Integration of Artificial Intelligence and GIS: An Application Study Based on Machine Learning Random Forest and SHAP

Feng Li

doi:10.62051/ijcsit.v8n2.02

Authors

Feng Li

DOI:

https://doi.org/10.62051/ijcsit.v8n2.02

Keywords:

Artificial Intelligence, Geographic Information Systems (GIS), Machine Learning, SHAP Model, Random Forest

Abstract

The integration of Geographic Information System (GIS) technology with artificial intelligence opens up innovative pathways for geospatial analysis. This study provides theoretical support and practical guidance for the deep integration of GIS and artificial intelligence, contributing to the advancement of geospatial analysis towards intelligence-driven approaches. With the evolution of GIS technology and the widespread adoption of artificial intelligence, The integration of Geographic Information System (GIS) technology and artificial intelligence has opened innovative paths for geographic spatial analysis. This study provides theoretical support and practical guidance for the deep integration of GIS and artificial intelligence, facilitating the move towards intelligent geographic spatial analysis. With the evolution of GIS technology and the widespread adoption of artificial intelligence, this research explores their innovative fusion in geographic spatial analysis. It focuses on the potential applications of the SHAP model in land use change prediction, environmental risk assessment, and urban planning, covering stages such as data preparation, model construction, interpretation, and spatial visualization. The results show that the SHAP model can effectively analyze the decision-making mechanisms of machine learning models and intuitively present the impact of geographic factors through spatial visualization.

Downloads

Download data is not yet available.

References

[1] He, Wenmin, Liu, Xuanyuan, Zhou, Qihai, et al. Accuracy optimization of Random Forest interpretation based on terrain data. Journal of Guangxi Normal University (Natural Science Edition), 2025.

[2] Lin, Na, Quan, Hailin, Li, Shuangtao, et al. Remote sensing extraction of abandoned farmland based on SHAP-explainable feature selection. Transactions of the Chinese Society for Agricultural Engineering, 2025.

[3] Guo, Song, Yang, Dongwei, Yin, Xiaoxing, et al. Land use classification of Poyang Lake Nanji Wetland based on feature selection. Yangtze River, 2025.

[4] Wu, Peiyu, Zhang, Xiaoli, Bi, Yuxin, et al. Study on spatiotemporal distribution and dynamic analysis of aboveground biomass of coniferous forests in Yunnan Province. Journal of Southwest Forestry University (Natural Science), 2025.

[5] Zhang, Ping, Tang, Xiaolu, Yang, Zhihan, et al. Analysis of land use change and landscape patterns in Luding County MS6.8 earthquake based on machine learning. Journal of Natural Disasters, 2025, (03).

[6] Hu, Xiangxiang, Shi, Yaya, Hu, Liangbai, et al. Loess landslide susceptibility evaluation based on the coupling model of InSAR and information content-machine learning. Northwestern Geology, 2025, (02): 159-171.

[7] Zhang, Huangfan, Xie, Zhengyi, Wen, Xiaojuan, et al. Driving mechanisms of traffic CO₂ and O₂ based on interpretable machine learning. China Environmental Science, 2025.

[8] Li, Guangyu, Ding, Guosheng, He, Shaoyao, et al. Study on the accessibility and influencing factors of rural educational facilities in Xiangxi Prefecture based on path planning data and RF-SHAP algorithm. Journal of Human Settlements in West China, 2025.

[9] Kong, Kunfeng, Chen, Yiling, Chen, Feng, et al. Multi-model decision-level fusion soil slope stability prediction model and interpretability analysis. Journal of Railway Science and Engineering, 2025.

[10] Gong, Yi, Du, Qiuyue, Zhang, Limei. Estimation of road surface adhesion coefficient based on XG-Boost SHAP dynamic information fusion. Era Car, 2025, (13): 96-98.

[11] Xie, Mei, Han, Congying, Duan, Ximing, et al. Land use classification research based on machine learning. Journal of China Agricultural Science and Technology Review, 2025.

[12] Wang, Huogen, Hu, Mengting, Liu, Xiaochun. Reconstruction and interpretability analysis of China's food security measurement based on machine learning and SHAP algorithm. Journal of China Agricultural University, 2025, (07): 264-274.