基于岩石图像深度学习的岩性自动识别与分类方法

岩石岩性的识别与分类对于地质分析极为重要,采用机器学习的方法建立识别模型进行自动分类是一条新的途径。基于Inception-v3深度卷积神经网络模型,建立了岩石图像集分析的深度学习迁移模型,运用迁移学习方法实现了岩石岩性的自动识别与分类。采用此方法对所采集的173张花岗岩图像、152张千枚岩图像和246张角砾岩图像进行了学习和识别分类研究,通过训练学习建立岩石图像深度学习迁移模型,并分别采用训练集和测试集中的岩石图像对模型进行了检验分析。对于训练集中的岩石图像,每组岩石分别用3张图像测试,三种岩石的岩性分类均正确,且分类概率值均达到90%以上,显示了模型良好的鲁棒性;对于测试集中的岩石图像,每组岩石分别采用9张图像进行识别分析,三种岩石的岩性分类均正确,并且千枚岩组图像分类概率均高于90%,但是花岗岩组2张图像和角砾岩组的1张图像分类概率值不足70%,概率值较其他岩石图像低,推测其原因是训练集中相同模式的岩石图像较少,导致模型的泛化能力减小。为了提高识别精确度,对准确率较低的岩石图像进行截取,分别取其中的3张图像加入训练集进行再训练,增加与测试图像具有相同模式的训练样本;在新的模型中,对3张图像进行二次检验,测试概率值均达到85%以上,说明在数据足够的状况下模型具有良好的学习能力。与传统的机器学习方法相比,所提出的岩石图像深度学习方法具有以下优点:第一,模型通过搜索图像像素点提取物体特征,不需要手动提取待分类物体特征;第二,对于图像像素大小,成像距离及光照要求低;第三,采用适当的训练集可获得较好的识别分类效果,并具有良好鲁棒性和泛化能力。     

A review of advances in China’s flash flood early-warning system

This paper summarizes the main flash flood early-warning systems of America, Europe, Japan, and Taiwan China and discusses their advantages and disadvantages. The latest development in flash flood prevention is also presented. China’s flash flood prevention system involves three stages. Herein, the warning methods and achievements in the first two stages are introduced in detail. Based on the worldwide experience of flash flood early-warning systems, the general research idea of the third stage is proposed from the viewpoint of requirements for flash flood prevention and construction progress of the next stage in China. Real-time dynamic warning systems can be applied to the early-warning platform at four levels (central level, provincial level, municipal level, and county level) . Through this, soil moisture, peak flow, and water level can be calculated in real-time using distributed hydrological models, and then flash flood warning indexes can be computed based on defined thresholds of runoff and water level. A compound warning index (CWI) can be applied to regions where rainfall and water level are measured by simple equipment. In this manner, flash-flood-related factors such as rainfall intensity and antecedent and cumulative rainfall depths can be determined using the CWI method. The proposed methodology for the third stage could support flash flood prevention measures in the 13th 5-Year Plan for Economic and Social Development of the People’s Republic of China (2016–2020). The research achievements will serve as a guidance for flash flood monitoring and warning as well as flood warning in medium and small rivers.     

Analysis of estimated satellite clock biases and their effects on precise point positioning

This study provides a systemic analysis to identify the biases in estimated satellite clocks and illustrates their effects in precise point positioning (PPP). First, the precise satellite clock estimation method considering pseudorange and carrier phase hardware delays is derived. Two methods for satellite clock estimation are compared, and their equivalency is discussed. The results show that apart from the well-known constant code hardware biases, the time-variant phase hardware biases are also absorbed by the estimated clocks. Also, the satellite clocks contain biases caused by modeling errors. To analyze the effects of these biases, they are grouped into initial clock biases (ICBs) and time-dependent biases (TDBs). Then, a detailed analysis of the impact of the biases on PPP-based troposphere and coordinate estimates is conducted. The experimental analysis demonstrates that TDBs affect positioning and tropospheric estimates, and their impacts are more significant in the static mode. The ICBs affect coordinate accuracy, zenith total delay mean bias, and its standard deviations only at the millimeter level for kinematic and static PPP, which is negligible. However, the ICBs affect the convergence period for both static and real kinematic PPP, and the magnitude of their impact largely depends on data quality. Note that satellites clocks are generally estimated with the P1/P2 and L1/L2 ionospheric-free combinations, and that hardware-specific parts of ICBs and TDBs cancel if users employ the same type of observables as the clock providers. Otherwise, the effects of biases cannot be ignored, especially for triple-frequency applications. Also, modeling-specific parts of ICBs and TDBs are significant in real-time clocks, which also affect user applications. Our conclusion is applicable for understanding the effects of these biases.     

Mapping fine‐scale urban housing prices by fusing remotely sensed imagery and social media data

The accurate mapping of urban housing prices at a fine scale is essential to policymaking and urban studies, such as adjusting economic factors and determining reasonable levels of residential subsidies. Previous studies focus mainly on housing price analysis at a macro scale, without fine‐scale study due to a lack of available data and effective models. By integrating a convolutional neural network for united mining (UMCNN) and random forest (RF), this study proposes an effective deep‐learning‐based framework for fusing multi‐source geospatial data, including high spatial resolution (HSR) remotely sensed imagery and several types of social media data, and maps urban housing prices at a very fine scale. With the collected housing price data from China's biggest online real estate market, we produced the spatial distribution of housing prices at a spatial resolution of 5 m in Shenzhen, China. By comparing with eight other multi‐source data mining techniques, the UMCNN obtained the highest housing price simulation accuracy (Pearson R = 0.922, OA = 85.82%). The results also demonstrated a complex spatial heterogeneity inside Shenzhen's housing price distribution. In future studies, we will work continuously on housing price policymaking and residential issues by including additional sources of spatial data.     

Drought prediction using in situ and remote sensing products with SVM over the Xiang River Basin,China

Natural Hazards - Droughts have caused many damages in many countries and might be aggravated around the world. Therefore, it is urgent to predict and monitor drought accurately. Soil moisture and...     

Destressing Mechanics Effect of Surrounding Rock Induced by Blasting Precondition at Deep Drift Development

Geotechnical and Geological Engineering - Using a detailed modeling simulation technology, a mechanics simulation model was constructed, including multiple development rounds, stress relief holes...     

Heat Islands of Small Towns and Villages in Moscow Region

Doklady Earth Sciences - Surface urban heat island, which are thermal anomalies in the field of surface temperatures, have been studied for the first time for different towns and villages of Moscow...     

New Data on the Chronostratigraphy of the Upper Pleistocene Loess–Soil Series in Southwestern Siberia

Doklady Earth Sciences - We have analyzed the modern status of the chronostratigraphic differentiation of the loess–paleosoil series in southwestern Siberia and the results of luminescence...     

浙中一次多风暴类型强对流天气成因及多普勒雷达特征

利用常规资料、区域自动站加密资料、探空资料、GFS 0.25°×0.25°逐6h的分析场数据和SB多普勒天气雷达资料对2018年5月18日发生在浙中地区的一次强对流天气过程进行分析。结果表明:此次过程产生了脉冲风暴、中等到强多单体风暴和飑线这3种风暴类型,分别出现冰雹、大范围强降水和雷雨大风等强天气。3种风暴的雷达回波在回波形态、强度、垂直结构、平均径向速度、垂直累积液态水含量VIL等特征如下:①脉冲风暴呈块状,初始回波高度在6～9km,强回波所在高度在-10℃等温线附近,强回波值达60dBz以上,VIL值出现跃升且最大值在50kg·m-2以上,冰雹出现在反射率因子核和VIL值迅速下降之后;②中等到强多单体风暴呈带状,大降水效率和"列车效应"是发生大范围强降水的主要原因,雷雨大风天气则与反射率因子核迅速下降、MARC、低层强辐散区有关;③飑线呈弓形回波形态,移速快,引起了大范围的雷雨大风天气。此次过程影响系统多,天气复杂,存在较大预报难点,在短时临近预报技术研究上有重要借鉴意义。     

浙江省涂膜柑橘贮藏期烂果风险区划及历史变化特征

为了了解浙江省涂膜柑橘贮藏期烂果风险的时空分布规律及其近60年的变化特征,利用1961—2016年常规站日气象观测资料,以涂膜柑橘贮藏腐烂阈值及各时段发生的频率为区划指标,采用距离权重反比法(IDW,Inverse Distance Weighted),开展了柑橘贮藏期烂果时间阈值风险区划,并分析了它的年代际变化。结果表明:2006年以后,浙江涂膜柑橘贮藏期烂果出现的时间越来越早,且从西南地区到东北地区柑橘贮藏期烂果出现时间逐渐推迟。最晚时间西南部地区在3月上旬,中西部地区和沿海南部地区在3月中旬,其他地区在3月下旬。21世纪10年代前6年与20世纪60年代相比较,丽水涂膜柑橘贮藏最早烂果时间从3月第1候提前到2月第4候,而最晚时间从4月第4候提前到第1候。区划结果将为橘农合理安排柑橘贮存、及时进行贩销提供参考和科学依据,从而减少对柑橘贮藏品质的影响。