extensive land-use changes and built-up area expansion, has considerably aggravated the Urban Heat Island (UHI) effect, presenting a grave challenge to the ecological integrity of cities and the well-being of their inhabitants. Constrained by the scarcity of urban land resources, cooling strategies relying on internal greening face practical bottlenecks, whereas the peri-urban areas possess significant yet long-overlooked cooling potential. To address the core questions—"What are the key driving factors?" and "How should the optimization range be determined?"—this study conducts a systematic investigation. Taking Kunming, China, as the study area, this study integrates multi-source remote sensing data to construct an analytical framework consisting of spectral indices, landscape metrics, and land surface temperature (LST). Eight machine learning models are employed to model the driving factors of LST in the main urban area, and the SHapley Additive exPlanations (SHAP) method is used to identify key variables. Furthermore, a progressively accumulated concentric buffer zone strategy is adopted, and SHAP together with Accumulated Local Effects (ALE) is applied to evaluate the response patterns of key features to LST across different surrounding buffer ranges, thereby identifying the optimal mitigation zone with the greatest cooling potential. The results show that: (1) spectral indices exhibit a stronger influence on LST than landscape metrics, making them the dominant driving factors; (2) the peri-urban area extending outward from the boundary of the main urban area to the equivalent radius constitutes the optimal mitigation zone that most significantly affects the thermal environment of the main urban area.

Guozhu Wang. Identifying the Optimal Mitigation Zone around the Main Urban Area via Feature Importance and Response Pattern Analysis. Academic Journal of Computing & Information Science (2026), Vol. 9, Issue 7: 1-8. https://doi.org/10.25236/AJCIS.2026.090701.

[1] Giannaros C, Agathangelidis I, Papavasileiou G, et al. The extreme heat wave of July–August 2021 in the Athens urban area (Greece): Atmospheric and human-biometeorological analysis exploiting ultra-high resolution numerical modeling and the local climate zone framework[J]. Science of The Total Environment, 2023, 857: 159300.

[2] Mayou L A, Alamdari N, Ahmadisharaf E, et al. Impacts of future climate and land use/land cover change on urban runoff using fine-scale hydrologic modeling[J]. Journal of Environmental Management, 2024, 362: 121284.

[3] Guan R, Huang W, Li Y, et al. Can land use/land cover optimization improve the environmental flow guarantee in regulated basins?[J]. Journal of Hydrology, 2023, 626: 130309.

[4] Zhang A, Xia C. Scale effect on the relationship between urban landscape patterns and land surface temperature[J]. Sustainable Cities and Society, 2024, 117: 105942.

[5] Zhu D, Zhou X, Cheng W. Water effects on urban heat islands in summer using WRF-UCM with gridded urban canopy parameters—A case study of Wuhan[J]. Building and Environment, 2022, 225: 109528.

[6] Deng X, Cao Q, Wang L, et al. Characterizing urban densification and quantifying its effects on urban thermal environments and human thermal comfort[J]. Landscape and Urban Planning, 2023, 237: 104803.

[7] Lin L, Zhao Y, Zhao J, et al. Comprehensively assessing seasonal variations in the impact of urban greenspace morphology on urban heat island effects: A multidimensional analysis[J]. Sustainable Cities and Society, 2025, 118: 106014.

[8] Qiu G Y, Yan C, Liu Y. Urban evapotranspiration and its effects on water budget and energy balance: Review and perspectives[J]. Earth-Science Reviews, 2023, 246: 104577.

[9] Gupta A, De B, Das S, et al. Thermal hazards in urban spaces: A review of climate-resilient planning and design to reduce the heat stress[J]. Urban Climate, 2025, 59: 102296.

[10] Patel S, Indraganti M, Jawarneh R N. A comprehensive systematic review: Impact of Land Use/Land Cover (LULC) on Land Surface Temperatures (LST) and outdoor thermal comfort[J]. Building and Environment, 2024, 249: 111130.

[11] Heinl M, Hammerle A, Tappeiner U, et al. Determinants of urban–rural land surface temperature differences–A landscape scale perspective[J]. Landscape and Urban Planning, 2015, 134: 33-42.

[12] Taloor A K, Parsad G, Jabeen S F, et al. Analytical study of land surface temperature for evaluation of UHI and UHS in the city of Chandigarh India[J]. Remote Sensing Applications: Society and Environment, 2024, 35: 101206.

[13] Wang C, Zhan W, Li L, et al. Urban heat islands characterized by six thermal indicators[J]. Building and Environment, 2023, 244: 110820.

[14] Cao S J, Zhang C K, Wang J Q, et al. Low-carbon design towards sustainable city development: Integrating glass space with natural greenery[J]. Science China Technological Sciences, 2024, 67(9): 2659-2674.

[15] Adilkhanova I, Santamouris M, Yun G Y. Green roofs save energy in cities and fight regional climate change[J]. Nature Cities, 2024, 1(3): 238-249.

[16] Motlagh Z K, Lotfi A, Pourmanafi S, et al. Spatial modeling of land-use change in a rapidly urbanizing landscape in central Iran: Integration of remote sensing, CA-Markov, and landscape metrics[J]. Environmental Monitoring and Assessment, 2020, 192(11): 695.

[17] Yang J, Huang X. The 30 m annual land cover dataset and its dynamics in China from 1990 to 2019[J]. Earth System Science Data, 2021, 13(8): 3907-3925.

[18] Gong P, Liu H, Zhang M, et al. Stable classification with limited sample: Transferring a 30-m resolution sample set collected in 2015 to mapping 10-m resolution global land cover in 2017[J]. Sci. Bull, 2019, 64(6): 370-373.

[19] Li Z, He W, Cheng M, et al. SinoLC-1: The first 1 m resolution national-scale land-cover map of China created with a deep learning framework and open-access data[J]. Earth system science data, 2023, 15(11): 4749-4780.

[20] Angel S, Parent J, Civco D L, et al. The dimensions of global urban expansion: Estimates and projections for all countries, 2000–2050[J]. Progress in planning, 2011, 75(2): 53-107.

[21] Yao R, Wang L, Huang X, et al. Greening in rural areas increases the surface urban heat island intensity[J]. Geophysical Research Letters, 2019, 46(4): 2204-2212.

[22] Guan S, Chen Y, Wang T, et al. Mitigating urban heat island through urban-rural transition zone landscape configuration: Evaluation based on an interpretable ensemble machine learning framework[J]. Sustainable Cities and Society, 2025, 123: 106272.