期刊文献+
共找到10,055篇文章
< 1 2 250 >
每页显示 20 50 100
Hierarchical multihead self-attention for time-series-based fault diagnosis
1
作者 Chengtian Wang Hongbo Shi +1 位作者 Bing Song Yang Tao 《Chinese Journal of Chemical Engineering》 SCIE EI CAS CSCD 2024年第6期104-117,共14页
Fault diagnosis is important for maintaining the safety and effectiveness of chemical process.Considering the multivariate,nonlinear,and dynamic characteristic of chemical process,many time-series-based data-driven fa... Fault diagnosis is important for maintaining the safety and effectiveness of chemical process.Considering the multivariate,nonlinear,and dynamic characteristic of chemical process,many time-series-based data-driven fault diagnosis methods have been developed in recent years.However,the existing methods have the problem of long-term dependency and are difficult to train due to the sequential way of training.To overcome these problems,a novel fault diagnosis method based on time-series and the hierarchical multihead self-attention(HMSAN)is proposed for chemical process.First,a sliding window strategy is adopted to construct the normalized time-series dataset.Second,the HMSAN is developed to extract the time-relevant features from the time-series process data.It improves the basic self-attention model in both width and depth.With the multihead structure,the HMSAN can pay attention to different aspects of the complicated chemical process and obtain the global dynamic features.However,the multiple heads in parallel lead to redundant information,which cannot improve the diagnosis performance.With the hierarchical structure,the redundant information is reduced and the deep local time-related features are further extracted.Besides,a novel many-to-one training strategy is introduced for HMSAN to simplify the training procedure and capture the long-term dependency.Finally,the effectiveness of the proposed method is demonstrated by two chemical cases.The experimental results show that the proposed method achieves a great performance on time-series industrial data and outperforms the state-of-the-art approaches. 展开更多
关键词 Self-attention mechanism Deep learning Chemical process time-series Fault diagnosis
下载PDF
Modeling urban redevelopment:A novel approach using time-series remote sensing data and machine learning
2
作者 Li Lin Liping Di +6 位作者 Chen Zhang Liying Guo Haoteng Zhao Didarul Islam Hui Li Ziao Liu Gavin Middleton 《Geography and Sustainability》 CSCD 2024年第2期211-219,共9页
Accurate mapping and timely monitoring of urban redevelopment are pivotal for urban studies and decisionmakers to foster sustainable urban development.Traditional mapping methods heavily depend on field surveys and su... Accurate mapping and timely monitoring of urban redevelopment are pivotal for urban studies and decisionmakers to foster sustainable urban development.Traditional mapping methods heavily depend on field surveys and subjective questionnaires,yielding less objective,reliable,and timely data.Recent advancements in Geographic Information Systems(GIS)and remote-sensing technologies have improved the identification and mapping of urban redevelopment through quantitative analysis using satellite-based observations.Nonetheless,challenges persist,particularly concerning accuracy and significant temporal delays.This study introduces a novel approach to modeling urban redevelopment,leveraging machine learning algorithms and remote-sensing data.This methodology can facilitate the accurate and timely identification of urban redevelopment activities.The study’s machine learning model can analyze time-series remote-sensing data to identify spatio-temporal and spectral patterns related to urban redevelopment.The model is thoroughly evaluated,and the results indicate that it can accurately capture the time-series patterns of urban redevelopment.This research’s findings are useful for evaluating urban demographic and economic changes,informing policymaking and urban planning,and contributing to sustainable urban development.The model can also serve as a foundation for future research on early-stage urban redevelopment detection and evaluation of the causes and impacts of urban redevelopment. 展开更多
关键词 Urban redevelopment Urban sustainability Remote sensing time-series analysis Machine learning
下载PDF
Missing Value Imputation for Radar-Derived Time-Series Tracks of Aerial Targets Based on Improved Self-Attention-Based Network
3
作者 Zihao Song Yan Zhou +2 位作者 Wei Cheng Futai Liang Chenhao Zhang 《Computers, Materials & Continua》 SCIE EI 2024年第3期3349-3376,共28页
The frequent missing values in radar-derived time-series tracks of aerial targets(RTT-AT)lead to significant challenges in subsequent data-driven tasks.However,the majority of imputation research focuses on random mis... The frequent missing values in radar-derived time-series tracks of aerial targets(RTT-AT)lead to significant challenges in subsequent data-driven tasks.However,the majority of imputation research focuses on random missing(RM)that differs significantly from common missing patterns of RTT-AT.The method for solving the RM may experience performance degradation or failure when applied to RTT-AT imputation.Conventional autoregressive deep learning methods are prone to error accumulation and long-term dependency loss.In this paper,a non-autoregressive imputation model that addresses the issue of missing value imputation for two common missing patterns in RTT-AT is proposed.Our model consists of two probabilistic sparse diagonal masking self-attention(PSDMSA)units and a weight fusion unit.It learns missing values by combining the representations outputted by the two units,aiming to minimize the difference between the missing values and their actual values.The PSDMSA units effectively capture temporal dependencies and attribute correlations between time steps,improving imputation quality.The weight fusion unit automatically updates the weights of the output representations from the two units to obtain a more accurate final representation.The experimental results indicate that,despite varying missing rates in the two missing patterns,our model consistently outperforms other methods in imputation performance and exhibits a low frequency of deviations in estimates for specific missing entries.Compared to the state-of-the-art autoregressive deep learning imputation model Bidirectional Recurrent Imputation for Time Series(BRITS),our proposed model reduces mean absolute error(MAE)by 31%~50%.Additionally,the model attains a training speed that is 4 to 8 times faster when compared to both BRITS and a standard Transformer model when trained on the same dataset.Finally,the findings from the ablation experiments demonstrate that the PSDMSA,the weight fusion unit,cascade network design,and imputation loss enhance imputation performance and confirm the efficacy of our design. 展开更多
关键词 Missing value imputation time-series tracks probabilistic sparsity diagonal masking self-attention weight fusion
下载PDF
基于半经验半机理建模的冬小麦LAI反演及长势评估 被引量:2
4
作者 刘昕哲 武璐 +3 位作者 陈李金 马宇帆 李涛 吴婷婷 《农业工程学报》 EI CAS CSCD 北大核心 2024年第1期162-170,共9页
为了提高无人机遥感对冬小麦叶面积指数(leaf area index,LAI)反演模型的精度与泛化能力,该研究利用无人机搭载多光谱相机获取不同氮素处理和不同复种方式的冬小麦生长实测数据,结合PROSAIL辐射传输模型生成包含机理信息的模拟数据,基... 为了提高无人机遥感对冬小麦叶面积指数(leaf area index,LAI)反演模型的精度与泛化能力,该研究利用无人机搭载多光谱相机获取不同氮素处理和不同复种方式的冬小麦生长实测数据,结合PROSAIL辐射传输模型生成包含机理信息的模拟数据,基于不同组合方式建立了5种LAI反演混合数据集,结合多种机器学习方法,以期构建经验与机理相结合的LAI高精度反演模型。由于LAI反演受近红外波段(near infrared,NIR)反射率影响大,该研究筛选7种与NIR波段相关的植被指数提取冬小麦光谱特征,构建与混合数据集LAI的相关系数矩阵,进一步探究不同光谱特征对冬小麦LAI的影响程度。在此基础上,采用具有代表性和普适性的4种机器学习方法,即贝叶斯岭回归模型、线性回归模型、弹性网络模型和支持向量回归模型,构建不同冬小麦LAI反演模型,用以评估基于半经验半机理数据反演冬小麦LAI的可行性,进一步探索其对不同氮素水平和复种方式的冬小麦长势评估能力。结果表明:1)筛选的与NIR波段相关的植被指数与冬小麦LAI之间存在较强的相关性,其中归一化差异植被指数、增强植被指数、归一化差异红边指数、比值植被指数、红边叶绿素植被指数、土壤调节植被指数与LAI呈正相关,结构不敏感色素植被指数与LAI呈负相关;2)辐射传输模型中体现了冬小麦LAI影响太阳光线传播的机理,结果表明,与实测数据混合建立的模型,具有较强的鲁棒性和泛化能力。相比于其他3种模型,支持向量回归模型在各种数据组合下均取得了较好的LAI预测性能,在C1、C2、C3、C4这4种训练-测试组合的训练集中R^(2)依次为0.86、0.87、0.88、0.91,RMSE依次为0.47、0.45、0.45、0.41;在测试集的R^(2)依次为0.85、0.19、0.89、0.87,RMSE依次为0.45、1.31、0.49、0.50;3)使用支持向量机生成试验区LAI反演图,对4种氮素水平和2种复种方式的冬小麦长势评估,结果表明,适当的施加氮素处理能提高冬小麦LAI值,麦-豆复种方式下的冬小麦LAI值普遍高于麦-玉复种的LAI值。该研究为冬小麦LAI的反演提供了一种有效的方法,并为高效评估冬小麦长势研究提供了参考。 展开更多
关键词 无人机 遥感 辐射传输模型 植被指数 lai反演 机器学习
下载PDF
基于无人机影像的冬小麦株高提取与LAI估测模型构建
5
作者 夏积德 牟湘宁 +4 位作者 张鑫 张怡宁 梁琼丹 张青峰 王稳江 《陕西农业科学》 2024年第6期77-84,共8页
株高和叶面积指数(Leaf Area Index,LAI)反映着作物的生长发育状况。为了探究基于无人机可见光遥感提取冬小麦株高的可靠性,以及利用株高和可见光植被指数估算LAI的精度,本文获取了拔节期、抽穗期、灌浆期的无人机影像,提取了冬小麦株... 株高和叶面积指数(Leaf Area Index,LAI)反映着作物的生长发育状况。为了探究基于无人机可见光遥感提取冬小麦株高的可靠性,以及利用株高和可见光植被指数估算LAI的精度,本文获取了拔节期、抽穗期、灌浆期的无人机影像,提取了冬小麦株高与可见光植被指数,使用逐步回归、偏最小二乘、随机森林、人工神经网络四种方法建立LAI估测模型,并对株高提取及LAI估测情况进行精度评价。结果显示:(1)株高提取值Hc与实测值Hd高度拟合(R^(2)=0.894,RMSE=6.695,NRMSE=9.63%),株高提取效果好;(2)与仅用可见光植被指数相比,基于株高与可见光植被指数构建的LAI估测模型精度更高,且随机森林为最优建模方法,当其决策树个数为50时模型估测效果最好(R^(2)=0.809,RMSE=0.497,NRMSE=13.85%,RPD=2.336)。利用无人机可见光遥感方法,高效、准确、无损地实现冬小麦株高及LAI提取估测可行性较高,该研究结果可为农情遥感监测提供参考。 展开更多
关键词 无人机可见光遥感 冬小麦 株高 叶面积指数 估测模型
下载PDF
Meteorological factors, ambient air pollution, and daily hospital admissions for depressive disorder in Harbin: A time-series study 被引量:1
6
作者 Ting Hu Zhao-Yuan Xu +2 位作者 Jian Wang Yao Su Bing-Bing Guo 《World Journal of Psychiatry》 SCIE 2023年第12期1061-1078,共18页
BACKGROUND The literature has discussed the relationship between environmental factors and depressive disorders;however,the results are inconsistent in different studies and regions,as are the interaction effects betw... BACKGROUND The literature has discussed the relationship between environmental factors and depressive disorders;however,the results are inconsistent in different studies and regions,as are the interaction effects between environmental factors.We hypo-thesized that meteorological factors and ambient air pollution individually affect and interact to affect depressive disorder morbidity.AIM To investigate the effects of meteorological factors and air pollution on depressive disorders,including their lagged effects and interactions.METHODS The samples were obtained from a class 3 hospital in Harbin,China.Daily hos-pital admission data for depressive disorders from January 1,2015 to December 31,2022 were obtained.Meteorological and air pollution data were also collected during the same period.Generalized additive models with quasi-Poisson regre-ssion were used for time-series modeling to measure the non-linear and delayed effects of environmental factors.We further incorporated each pair of environ-mental factors into a bivariate response surface model to examine the interaction effects on hospital admissions for depressive disorders.RESULTS Data for 2922 d were included in the study,with no missing values.The total number of depressive admissions was 83905.Medium to high correlations existed between environmental factors.Air temperature(AT)and wind speed(WS)significantly affected the number of admissions for depression.An extremely low temperature(-29.0℃)at lag 0 caused a 53%[relative risk(RR)=1.53,95%confidence interval(CI):1.23-1.89]increase in daily hospital admissions relative to the median temperature.Extremely low WSs(0.4 m/s)at lag 7 increased the number of admissions by 58%(RR=1.58,95%CI:1.07-2.31).In contrast,atmospheric pressure and relative humidity had smaller effects.Among the six air pollutants considered in the time-series model,nitrogen dioxide(NO_(2))was the only pollutant that showed significant effects over non-cumulative,cumulative,immediate,and lagged conditions.The cumulative effect of NO_(2) at lag 7 was 0.47%(RR=1.0047,95%CI:1.0024-1.0071).Interaction effects were found between AT and the five air pollutants,atmospheric temperature and the four air pollutants,WS and sulfur dioxide.CONCLUSION Meteorological factors and the air pollutant NO_(2) affect daily hospital admissions for depressive disorders,and interactions exist between meteorological factors and ambient air pollution. 展开更多
关键词 Mental health Depressive disorder Hospital admissions Meteorological factors Air pollution time-series
下载PDF
Mapping winter wheat using phenological feature of peak before winter on the North China Plain based on time-series MODIS data 被引量:17
7
作者 TAO Jian-bin WU Wen-bin +2 位作者 ZHOU Yong WANG Yu JIANG Yan 《Journal of Integrative Agriculture》 SCIE CAS CSCD 2017年第2期348-359,共12页
By employing the unique phenological feature of winter wheat extracted from peak before winter (PBW) and the advantages of moderate resolution imaging spectroradiometer (MODIS) data with high temporal resolution a... By employing the unique phenological feature of winter wheat extracted from peak before winter (PBW) and the advantages of moderate resolution imaging spectroradiometer (MODIS) data with high temporal resolution and intermediate spatial resolution, a remote sensing-based model for mapping winter wheat on the North China Plain was built through integration with Landsat images and land-use data. First, a phenological window, PBW was drawn from time-series MODIS data. Next, feature extraction was performed for the PBW to reduce feature dimension and enhance its information. Finally, a regression model was built to model the relationship of the phenological feature and the sample data. The amount of information of the PBW was evaluated and compared with that of the main peak (MP). The relative precision of the mapping reached up to 92% in comparison to the Landsat sample data, and ranged between 87 and 96% in comparison to the statistical data. These results were sufficient to satisfy the accuracy requirements for winter wheat mapping at a large scale. Moreover, the proposed method has the ability to obtain the distribution information for winter wheat in an earlier period than previous studies. This study could throw light on the monitoring of winter wheat in China by using unique phenological feature of winter wheat. 展开更多
关键词 time-series MODIS data phenological feature peak before wintering winter wheat mapping
下载PDF
基于集合卡尔曼滤波的帽儿山森林多源LAI产品重建及融合校正方法
8
作者 包塔娜 范文义 《浙江农林大学学报》 CAS CSCD 北大核心 2024年第4期841-849,共9页
【目的】现有叶面积指数(LAI)产品大多存在分辨率低、数据异常和精度低等问题,难以满足某些应用需求。因此,本研究提出一种多源LAI数据的融合方法,以减少不同来源数据的差异并提高产品精度。【方法】以帽儿山实验林场的阔叶林和针叶林... 【目的】现有叶面积指数(LAI)产品大多存在分辨率低、数据异常和精度低等问题,难以满足某些应用需求。因此,本研究提出一种多源LAI数据的融合方法,以减少不同来源数据的差异并提高产品精度。【方法】以帽儿山实验林场的阔叶林和针叶林区域为研究区,基于2017年的MODIS、VIIRS和PROBA-V的LAI产品,利用多年LAI数据作为先验知识建立LAI背景库修正低质量数据,对3种LAI数据集进行混合像元分解的降尺度处理,基于Sentinel-2反射率产品耦合集合卡尔曼滤波(EnKF)算法、LAI动态模型和辐射传输模型进行数据同化,最后对同化后的3种LAI数据进行赋权融合,使用实测数据进行精度评价。【结果】在阔叶林,同化后的MODIS、VIIRS和PROBA-V LAI与实测数据的相关系数分别为0.59、0.56和0.62,比原始数据提升了0.57、0.52和0.57;均方根误差分别为0.37、0.31和0.14,比原始数据减小了1.23、1.69和1.06。在针叶林,同化后的MODIS、VIIRS和PROBA-V LAI与实测数据的相关系数分别为0.59、0.49和0.56,比原始数据提升了0.52、0.30和0.40;均方根误差分别为0.24、0.28和0.19,比原始数据减小了1.22、0.67和1.35。通过融合方法,阔叶林LAI和针叶林LAI的相关系数分别为0.83和0.76,比同化后数据的相关性更高;均方根误差分别为0.15和0.13,比同化后数据的误差更小。【结论】通过数据同化提升了3种LAI产品精度,融合后LAI较同化后单一LAI具有更高的精度和可靠性。 展开更多
关键词 叶面积指数(lai) MODIS VIIRS PROBA-V 重建 集合卡尔曼滤波(EnKF) 数据融合
下载PDF
Graph Construction Method for GNN-Based Multivariate Time-Series Forecasting
9
作者 Wonyong Chung Jaeuk Moon +1 位作者 Dongjun Kim Eenjun Hwang 《Computers, Materials & Continua》 SCIE EI 2023年第6期5817-5836,共20页
Multivariate time-series forecasting(MTSF)plays an important role in diverse real-world applications.To achieve better accuracy in MTSF,time-series patterns in each variable and interrelationship patterns between vari... Multivariate time-series forecasting(MTSF)plays an important role in diverse real-world applications.To achieve better accuracy in MTSF,time-series patterns in each variable and interrelationship patterns between variables should be considered together.Recently,graph neural networks(GNNs)has gained much attention as they can learn both patterns using a graph.For accurate forecasting through GNN,a well-defined graph is required.However,existing GNNs have limitations in reflecting the spectral similarity and time delay between nodes,and consider all nodes with the same weight when constructing graph.In this paper,we propose a novel graph construction method that solves aforementioned limitations.We first calculate the Fourier transform-based spectral similarity and then update this similarity to reflect the time delay.Then,we weight each node according to the number of edge connections to get the final graph and utilize it to train the GNN model.Through experiments on various datasets,we demonstrated that the proposed method enhanced the performance of GNN-based MTSF models,and the proposed forecasting model achieve of up to 18.1%predictive performance improvement over the state-of-the-art model. 展开更多
关键词 Deep learning graph neural network multivariate time-series forecasting
下载PDF
Sentinel-1 In SAR observations and time-series analysis of co-and postseismic deformation mechanisms of the 2021 Mw 5.8 Bandar Ganaveh Earthquake,Southern Iran
10
作者 Reza SABER Veysel ISIK +1 位作者 Ayse CAGLAYAN Marjan TOURANI 《Journal of Mountain Science》 SCIE CSCD 2023年第4期911-927,共17页
In the past two decades,because of the significant increase in the availability of differential interferometry from synthetic aperture radar and GPS data,spaceborne geodesy has been widely employed to determine the co... In the past two decades,because of the significant increase in the availability of differential interferometry from synthetic aperture radar and GPS data,spaceborne geodesy has been widely employed to determine the co-seismic displacement field of earthquakes.On April 18,2021,a moderate earthquake(Mw 5.8)occurred east of Bandar Ganaveh,southern Iran,followed by intensive seismic activity and aftershocks of various magnitudes.We use two-pass D-InSAR and Small Baseline Inversion techniques via the LiCSBAS suite to study the coseismic displacement and monitor the four-month post-seismic deformation of the Bandar Ganaveh earthquake,as well as constrain the fault geometry of the co-seismic faulting mechanism during the seismic sequence.Analyses show that the co-and postseismic deformation are distributed in relatively shallow depths along with an NW-SE striking and NE dipping complex reverse/thrust fault branches of the Zagros Mountain Front Fault,complying with the main trend of the Zagros structures.The average cumulative displacements were obtained from-137.5 to+113.3 mm/yr in the SW and NE blocks of the Mountain Front Fault,respectively.The received maximum uplift amount is approximately consistent with the overall orogen-normal shortening component of the Arabian-Eurasian convergence in the Zagros region.No surface ruptures were associated with the seismic source;therefore,we propose a shallow blind thrust/reverse fault(depth~10 km)connected to the deeper basal decollement fault within a complex tectonic zone,emphasizing the thin-skinned tectonics. 展开更多
关键词 Sentinel‑1 InSAR time-series Neotectonic reactivation Seismogenic fault Bandar Ganaveh earthquakes Zagros Fold-Thrust Belt Arabian-Eurasian collision
下载PDF
Generating Time-Series Data Using Generative Adversarial Networks for Mobility Demand Prediction
11
作者 Subhajit Chatterjee Yung-Cheol Byun 《Computers, Materials & Continua》 SCIE EI 2023年第3期5507-5525,共19页
The increasing penetration rate of electric kickboard vehicles has been popularized and promoted primarily because of its clean and efficient features.Electric kickboards are gradually growing in popularity in tourist... The increasing penetration rate of electric kickboard vehicles has been popularized and promoted primarily because of its clean and efficient features.Electric kickboards are gradually growing in popularity in tourist and education-centric localities.In the upcoming arrival of electric kickboard vehicles,deploying a customer rental service is essential.Due to its freefloating nature,the shared electric kickboard is a common and practical means of transportation.Relocation plans for shared electric kickboards are required to increase the quality of service,and forecasting demand for their use in a specific region is crucial.Predicting demand accurately with small data is troublesome.Extensive data is necessary for training machine learning algorithms for effective prediction.Data generation is a method for expanding the amount of data that will be further accessible for training.In this work,we proposed a model that takes time-series customers’electric kickboard demand data as input,pre-processes it,and generates synthetic data according to the original data distribution using generative adversarial networks(GAN).The electric kickboard mobility demand prediction error was reduced when we combined synthetic data with the original data.We proposed Tabular-GAN-Modified-WGAN-GP for generating synthetic data for better prediction results.We modified The Wasserstein GAN-gradient penalty(GP)with the RMSprop optimizer and then employed Spectral Normalization(SN)to improve training stability and faster convergence.Finally,we applied a regression-based blending ensemble technique that can help us to improve performance of demand prediction.We used various evaluation criteria and visual representations to compare our proposed model’s performance.Synthetic data generated by our suggested GAN model is also evaluated.The TGAN-Modified-WGAN-GP model mitigates the overfitting and mode collapse problem,and it also converges faster than previous GAN models for synthetic data creation.The presented model’s performance is compared to existing ensemble and baseline models.The experimental findings imply that combining synthetic and actual data can significantly reduce prediction error rates in the mean absolute percentage error(MAPE)of 4.476 and increase prediction accuracy. 展开更多
关键词 Machine learning generative adversarial networks electric vehicle time-series TGAN WGAN-GP blend model demand prediction regression
下载PDF
基于无人机多光谱遥感的玉米LAI监测研究
12
作者 陈盛德 陈一钢 +4 位作者 徐小杰 刘俊宇 郭健洲 胡诗云 兰玉彬 《华南农业大学学报》 CAS CSCD 北大核心 2024年第4期608-617,共10页
[目的]探究更高效估测玉米LAI的无人机多光谱遥感监测模型,实现对玉米叶面积指数(Leaf area index,LAI)的快速预测估算。[方法]以全生长周期的玉米植株为研究对象,通过多光谱遥感无人机获取玉米植株影像并实地采集玉米LAI,利用多光谱信... [目的]探究更高效估测玉米LAI的无人机多光谱遥感监测模型,实现对玉米叶面积指数(Leaf area index,LAI)的快速预测估算。[方法]以全生长周期的玉米植株为研究对象,通过多光谱遥感无人机获取玉米植株影像并实地采集玉米LAI,利用多光谱信息研究植被指数与玉米LAI之间的定量关系,并选择相关的植被指数;分别使用多元线性逐步回归、支持向量机回归算法(Support vector machine regression,SVM)、随机森林回归算法(Random forest regression,RF)和基于鲸鱼算法(Whale optimization algorithm,WOA)优化的随机森林算法(WOA-RF)构建玉米LAI预测模型,通过分析对比,选择最优预测模型。[结果]筛选出的植被指数NDVI、NDRE、EVI、CIG与LAI呈极显著相关(P<0.01),构建了多元线性回归模型、SVM模型、RF模型和WOARF模型的预测模型,R2分别为0.873 2、0.878 0、0.917 7和0.940 8,RMSE分别为0.277 5、0.236 5、0.209 0和0.128 7。[结论]基于WOA-RF的玉米LAI预测模型的预测精度能够满足玉米生产的需要,对玉米生长期间的种植管理具有指导意义。 展开更多
关键词 无人机(UAV) 遥感 多光谱 玉米 叶面积指数(lai) 监测
下载PDF
基于数值稳定型神经网络的Villain-Lai-Das Sarma方程的动力学标度行为研究
13
作者 宋天舒 夏辉 《物理学报》 SCIE EI CAS CSCD 北大核心 2024年第16期28-35,共8页
Villain-Lai-Das Sarma(VLDS)方程因其能够有效描述分子束外延生长过程而在表面生长动力学等领域中备受关注.然而,长程关联噪声驱动下的VLDS方程的标度结果尚不明确,不同解析近似方法所得的标度结果仍不自洽.在数值模拟方面,由于非线性... Villain-Lai-Das Sarma(VLDS)方程因其能够有效描述分子束外延生长过程而在表面生长动力学等领域中备受关注.然而,长程关联噪声驱动下的VLDS方程的标度结果尚不明确,不同解析近似方法所得的标度结果仍不自洽.在数值模拟方面,由于非线性项的存在,VLDS方程一直存在数值发散的问题.当前主要引入指数衰减技术替换非线性项以缓解数值发散的问题,但是最近研究表明,这种方法会导致所获得的标度指数发生歧变.因此本文基于深度神经网络来表征VLDS方程中的各个确定项,并基于数值稳定型神经网络分别对含长程时间和空间关联噪声的VLDS系统进行有效的数值模拟.结果表明,我们所构建的深度神经网络具有良好的数值计算稳定性和泛化性,可以获得不同关联噪声驱动下的VLDS方程的可靠标度指数.同时,本文还发现长程时间关联噪声驱动的VLDS系统在时间关联指数较大时呈现谷堆状的表面形貌,而空间关联噪声驱动下的表面形貌则仍然呈现自仿射分形结构. 展开更多
关键词 神经网络 分子束外延生长 Villain-lai-Das Sarma方程 动力学标度
下载PDF
融合无人机多光谱和纹理特征的马铃薯LAI估算 被引量:3
14
作者 李健 江洪 +2 位作者 罗文彬 麻霞 张雍 《华南农业大学学报》 CAS CSCD 北大核心 2023年第1期93-101,共9页
【目的】研究融合无人机遥感影像多光谱信息和纹理特征估算马铃薯Solanum tuberosum叶面积指数(Leaf area index,LAI)方法,提高马铃薯LAI反演精度。【方法】利用大疆P4M无人机采集2021年2-4月南方冬种马铃薯幼苗期、现蕾期、块茎膨大期... 【目的】研究融合无人机遥感影像多光谱信息和纹理特征估算马铃薯Solanum tuberosum叶面积指数(Leaf area index,LAI)方法,提高马铃薯LAI反演精度。【方法】利用大疆P4M无人机采集2021年2-4月南方冬种马铃薯幼苗期、现蕾期、块茎膨大期多光谱影像,用LAI-2000冠层分析仪实测LAI数据。提取影像光谱、纹理等信息,分析植被指数、纹理特征与LAI的相关性,基于R^(2)_(adj)的全子集分析优选特征变量。采用主成分分析,融合光谱和纹理特征,用PCA-MLR(Principal component analysis-multiple linear regression)模型估算马铃薯LAI。【结果】从幼苗期到块茎膨大期,PCA-MLR估算模型优于T-MLR(Texture multiple linear regression)和VIMLR(Vegetation index multiple linear regression)模型,R2分别为0.73、0.59和0.66。【结论】本研究提出一种估算马铃薯LAI的PCA-MLR方法,为马铃薯的长势监测和田间管理提供数据支持。 展开更多
关键词 无人机 遥感影像 lai 多光谱 纹理特征 马铃薯
下载PDF
基于PROSAIL混合反演模型的MODIS LAI产品改进及评估
15
作者 赫晓慧 张乐涵 +2 位作者 乔梦佳 田智慧 周广胜 《生态学报》 CAS CSCD 北大核心 2023年第22期9328-9341,共14页
叶面积指数(Leaf Area Index,LAI)是定量陆地生态系统中光合作用、呼吸作用、蒸腾、碳和养分循环等过程中物质与能量交换的重要结构参数。目前大、中尺度的气候和生态水文建模使用的LAI产品主要来源于中分辨率成像光谱仪(MODIS),但由于... 叶面积指数(Leaf Area Index,LAI)是定量陆地生态系统中光合作用、呼吸作用、蒸腾、碳和养分循环等过程中物质与能量交换的重要结构参数。目前大、中尺度的气候和生态水文建模使用的LAI产品主要来源于中分辨率成像光谱仪(MODIS),但由于其反演过程中的不确定性因素导致MODIS LAI产品在部分地区存在质量问题。以青海省复杂植被地区为研究区域,基于实地考察与采样验证了区域内MODIS LAI所存在的质量问题分布,并揭示了不确定因素的影响。与此同时,提出了一种基于PROSAIL模型与深度神经网络(DNN)的混合建模技术,针对MODIS LAI生成机制中地表分类数据、地表反射率数据和反演算法的不确定性进行改进,并基于青海省大范围实测LAI数据评估了改进前后产品的准确度,实测数据的验证结果发现:改进模型的LAI准确度(RMSE=0.48,R^(2)=0.64)显著高于MODIS LAI(RMSE=0.71,R^(2)=0.56),预测结果与实测结果之间的偏差显著减少;区域尺度上,柴达木荒漠植被低覆盖典型区域、三江源高寒草甸中覆盖典型区域与青海湖牧场草地高覆盖典型区域的RMSE分别提高了0.19、0.10、0.54,改进方法有效解决了MODIS LAI产品中高覆盖植被饱和效应导致的高估以及低覆盖植被未检索导致低估的质量问题,改进结果分布连续,更符合真实植被状况。基于以上研究,充分证明了研究方法对MODIS LAI产品的改进具有可靠性,能够在缺少实测样本数据的情况下有效提高MODIS LAI的质量,为全球植被环境监测与生态建模提供重要的数据支持。 展开更多
关键词 MODIS lai PROSAIL模型 叶面积指数 深度神经网络
下载PDF
Temperature and Daily Mortality in Shanghai:A Time-series Study 被引量:21
16
作者 HAI-DONGKAN JIANJIA BING-HENGCHEN 《Biomedical and Environmental Sciences》 SCIE CAS CSCD 2003年第2期133-139,共7页
To investigate the association between temperature and daily mortality in Shanghai from June 1, 2000 to December 31, 2001. Methods Time-series approach was used to estimate the effect of temperature on daily tota... To investigate the association between temperature and daily mortality in Shanghai from June 1, 2000 to December 31, 2001. Methods Time-series approach was used to estimate the effect of temperature on daily total and cause-specific mortality. We fitted generalized additive Poisson regression using non-parametric smooth functions to control for long-term time trend, season and other variables. We also controlled for day of the week. Results A gently sloping V-like relationship between total mortality and temperature was found, with an optimum temperature (e.g. temperature with lowest mortality risk) value of 26.7癈 in Shanghai. For temperatures above the optimum value, total mortality increased by 0.73% for each degree Celsius increase; while for temperature below the optimum value, total mortality decreased by 1.21% for each degree Celsius increase. Conclusions Our findings indicate that temperature has an effect on daily mortality in Shanghai, and the time-series approach is a useful tool for studying the temperature-mortality association. 展开更多
关键词 TEMPERATURE MORTALITY time-series
下载PDF
Review of the SBAS InSAR Time-series algorithms, applications, and challenges 被引量:13
17
作者 Shaowei Li Wenbin Xu Zhiwei Li 《Geodesy and Geodynamics》 CSCD 2022年第2期114-126,共13页
In the past 30 years,the small baseline subset(SBAS)InSAR time-series technique has emerged as an essential tool for measuring slow surface displacement and estimating geophysical parameters.Because of its ability to ... In the past 30 years,the small baseline subset(SBAS)InSAR time-series technique has emerged as an essential tool for measuring slow surface displacement and estimating geophysical parameters.Because of its ability to monitor large-scale deformation with millimeter accuracy,the SBAS method has been widely used in various geodetic fields,such as ground subsidence,landslides,and seismic activity.The obtained long-term time-series cumulative deformation is vital for studying the deformation mecha-nism.This article reviews the algorithms,applications,and challenges of the SBAS method.First,we recall the fundamental principle and analyze the shortcomings of the traditional SBAS algorithm,which provides a basic framework for the following improved time series methods.Second,we classify the current improved SBAS techniques from different perspectives:solving the ill-posed equation,increasing the density of high-coherence points,improving the accuracy of monitoring deformation and measuring the multi-dimensional deformation.Third,we summarize the application of the SBAS method in monitoring ground subsidence,permafrost degradation,glacier movement,volcanic activity,landslides,and seismic activity.Finally,we discuss the difficulties faced by the SBAS method and explore its future development direction. 展开更多
关键词 INSAR Small baseline subset time-series InSAR DEFORMATION
下载PDF
晚籼杂交稻LAI、SPAD和LTR的动态变化及对产量性状的影响
18
作者 廖亦龙 柳武革 +8 位作者 王丰 刘迪林 孔乐 李金华 付崇允 曾学勤 朱满山 马晓智 霍兴 《华南农业大学学报》 CAS CSCD 北大核心 2023年第6期936-948,共13页
【目的】研究晚籼杂交稻单株穗数、叶面积指数(Leaf area index,LAI)、叶片SPAD和透光率(Light transmittance rate,LTR)等指标的动态变化,进一步明确它们之间的相互关系及其对杂交稻产量和产量性状的影响,为杂交水稻育种和生产实践提... 【目的】研究晚籼杂交稻单株穗数、叶面积指数(Leaf area index,LAI)、叶片SPAD和透光率(Light transmittance rate,LTR)等指标的动态变化,进一步明确它们之间的相互关系及其对杂交稻产量和产量性状的影响,为杂交水稻育种和生产实践提供理论指导。【方法】以华南地区广泛应用的5个三系不育系和6个恢复系配置杂交组合,于2021年晚季在广州进行27个杂交组合的随机区组试验,分析杂种光合参数的动态变化规律以及不同发育阶段各光合参数对产量及产量性状的影响及相关性。【结果】杂种茎蘖数自移栽后直线上升,于移栽后25 d达分蘖高峰,始穗期(移栽后60 d)进入平稳期;杂种LAI自移栽后快速上升,于幼穗分化后期(移栽后50 d)后达最高值,之后进入回落期;叶片SPAD自移栽后逐步走低,生长发育前期组合间叶片SPAD差异不明显,进入灌浆结实期后存在显著(P<0.05)或极显著(P<0.01)差异;杂种群体LTR随发育进程呈逐步下降趋势。相关分析表明:分蘖盛期前(移栽后10~20 d)以及始穗期至灌浆期(移栽后60~76 d)的单株茎蘖数与杂种产量呈极显著正相关,增产作用主要通过增加单株实粒数实现;分蘖盛期至幼穗分化后期(移栽后25~50 d)的茎蘖数过多,增加了杂种群体的无效分蘖,造成杂种结实率下降和产量显著降低;分蘖前期(移栽后20 d)和始穗期(移栽后60 d)杂种LAI与产量呈极显著和显著正相关,相关系数分别为0.296和0.255,增产作用主要通过提高单株实粒数和千粒质量实现;灌浆期(移栽后76 d)的LAI与产量呈极显著负相关,相关系数为-0.312;生育前期(移栽后15~50 d)杂种SPAD对产量具有显著或极显著增产效应,而灌浆结实期(移栽后76~90 d)的SPAD则造成极显著减产;杂种群体LTR与产量呈极显著负相关,分蘖前期(移栽后20 d)和幼穗分化前期(移栽后38 d)的LTR与产量的相关系数分别为-0.282和-0.384。【结论】‘天丰A’‘五丰A’‘广恢998’和‘广恢308’组合的前期分蘖力强,茎蘖数多,叶面积系数大,早生快发性好;‘扬泰A’‘广恢998’等组合前期LTR较低、后期较高,有利于植株光合作用和产量提高。在不同生长发育阶段,光合参数通过影响杂种的不同产量性状,实现对杂种产量的影响。通过光合参数与杂种产量回归方程的拟合,能较好地对杂交水稻早期产量进行预测。 展开更多
关键词 杂交稻 动态变化 叶面积指数 SPAD 单株茎蘖数 透光率 产量性状
下载PDF
Clustering Structure Analysis in Time-Series Data With Density-Based Clusterability Measure 被引量:6
19
作者 Juho Jokinen Tomi Raty Timo Lintonen 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2019年第6期1332-1343,共12页
Clustering is used to gain an intuition of the struc tures in the data.Most of the current clustering algorithms pro duce a clustering structure even on data that do not possess such structure.In these cases,the algor... Clustering is used to gain an intuition of the struc tures in the data.Most of the current clustering algorithms pro duce a clustering structure even on data that do not possess such structure.In these cases,the algorithms force a structure in the data instead of discovering one.To avoid false structures in the relations of data,a novel clusterability assessment method called density-based clusterability measure is proposed in this paper.I measures the prominence of clustering structure in the data to evaluate whether a cluster analysis could produce a meaningfu insight to the relationships in the data.This is especially useful in time-series data since visualizing the structure in time-series data is hard.The performance of the clusterability measure is evalu ated against several synthetic data sets and time-series data sets which illustrate that the density-based clusterability measure can successfully indicate clustering structure of time-series data. 展开更多
关键词 CLUSTERING EXPLORATORY data analysis time-series UNSUPERVISED LEARNING
下载PDF
Wavelet matrix transform for time-series similarity measurement 被引量:2
20
作者 胡志坤 徐飞 +1 位作者 桂卫华 阳春华 《Journal of Central South University》 SCIE EI CAS 2009年第5期802-806,共5页
A time-series similarity measurement method based on wavelet and matrix transform was proposed,and its anti-noise ability,sensitivity and accuracy were discussed. The time-series sequences were compressed into wavelet... A time-series similarity measurement method based on wavelet and matrix transform was proposed,and its anti-noise ability,sensitivity and accuracy were discussed. The time-series sequences were compressed into wavelet subspace,and sample feature vector and orthogonal basics of sample time-series sequences were obtained by K-L transform. Then the inner product transform was carried out to project analyzed time-series sequence into orthogonal basics to gain analyzed feature vectors. The similarity was calculated between sample feature vector and analyzed feature vector by the Euclid distance. Taking fault wave of power electronic devices for example,the experimental results show that the proposed method has low dimension of feature vector,the anti-noise ability of proposed method is 30 times as large as that of plain wavelet method,the sensitivity of proposed method is 1/3 as large as that of plain wavelet method,and the accuracy of proposed method is higher than that of the wavelet singular value decomposition method. The proposed method can be applied in similarity matching and indexing for lager time series databases. 展开更多
关键词 wavelet transform singular value decomposition inner product transform time-series similarity
下载PDF
上一页 1 2 250 下一页 到第
使用帮助 返回顶部