Results 11 to 20 of about 302,283 (150)

基于反向传播神经网络的闽台ML震级偏差分析与修正

open access: yesDizhen xuebao, 2019
选取我国台湾地区2012—2018年期间的浅源地震资料,将台湾气象局与福建地震台网中心测定的ML震级进行对比分析,得出两机构测定的震级之间的差异主要是受地震震级大小、震源深度、震源地理位置等因素的影响,并采用线性回归方法对两机构测定的ML之间的模型关系进行拟合。与此同时,引入反向传播神经网络技术对两机构测定震级之间的偏差进行预测训练,构建4−9−9−9−4的五层网络模型,利用2012—2017年台湾震例作为训练集进行学习训练,2018年数据作为测试集进行预测效果分析。测试结果表明 ...
Binhua Lin   +6 more
doaj   +1 more source

区域选取对图像信息法可预测性的影响

open access: yesDizhen xuebao
图像信息(PI)法是一种基于统计物理学的地震预测方法,因其对中长期地震预测有较好的效果已在国内外广泛应用。PI方法在计算过程中对选取区域的所有网格参量进行了归一化,因此不同的区域选取会产生PI热点结果的变化。本文基于中国地震台网中心自1970年以来的全国MS≥3.0地震目录,采用5年尺度的“异常学习时段”和“预测时间窗”以及1年尺度的滑动时间步长,以南北地震带2016年以来发生的MS≥6.0地震的回溯性预测检验为例,研究了不同空间范围的选取对PI方法地震预测效能的影响 ...
Weixi Tian   +3 more
doaj   +1 more source

Hourly concentration prediction of PM2.5 based on RNN-CNN ensemble deep learning model(基于RNN-CNN 集成深度学习模型的PM2.5小时浓度预测)

open access: yesZhejiang Daxue xuebao. Lixue ban, 2019
针对目前大部分PM2.5 预测模型预测效果不稳定、泛化能力不强的现状,以记忆能力较强的循环神经网络(RNN) 和特征表达能力较强的卷积神经网络(CNN) 为基础,采取Stacking 集成策略对两者进行融合,提出了RNN-CNN 集成深度学习预测模型。该模型不仅充分利用时间轴上的前后关联信息去预测未来的浓度,而且在不同层次上将自动提取的高维时序数据通用特征用于预测,以保证预测结果的稳定性。最后,对集成之前的 RNN、CNN 和集成之后的RNN-CNN 模型,以2016 年中国大陆地区1 466 ...
HUANGJie(黄婕)   +4 more
doaj   +1 more source

基于地震活动图像的机器学习地震预测方法及其在华北地区的应用

open access: yesDizhen xuebao
本文开展了基于地震活动图像预测华北地区地震的机器学习方法研究。根据华北地区M≥5.0中强震、强震及大震的地震平均时间间隔,采用1970年以来华北地区M≥5.0中强震、强震及大震震前大量不同时窗长的ML≥3.0地震活动图像作为输入数据集,提出了基于地震活动图像预测地震的机器学习方法,并进行了震例回溯。利用本文提出的方法选取“未拓展图像数据集”和“含拓展图像数据集”对华北地区发生中强地震进行预测对比,结果显示,数据集样本量的增加有利于提高地震预测模型的精度,其中“含拓展图像数据集”预测地震的准确率可达77%;
Xiaofei Yin   +4 more
doaj   +1 more source

Subspecies taxonomy reflects social and geographic patterns of taxonomic effort in tetrapods

open access: yesConservation Biology, EarlyView.
Abstract Subspecies have been used in conservation biology to account for intraspecific patterns in genetic diversity, which is crucial to long‐term population viability. Although over 3200 subspecies are currently assessed by the International Union for Conservation of Nature Red List, their biological relevance remains controversial.
Jhonny J. M. Guedes   +3 more
wiley   +1 more source

Removal Thickness Prediction and Process‐Window Identification in Laser Cleaning of Multilayer Aerospace Coatings

open access: yesRare Metals, Volume 45, Issue 10, October 2026.
ABSTRACT Precise control of removal thickness is critical for laser cleaning of multilayer aerospace coatings particularly for selective removal without substrate exposure. However, the process response becomes highly sensitive near coating interfaces, making reliable parameter selection difficult.
Fanzhou Zeng   +6 more
wiley   +1 more source

Rapid Analysis Model of Apple Sugar Degree Using Portable Near-Infrared Spectrometer(应用便携式近红外光谱仪研究苹果糖度的快速分析模型) [PDF]

open access: yesShipin kexue jishu xuebao, 2018
In order to realize the fast lossless field detection of apple sugar by portable near infrared spectrometer, the K-S algorithm was used to divide the sample set.
LEI Ying(雷鹰)   +2 more
doaj   +1 more source

Integrating fossil data in ecological niche models to improve predictions of future habitat of Caribbean corals

open access: yesConservation Biology, Volume 40, Issue 5, October 2026.
Abstract Ecological niche models (ENMs) are used to assess the abiotic preferences of species by linking their occurrences to the environmental conditions in which they live. We developed a fossil‐informed ENM framework that integrates mid‐Holocene and modern occurrences to test niche stability and reconstruct abiotic niche characteristics for four ...
Claire. M. Williams   +3 more
wiley   +1 more source

鄂尔多斯地块北缘b值的时空特征及其地震预测效能分析

open access: yesDizhen xuebao, 2018
使用中国地震台网1970—2017年地震目录,在评估目录完整性和删除余震的基础上,使用最大似然法对鄂尔多斯地块北缘进行b值时空扫描. 扫描结果显示,鄂尔多斯地块北缘的低b值区域主要分布于阿拉善和晋冀蒙地区,低b值区域的空间分布随时间呈现一定变化. 低b值区域与中强地震存在一定的对应关系,对14次震例的回溯性检验显示,其中10次地震发生在低b值区域及其边缘.
Fan Zhang   +5 more
doaj   +1 more source

Psychometric framework for coexistence with large carnivores

open access: yesConservation Biology, Volume 40, Issue 5, October 2026.
Abstract Human–carnivore coexistence is essential for biodiversity conservation, yet measuring the attitudes and behaviors that support it remains methodologically challenging. We developed psychometric scales to assess willingness to coexist with carnivores and the underlying beliefs of this coexistence through an iterative expert elicitation process ...
Benjamin Ghasemi   +14 more
wiley   +1 more source

Home - About - Disclaimer - Privacy