Two stages power generation test of the hot dry rock exploration and production demonstration project in the Gonghe Basin,northeastern Qinghai-Tibet plateau,China

The Hot Dry Rock(HDR)is considered as a clean and renewable energy,poised to significantly contribute to the global energy decarbonization agenda.Many HDR projects worldwide have accumulated valuable experience in efficient drilling and completion,reservoir construction,and fracture simulation.In 2019,China Geological Survey(CGS)initiated a demonstration project of HDR exploration and production in the Gonghe Basin,aiming to overcome the setbacks faced by HDR projects.Over the ensuing four years,the Gonghe HDR project achieved the first power generation in 2021,followed by the second power generation test in 2022.After establishing the primary well group in the initial phase,two directional wells and one branch well were drilled.Noteworthy progress was made in successfully constructing the targeted reservoir,realizing inter-well connectivity,power generation and grid connection,implementing of the real-time micro-seismic monitoring.A closed-loop technical validation of the HDR exploration and production was completed.However,many technical challenges remain in the process of HDR industrialization,such as reservoir fracture network characterization,efficient drilling and completion,multiple fracturing treatment,continuous injection and production,as well as mitigation of induced seismicity and numerical simulation technology.

The first power generation test of hot dry rock resources exploration and production demonstration project in the Gonghe Basin,Qinghai Province,China

Hot dry rock(HDR)is a kind of clean energy with significant potential.Since the 1970s,the United States,Japan,France,Australia,and other countries have attempted to conduct several HDR development research projects to extract thermal energy by breaking through key technologies.However,up to now,the development of HDR is still in the research,development,and demonstration stage.An HDR exploration borehole(with 236℃ at a depth of 3705 m)was drilled into Triassic granite in the Gonghe Basin in northwest China in 2017.Subsequently,China Geological Survey(CGS)launched the HDR resources exploration and production demonstration project in 2019.After three years of efforts,a sequence of significant technological breakthroughs have been made,including the genetic model of deep heat sources,directional drilling and well completion in high-temperature hard rock,large-scale reservoir stimulation,reservoir characterization,and productivity evaluation,reservoir connectivity and flow circulation,efficient thermoelectric conversion,monitoring,and geological risk assessment,etc.Then the whole-process technological system for HDR exploration and production has been preliminarily established accordingly.The first power generation test was completed in November 2021.The results of this project will provide scientific support for HDR development and utilization in the future.

Classification of hyperspectral images based on a convolutional neural network and spectral sensitivity

In recent years,deep learning methods have gradually come to be used in hyperspectral imaging domains.Because of the peculiarity of hyperspectral imaging,a mass of information is contained in the spectral dimensions of hyperspectral images.Also,different ob jects on a land surface are sensitive to different ranges of wavelength.To achieve higher accuracy in classification,we propose a structure that combines spectral sensitivity with a convolutional neural network by adding spectral weights derived from predicted outcomes before the final classification layer.First,samples are divided into visible light and infrared,with a portion of the samples fed into networks during training.Then,two key parameters,unrecognized rate(δ)and wrongly recognized rate(γ),are calculated from the predicted outcome of the whole scene.Next,the spectral weight,derived from these two parameters,is calculated.Finally,the spectral weight is added and an improved structure is constructed.The improved structure not only combines the features in spatial and spectral dimensions,but also gives spectral sensitivity a primary status.Compared with inputs from the whole spectrum,the improved structure attains a nearly 2%higher prediction accuracy.When applied to public data sets,compared with the whole spectrum,on the average we achieve approximately 1%higher accuracy.

基于高光谱遥感影像的建筑物表面材质识别方法（英文）

目的:建筑物的材质信息是灾害评估和城市调查等领域的重要信息。本文旨在利用高光谱遥感影像提取地面建筑物的表面材质信息(包括材质类型和主要组成成份),并对提取方法进行对比,给出应用建议。创新点:对建筑物材料进行光谱测试,并对其高光谱响应规律进行分析,找出有诊断意义的光谱位置;基于实验和验证得出应用方法的适应性,以提高信息提取精度。方法:1.设计建筑物材质信息提取流程(图1),并对高光谱数据进行基础处理;2.对建筑物材料进行光谱测试(波长范围为350~2500 nm,图3),并完成各类建筑物的诊断性光谱分析;3.利用光谱角度法(公式(1))和光谱信息散度法(公式(2))进行材质信息提取(图5和6);4.综合分析两种方法的应用过程与控制参数和准确率的关系。结论:1.两种方法皆可提取建筑物材质信息,但在应用过程中需要进行参数的适应性调整,这是提高准确率的关键;2.在建筑物材质信息提取方面,光谱角度法的提取准确率略高于光谱散度法。