Geological information prediction for shield machine using an enhanced multi-head self-attention convolution neural network with two-stage feature extraction

Due to the closed working environment of shield machines, the construction personnel cannot observe the construction geological environment, which seriously restricts the safety and efficiency of the tunneling process. In this study, we present an enhanced multi-head self-attention convolution neural network (EMSACNN) with two-stage feature extraction for geological condition prediction of shield machine. Firstly, we select 30 important parameters according to statistical analysis method and the working principle of the shield machine. Then, we delete the non-working sample data, and combine 10 consecutive data as the input of the model. Thereafter, to deeply mine and extract essential and relevant features, we build a novel model combined with the particularity of the geological type recognition task, in which an enhanced multi-head self-attention block is utilized as the first feature extractor to fully extract the correlation of geological information of adjacent working face of tunnel, and two-dimensional CNN (2dCNN) is utilized as the second feature extractor. The performance and superiority of proposed EMSACNN are verified by the actual data collected by the shield machine used in the construction of a double-track tunnel in Guangzhou, China. The results show that EMSACNN achieves at least 96% accuracy on the test sets of the two tunnels, and all the evaluation indicators of EMSACNN are much better than those of classical AI model and the model that use only the second-stage feature extractor. Therefore, the proposed EMSACNN achieves high accuracy and strong generalization for geological information prediction of shield machine, which is of great guiding significance to engineering practice.     

Biome-level relationships between vegetation indices and climate variables using time-series analysis of remotely-sensed data

ABSTRACT

Climatic factors such as rainfall and temperature play a vital role in the growth characteristics of vegetation. While the relationship between climate and vegetation growth can be accurately predicted in instances where vegetation is homogenous, this becomes complex to determine in heterogeneous vegetation environments. The aim of this paper was to study the relationship between remotely-sensed monthly vegetation indices (i.e. Normalized Difference Vegetation Index and Enhanced Vegetation Index) and climatic variables (temperature and precipitation) using time-series analysis at the biome-level. Specifically, the autoregressive distributed lag model (ARDL1 and ARDL2, corresponding respectively to one month and two month lags) and the Koyck-transformed distributed lag model were used to build regression models. All three models estimated NDVI and EVI fairly accurately in all biomes (Relative Root-Mean-Squared-Error (RMSE): 12.0–26.4%). Biomes characterized by relative homogeneity (Grassland, Savanna, Indian Ocean Coastal Belt and Forest Biomes) achieved the most accurate estimates due to the dominance of a few species. Comparisons of lag size (one month compared to two months) generally showed similarities (Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC) and log-likelihood) with quite high comparability in certain biomes – this indicates the utility of the ARDL1 and ARDL2 model, depending on the availability of appropriate data. These findings demonstrate the variation in estimation linked to the biome, and thus the validity of biome-level correlation of climatic data and vegetation indices.     

Urbanization effects on vegetation cover in major African cities during 2001-2017

Urbanization effects on vegetation cover (VC) have been analyzed in many regions. However, little attention has been paid to Africa, which has undergone rapid urbanization in recent decades. In this study, MODIS land cover and enhanced vegetation index (EVI) data were used to examine urbanization effects on VC in 59 large cities in Africa during 2001–2017. The ΔEVI (urban EVI minus rural EVI) was used to represent urbanization effects on VC. Major findings include: (1) for 59 cities averaged, annual ΔEVI averaged from 2015 to 2017 was -0.116. Negative annual ΔEVI (i.e. urban EVI lower than rural) were observed in 56 of 59 cities. (2) For 59 cities averaged, urban area increased 17.9% from 2001 (262.8 km²) to 2016 (309.8 km²). (3) Annual ΔEVI decreased significantly (p<0.05) in 44 of 59 cities for the period 2001–2017, and annual average area of urbanization effects on VC increased significantly in 40 of 59 cities. For 59 cities averaged, the percentage of urban area with significant decreasing trends of annual ΔEVI was 60.0%. Spatially, cities near the Gulf of Guinea showed more significant decreasing ΔEVI than cities in other regions. In addition, the trends and spatial distributions of urbanization effects on VC differed little by seasons. These results suggested that urbanization and its effects on VC in Africa should arouse more attentions.     

多光谱遥感技术预测矿产资源的潜能——以蒙古国欧玉陶勒盖铜金矿床为例

建议把蚀变遥感异常作为一个新的找矿参数,文中讨论了蚀变遥感异常的地质基础和光谱前提。在矿床地质学和蚀变矿物光谱参数特征的基础上,编制了一张用于蚀变遥感异常提取及对其地质解释的表格。设计了从ETM+和ASTER数据中提取羟基蚀变矿物组合信息的独特流程方案。这个方案称之为"去干扰异常主分量门限化技术",文中示以简化的流程图。ETM+数据用来研究位于欧玉陶勒盖铜金矿床东北部的汉保各德中酸性火成杂岩体岩性特征,ASTER近红外和短波红外数据用来提取欧玉陶勒盖斑岩铜金矿矿床及其近区的羟基异常,通过选择性主分量分析判断欧玉陶勒盖铜金矿矿床的矿床类型为斑岩型。已知矿区各矿体的羟基异常都十分清晰,此外在矿床西部还发现了三个新的有希望的羟基异常。此工作进一步展示出多光谱遥感技术对于金属矿床的预测具有极好的潜能。     

Late Quaternary Alluviation Along Intermittent Streams in Kakadu National Park,Northern Territory

Sedimentation along small, intermittent streams on Kapalga Research Station in Kakadu National Park may have responded to increased base levels following post-glacial flooding of the valleys of the Alligator Rivers. Alternatively, regional climate changes may have controlled sedimentation. Using thermoluminescence dating, we determined that sediments from two streams at Kapalga date from 21.5 ± 4.0 ka. On a third stream, sediments dated from 7.6 ± 1.1 ka, with younger sediments occurring downstream. We interpreted the pre-Holocene dates and the lack of evidence of upstream progradation to indicate that climate variation was more important to sedimentation than base levels. Predicted increases in rainfall variability and in the frequency of high-intensity rainfall under enhanced greenhouse conditions may cause renewed sediment mobilisation. At the outflow of one stream on to the South Alligator flood plain, we found 15 m of sandy alluvia underlying 3-5 m of estuarine muds deposited as a result of sea-level rise. These sandy alluvia dated from about 77 ka at 4 m to more than 300 ka at 19 m depth. These ages are consistent with those recorded on the Magela Creek system, 50 km to the east.     

兰州区域气象中心暴雨增强数值预报业务系统

兰州区域气象中心暴雨增强数值预报业务系统包括资料处理，质量控制、客观分析、模式预报、图形处理及显示、评分检验和作业流程控制等。由于业务系统采用了先进的并行计算技术，同时对模式结构和部分物理过程进行了改进，使模式的分辨率得到了大幅度的提高。     

基于MODIS时序数据的中国西南地区主要植被生态系统干扰动态监测及分析

在自然或人为活动的干扰下,生态系统的正常功能或多或少受到影响.生态系统干扰信息可为跟踪气候变化响应、探寻全球碳循环路径和维系生态系统功能提供重要参考.飞速发展的遥感技术为生态系统干扰信息的获取提供了新的思路,高时空分辨率的遥感影像能及时有效地监测干扰事件发生的时间和位置.本文以中国西南地区为例,选用2005-2016年...     

Blue Earth River quality monitoring using ARCHER hyperspectral data and field measurements

In past decades, remote sensing studies on water quality mapping mainly focused on lakes using medium resolution imagery. Little research utilizes hyperspectral images to assess river water quality. This study aims to assess the capability of using Airborne Real-time Cueing Hyperspectral Enhanced Reconnaissance (ARCHER) for river water quality mapping and to characterize spatial patterns of turbidity and chlorophyll in the Blue Earth River (BER) system of Minnesota. The BER was characterized by both hyperspectral imagery (HSI) and laboratory analysis of synchronously collected water quality data. The optimal bands for water quality mapping were determined using a method based on hyperspectral profiles and derivative analysis. Finally, based on the regression analysis and modelling, we mapped continuous surface water turbidity. The results revealed that the ratio of HSI band 17 to band 9 effectively determined turbidity and chlorophyll concentrations. The study also found that turbidity and chlorophyll in the river generally increases downstream.