A graph deep learning method for landslide displacement prediction based on global navigation satellite system positioning

The accurate prediction of displacement is crucial for landslide deformation monitoring and early warning. This study focuses on a landslide in Wenzhou Belt Highway and proposes a novel multivariate landslide displacement prediction method that relies on graph deep learning and Global Navigation Satellite System (GNSS) positioning. First model the graph structure of the monitoring system based on the engineering positions of the GNSS monitoring points and build the adjacent matrix of graph nodes. Then construct the historical and predicted time series feature matrixes using the processed temporal data including GNSS displacement, rainfall, groundwater table and soil moisture content and the graph structure. Last introduce the state-of-the-art graph deep learning GTS (Graph for Time Series) model to improve the accuracy and reliability of landslide displacement prediction which utilizes the temporal-spatial dependency of the monitoring system. This approach outperforms previous studies that only learned temporal features from a single monitoring point and maximally weighs the prediction performance and the priori graph of the monitoring system. The proposed method performs better than SVM, XGBoost, LSTM and DCRNN models in terms of RMSE (1.35 mm), MAE (1.14 mm) and MAPE (0.25) evaluation metrics, which is provided to be effective in future landslide failure early warning.     

Agnotology as a Teaching Tool: Learning Climate Science by Studying Misinformation

Abstract

Foreign travel for secondary school teachers is beneficial for enhancement of classroom curriculum. The dual nature of the U.S. Navy-National Geographic co-sponsored trips is key to enriching the global geography perspective in the classroom. A travel study to Japan provides in-service benefit for teacher peers and community groups by enhancing geography through the link between the natural and social sciences.     

“深部综合信息矿产资源预测评价”专辑特邀主编寄语

深部综合信息矿产资源预测评价研究是地球系统科学研究中最具有交叉学科性质的领域。随着地表矿、浅部矿、易识别矿的日益减少,地质找矿工作逐步向第二深度空间发展。深部矿产资源三维预测已成为当前成矿预测研究的重点领域,地质学家们经过长期的持续研究,在该领域取得了一系列重大成果与重要认识。《地球学报》集中在2020年第2期刊发15篇文章作为“深部综合信息矿产资源预测评价”专辑,专辑涵盖了三个方向的研究成果:(1)矿产资源三维预测;(2)地质调查与研究;(3)地质、地化数据处理方法等。这些工作主要涉及矿产资源预测评价的两个方面,即预测方法和成矿规律,具体包括深部构造三维重建技术方法、同位素定年及示踪在成矿规律研究中的应用以及地球化学异常信息机器学习提取方法等方面的内容。本文将简要介绍收入本专辑论文的研究工作,对深入研究和认识深部综合信息矿产资源预测评价提供一定参考价值。     

一种基于Co-Training的海洋文献分类方法

使用有监督机器学习方法进行海洋文献的分类往往存在人工标注量太大的缺点,针对这个问题,提出利用半监督机器学习中的协同训练(Co-training)方法来实现减小人工标注量的目标。该方法从2个View分别训练不同的分类器,在此基础上,根据少量有标注文档从大量无标注文档中获取有用信息,通过协同训练来提升2个分类器的性能,并训练出最终分类模型。实验结果表明,在人工标注仅2篇文献的条件下,该方法最终的分类性能十分接近需人工标注1 500多篇文献的有监督分类器。这说明将Co-training方法应用于海洋文献分类可以大大减小人工标注量,并有着较为良好的分类性能。     

基于三种机器学习方法的降水相态高分辨率格点预报模型的构建及对比分析

冬季降水相态及其转变时间的精细化客观预报对提高气象预报和服务质量具有重要的现实意义。利用京津冀地区国家级自动气象站观测资料及网格化快速更新精细集成产品,统计分析了京津冀地区复杂地形下各类降水相态温度和湿球温度平均气候概率的分布差异及不同降水相态时网格化快速更新精细集成产品中可能影响降水相态判断的特征信息。然后将地面观测天气现象资料、复杂地形下降水相态气候特征及高分辨率模式输出产品作为特征向量,分别基于梯度提升（XGBoost）、支持向量机（SVM）、深度神经网络（DNN）3种机器学习方法建立了降水相态的高分辨率客观分类模型,并对同样条件下3种机器学习方法对雨、雨夹雪和雪3种京津冀主要降水相态的预报效果进行了对比检验,进一步提升了雨夹雪复杂降水相态的客观分类预报技巧。      

Automatic extraction of road intersection points from USGS historical map series using deep convolutional neural networks

ABSTRACT

Road intersection data have been used across a range of geospatial analyses. However, many datasets dating from before the advent of GIS are only available as historical printed maps. To be analyzed by GIS software, they need to be scanned and transformed into a usable (vector-based) format. Because the number of scanned historical maps is voluminous, automated methods of digitization and transformation are needed. Frequently, these processes are based on computer vision algorithms. However, the key challenges to this are (1) the low conversion accuracy for low quality and visually complex maps, and (2) the selection of optimal parameters. In this paper, we used a region-based deep convolutional neural network-based framework (RCNN) for object detection, in order to automatically identify road intersections in historical maps of several cities in the United States of America. We found that the RCNN approach is more accurate than traditional computer vision algorithms for double-line cartographic representation of the roads, though its accuracy does not surpass all traditional methods used for single-line symbols. The results suggest that the number of errors in the outputs is sensitive to complexity and blurriness of the maps, and to the number of distinct red-green-blue (RGB) combinations within them.     

Illustrative Materials for Geography

Abstract

Studies dealing with characteristics of housing and settlement have been based almost entirely on field observation or aerial photographs. However, this report uses information from the Department of Census and Statistics of Ceylon to plot the distribution of dwellings with specific construction material characteristics for Ceylon, thus indicating an aspect of rural housing characteristics and settlement. Use of dwelling construction materials such as mud, clay, stone, brick, cadjan, and thatch can be related to physical characteristics of the area involved, availability of building materials, and level of living and culture of the inhabitants. Cost of construction material must also be considered. If similar housing data, but more complete and of greater scope, were available from the census of every nation, much could be achieved rapidly in the geography of settlement.     

Monitoring early stage invasion of exotic Spartina alterniflora using deep-learning super-resolution techniques based on multisource high-resolution satellite imagery: A case study in the Yellow River Delta,China

Over the past decades, Spartina alterniflora, one of the top exotic invasive plants in China, has expanded throughout coastal China. In the Yellow River Delta (YRD), the rapid expansion of S. alterniflora has caused serious negative ecological effects. Current studies have concentrated primarily on mapping the distribution of S. alterniflora with medium-resolution satellite imagery at the regional or landscape scale, which have a limited capability in early detection and monitoring of the invasive process at the patch scale. In this study, we proposed a framework for monitoring the early stage invasion of S. alterniflora patches in the YRD using multiyear multisource high-spatial-resolution satellite imagery with various ground sampling distances (WorldView-2, SPOT-6, GaoFen-1, GaoFen-2, and GaoFen-6 from 2012 to 2019). First, we proposed to use deep-learning-based image super-resolution models to enhance all images to submeter (0.5 m) resolution. Then, we adopted stepwise evolution analysis-based image segmentation and object-based classification rules to detect and delineate S. alterniflora patches from the super-resolved imagery. By investigating Super-Resolution Convolutional Neural Networks (SRCNN) and Fast Super-Resolution Convolutional Neural Networks (FSRCNN) and comparing these methods with the conventional bicubic interpolation method for image resolution enhancement, we concluded that FSRCNN was superior in constructing spectral and structural details from the 1 m/1.5 m/2 m resolution images to 0.5 m resolution. FSRCNN, in particular, was more effective and efficient in discerning and estimating the size of small S. alterniflora patches (<50 m²). Using our method, 76 of 83 field-measured small patches were accurately detected and the delineated S. alterniflora patch perimeters agreed well with the field-measured patch perimeters (root mean square error [RMSE] = 8.29 m, mean absolute percentage error [MAPE] = 23.46 %). The invasion process showed fast expansion from 2012 to 2015 and slow growth from 2016 to 2019. We observed that the landward limits of S. alterniflora patches were influenced by elevation and vicinity to tidal creeks.     

1980-2017年中国碳强度关键影响因子变化特征

The Chinese government ratified the Paris Climate Agreement in 2016.Accordingly,China aims to reduce carbon dioxide emissions per unit of gross domestic product(carbon intensity)to 60%–65%of 2005 levels by 2030.However,since numerous factors influence carbon intensity in China,it is critical to assess their relative importance to determine the most important factors.As traditional methods are inadequate for identifying key factors from a range of factors acting in concert,machine learning was applied in this study.Specifically,random forest algorithm,which is based on decision tree theory,was employed because it is insensitive to multicollinearity,is robust to missing and unbalanced data,and provides reasonable predictive results.We identified the key factors affecting carbon intensity in China using random forest algorithm and analyzed the evolution in the key factors from 1980 to 2017.The dominant factors affecting carbon intensity in China from 1980 to 1991 included the scale and proportion of energy-intensive industry,the proportion of fossil fuel-based energy,and technological progress.The Chinese economy developed rapidly between 1992 and 2007;during this time,the effects of the proportion of service industry,price of fossil fuel,and traditional residential consumption on carbon intensity increased.Subsequently,the Chinese economy entered a period of structural adjustment after the 2008 global financial crisis;during this period,reductions in emissions and the availability of new energy types began to have effects on carbon intensity,and the importance of residential consumption increased.The results suggest that optimizing the energy and industrial structures,promoting technological advancement,increasing green consumption,and reducing emissions are keys to decreasing carbon intensity within China in the future.These approaches will help achieve the goal of reducing carbon intensity to 60%–65%of the 2005 level by 2030.     

基于注意力机制和迁移学习的COVID-19深度学习诊断方法

目的：结合2019新型冠状病毒（COVID-19）肺炎患者肺CT影像学特征,提出一种多级空间注意力机制（ML-SAM）下的肺CT图像自动诊断模型,探讨该模型在COVID-19辅助诊断上的价值。方法：收集目前公开的COVID-19患者肺CT数据样本,在深度迁移学习框架下引入空间注意力多级聚焦策略,将数据样本、注意力机制与深度迁移学习卷积神经网络相结合,构建可在肺CT图像上自动诊断COVID-19肺炎的融合模型。结果：本文建立的融合模型对肺CT图像具有较好的分类性能,模型对COVID-19的正确识别率可达95%,同时实现了弱监督条件下肺CT图像关键特征的有效聚焦和提取。结论：本文建立的融合模型可被放射科医生或医疗保健专业人员作为COVID-19爆发期间快速、有效筛查COVID-19病例的智能辅助工具。