Information extraction of coal gangue mountain based on random forest algorithm
FAN Yinglin1,2(), DU Song1,2(), ZHAO Yue1,2, QIU Jingzhi3, DU Xiaochuan4, ZHANG Yufeng1,2, DING Yan1,2, SONG Sitong1,2, CHE Qiaohui1,2
1. General Prospecting Institute of China National Administration of Coal Geology, Institute of Geological Deep Well Injection and Stroage, Beijing 100039, China 2. China National Administration of Coal Geology, Beijing 100038, China 3. China Mining Association, Beijing 100029, China 4. Suzhou Industry Park Mapping Co., Ltd., Suzhou 215000, China
Coal gangue mountains are key areas for the ecological restoration of coal mines. Understanding their geographical distribution holds great significance for regional environmental management. This study focused on part of Xinluo District, Longyan City, Fujian Province. Using GF-2 remote sensing images and data from the ASTER GDEM digital elevation model, this study extracted spectral, texture, and topographic features and then optimized these features using the sequential forward selection method. Subsequently, this study developed a model for surface feature classification using a random forest algorithm. Using this model, this study categorized surface features by integrating multi-source data and comprehensive feature combinations and then achieved the identification and information extraction of coal gangue mountains. The results indicate that the classification accuracy did not necessarily increase with the number of features. After feature selection, the number of features was reduced from 17 to 9, and the overall extraction accuracy of coal gangue mountains reached 94.07%, with a Kappa coefficient of 0.819. Factors playing an important role in the identification and information extraction of coal gangue deposit areas included elevation, slope, aspect, multi-spectral bands B1, B2, and B4 in the spectral characteristics, normalized vegetation index, and grayscale value of images. In contrast, texture features merely improved the accuracy of surface feature types with distinct textural variations, while producing limited effects on the information extraction of coal gangue mountains. For the study area, only the mean texture feature produced significant effects on the information extraction accuracy of coal gangue mountains. The combination of random forest and feature optimization algorithm can effectively enhance the information extraction accuracy of coal gangue mountain, efficiently integrate multi-source feature data, and accelerate model calculation, serving as a practically feasible method for the information extraction of coal gangue mountains.
范莹琳, 杜松, 赵岳, 邱景智, 杜晓川, 张玉峰, 丁晏, 宋思彤, 车巧慧. 基于随机森林算法的煤矸石山信息提取[J]. 自然资源遥感, 2025, 37(1): 54-61.
FAN Yinglin, DU Song, ZHAO Yue, QIU Jingzhi, DU Xiaochuan, ZHANG Yufeng, DING Yan, SONG Sitong, CHE Qiaohui. Information extraction of coal gangue mountain based on random forest algorithm. Remote Sensing for Natural Resources, 2025, 37(1): 54-61.
Li L J, Fan S X, Wang X W, et al. Classification method of coal and gangue based on hyperspectral imaging technology[J]. Spectro-scopy and Spectral Analysis, 2022, 42(4):1250-1256.
Li J Q, Zhao Y L, Ren H, et al. Remote sensing recognition of spontaneous combustion gangue dump:Based on Landsat8 thermal infrared band land surface temperature inversion data[J]. Metal Mine, 2022(3):205-212.
Hou F, Hu Z L. Remote sensing information extraction of typical surface objects in a coal mining area based on multiple-scale segmentation[J]. Bulletin of Surveying and Mapping, 2012(1):22-25.
Xu L J, Huang C, Zhang R Q, et al. Physical and chemical properties and distribution characteristics of heavy metals in reclaimed land filled with coal gangue[J]. Transactions of the Chinese Society of Agricultural Engineering, 2014, 30(5):211-219.
Wang X Y, Niu Y X. Review of research on coal gangue with its classification,hazards and comprehensive utilization[J]. Industrial Minerals and Processing, 2023, 52(11):18-25.
Chang J W, Du G J, Du J L, et al. Current situation of the comprehensive utilization of coal gangue in China and the related problems and recommendations[J]. China Environmental Protection Industry, 2022(8):13-17.
Wang H M. Analysis on existing problems and countermeasures of comprehensive utilization of coal gangue[J]. Resources Economi-zation and Environmental Protection, 2022(1):115-117.
Jing Q Q, Zhang Z, Wang X. Collecting method of coal refuse distribution information based on ASTER remote sensing images[J]. Coal Science and Technology, 2008, 36(5):93-96.
[9]
Nádudvari Á. Thermal mapping of self-heating zones on coal waste dumps in Upper Silesia (Poland): A case study[J]. International Journal of Coal Geology, 2014,128/129:47-54.
Zhou T, Hu Z Q, Ruan M Y, et al. Classification of coal gangue pile vegetation based on UAV remote sensing[J]. Coal Science and Technology, 2023, 51(5):245-259.
[11]
Bengio Y, Courville A, Vincent P. Representation learning:A review and new perspectives[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(8):1798-1828.
Wang S Y, Zhang Y W, Yu Z H. Classification of Honghe wetland remote sensing image based on random forests[J]. Geomatics & Spatial Information Technology, 2014, 37(4):83-85,93.
He Z Q. The situation of coal resources and the prediction of prospective resource areas have been proved in Longyan City[C]// Proceedings of the 2007 Joint Academic Exchange meeting of Coal societies of Jiangxi,Anhui,Hunan,Jiangsu and Fujian Provinces. Editorial Department of Energy and Environment,2007:363-365.
Fujian Daily. Longyan Xinluo District:Coal gangue waste into trea-sure coal platform covered with "new green"[EB/OL].(2021-08-18).http://fjnews.fjsen.com/2021-08/18/content_30813574.htm.
Shuai S, Zhang Z, Zhang T, et al. Method for classifying vegetation types in arid areas combining spectral and textural features of ZY-1 02D[J]. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(21):199-207.
[17]
Haralick R M, Shanmugam K, Dinstein I. Textural features for image classification[J]. IEEE Transactions on Systems,Man,and Cybernetics, 1973, SMC-3(6):610-621.
Zhang B H, Zhang Y L, Gu C J, et al. Land cover classification based on random forest and feature optimism in the Southeast Qinghai-Tibet Plateau[J]. Scientia Geographica Sinica, 2023, 43(3):388-397.
doi: 10.13249/j.cnki.sgs.2023.03.002
Liu M X, Liu J H, Ma M F, et al. Monitoring of Zanthoxylum bungeanum Maxim planting using GF-2 PMS images and the random forest algorithm:A case study of Linxia,Gansu Province[J]. Remote Sensing for Natural Resources, 2022, 34(1):218-229.
Du X C, Lou D B, Xu L G, et al. Extracting granite pegmatite information based on GF-2 images and the random forest algorithm[J]. Remote Sensing for Natural Resources, 2023, 35(4):53-60.doi:10.6046/zrzyyg.2022280.
Li L H, Huang C C, Zhang Y L, et al. Mapping the multi-temporal grazing intensity on the Qinghai-Tibet Plateau using geographically weighted random forest[J]. Scientia Geographica Sinica, 2023, 43(3):398-410.
doi: 10.13249/j.cnki.sgs.2023.03.003
Chen H X. Population estimation at the building level based on multi-source data and random forest algorithm[D]. Shanghai: East China Normal University, 2021.
Hu Y P, Li Y, Yao Y K, et al. Refrigeration system fault diagnosis based on sequential forward order feature selection algorithm[J]. Energy Research and Information, 2016, 32(2):90-95.
Wang B, He B H, Lin N, et al. Tea plantation remote sensing extraction based on random forest feature selection[J]. Journal of Jilin University (Engineering and Technology Edition), 2022, 52(7):1719-1732.
2025, Vol. 37 
), 杜松1,2(
