THE REMOTE SENSING IN COAL GEOLOGY——A study on detection of coal spontanous burning by remote sensing in the coal fields in the north of China

The spontaneous burning has been lasting for thousands of years in the coal fields in the north of China. It spreads from the west (Tianshan coal field) to the east (Huolinhe coal field). Its E-W extension is up to 3750km, concentrating in N35°toN45°, its vertical depth up to 260m, and the surface temprature locally up to 270℃. Annually, it burns out 0, 250-300 million tones of coal, causing economic loss equivalent to 2-3 billion R.M.B. Yuan.It destroies coal resources and causes hazards in coal mines. In order to locate the extent and the direction in coal burning areas, the remote sensing technique has heen used and has produced an obvious benefit.

Theory of Geological Anomaly in Remote Sensing

Geological anomaly is geological body or complex body with obviously different compositions, structures or orders of genesis as compared with those in the surrounding areas. Geological anomaly, restrained by the geological factors closely associated with ore forming process, is an important clue to ore deposits. The geological anomaly serves as a geological sign to locate ore deposits. Therefore, it is very important to study how to define the characteristics of geological anomaly and further to locate the changes in these characteristics. In this paper, the authors propose the geological anomaly based on the remote sensing images and data, and expound systematically such image features as scale, size, boundary, morphology and genesis of geological anomalies. Then the authors introduce the categorization of the geological anomalies according to their geneses. The image characteristics of some types of geological anomalies, such as the underground geological anomaly, are also explained in detail. Based on the remote sensing interpretation of these geological anomalies, the authors conclude that the forecasting and exploration of ore deposits should be focused on the following three aspects: (1) the analysis of geological setting and geological anomaly; (2) the analysis of circular geological anomaly, and (3) the comprehensive forecasting of ore deposits and the research into multi source information.

Understanding the drivers of woody plant diversity in urban parks in a snow climate city of China

Urban parks are an important part of urban ecosystems and play an important role in biodiversity conservation.However,it is still unclear how park characteristics aff ect plant diversity which could hinder the conservation of urban biodiversity due to the ineff ective design of urban parks.The diversity of woody plants in 33 parks of Changchun,China,was measured with plot measurements and linked with urban park characteristics(e.g.,size and age of the park)to uncover the relationship between them.The results show that urban woody plant species were abundant,with 98 species belonging to 51 genera and 26 families in the snow climate city of Changchun.The variation in woody plant diversity was largely explained by internal patch characteristics(e.g.,size,age,shape),and external factors surrounding the park(e.g.,land use type and socioeconomic level)accounted for only 16.0%in our study.For internal patch characteristics,older urban parks with larger areas demonstrated a richer level of plant diversity and increased nonlinearly with increasing park area.The threshold size signifi cantly aff ecting plant diversity variation was approximately 30 ha.Plant diversity had positive linear relationships with the ages of urban parks,supporting the legacy eff ect.In addition,woody plant diversity nonlinearly decreased with increasing park shape index,which suggested that the plant diversity could also be increased by optimizing the park shape.Regarding the external factors surrounding parks,the spatial distribution of woody plant diversity varied greatly from the urban center to the suburbs.House prices around the park had positive linear relationships with woody plant diversity in parks,supporting the luxury eff ect.However,building and road proportions,and green space proportion had no relationship with plant diversity in parks.This study can provide a robust reference for enriching plant diversity in urban parks,thus improving the development of urban sustainable cities.

An applied research on remote sensing classification in the Loess Plateau

Dae to complex terrain of the Loess Plateau, the classification accuracy is unsatisfactory when a single supervised classification is used in die remote sensing investigation of the sloping field. Taking the loess hill and gully area of northern Shaanxi Province as a test area, a research was conducted to extract sloping field and other land use categories by applying an integrated classification. Based on an integration of supervised classification aad unsupervised classification, sampling method is remarkably unproved. The results show that the classification accuracy is satisfactory by the method and is of critical significance in obtaining up-to-date information of the sloping field, which should be helpful in the state key project of converting farmland to forest and grassland on slope land in this area. This research sought to improve the application accuracy of image classification in complex terrain areas.

Separate Analysis of Remote Sensing Information of Structures of Different Geological Periods and Quantitative Study of Corresponding Tectonic Stress Fields

The structural feature shown on a remote sensing image is a synthetic result ofcombination of the deformations produced during the entire geological history of an area.Therefore, the respective tectonic stress field of each of the different stages in the complexdeformation of an area can be reconstructed in three steps: (1) geological structures formed atdifferent times are distinguished in remote sensing image interpretation; (2) structuraldeformation fields at different stages are determined by analyzing relationships betweenmicrostructures (joints and fractures) and the related structures (folds and faults); and (3)tectonic stress fields at different stages are respectively recovered through a study of the featuresof structural deformation fields in different periods. Circular structures and related circlular and radial joints are correlated in space to con-cealed structural rises. The authors propose a new method for establishing a natural model ofthe concealed structural rises and calculating the tectonic stress field by using quantitative dataof the remote sensing information of circular structures and related linear structures.

Gravity and magnetic field characteristics and regional ore prospecting of the Yili ancient continent, West Tianshan, Xinjiang Uygur Autonomous Region, China

Gold,iron,copper,lead-zinc and other mineral exploration in West Tianshan,Xinjiang Uygur Autonomous Region,has made remarkable progress in recent years.However,due to the dispute on the tectonic division of West Tianshan,the ore-controlling factors and the regional metallogenic laws are controversial.The authors analyze regional gravity data and notice that the high-value region corresponds to the Yili ancient continent,thus the southeastern boundary of the Yili ancient continent is delineated.Comparative analysis of gravity,aeromagnetic and geologic data reveals that the Tulasu basin,where some medium to large epithermal gold deposits locate,lies above the Yili ancient continent;the Yili Carboniferous-Permian rift extends in E-W direction,numbers of copper deposits have been found in the mid-west section of the rift which lies above the Yili ancient continent,whereas few copper deposits have been discovered in the east section which is outside the Yili ancient continent.Accordingly,the Yili ancient continent may be rich in gold,copper and other metal elements;the metal-bearing hydrothermal solution moves up with the activity of magmatism,and deposits in the favorable places(the Tulasu basin and the Yili Carboniferous-Permian rift),forming numerous small and medium gold,copper deposits,as well as some large and super-large gold deposits.Therefore,the tectonic-magmatic hydrothermal zone above the Yili ancient continent should be the prospective area for epithermal gold and copper polymetallic deposits.

High-resolution remote sensing image-based extensive deformation-induced landslide displacement field monitoring method

Landslide is one of the multitudinous serious geological hazards. The key to its control and reduction lies on dynamic monitoring and early warning. The article points out the insufficiency of traditional measuring means applied for large-scale landslide monitoring and proposes the method for extensive landslide displacement field monitoring using high- resolution remote images. Matching of cognominal points is realized by using the invariant features of SIFT algorithm in image translation, rotation, zooming, and affine transformation, and through recognition and comparison of characteristics of high-resolution images in different landsliding periods. Following that, landslide displacement vector field can be made known by measuring the distances and directions between cognominal points. As evidenced by field application of the method for landslide monitoring at West Open Mine in Fushun city of China, the method has the attraction of being able to make areal measurement through satellite observation and capable of obtaining at the same time the information of large- area intensive displacement field, for facilitating automatic delimitation of extent of landslide displacement vector field and sliding mass. This can serve as a basis for making analysis of laws governing occurrence of landslide and adoption of countermeasures.

Soil Erosion Changes over the Past Five Decades in the Red Soil Region of Southern China

This paper reports the dynamic changes of soil and water loss in the red soil region of Southern China since the 1950s. The red soil region covers eight provinces: Jiangxi, Zhejiang, Fujian, Anhui, Hubei, Hunan, Guangdong and Hainan. From the 1950s to 1986, the annual rate of soil erosion increased by 3.4%. From 1986 to 1996 and from 1996 to 2000, the annual rates of soil erosion decreased by 2.0% and 0.32%, respectively. Field surveys showed that from 2000 to 2005, the area of soil and water loss decreased annually by 1.2%. This decrease was a result of large-scale erosion control activities across China. Although the eroded soil has been restored, the restoration process is very slow and full restoration will take a long time. Our report suggests that controlling soil and water loss is a challenging task, and additional measures must be taken to effectively control the soil erosion in the red soil region.

A new algorithm based on the background field for red tide monitoring in the East China Sea

Remote sensing has been proven to be an effective means of monitoring red tides. The spectral information is an important basis for establishing a model to monitor red tides. The spectral curves of red tide events are analyzed and compared with multiyear monthly averaged spectral curves based on MODIS data from July 2002 to June 2012, as well as spectral differences at the same location during red tide presence and absence. A red tide monitoring algorithm is developed based on the background field to extract the red tide information of the East China Sea （ECS）. With the application of the algorithm in the ECS, the results reveal that the developed model can effectively determine the location of red tides, with good correspondence to the results from an official bulletin. This demonstrates that the algorithm can effectively extract the red tide information.

A Remote Sensing Image Semantic Segmentation Method by Combining Deformable Convolution with Conditional Random Fields

Currently,deep convolutional neural networks have made great progress in the field of semantic segmentation.Because of the fixed convolution kernel geometry,standard convolution neural networks have been limited the ability to simulate geometric transformations.Therefore,a deformable convolution is introduced to enhance the adaptability of convolutional networks to spatial transformation.Considering that the deep convolutional neural networks cannot adequately segment the local objects at the output layer due to using the pooling layers in neural network architecture.To overcome this shortcoming,the rough prediction segmentation results of the neural network output layer will be processed by fully connected conditional random fields to improve the ability of image segmentation.The proposed method can easily be trained by end-to-end using standard backpropagation algorithms.Finally,the proposed method is tested on the ISPRS dataset.The results show that the proposed method can effectively overcome the influence of the complex structure of the segmentation object and obtain state-of-the-art accuracy on the ISPRS Vaihingen 2D semantic labeling dataset.

Improved strategy for estimating stem volume and forest biomass using moderate resolution remote sensing data and GIS

This study presents the utility of remote sensing （RS）, GIS and field observation data to estimate above ground biomass （AGB） and stem volume over tropical forest environment. Application of those data for the modeling of forest properties is site specific and highly uncertain, thus further study is encouraged. In this study we used 1460 sampling plots collected in 16 transects measuring tree diameter （DBH） and other forest properties which were useful for the biomass assessment. The study was carded out in tropical forest region in East Kalimantan, Indo- nesia. The AGB density was estimated applying an existing DBH - biomass equation. The estimate was superimposed over the modified GIS map of the study area, and the biomass density of each land cover was calculated. The RS approach was performed using a subset of sample data to develop the AGB and stem volume linear equation models. Pearson correlation statistics test was conducted using ETM bands reflectance, vegetation indices, image transform layers, Principal Component Analysis （PCA） bands, Tasseled Cap （TC）, Grey Level Co-Occurrence Matrix （GLCM） texture features and DEM data as the predictors. Two linear models were generated from the significant RS data. To analyze total biomass and stem volume of each land cover, Landsat ETM images from 2000 and 2003 were preprocessed, classified using maximum likelihood method, and filtered with the majority analysis. We found 158±16 m^3.ha^-1 of stem volume and 168±15 t.ha^-1 of AGB estimated from RS approach, whereas the field measurement and GIS estimated 157±92 m^3.ha^-1 and 167±94 t.ha^-1 of stem volume and AGB, respectively. The dynamics of biomass abundance from 2000 to 2003 were assessed from multi temporal ETM data and we found a slightly declining trend of total biomass over these periods. Remote sensing approach estimated lower biomass abundance than did the GIS and field measurement data. The earlier approach predicted 10.5 Gt and 10.3 Gt of total biomasses in 2000 and 2003, while the later estimated 11.9 Gt and 11.6 Gt of total biomasses, respectively. We found that GLCM mean texture features showed markedly strong correlations with stem volume and biomass.

基于Sentinel-2数据提取江汉平原虾稻田分布方法

以江汉平原为研究区,基于AI Earth阿里云平台提供的Sentinel-2 MSI L2数据,在实地采样样本和目视解译样本的基础上,通过分析遥感影像中虾稻田的时序变化规律,总结出区分虾稻田与其他地物类型的关键时间以及指数阈值,从而构建虾稻田提取的决策树模型,最终提取出江汉平原2022—2023年虾稻田的空间分布。最后,基于样本数据评估了该方法的精度,总体精度达93.25%,Kappa系数为0.8429,结果表明该方法具有较好的提取结果。

Redevelopment of Daqing Oil Field distributed earthquake disaster reduction system skeleton

Through investigation on the international development trend of earthquake disaster reduction system(EDRS)researches,a well finished Daqing Oilfield EDRS is introduced.Based on the PC System,redevelopment of the EDRS skeleton is well discussed,including the technical skeleton,function composition,structures of software and hardware,redevelopment languages,database,and remote linking and calling of analysis modules.Meanwhile,it is pointed out that extending and utilizing the function of remote sensing information on the basis of the current distributed EDRS skeleton will become another study direction of EDRS.

Prospecting for coal in China with remote sensing

With the rapid development of China＇s economy, coal resources are increasingly in great demand. As a result, the remaining coal reserves diminish gradually with large-scale exploitation of coal resources. Easily-found mines which used to be identified from outcrops or were buried under shallow overburden are decreasing, especially in the prosperous eastern regions of China, which experience coal shortages. Currently the main targets of coal prospecting are concealed and unidentified underground coal bodies, making it more and more difficult for coal prospecting. It is therefore important to explore coal prospecting by taking advantage of modern remote sensing and geographic information system technologies. Given a theoretical basis for coal prospecting by remote sensing, we demonstrate the methodologies and existing problems systematically by summarizing past practices of coal prospecting with remote sensing. We propose a new theory of coal prospecting with remote sensing. In uncovered areas, coal resources can be prospected for by direct interpretation. In coal beating strata of developed areas covered by thin Quaternary strata or vegetation, prospecting for coal can be carried out by indirect interpretation of geomorphology and vegetation. For deeply buried underground deposits, coal prospecting can rely on tectonic structures, interpretation and analysis of new tectonic clues and regularity of coal formation and preservation controlled by tectonic structures. By applying newly hyper-spectral, multi-polarization, multi-angle, multi-temporal and multi-resolution remote sensing data and carrying out integrated analysis of geographic attributes, ground attributes, geophysical exploration results, geochemical exploration results, geological drilling results and remote sensing data by GIS tools, coal geology resources and mineralogical regularities can be explored and coal resource information can be acquired with some confidence.

Small-scale area survey and analysis of Xinjiang's coal field fire in China

In this paper, Xinjiang＇s coal field is selected as the investigation area. Through a series of field surveys in Xinjiang, we made the small-scale area analysis of coal field fire using the ground remote sensing technique, and presented the reasonable evaluation of thermal anomaly conditions of Xinjiang＇s coal field arising from coal self-ignition fires. The results show that the method of small-scale area analysis is available for examining the extinguished actuality of coal fires and detecting fire spots. Therefore, for the selected fire-extlngulshed coal field in Xinjiang, the fire extinguishing effect was effectively analyzed by the means, and the new hidden thermal dangers were sought and diagnosed. For the coal field where the fire has not been extinguished, the utilization of this means approximately identified the severity and range of the fire area, and provided the quantitative and ground references for extinguish engineering.

Trace element geochemical characteristics of plants and their influence on the remote-sensing spectral properties in the North Jiangsu oil field

This paper presents the contents of 17 kinds of trace elements in plant leaf samples collected from 4 sections in the North Jiangsu oil field, and the dada on their visible-near infrared spectra. By comparing the results of the inner and outer oil-gas remote-sensing anomaly areas, the plant trace element composition, and the enrichment characteristics and their influence on the plant spectral properties are described. The results indicated that the plant leaves had very strong enrichment ability toward some elements such as Mg, Ca, K, Na, Fe, Al, Mn, V, Zn and Cr. The plant leaves from the oil-gas abnormal areas were enriched in trace elements of the Fe-series, but depleted in alkali and alkali-earth metal elements. The plant trace elements had a strong influence on the 'blue-shift' strength and the reflectance of visible bands. And the ratios between Fe, Co and K, Na, Cd, Cu, Ba are the effective remote-sensing oil-indicating factors of plant trace elements. plant trace element, geochemistry, remote

Performance of the Large Field of View Airborne Infrared Scanner and its application potential in land surface temperature retrieval

The Large Field of View Airborne Infrared Scanner is a newly developed multi-spectral instrument that collects images from the near-infrared to long-wave infrared channels.Its data can be used for land surface temperature(LST)retrieval and environmental monitoring.Before data application,quality assessment is an essential procedure for a new instrument.In this paper,based on the data collected by the scanner near the Yellow River in Henan Province,the geometric and radiometric qualities of the images are first evaluated.The absolute geolocation accuracy of the ten bands of the scanner is approximately 5.1 m.The ground sampling distance is found to be varied with the whisk angles of the scanner and the spatial resolution of the images.The band-to-band registration accuracy between band one and the other nine bands is approximately 0.25 m.The length and angle deformations of the ten bands are approximately 0.67%and 0.3°,respectively.The signal-to-noise ratio(SNR)and relative radiometric calibration accuracy of bands 4,9,and 10 are relatively better than those of the other bands.Secondly,the radiative transfer equation(RTE)method is used to retrieve the LST from the data of the scanner.Measurements of in situ samples are collected to evaluate the retrieved LST.Neglecting the samples with unreasonable retrieved LST,the bias and RMSE between in situ LST measured by CE312 radiometer and retrieved LST are−0.22 K and 0.94 K,and the bias and RMSE are 0.27 K and 1.59 K for the InfReC R500-D thermal imager,respectively.Overall,the images of the Large Field of View Airborne Infrared Scanner yield a relatively satisfactory accuracy for both LST retrieval and geometric and radiometric qualities.

Simulation of leaf area index and biomass at landscape scale

The method for simulating the temporal and spatial distribution patterns of leaf area index (LAI) and biomass at landscape scale using remote sensing images and surface data was discussed in this paper. The procedure was: (1) annual maximum normalized difference vegetation index (NDVI) over the landscape was calculated from TM images; (2) the relationship model between NDVI and LAI was built and annual maximum LAI over the landscape was simulated; (3) the relationship models between LAI and biomass were built and annual branch, stem, root and maximum leaf biomass over the landscape were simulated; (4) spatial distribution patterns of leaf biomass and LAI in different periods all the year round were obtained. The simulation was based on spatial analysis module GRID in ArcInfo software. The method is also a kind of scaling method from patch scale to landscape scale. A case study of Changbai Mountain Nature Reserve was dissertated. Analysis and primary validation were carried out to the simulated LAI and biomass for the major vegetation types in the Changbai Mountain in 1995.

基于改进YOLOv5的遥感图像目标检测

目前目标检测技术虽然已经趋于成熟,但是对遥感图像的检测仍存在不少挑战。针对遥感图像的背景复杂、目标尺度差异大、目标方向任意等特点造成目标检测精度低下的问题,提出一种基于改进YOLOv5的遥感图像目标检测算法。首先,构建一种联合注意力的多尺度特征增强网络,充分融合高低层特征,使特征层具有语义信息的同时包含丰富的细节信息,并在融合过程中利用设计的特征聚焦模块帮助模型选择关键特征,抑制无关信息。其次,使用感受野模块(RFB)对融合后的特征图进行更新,扩大特征图的感受野,减少特征信息损失。最后,对目标增加旋转角度,并采用圆形平滑标签将回归问题转化成分类问题,提高遥感目标定位的准确性。在用于航拍图像目标检测的大规模数据集(DOTA)上的实验结果表明,与YOLOv5算法相比,所提算法的交并比(Io U)为0.5和0.5~0.95时的平均精度均值(m AP@0.5和m AP@0.5∶0.95)分别提高了7.3和3.3个百分点,能够明显提高复杂背景下遥感图像目标的检测精度,并改善对遥感目标的漏检和误检情况。

基于Transformer的多尺度遥感语义分割网络

为了提升遥感图像语义分割效果,本文针对分割目标类间方差小、类内方差大的特点,从全局上下文信息和多尺度语义特征2个关键点提出一种基于Transformer的多尺度遥感语义分割网络(muliti-scale Transformer network,MSTNet)。其由编码器和解码器2个部分组成,编码器包含基于Transformer改进的视觉注意网络(visual attention network,VAN)主干和基于空洞空间金字塔池化(atrous spatial pyramid pooling, ASPP)结构改进的多尺度语义特征提取模块(multi-scale semantic feature extraction module, MSFEM)。解码器采用轻量级多层感知器(multi-layer perception,MLP)配合编码器设计,充分分析所提取的包含全局上下文信息和多尺度表示的语义特征。MSTNet在2个高分辨率遥感语义分割数据集ISPRS Potsdam和LoveDA上进行验证,平均交并比(mIoU)分别达到79.50%和54.12%,平均F1-score(m F1)分别达到87.46%和69.34%,实验结果验证了本文所提方法有效提升了遥感图像语义分割的效果。