A machine learning approach for predicting computational intensity and domain decomposition in parallel geoprocessing     

Peng Yue  Fan Gao  Boyi Shangguan  Zheren Yan 《International journal of geographical information science》2020,34(11):2243-2274

ABSTRACT

High performance computing is required for fast geoprocessing of geospatial big data. Using spatial domains to represent computational intensity (CIT) and domain decomposition for parallelism are prominent strategies when designing parallel geoprocessing applications. Traditional domain decomposition is limited in evaluating the computational intensity, which often results in load imbalance and poor parallel performance. From the data science perspective, machine learning from Artificial Intelligence (AI) shows promise for better CIT evaluation. This paper proposes a machine learning approach for predicting computational intensity, followed by an optimized domain decomposition, which divides the spatial domain into balanced subdivisions based on the predicted CIT to achieve better parallel performance. The approach provides a reference framework on how various machine learning methods including feature selection and model training can be used in predicting computational intensity and optimizing parallel geoprocessing against different cases. Some comparative experiments between the approach and traditional methods were performed using the two cases, DEM generation from point clouds and spatial intersection on vector data. The results not only demonstrate the advantage of the approach, but also provide hints on how traditional GIS computation can be improved by the AI machine learning.  相似文献   

成矿预测:从二维到三维   总被引：1，自引：0，他引：1  

袁峰  张明明  李晓晖  葛粲  陆三明  李建设  周宇章  兰学毅 《岩石学报》2019,35(12):3863-3874

随着矿产资源勘探方法以及计算机科学技术的不断发展,成矿预测的理论和方法已从定性发展至定量,从二维拓展到三维。近十年来,随着深部矿产资源勘探工作的推进,三维成矿预测研究得到了迅猛发展,相关理论与方法也已逐步走向成熟。本文总结了国内外二维成矿预测研究的现状,同时对近十年来国内外学者在三维地质建模技术、三维成矿预测方法等方面的主要成果和进展做了系统总结和分析。目前,国内外多个地区已相继开展了三维成矿预测工作,并成功圈定多个深部找矿靶区,相关成果为深部找矿勘探工作提供了新的方法和方向。在此基础上,本文对未来三维成矿预测的发展趋势进行展望,相较于传统的二维成矿预测,三维成矿预测往往受限于三维预测信息的缺乏。如何更好的挖掘二维数据在深度方向的指示能力,将二维数据推演至三维环境,利用数值模拟、机器学习等方法开展数据挖掘、充分发挥已有数据的内蕴信息将在未来推动三维成矿预测理论的深入发展,提高三维成矿预测的理论方法及应用实践水平。  相似文献   

基于EEMD和ARIMA的海温预测模型研究          下载免费PDF全文

张莹  谭艳春  彭发定  廖杏杰  余昱昕 《海洋学研究》2019,37(1):9-14

类型丰富、时空分辨率高的海洋探测数据,为信号分解和机器学习算法的应用提供了可能。本文针对如何建立有效的海温预测模型这一问题,使用高时空分辨率的海表温度(SST)融合产品,引入信号处理领域的集合经验模态分解(EEMD)和机器学习领域的自回归积分滑动平均模型(ARIMA)。首先利用最适于分解自然信号的EEMD方法,将海温数据分解成多个确定频率的序列;再利用ARIMA分别对各个频率的序列进行预测,最后将各个序列的预测结果进行组合。该方法在丰富数据的支撑下,比以往直接使用海温数据所建立的预测模型精度更高,为更好地进行海温预测提供了新方法。  相似文献   

Application of PSO-LIBSVM in Recognition of Potassium Salt Deposits     

Fuqiang Yang  Kegui Chen  Changbing Huang  Yuanyuan Chen  Jin Li  Xiaolin Ma 《地球科学进展》2019,34(7):757-764

The shortage of potassium salt seriously restricts the development of China's agriculture. Increasing the exploration and development of potash will help improve the self-sufficiency of potassium in China. With rich potassium salt resources, Sichuan basin is one of the most important research areas for potash exploration and development in China. Polyhalite is an important solid potassium salt mineral in Sichuan basin, often intercalated in rock minerals such as anhydrite, rock salt and dolomite. Aiming at the problem that conventional log interpretation methods are difficult to accurately identify polyhalites, this paper proposed a new Support Vector Machine (SVM) recognition method based on Particle Swarm Optimization (PSO) to classify polyhalites in Sichuan basin. Based on particle swarm optimization and support vector machine theory, combined with logging interpretation theory, the effective data sensitive to polyhalite logging response were selected as input samples to generate training sets and test sets randomly. The Radial Basis Function (RBF) parameters were optimized by particle swarm optimization, and the classification and prediction model of polyhalite was established. Compared with mud logging results, the recognition accuracy of SVM model based on particle swarm optimization reached 97.5758%, which is obviously better than that of SVM model optimized by cross validation method in recognition accuracy and speed. The results show that the model has broad application prospects in potash exploration in Sichuan basin.  相似文献   

基于钻进状态监测的智能工况识别          下载免费PDF全文

范海鹏  吴敏  曹卫华  赖旭芝  陈略峰  陆承达 《探矿工程》2020,47(4):106-113

钻进过程状态监测旨在实时描述钻进工况，判断运行性能优劣程度进行非优追溯，及时指导司钻人员调整作业操作,保证钻进过程安全、高效、稳定开展。钻进工况是钻进系统运行状态的反映，因此开展面向状态监测技术的钻进工况识别研究具有重要的理论和应用价值。本文针对钻进工况识别问题，基于状态监测数据，建立基于支持向量机的钻进工况识别模型，对钻进工况进行识别。综合工况识别结果，对钻进效率进行评估，并对影响钻进效率的因素进行讨论，寻找提升钻进效率的手段。最后，采用钻进现场实钻数据进行仿真实验,验证所提方法的可行性和有效性。  相似文献   

一种基于M估计的Robust-ELM滑坡位移预测方法     

高彩云  高宁 《大地测量与地球动力学》2019,39(2):153-157

采用传统ELM算法进行滑坡位移预测时，其网络输出权值由最小二乘估计得出，导致ELM抗差能力较差，从而造成网络训练参数不准确。为此，将M估计与ELM相结合，提出一种基于M估计的Robust-ELM滑坡变形预测方法。该方法利用加权最小二乘方法来取代最小二乘法计算ELM输出权值，以减少滑坡监测数据中粗差对ELM预测的干扰。分别以链子崖、古树屋滑坡体为例，将Robust-ELM进行了单维、多维粗差的抵御性验证。结果表明，该方法能够有效降低粗差对预测的影响，具有良好的抗差能力。  相似文献   

基于深度残差网络的机载LiDAR点云分类     

赵传  郭海涛  卢俊  余东行  张保明 《测绘学报》2020,49(2):202-213

机载LiDAR点云的分类是利用其进行城市场景三维重建的关键步骤之一。为充分利用现有的图像领域性能较好的深度学习网络模型,提高点云分类精度,并降低训练时间和对训练样本数量的要求,本文提出一种基于深度残差网络的机载LiDAR点云分类方法。首先提取归一化高程、表面变化率、强度和归一化植被指数4种具有较高区分度的点云低层次特征;然后通过设置不同的邻域大小和视角,利用所提出的点云特征图生成策略,得到多尺度和多视角点云特征图;再将点云特征图输入到预训练的深度残差网络,提取多尺度和多视角深层次特征;最后构建并训练神经网络分类器,利用训练的模型对待分类点云进行预测,经后处理得到分类结果。利用ISPRS三维语义标记竞赛的公开标准数据集进行试验,结果表明,本文方法可有效区分建筑物、地面、车辆等8类地物,分类结果的总体精度为87.1%,可为城市场景三维重建提供可靠的信息。  相似文献   

How do machine learning techniques help in increasing accuracy of landslide susceptibility maps?     

《地学前缘(英文版)》2020,11(3):871-883

Landslides are abundant in mountainous regions.They are responsible for substantial damages and losses in those areas.The A1 Highway,which is an important road in Algeria,was sometimes constructed in mountainous and/or semi-mountainous areas.Previous studies of landslide susceptibility mapping conducted near this road using statistical and expert methods have yielded ordinary results.In this research,we are interested in how do machine learning techniques help in increasing accuracy of landslide susceptibility maps in the vicinity of the A1 Highway corridor.To do this,an important section at Ain Bouziane(NE,Algeria) is chosen as a case study to evaluate the landslide susceptibility using three different machine learning methods,namely,random forest(RF),support vector machine(SVM),and boosted regression tree(BRT).First,an inventory map and nine input factors were prepared for landslide susceptibility mapping(LSM) analyses.The three models were constructed to find the most susceptible areas to this phenomenon.The results were assessed by calculating the receiver operating characteristic(ROC) curve,the standard error(Std.error),and the confidence interval(CI) at 95%.The RF model reached the highest predictive accuracy(AUC=97.2%) comparatively to the other models.The outcomes of this research proved that the obtained machine learning models had the ability to predict future landslide locations in this important road section.In addition,their application gives an improvement of the accuracy of LSMs near the road corridor.The machine learning models may become an important prediction tool that will identify landslide alleviation actions.  相似文献   

基于离散Gabor变换的磁暴识别     

王静  贺巍  汪伟明 《地震地磁观测与研究》2020,41(4):64-69

以地磁秒数据为研究对象，通过离散Gabor变换将时域的地磁数据转换至二维时频面，提取Gabor变换谱图的均值和方差作为特征值，使用支持向量机实现地磁正常数据与磁暴干扰数据的自动分类识别。对5个地磁台的200组地磁秒数据进行计算分析，结果表明该方法对测试样本数据的识别率可达94%。  相似文献   

基于随机森林的光子计数激光雷达点云滤波     

陈博伟  庞勇  李增元  卢昊  梁晓军 《地球信息科学学报》2019,21(6):898-906

新一代星载激光雷达卫星ICESat-2首次采用了微脉冲光子计数激光雷达技术,由于单光子探测的灵敏性导致数据在大气和地表下层产生了大量噪声,因此对光子计数激光雷达点云数据实现信号和噪声的分离是开展进一步应用研究的前提和基础。本文选择美国俄勒冈州和弗吉尼亚州2个研究区,采用MATLAS数据,根据光子点云数据的特点构造了12个光子点云特征,对所构造的特征利用随机森林进行变量筛选,用机器学习方法对光子点云进行分类,并将建立好的模型推广到整个研究区。研究结果表明,本文构建的分类器分类总精度达到了96.79%,Kappa系数为0.94,平均生产者精度和用户精度分别为97.1%和96.8%。在相对弱噪声、平坦地形区域和强噪声、复杂地形区域都取得较好的分类结果。本文结果显示了基于少量样本通过机器学习的方法构建模型,可以推广到较大范围区域的光子点云分类应用中。  相似文献