1.School of Resources and Geosciences,China University of Mining and Technology,Xuzhou,Jiangsu 221116,China
2.Key Laboratory of Coalbed Methane Resources & Reservoir Formation Process,Ministry of Education,China University of Mining and Technology,Xuzhou,Jiangsu 221116,China
Coal fires are a major geological hazard that severely constrain coal resource security and ecological environmental protection in China. To address the limitations of traditional remote sensing methods for coal fire monitoring, specifically in spatial resolution and anomaly extraction accuracy, this study takes the Laojunmiao coalfield in the eastern Junggar Basin of Xinjiang as the research area and develops an intelligent coal fire monitoring framework based on the Google Earth Engine (GEE) platform by integrating multi‑source remote sensing data. First, high‑resolution multispectral features from Sentinel‑2 and thermal infrared data from Landsat‑8 are fused to construct a multi‑dimensional input feature set composed of spectral bands and indices. An improved U‑Net network is then employed to achieve 10 m spatial downscaling reconstruction of land surface temperature (LST), significantly enhancing the spatial accuracy of thermal anomaly information. Second, an unsupervised anomaly detection method based on autoencoders is introduced to automatically identify coal fire regions without the need for manual labeling, enabling precise boundary extraction and dynamic tracking of distribution changes. Finally, by combining multi‑temporal coal fire identification results, a coal fire thermal anomaly index (CFTA) is proposed to quantitatively analyze the spatiotemporal evolution of coal fire activities and their mitigation effects from 2016 to 2025. The results demonstrate that the proposed intelligent monitoring framework can effectively capture the dynamic changes during coal fire development and remediation processes, offering high spatial resolution and sensitivity. This provides a reliable technical pathway for accurate monitoring and prevention of coal fire hazards.
为突破热红外遥感地表温度产品空间分辨率较低导致的细节表达不足问题,本文在经典U‑Net编码器‑解码器框架基础上构建改进型降尺度网络,实现将Landsat 8的30 m LST增强至10 m分辨率.模型采用对称的下采样/上采样结构以提取多尺度空间特征,并进一步引入通道注意力与空间注意力机制,以提升煤火热点区及边缘过渡带的结构恢复能力.同时,为提高训练稳定性与收敛效率,本文采用残差学习策略,即网络不直接回归高分辨率LST,而是学习初始上采样温度场与高分辨率参考LST之间的残差项.具体细节如下:
为进一步刻画煤火灾害的演化过程与治理成效,本研究在多时相提取的煤火区掩膜基础上,进一步提出了煤火区热异常指数(Coal Fire Thermal Anomaly index,CFTA),用于综合评价不同年份煤火热异常的强度与空间爆发程度.该指数综合考虑了煤火区域与研究区的温度差异,并通过归一化标准差和面积占比进行尺度统一与调节,其定义如下:
DENGJun, LIBei, WANGKai, et al. Research status and outlook on prevention and control technology of coal fire disaster in China [J]. Coal Science and Technology, 2016, 44(10): 1‑7.
WUJianjun, JIANGWeiguo, LIUXiaochen, et al. Innovative technologies for exploration,monitoring and extinction of underground coal fires [J]. Journal of China Coal Society, 2009, 34(12): 1669‑1674.
[5]
SONGZ, KUENZERC. Coal fires in China over the last decade: A comprehensive review [J]. International Journal of Coal Geology, 2014, 133: 72‑99.
[6]
LIUY, QIX Y, LUOD Y, et al. Detection and management of coal seam outcrop fire in China: A case study [J]. Scientific Reports, 2024, 14(1): 16.
WANGYunjia, YUANGang, WANGTeng, et al. Research on multi‑source remote sensing detection of concealed fire sources in coalfields [J]. Geomatics and Information Science of Wuhan University, 2022, 47(10): 1651‑1661.
CHENYunhao, LIJing, YANGBo, et al. Monitoring coal fires based on remotely sensed data and GIS technique in coalfields: A case study of Rujigou coal field in Nixia, China[J]. Journal of China University of Mining & Technology, 2005,34(2): 97‑101.
JIANGWeiguo, WUJianjun, GULei, et al. Monitoring method of underground coal fire based on night thermal infrared remote sensing technology[J]. Spectroscopy and Spectral Analysis, 2011, 31(2): 357‑361.
[15]
杜晓敏. 热红外遥感煤火探测方法及煤火变化检测[D].北京:中国矿业大学(北京),2015.
[16]
DUXiaomin. Methods for coal fire detection using thermal infrared remote sensing and change detection of coal fires[D]. Beijing: China University of Mining and Technology (Beijing), 2015.
QIUChengjin, WANGJian, LIULicong, et al. Remote sensing technology applied to fire disaster monitoring and measuring of Wuda coalfield [J]. Coal Engineering, 2012(8): 130‑133.
[19]
HUOH Y, NIZ Y, GAOC X, et al. A study of coal fire propagation with remotely sensed thermal infrared data[J]. Remote Sensing, 2015, 7(3): 3088‑3113.
[20]
ROYP, GUHAA, KUMARK V. An approach of surface coal fire detection from ASTER and Landsat‑8 thermal data: Jharia coal field, India[J]. International Journal of Applied Earth Observation and Geoinformation, 2015, 39: 120‑127.
[21]
CHENX, PENGJ H, SONGZ Y, et al. Monitoring persistent coal fire using Landsat time series data from 1986 to 2020 [J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 1‑16.
MAZijun, LIYuanyuan, WUJing, et al. Coal fire identification through satellite remote sensing considering the landscapes [J]. Coal Science and Technology, 2023, 51(Sup 2): 92‑103.
ZHUYanyin, GUHaotian, ZHENGYi, et al. Detecting coal fire areas by using Landsat 8 and Sentinel‑2 images:A case study of Jiangjun Gebi Mining Area [J]. Remote Sensing Information, 2025, 40(2): 149‑158.
[26]
LIUJ L, ZHAOF, WANGY J, et al. Advancing coal fire detection model for large‑scale areas based on RS indices and machine learning [J]. International Journal of Applied Earth Observation and Geoinformation, 2025, 140: 104587.
CHENYu, CHENGHuibin, DUPeijun, et al. A review of remote sensing detection and identification methods for underground coal fire areas[J]. Remote Sensing Technology and Application, 2025, 40(4): 816‑834.
SUYadong, HEHao, TANChongjiu, et al. Multi‑source remote sensing detection methods for hidden fire sources in coal mines[J]. Surveying and Mapping of Geology and Mineral Resources, 2025, 41(2): 6‑12.
HUAJunwei, ZHUShanyou, ZHANGGuixin. Downscaling land surface temperature based on the random forest algorithm [J]. Remote Sensing for Natural Resources, 2018, 30(1): 78‑86.
[33]
HUTENGSC, VOHLANDM. Downscaling land surface temperatures at regional scales with random forest regression [J]. Remote Sensing of Environment, 2016, 178: 127‑141.
[34]
KUENZERC, ZHANGJ, LIJ, et al. Detecting unknown coal fires: Synergy of automated coal fire risk area delineation and improved thermal anomaly extraction[J]. International Journal of Remote Sensing, 2007, 28(20): 4561‑4585.
[35]
YUB, SHEJ, LIUG X, et al. Coal fire identification and state assessment by integrating multitemporal thermal infrared and InSAR remote sensing data: A case study of Midong District, Urumqi, China[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2022, 190: 144‑164.
[36]
MUJAWDIYAR, CHATTERJEER S, KUMARD. A time series decomposition approach to detect coal fires in parts of the Gondwana coalfields of India from VIIRS data [J]. Journal of Spatial Science, 2024, 69(1): 121‑136.
[37]
SYEDT H, RIYASM J, KUENZERC. Remote sensing of coal fires in India: A review[J]. Earth‑Science Reviews, 2018, 187: 338‑355.
[38]
ZHANGL F, ZHANGL P. Artificial intelligence for remote sensing data analysis: A review of challenges and opportunities[J]. IEEE Geoscience and Remote Sensing Magazine, 2022, 10(2): 270‑294.
WANGLibing, RENYuxin, MAKun, et al. AI model for intelligent recognition of coal mine scene features through multisource data fusion[J]. Journal of China Coal Society, 2023, 48(12): 4617‑4631.
[41]
GAUTAMA, GAUTAMR S, SAXENAN. An intelligent wavelet transform‑based framework to detect subsurface fires with NOAA‑AVHRR images [J]. International Journal of Remote Sensing, 2012, 33(4): 1276‑1295.
[42]
CHENY, DINGK W, SUOZ H, et al. A multisource remote sensing identification method for coal fire zones based on a three‑layer ensemble learning model[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17: 12666‑12684.
ZHANGZhongsheng, CHENJie, LIQilong, et al. Deep contrastive learning: A survey[J]. Acta Automatica Sinica, 2023, 49(1): 15‑39.
[47]
王小娜,田金炎,李小娟,等. Google Earth Engine云平台对遥感发展的改变[J]. 遥感学报,2022,26(2):299‑309.
[48]
WANGXiaona, TIANJinyan, LIXiaojuan, et al. Benefits of Google Earth Engine in remote sensing [J]. National Remote Sensing Bulletin, 2022, 26(2): 299‑309.
ZHAOYanling, DINGBaoliang, HETingting, et al. Monitoring of subsidence water body change based on Google Earth Engine[J]. Journal of China Coal Society, 2022, 47(7): 2745‑2755.
ZHANGPengyu, MALi, SHIXinhui, et al. Analysis of slope stability in Laojunmiao opencast coal mine [J]. Journal of China University of Mining & Technology, 2025,54(3):653‑666.
DAIMeiyi, LIHengkai, LONGBeiping, et al. Quantitative identification method of landslide hazard in rare earth mining area based on multi‑source data[J]. Journal of China University of Mining & Technology, 2024,53(1):198‑210.
[55]
常贵平. 老君庙露天煤矿边坡稳定性分析[J]. 现代矿业,2018,34(2):211‑214.
[56]
CHANGGuiping. Analysis of slope stability in Laojunmiao opencast coal mine[J]. Modern Mining, 2018, 34(2): 211‑214.