深度学习网络在降水相态判识和预报中的应用

利用1996-2015年中国的高空探测资料和地面观测数据,挑选发生降水的数十万个样本将其分为降雨和降雪两类事件,抽象为二分类问题,采用深度学习网络技术构建降水相态判识模型,并用2016 2017年的数据进行测试检验,针对2018年1月下旬中国一次大范围雨雪天气过程进行个例检验,在此基础上探讨了深度学习网络在降水相态判识...     

机器学习在气象领域的应用现状与展望

机器学习是人工智能的核心,是使计算机具有智能的根本途径之一。随着以深度学习为代表的机器学习算法取得突破,人工智能呈现了加速发展的趋势,在各行业取得了广泛的应用。机器学习在计算效率、准确性、可移植性、协同性、灵活性、易用性等方面具有较大的优势,下一步将有可能改变传统的气象观测模式,加速和改善气象观测数据的处理,改善数值天气预报质量以及推进地球科学的交叉融合。为更好地推动人工智能相关技术在气象领域的应用,本文从气象观探测、数值预报、危险天气识别与预警和卫星资料处理等方面对机器学习算法的应用现状进行了整理。     

行星遥感影像目标识别与分类进展

从行星遥感海量数据中对地形地貌特征进行识别和分类,是行星科学研究中的一项重要基础工作.本文综述了自实施月球和深空探测任务以来,国际、国内采用行星影像数据进行地形地貌识别与分类技术的研究进展.首先,从月球、火星以及其他行星探测任务3个方面,对相关的探测任务和获取的影像数据进行简介.然后,在介绍通用目标识别与分类方法研究进...     

基于光谱—空间特征的ASTER影像岩性分类研究——以甘肃北山白峡尼山地区为例

遥感岩性制图是地质填图中的重要工作,基于光谱特征的岩性分类易受到色调、纹理等因素影响导致精度不佳。前人进行岩性自动分类研究多关注影像的光谱特征,而忽略空间特征,笔者等基于甘肃北山白峡尼山地区ASTER影像,将支持向量机、极限学习机两种机器学习分类方法与基于空间特征的快速漂移算法相结合进行岩性分类。结果表明支持向量机分类总体精度为89. 17%;极限学习机不但具有需调节参数少的优势,且分类精度和速度均优于支持向量机,分类总体精度达96. 70%;利用快速漂移算法提取的影像空间特征可有效减少错分区,提升岩性分类效果。研究证实将基于光谱特征的极限学习机和基于空间特征的快速漂移算法结合的岩性分类方法具有客观、高效、高精度等优势,可为后续地质填图和找矿勘查工作提供可靠数据支撑,在遥感岩性分类领域具有较高的推广价值。     

基于改进InceptionV3模型的常见矿物智能识别

以常见的16类矿物作为研究对象,收集每一类矿物约1000张图像,按比例划分为训练集、验证集和测试集,通过图像随机选取增加数据的多样性,建立矿物识别InceptionV3模型,训练7万次在测试集上获得81%的识别正确率。通过对损失函数的改进,引入Center Loss损失函数,训练40万次识别准确率提高到86%。对分类的混淆矩阵分析发现,孔雀石等外观特征明显的矿物识别正确率很高,而闪锌矿等与其他矿物容易混淆导致正确率较低。从特征图分析看出,模型很好地提取了孔雀石的放射状特征,矿物图像特征向量聚集程度很高,也说明了模型的可靠性。     

Development and future prospects of quantitative mineral assessment in China

Mineral potential assessment at the Earth’s surface has been an important research for geoscientists around the world in the past five decades. The fundamental aspects of mineral assessment at different scales can be associated with the following tasks, e.g., mineral potential mapping and estimation of mineral resources. This paper summarized the history and development in terms of theories, methods technologies and software platforms for quantitative assessment of mineral resources in China, e.g. comprehensive information methodology, geological anomaly, three-component quantitative prediction method, 5P ore-finding area, integrated information assessment method, nonlinear process modeling and fractals, three dimensional mineral potential mapping, etc. At last, to discuss the future of quantitative mineral assessment in an era of big data including platform for 3D visualization, analysis and sharing, new methods and protocols for data cleaning, information enhancement, information integration, and uncertainties and multiple explanations of multi-information.© 2019 China Geology Editorial Office.     

Learning from the South: common challenges and solutions for small-scale farming

Small-scale farmers all over the world face a number of common biophysical and socio-economic challenges. In this paper we draw on data from a workshop held in the UK in 2005, to assess whether experiences in addressing these challenges, as gained in the global South, may be used to inform solutions to similar challenges in the UK. In doing so, we contribute to a growing body of literature that seeks to challenge predominantly North–South flows of knowledge and resources. We first identify specific common challenges faced by small-scale farmers in the global North and South. We then compare the different solutions used to address these problems, drawing on the first-hand experiences of the academics, small-scale farmers, NGO staff and policymakers who participated in the workshop. Next, we examine the transferability of solutions between locations, elucidating the conditions that support and hinder such transfers. Finally, we evaluate the potential for a workshop approach to act as a 'learning space', in which the sharing of experiences can foster learning for participants and lead to new, creative ways of thinking about the process-based challenges faced by small-scale farmers     

基于改进U-Net网络的海洋中尺度涡自动检测模型

海洋中尺度涡对浮游生物的分布、能量和盐分的输送具有非常重要的影响,海洋中尺度涡的自动检测是监测、分析中尺度涡时空变化的重要基础.针对传统基于物理特征检测海洋中尺度涡的方法存在受限于人工设计参数导致精度不高的问题,本文依据海洋卫星反演的海表面高度图,提出了一种基于改进U-Net网络的海洋中尺度涡自动检测模型.该模型在海洋...     

A constructivist approach to using GIS in the New Zealand classroom

The development of the revised New Zealand Curriculum provides an excellent opportunity to investigate GIS-based learning pedagogies within the social sciences classroom. The new curriculum privileges inquiry-based activities with a more participatory approach to learning, providing students with greater autonomy in their studies. This paper emphasises the value of GIS technology for extending student learning when situated within a problem-based learning (PBL) framework. Using GIS, students undertake geographic inquiry through meaningful learning grounded in constructivist learning theory. PBL is well suited as an instructional strategy for integrating GIS as students actively learn when presented with authentic, real-world problems.