基于机器学习的目标点雷电安全风险预警方法研究     

殷启元  林蟒  杨思鹏  朱怡颖  方俏娴  杜晖  周方聪 《热带气象学报》2024,(2):217-225

收集广东地区1404组包括四个预警类型历史雷暴过程数据样本。结合目标点周围雷电发生的物理特征、雷电灾害的孕灾环境和承灾体特征的7个预报因子,利用四种机器学习算法训练得到面向目标点的雷电安全风险分级预警模型,并开展多指标对各模型进行评价分析,发现无等级模型和四级等级模型中都是随机森林算法的预警准确率最好,分别是95%和73%,而传统的卷积神经网络模型效果不佳。并选取广州塔作为目标点进行模型验证方法可行性,最终得到适应于广东雷暴特征的雷电安全风险预警分级模型。同时,根据本研究过程中可能存在不足提出下一步优化升级思路和方法。  相似文献   

Modelling of shallow landslides with machine learning algorithms     

Zhongqiang Liu  Graham Gilbert  Jose Mauricio Cepeda  Asgeir Olaf Kydland Lysdahl  Luca Piciullo  Heidi Hefre  Suzanne Lacasse 《地学前缘(英文版)》2021,12(1):385-393

This paper introduces three machine learning(ML)algorithms,the‘ensemble'Random Forest(RF),the‘ensemble'Gradient Boosted Regression Tree(GBRT)and the Multi Layer Perceptron neural network(MLP)and applies them to the spatial modelling of shallow landslides near Kvam in Norway.In the development of the ML models,a total of 11 significant landslide controlling factors were selected.The controlling factors relate to the geomorphology,geology,geo-environment and anthropogenic effects:slope angle,aspect,plan curvature,profile curvature,flow accumulation,flow direction,distance to rivers,water content,saturation,rainfall and distance to roads.It is observed that slope angle was the most significant controlling factor in the ML analyses.The performance of the three ML models was evaluated quantitatively based on the Receiver Operating Characteristic(ROC)analysis.The results show that the‘ensemble'GBRT machine learning model yielded the most promising results for the spatial prediction of shallow landslides,with a 95%probability of landslide detection and 87%prediction efficiency.  相似文献   

基于机器学习的岩体结构面剪切破坏区域预测研究     

王松挺 《地质与勘探》2024,60(2):388-406

剪切破坏区域是岩体结构面上下盘相对运动的主要接触区域,对抗剪强度具有重要影响。鉴于结构面剪切破坏区域与形貌特征的高度非线性关系,本文在分析结构面表面形貌特征及剪切机制的基础上,以粗糙度参数倾向、倾角、曲率、高差和孔径分布来描述结构面表面形貌特征。对结构面试样开展法向应力为1.0MPa的直剪试验,通过图像分割技术提取剪切破坏区域,利用多种机器学习方法构建结构面剪切破坏区域预测模型,建立结构面粗糙度参数与破坏状态之间的非线性关系,并采用训练准确率和AUC（Area Under Curve）值等指标对模型预测性能进行评估。结果表明所建立的模型中集成装袋树预测性能最好,其次是K最近邻,其训练准确率最高分别可达98.02%和97.38%,AUC值最高分别可达0.78和0.74。通过敏感性分析发现孔径分布对剪切破坏区域的影响最大。本研究对有效分析结构面的剪切破坏机理和准确评价抗剪强度具有重要意义。  相似文献   

基于深度学习的中国地面气温的多模式集成预报研究   总被引：1，自引：0，他引：1       下载免费PDF全文

智协飞  王田  季焱 《大气科学学报》2020,43(3):435-446

基于TIGGE资料中的欧洲中期天气预报中心、英国气象局、美国国家环境预报中心、韩国气象厅和日本气象厅2015年1月1日—9月30日中国及周边地区地面2 m气温24～168 h集合预报资料,利用长短期记忆神经网络(Long Short-Term Memory,LSTM)、浅层神经网络(Neural Networks,NN)、滑动训练期消除偏差集合平均(BREM)和滑动训练期多模式超级集合(SUP)方法对2015年9月5—30日26 d预报期进行集成预报试验。结果表明,BREM对5个单模式进行等权集成,预报结果易受预报效果较差模式的影响,整体预报技巧略低于单个最优模式ECMWF的预报技巧。其中在新疆南部,等权集成后的预报技巧更低。SUP的预报结果比所有单个模式预报更为准确。在144 h之前,SUP的误差明显小于ECMWF的预报误差,但随预报时效增加,误差增长幅度增大。NN对地面气温的预报效果与SUP的预报效果相当。LSTM整体预报效果最好,特别是在预报时效较长(超过72 h)时,比其他方法预报准确率明显提高。LSTM神经网络方法明显改进了我国西北、华北、东北、西南和华南大部分地区的气温预报,但在南疆部分地区误差较大。  相似文献   

基于牛顿力学积分的水下滑翔机群协同控制研究          下载免费PDF全文

王贵凯  马纯永  高占文  张胜胜  陈戈 《海洋学研究》2021,39(1):29-37

水下滑翔机是开展海洋无人移动观测的重要平台,其实际航行轨迹往往与预设路径存在较大差异,多台水下滑翔机协同观测时,难以始终保持预设的组网阵列.本研究提出一种基于牛顿力学积分的水下滑翔机群协同控制算法,根据水下滑翔机群出、入水的异步性调节水下滑翔机入水前的运动参数.基于对水下滑翔机受力分析,利用牛顿力学积分还原水下滑翔机在...  相似文献   

基于双极化SAR图像的U-Net海冰多分类模型     

黄岩  任沂斌 《海洋与湖沼》2023,54(6):1551-1563

北极多年冰在近几十年有明显的减少趋势,与北极海冰的厚度、体积和夏季最小海冰范围的减少密切相关。合成孔径雷达(synthetic aperture radar, SAR)具有全天时、全天候成像能力,基于SAR卫星影像的海冰分类对监测北极多年冰具有重要意义。基于深度学习U-Net模型,以SAR图像的双极化信息为模型输入,构建了像素级的海水、一年冰和多年冰多分类模型。与已有SAR图像海冰分类方法(支持向量机、随机森林和卷积神经网络)进行对比,基于双极化SAR图像的U-Net海冰分类模型的准确率、平均重叠度和Kappa系数,分别达到了90.73%、0.831和0.849,优于其他对比模型,分别提升了4.08%～19.04%, 0.063～0.321和0.111～0.335。此外,针对SAR图像水平-垂直极化(horizontal-vertical polarization, HV)有明显的条状热噪声和水平-水平极化(horizontal-horizontal polarization, HH)受入射角效应而亮度不均匀的特点,设计敏感性实验,研究HV噪声、入射角和灰度共生矩阵(gray leve...  相似文献   

The exemplar‐aided constructor of hyper‐rectangles learning algorithm for stream flow estimation     

Fi‐John Chang  Hui‐Fen Lin 《水文研究》2000,14(1):79-90

The exemplar‐aided constructor of hyper‐rectangles (EACH) model which simulates human intelligence by learning from experience and adjusting in time, proposed by Salzberb (1991), is presented and modified to strengthen its performance in variable stream flow extension. The modification is intended to resolve the contradiction between building hyper‐rectangles and predictive accuracy in which the number of hyper‐rectangles becomes too large if higher accuracy is required. To explore the feasibility of the modified EACH, a mathematical function is simulated by the model. It is then applied to extend the 10‐day stream flow records according to the nearby rainfall and/or stream flow gauges. The results show that the modified EACH achieves the goal of saving memory space and promoting predictive accuracy, and its performance is better than those of the original EACH and traditional methods. This research suggests that the modified EACH shows considerable promise in stream flow estimation. Copyright © 2000 John Wiley & Sons, Ltd.  相似文献   

基于深度学习的智能矿物识别方法研究     

郭艳军  周哲  林贺洵  刘小辉  陈丹丘  祝佳琪  伍峻琦 《地学前缘》2020,27(5):39-47

矿物识别在许多研究领域都有着重要作用,基于深度学习技术的智能矿物识别为这些领域带来了新的发展方向,不仅能有效节省人工成本,还能减小识别错误。针对石英、角闪石、黑云母、石榴石和橄榄石共5种矿物进行实验,提出了一种准确高效的智能矿物识别方法。实验采用图像分析常用的卷积神经网络建立模型,设计出一套基于残差神经网络的矿物识别方法。本实验独立采集了5种矿物的偏光显微图像数据集,用于模型的训练、验证和测试,并通过合理的数据增强策略来扩充训练数据集。在卷积神经网络的结构设计上,选取了ResNet-18作为框架,最终于模型测试中取得89%的准确率,成功训练出一个较为精准的矿物识别模型,实现了基于深度学习的智能矿物识别方法。  相似文献   

Physics informed machine learning: Seismic wave equation     

《地学前缘(英文版)》2020,11(6):1993-2001

Similar to many fields of sciences, recent deep learning advances have been applied extensively in geosciences for both small- and large-scale problems. However, the necessity of using large training data and the ‘black box’ nature of learning have limited them in practice and difficult to interpret. Furthermore, including the governing equations and physical facts in such methods is also another challenge, which entails either ignoring the physics or simplifying them using unrealistic data. To address such issues, physics informed machine learning methods have been developed which can integrate the governing physics law into the learning process. In this work, a 1-dimensional (1D) time-dependent seismic wave equation is considered and solved using two methods, namely Gaussian process (GP) and physics informed neural networks. We show that these meshless methods are trained by smaller amount of data and can predict the solution of the equation with even high accuracy. They are also capable of inverting any parameter involved in the governing equation such as wave velocity in our case. Results show that the GP can predict the solution of the seismic wave equation with a lower level of error, while our developed neural network is more accurate for velocity (P- and S-wave) and density inversion.  相似文献   

多分类器实例协同训练遥感图像检索   总被引：1，自引：0，他引：1  

李士进  陶剑  万定生  冯钧 《遥感学报》2010,14(3):500-512

提出一种基于多分类器协同训练的遥感图像检索方法,该方法在不同特征集上分别建立分类器,利用不同分类器的协同性自动标记未知样本,从而有效解决了小样本问题。通过与相关反馈方法进行实验比较分析,结果表明,这两种方法各有优劣,检索结果基本相当,然而多分类器协同训练方法避免了相关反馈过程中人工的多次反馈,自动化程度更高。  相似文献