基于随机森林算法的煤矸石山信息提取
|
范莹琳(1996-),女,硕士,助理工程师,主要从事遥感地质研究。Email: 18811458838@163.com。 |
Copy editor: 陈庆
收稿日期: 2023-07-24
修回日期: 2023-10-24
网络出版日期: 2026-06-03
基金资助
国家重点研发计划项目“高硫矿区地下水污染过程与协同治理技术”(2022YFC3702200)
Information extraction of coal gangue mountain based on random forest algorithm
Received date: 2023-07-24
Revised date: 2023-10-24
Online published: 2026-06-03
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 . DOI: 10.6046/zrzyyg.2023231
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.
表1 分类精度评价Tab.1 Classification accuracy evaluation |
| 地物类别 | 正确分类点 总和/像元 | 重度与轻度 煤矸石错分 点/像元 | 验证点总 和/像元 | 生产者精 度/% | 用户精度/% | 错分误差/% | 漏分误差/% | 煤矸石总体 分类精度/% | Kappa系数 |
|---|---|---|---|---|---|---|---|---|---|
| 煤矸石重度堆积区 | 71 | 3 | 78 | 91.03 | 97.26 | 2.74 | 6.41 | 94.07 | 0.819 |
| 煤矸石轻度堆积区 | 52 | 1 | 57 | 91.23 | 77.61 | 22.39 | 8.77 | ||
| 煤矸石堆积区 | 127 | 4 | 135 | 94.07 | 90.71 | 9.29 | 5.93 |
| [1] |
李廉洁, 樊书祥, 王学文, 等. 高光谱成像的煤与矸石分类[J]. 光谱学与光谱分析, 2022, 42(4):1250-1256.
|
| [2] |
李嘉琪, 赵艳玲, 任河, 等. 自燃煤矸石山的遥感识别——基于Landsat8热红外波段地表温度反演数据[J]. 金属矿山, 2022(3):205-212.
|
| [3] |
侯飞, 胡召玲. 基于多尺度分割的煤矿区典型地物遥感信息提取[J]. 测绘通报, 2012(1):22-25.
|
| [4] |
徐良骥, 黄璨, 章如芹, 等. 煤矸石充填复垦地理化特性与重金属分布特征[J]. 农业工程学报, 2014, 30(5):211-219.
|
| [5] |
王小云, 牛艳霞. 煤矸石研究综述: 分类、危害及综合利用[J]. 化工矿物与加工, 2023, 52(11):18-25.
|
| [6] |
常纪文, 杜根杰, 杜建磊, 等. 我国煤矸石综合利用的现状、问题与建议[J]. 中国环保产业, 2022(8):13-17.
|
| [7] |
王红美. 煤矸石综合利用现存问题分析与解决对策研究[J]. 资源节约与环保, 2022(1):115-117.
|
| [8] |
荆青青, 张志, 王旭. 基于ASTER遥感影像的煤矸石分布信息提取方法[J]. 煤炭科学技术, 2008, 36(5):93-96.
|
| [9] |
|
| [10] |
周涛, 胡振琪, 阮梦颖, 等. 基于无人机遥感的煤矸石山植被分类[J]. 煤炭科学技术, 2023, 51(5):245-259.
|
| [11] |
|
| [12] |
王书玉, 张羽威, 于振华. 基于随机森林的洪河湿地遥感影像分类研究[J]. 测绘与空间地理信息, 2014, 37(4):83-85,93.
|
| [13] |
龙岩市人民政府. 自然地理[EB/OL].(2023-03-16)http://www.longyan.gov.cn/sqk/lygk/zrhj/201809/t20180920_1380306.htm.
Longyan City People’s Government. Physical geography[EB/OL].(2023-03-16)http://www.longyan.gov.cn/sqk/lygk/zrhj/201809/t20180920_1380306.htm.
|
| [14] |
何仲秋. 龙岩市现已探明煤炭资源状况及远景资源区预测[C]// 2007年赣皖湘苏闽五省煤炭学会联合学术交流会论文集. 厦门,2007:363-365.
|
| [15] |
福建日报. 龙岩新罗区: 煤矸石变废为宝煤台披上“新绿装”[EB/OL].(2021-08-18).http://fjnews.fjsen.com/2021-08/18/content_30813574.htm.
|
| [16] |
帅爽, 张志, 张天, 等. 结合ZY-1 02D光谱与纹理特征的干旱区植被类型遥感分类[J]. 农业工程学报, 2021, 37(21):199-207.
|
| [17] |
|
| [18] |
张炳华, 张镱锂, 谷昌军, 等. 基于随机森林与特征选择的藏东南土地覆被分类方法及精度评价[J]. 地理科学, 2023, 43(3):388-397.
|
| [19] |
方匡南, 吴见彬, 朱建平, 等. 随机森林方法研究综述[J]. 统计与信息论坛, 2011, 26(3):32-38.
|
| [20] |
柳明星, 刘建红, 马敏飞, 等. 基于GF-2 PMS影像和随机森林的甘肃临夏花椒树种植监测[J]. 自然资源遥感, 2022, 34(1):218-229.
|
| [21] |
|
| [22] |
李兰晖, 黄聪聪, 张镱锂, 等. 基于地理加权随机森林的青藏地区放牧强度时空格局模拟[J]. 地理科学, 2023, 43(3):398-410.
|
| [23] |
陈红星. 基于多源数据和随机森林算法的建筑物尺度人口估算[D]. 上海: 华东师范大学, 2021.
|
| [24] |
胡永攀, 李瑛, 姚熠凯, 等. 基于顺序向前选择算法的制冷系统故障诊断分析[J]. 能源研究与信息, 2016, 32(2):90-95.
|
| [25] |
王斌, 何丙辉, 林娜, 等. 基于随机森林特征选择的茶园遥感提取[J]. 吉林大学学报(工学版), 2022, 52(7):1719-1732.
|
/
| 〈 |
|
〉 |