基于Stacked ConvLSTM的时间序列森林火烧迹地检测
Forest burned area detection with time series data based on Stacked ConvLSTM
- 2022年26卷第10期 页码:1976-1987
纸质出版日期: 2022-10-07
DOI: 10.11834/jrs.20210471
引用
阅读全文PDF
扫 描 看 全 文
纸质出版日期: 2022-10-07
扫 描 看 全 文
引用
阅读全文PDF
确定森林火烧迹地的准确时间点以及空间范围对于森林的受损评价、管理、碳核算以及森林恢复的管理有重要意义。由于森林火烧迹地在空间分布上具有一定的连续性,现有的森林火烧迹地提取方法大都采用先分类再后处理的两步处理策略来抑制虚警像素的影响。本文提出将时空检测方法Stacked ConvLSTM用于时间序列森林火烧迹地的检测,在保持结果具有较好空间连续性的基础上避免了具有主观性的后处理操作,实现端到端提取森林火烧迹地信息,提升了森林火烧迹地的提取精度。采用MODIS时间序列数据,基于2001年—2008年以及2001年—2016年的黑龙江沾河林业局伊南河林场和内蒙古自治区毕拉河林业局北大河林场两个区域的历史时间序列,分别对这两个区域2009年以及2017年发生的特大火灾区域进行火烧迹地检测,利用Stacked ConvLSTM、Stacked LSTM以及bfast算法在两个区域的MODIS时间序列中提取森林火烧迹地,并将火烧迹地检测结果与ESA发布的Fire_CCI 5.1火烧迹地产品进行对比分析。结果表明:首先,从目视效果来看,在研究区域Ⅰ,Stacked ConvLSTM检测的结果比Stacked LSTM和bfast算法错误检测点少,并且在空间分布也保持较高连续性;在研究区域Ⅱ,Stacked ConvLSTM检测到了较完整的火烧迹地区域。其次,在定量的精度评价指标上,在研究区域Ⅰ,Stacked ConvLSTM的精确度比Stacked LSTM和bfast算法分别高出0.120和0.405,并且召回率、准确度和F1-score也更高,Fire_CCI 5.1召回率虽更高,由于错检区域较大,其他精度指标远低于Stacked ConvLSTM;在研究区域Ⅱ,Stacked ConvLSTM精确度达0.924,召回率、准确度和F1-score相比Stacked LSTM和bfast算法以及Fire_CCI 5.1更高。
As the largest land cover, forests play an important role in human living environment, biological habitat, and global carbon cycle. Forest health is directly related to global ecological security and sustainable development of human society. In recent years, urban construction, disasters, forest management and deforestation, and other factors have caused different degrees of disturbance to forests. It is important to determine the exact time point and spatial range of forest burned area for forest damage assessment, management, carbon accounting, and forest restoration management. Owing to the continuity of spatial distribution of forest burned areas, most of the existing methods of forest burned area extraction use the two-step treatment strategy of first classification and then post-processing to suppress the effect of false alarm pixels. In this paper, a spatiotemporal detection method, Stacked ConvLSTM, is proposed for the detection of forest fire tracks in time series. This method avoids subjective post-processing operations on the basis of maintaining better spatial continuity of the results, and achieves end-to-end extraction of forest burned area information, which improves the extraction accuracy of forest fire-burning land. This paper proposes to use Stacked ConvLSTM to detect forest disturbance in time and space. Combined with the characteristics of ConvLSTM in extracting temporal and spatial characteristics from long-term historical series, it can predict the change trend of vegetation in a period of time in the future, and accurately determine the time point and spatial range of forest disturbance. ConvLSTM is an LSTM variant proposed on the basis of LSTM. The full connection state from input layer to hidden layer and from hidden layer to hidden layer of LSTM is replaced by convolution connection, which can make full use of spatial information. Compared with single-pixel-based methods, ConvLSTM can extract the spatiotemporal structure information of time series images at the same time, which is better for spatiotemporal analysis. In this paper, Stacked ConvLSTM is used to detect the temporal and spatial distribution of forest burned areas, predict the change trend of vegetation in a period of time in the future, and determine the presence of forest burned areas by comparing with the newest time-series images. With MODIS long time series data, based on the historical time series of Yinanhe Forest Farm of Zhanhe Forestry Bureau in Heilongjiang Province and Beidahe Forest Farm of Bilahe Forestry Bureau in Inner Mongolia from 2001—2008 and 2001—2016, the extraction results of burned areas were compared with Stacked LSTM and bfast algorithm. The Stacked ConvLSTM, Stacked LSTM, and bfast algorithms were used to extract forest burned areas from MODIS time series in both regions, and to compare the detection results with the Fire_CCI 5.1 burned areas products released by ESA. Results show that, firstly, from the visual effect, in study area Ⅰ, the error detection of Stacked ConvLSTM is fewer than that of Stacked LSTM and bfast algorithm and maintains high continuity in spatial distribution. In study Area Ⅱ, Stacked ConvLSTM detected a more complete area of fire. Secondly, in study area Ⅰ , Stacked ConvLSTM was 0.120 and 0.405 more accurate than Stacked LSTM and bfast algorithms, respectively. Moreover, the recall rate, accuracy, and Fire_CCI 5.1 F1-score were higher. In study area Ⅰ , the accuracy of Stacked ConvLSTM is 0.924 had a higher recall rate, accuracy, and F1-score than Stacked LSTM, bfast algorithms, and Fire_CCI 5.1. The detection accuracy of ConvLSTM model in space is higher than that of the other two methods, and its continuity of detection results in space is better. The detection effect of ConvLSTM model is equivalent to that of Stacked LSTM in time, but both of them are closer to the real fire time point than bfast algorithm. Results show that Stacked ConvLSTM has advantages in obtaining the change trend of forest long-term historical series for spatiotemporal prediction, and improves the detection accuracy of forest fire to a certain extent.
森林火灾是一种突发性强、破坏性高、处置困难的自然灾害(
根据数学统计方法划分,传统的时间序列变化检测算法可分为6大类,包括阈值法、差分法、分段法、轨迹分类法、统计边界法和回归法(
近年来,深度学习得以迅速发展,并越来越多地用于时间序列分析(
为在时间序列预测中同时考虑空间信息,
由于Stacked ConvLSTM尚未用于森林火烧迹地检测,其在森林火烧迹地检测的有效性和效果有待验证,本文提出将时空检测方法Stacked ConvLSTM用于时间序列森林火烧迹地的检测,实现端到端提取森林火烧迹地信息。由于火烧迹地在空间分布上具有连续性(
两个研究区域分布如
图1 研究区域(研究区域Ⅰ:伊南河林场火灾区域,研究区域Ⅱ:北大河林场火灾区域)
Fig. 1 Study area (study area Ⅰ: Yinanhe Forest Farm fire area, study area Ⅱ: Beidahe Forest Farm fire area)
研究区域Ⅱ在内蒙古自治区毕拉河林业局北大河林场,地理位置在49°31′N,123°06′E附近,2017年5月2日发生森林火灾,过火面积115 km2,有林地占60%,受害森林面积达82.816 km2。
选择这两个研究区域的原因有以下几点:(1)两个研究区域的火灾面积较大,在遥感影像上有明显的过火区域轮廓,便于研究实验的进行;(2)两个区域的历史时间序列都比较平稳,除了已知的火灾外没有受到其他明显的森林干扰发生,便于模型算法的验证;(3)两个研究区分别包含草甸森林和森林区域,为在不同的森林覆盖类型验证模型的有效性提供了条件。
本文采用的研究数据是中分辨率成像仪(MODIS)陆地产品MOD13Q1。MOD13Q1空间分辨率250 m,是16 d合成产品,每年有23幅影像。分别获取了研究区域Ⅰ的2001年—2009年以及研究区域Ⅱ的2001年—2017年间的时间序列数据。实验剔除了序列中受云、雪影响大的春冬季影像,采用一年中季相变化比较明显的14幅影像作为研究的时间窗口(DOY97—DOY305)。
MODIS数据的MOD13Q1产品中增强型植被指数(EVI)在植被监测中具有时相多、覆盖面广、且不易产生过饱和等优势(
EVI=2.5ρNIR-ρRρNIR-6ρR-7.5ρB+1 | (1) |
式中,ρR、ρB、ρNIR分别表示MODIS数据的红、蓝和近红外波段的反射率。
选择MODIS数据的原因主要有两点:(1)MODIS数据的时间跨度长,可以提供足够长的时间序列;(2)MODIS 16 d合成产品,时间间隔均匀,方便用于时间序列的统计建模。
时间序列数据预测是指学习过去的时间序列并预测未来的变化。传统的神经网络无法解决随时间轴变化的问题,随之诞生了RNN(Recurrent Neural Network)(
It=σ(WxiXt+WhiHt-1+WciоCt-1+bi) | (2) |
Ft=σ(WxfXt+WhfHt-1+WcfоCt-1+bf) | (3) |
Ct=FtоCt-1+Itоtanh(WxcXt+WhcHt-1+bc) | (4) |
Ot=σ(WxoutXt+WhoutHt-1+WcoutоCt-1+bo) | (5) |
式中,I、F、O分别表示输入门、遗忘门和输出门,C和H分别表示细胞状态(经过门控输出的信息)和隐藏状态(每个时间点的输出值),W表示对应数据的权重,X表示输入数据,b表示偏置值,σ表示激活函数,о表示哈达玛积,下标t表示t时刻;下标i、f、out分别表示3个控制门对应的权重和偏置值,下标c表示细胞状态C对应的权重和偏置;W的下标x表示对应输入数据X的权重,h表示对应隐藏状态H的权重。
ConvLSTM是在LSTM基础上提出来的一种LSTM变体,将LSTM的输入层到隐藏层和隐藏层到隐藏层之间的全连接状态替换为卷积连接,对LSTM无法充分利用空间信息进行了改进。LSTM在处理图像数据时需要将图像数据转为一维向量,无法处理原图像数据的空间结构信息。相比LSTM模型,ConvLSTM能够更好地提取时间序列图像中的时空结构信息。ConvLSTM模型公式表示如下:
It=σ(Wxi*Xt+Whi*Ht-1+WciоCt-1+bi) | (6) |
Ft=σ(Wxf*Xt+Whf*Ht-1+WcfоCt-1+bf) | (7) |
Ct=FtоCt-1+Itоtanh(Wxc*Xt+Whc*Ht-1+bc) | (8) |
Ot=σ(Wxout*Xt+Whout*Ht-1+WcoutоCt-1+bout) | (9) |
式(
图2 ConvLSTM内部结构
Fig. 2 Internal structure of ConvLSTM
本文的Stacked ConvLSTM网络结构如
图3 堆叠ConvLSTM
Fig. 3 Stacked ConvLSTM
实验中预测序列(ˆXn+1,ˆXn+2,…,ˆXn+m)和目标序列(Xn+1,Xn+2,…,Xn+m)采用的损失函数是均方误差MSE函数,损失函数的计算可表示为
Loss=n+m∑i=n+1||Xi-ˆXi||2 | (10) |
式中,Xi表示第i时间点目标序列值,ˆXi表示第i时间点网络模型的预测值。
混淆矩阵也称作误差矩阵,是表示分类精度的一个n×n矩阵(
基于混淆矩阵,进一步计算以下常用的结果评价指标,包括:精确度(P)、召回率(R)、准确度(Acc)、F1-score值(F1)。以上4个评估指标公式如下:
P=TPTP+FP | (11) |
R=TPTP+FN | (12) |
Acc=TP+TNTP+TN+FP+FN | (13) |
F1=2·P·RP+R | (14) |
式中,TP表示正确分为火烧迹地的像素个数,FP表示错误分为火烧迹地的像素个数,TN表示正确分为非火烧迹地的像素个数,FN表示错误分为非火烧迹地的像素个数;P′是分为火烧迹地的总像元个数,N′是分为非火烧迹地的总像元个数;P是真实火烧迹地像元个数,N是真实非火烧迹地像元个数。
基于深度学习框架Keras完成了Stacked ConvLSTM的构建(
图4 研究区域EVI在时间轴上变化
Fig. 4 EVI varies along the time axis in the study area
本文使用滑动窗口法(
本文对Stacked ConvLSTM模型中的超参数设置了不同的值进行实验,得到的最优参数分别为卷积核大小3×3,Batch Size大小设置为16,采用的优化器为RMSprop(
Stacked ConvLSTM的Stacked Layers及每层的单元个数对于网络模型的学习能力影响很大,因此对不同的网络结构进行测试。网络所测试的层数以及单元数是在Stacked ConvLSTM的应用以及实验中得出的经验值,根据预测精度取在本文数据表现最佳的网络层数和单元数,作为的森林火烧迹地检测网络结构。
研究区域Ⅰ测试结果如
将两个研究区域的Stacked ConvLSTM最佳网络结构用于MODIS数据的森林火烧迹地检测。取预测的时间序列以及验证的目标序列中像素区域大小10×10求平均值作图结果如
图5 未变化和变化区域时序拟合
Fig. 5 Unchanged and changed area fitting
对测试序列中每一个像元采用经验阈值的方法确定是否为变化像元(
图6 变化区域阈值
Fig. 6 Threshold of changed area
本文利用Stacked ConvLSTM、Stacked LSTM以及bfast算法在两个区域的MODIS时间序列中提取森林火烧迹地,并将火烧迹地检测结果与ESA发布的Fire_CCI 5.1火烧迹地产品进行了对比分析。地面真值数据分别由2009年5月23日Landsat-5 TM影像和2017年5月25日MODIS影像目视解译生成。
火烧迹地检测结果如
图7 森林火烧迹地检测结果图
Fig. 7 Forest burned areas detection results
由
将两个区域的精度表绘制成柱状统计图,见
图8 森林火烧迹地检测精度柱状统计图
Fig. 8 Precision of forest burned areas column chart
Stacked ConvLSTM在两个区域检测的火灾发生的时间点分别在MODIS时间序列中的2009年和2017年的第126天,而实际发生的火灾时间点分别在2009年的4月27日和2017年的5月2日,即第116天和第122天。以上3种方法在两个区域的检测时间点如
本文提出将Stacked ConvLSTM用于时间序列森林火烧迹地检测,利用Stacked ConvLSTM学习时空特征的优势,在保持结果具有较好空间连续性的基础上避免了具有主观性的后处理操作,实现端到端提取森林火烧迹地信息,提升了森林火烧迹地的提取精度。基于两个发生过特大火灾区域的MODIS时间序列数据,定性和定量分析Stacked ConvLSTM、Stacked LSTM以及经典的bfast算法火烧迹地提取结果,并将3种方法的火烧迹地提取结果与Fire_CCI 5.1火烧迹地产品进行了对比。研究结果表明,在检测精度和空间分布的连续性上,Stacked ConvLSTM检测的火烧迹地结果都有很大提高;此外,在火灾发生时间点检测效果上,由于MODIS时间分辨率(MOD13Q1数据为16 d合成数据)为16 d,Stacked ConvLSTM和Stacked LSTM均落后真实火灾时间点一步,但均比bfast算法的在时间上更准确一步。
Stacked ConvLSTM在森林火烧迹地检测存在一些不足之处。首先,本文基于单个EVI指数开展Stacked ConvLSTM在森林火烧迹地检测的有效性研究,更多植被相关指数及其组合的检测效果值得进一步研究;其次,确定火烧迹地区域的方法是基于经验阈值,有待研究自动的阈值计算方法;再次,由于MODIS数据的分辨率属于中低分辨率,Stacked ConvLSTM模型的卷积核设置太大反而会模糊空间信息,因此提取的空间信息有限,在更高空间分辨率和时间分辨率的影像数据上,Stacked ConvLSTM模型的时空预测表现可能会更好;最后,网络模型训练中是固定时间长度的输入输出,只能学习有限的时空序列信息,这大大限制了网络在时空预测上的表现。因此,在后续的研究中,考虑在Stacked ConvLSTM基础上加入一些可以输入输出不定长时序数据和更高效的措施如Encoder-Decoder结构以及Attention机制等,提高网络在时空序列上的预测效果。
致谢:此次实验过程中,在袁媛老师的帮助下获取了本文的实验数据,在此表示由衷感谢!
Bolton D K, Coops N C and Wulder M A. 2015. Characterizing residual structure and forest recovery following high-severity fire in the western boreal of Canada using Landsat time-series and airborne Lidar data. Remote Sensing of Environment, 163: 48-60 [DOI: 10.1016/j.rse.2015.03.004] [百度学术]
Cao Y C, Wu Z P, Zhou Y F, Wei S J and Feng X Q. 2020. Forest fire recognition method based on recurrent neural network. Forestry and Environmental Science, 36(5): 34-40 [百度学术]
曹毅超, 吴泽鹏, 周宇飞, 魏书精, 封晓强. 2020. 基于循环神经网络的森林火灾识别研究. 林业与环境科学, 36(5): 34-40 [DOI: 10.3969/j.issn.1006-4427.2020.05.006] [百度学术]
Chance C M, Hermosilla T, Coops N C, Wulder M A, White J C. 2016. Effect of topographic correction on forest change detection using spectral trend analysis of Landsat pixel-based composites. International Journal of Applied Earth Observation and Geoinformation, 44:186–194[DOI:10.1016/j.jag.2015.09.003] [百度学术]
Cheng M, Xu Q, Lv J M, Liu W Y, Li Q and Wang J P. 2016. MS-LSTM: a multi-scale LSTM model for BGP anomaly detection//2016 IEEE 24th International Conference on Network Protocols (ICNP). Singapore: IEEE: 1-6 [DOI: 10.1109/ICNP.2016.7785326] [百度学术]
Chollet F,others.2015.Keras.GitHub.[https://github.com/fchollet/keras] [百度学术]
Chuvieco E, Lizundia-Loiola J, Pettinari M L, Ramo R, Padilla M, Tansey K, Mouillot F, Laurent P, Storm T, Heil A and Plummer S. 2018. Generation and analysis of a new global burned area product based on MODIS 250 m reflectance bands and thermal anomalies. Earth System Science Data, 10(4): 2015-2031 [DOI: 10.5194/essd-10-2015-2018] [百度学术]
Chuvieco E, Yue C, Heil A, Mouillot F, Alonso-Canas I, Padilla M, Pereira J M, Oom D and Tansey K. 2016. A new global burned area product for climate assessment of fire impacts. Global Ecology and Biogeography, 25(5): 619-629 [DOI: 10.1111/geb.12440] [百度学术]
Gers F A and Schmidhuber J. 2000. Recurrent nets that time and count.//Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks//IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium. Como: IEEE: 189-194 [DOI: 10.1109/IJCNN.2000.861302] [百度学术]
Hilker T, Wulder M A, Coops N C, Linke J, McDermid G, Masek J G, Gao F and White J C. 2009. A new data fusion model for high spatial- and temporal-resolution mapping of forest disturbance based on Landsat and MODIS. Remote Sensing of Environment, 113(8): 1613-1627 [DOI: 10.1016/j.rse.2009.03.007] [百度学术]
Hochreiter S and Schmidhuber J. 1997. Long short-term memory. Neural Computation, 9(8): 1735-1780 [DOI: 10.1162/neco.1997.9.8.1735] [百度学术]
Huang C Q, Goward S N, Masek J G, Thomas N, Zhu Z L and Vogelmann J E. 2010. An automated approach for reconstructing recent forest disturbance history using dense Landsat time series stacks. Remote Sensing of Environment, 114(1): 183-198 [DOI: 10.1016/j.rse.2009.08.017] [百度学术]
Huang C Q, Goward S N, Schleeweis K, Thomas N, Masek J G and Zhu Z L. 2009. Dynamics of national forests assessed using the Landsat record: case studies in eastern United States. Remote Sensing of Environment, 113(7): 1430-1442 [DOI: 10.1016/j.rse.2008.06.016] [百度学术]
Huete A, Didan K, Miura T, Rodriguez E P, Gao X and Ferreira L G. 2002. Overview of the radiometric and biophysical performance of the MODIS vegetation indices. Remote Sensing of Environment, 83(1/2): 195-213 [DOI: 10.1016/S0034-4257(02)00096-2] [百度学术]
Huo L Z, Tang P, Zhang Z and Tuia D. 2015. Semisupervised classification of remote sensing images with hierarchical spatial similarity. IEEE Geoscience and Remote Sensing Letters, 12(1): 150-154 [DOI: 10.1109/LGRS.2014.2329713] [百度学术]
Jordan M I. 1997. Serial order: a parallel distributed processing approach. Advances in Psychology, 121: 471-495 [DOI: 10.1016/S0166-4115(97)80111-2] [百度学术]
Kennedy R E, Cohen W B and Schroeder T A. 2007. Trajectory-based change detection for automated characterization of forest disturbance dynamics. Remote Sensing of Environment, 110(3): 370-386 [DOI: 10.1016/j.rse.2007.03.010] [百度学术]
Kennedy R E, Yang Z Q and Cohen W B. 2010. Detecting trends in forest disturbance and recovery using yearly Landsat time series: 1. LandTrendr-temporal segmentation algorithms. Remote Sensing of Environment, 114(12): 2897-2910 [DOI: 10.1016/j.rse.2010.07.008] [百度学术]
Khan S H, He X M, Porikli F and Bennamoun M. 2017. Forest change detection in incomplete satellite images with deep neural networks. IEEE Transactions on Geoscience and Remote Sensing, 55(9): 5407-5423 [DOI: 10.1109/TGRS.2017.2707528] [百度学术]
Kim S, Hong S, Joh M and Song S K. 2017. DeepRain: ConvLSTM network for precipitation prediction using multichannel radar data. arXiv Preprint arXiv: 1711.02316[DOI: 10.48550/arXiv.1711.02316] [百度学术]
Kong Y L, Huang Q Q, Wang C Y, Chen J B, Chen J S and He D X. 2018. Long short-term memory neural networks for online disturbance detection in satellite image time series. Remote Sensing, 10(3): 452 [DOI: 10.3390/rs1003 0452] [百度学术]
Längkvist M, Karlsson L and Loutfi A. 2014. A review of unsupervised feature learning and deep learning for time-series modeling. Pattern Recognition Letters, 42: 11-24 [DOI: 10.1016/j.patrec.2014.01.008] [百度学术]
Liu C, Frazier P, Kumar L.2007. Comparative assessment of the measures of thematic classification accuracy. Remote Sensing of Environment, 107(4): 606–616[DOI:10.1016/j.rse.2006.10.010] [百度学术]
Markham B L, Helder D L.2012. Forty-year calibrated record of earth-reflected radiance from Landsat: a review. Remote Sensing of Environment, 122:30–40[DOI:10.1016/j.rse.2011.06.026] [百度学术]
Peng D L, Wu C Y, Li C J, Zhang X Y, Liu Z J, Ye H C, Luo S Z, Liu X J, Hu Y and Fang B. 2017. Spring green-up phenology products derived from MODIS NDVI and EVI: intercomparison, interpretation and validation using National Phenology Network and AmeriFlux observations. Ecological Indicators, 77: 323-336 [DOI: 10.1016/j.ecolind.2017.02.024] [百度学术]
Reddy D S and Prasad P R C. 2018. Prediction of vegetation dynamics using NDVI time series data and LSTM. Modeling Earth Systems and Environment, 4(1): 409-419 [DOI: 10.1007/s40808-018-0431-3] [百度学术]
Ruiz J A M, Lázaro J R G, Cano I D Á and Leal P H. 2014. Burned area mapping in the North American boreal forest using Terra-MODIS LTDR (2001—2011): a comparison with the MCD45A1, MCD64A1 and BAGEOLAND-2 products. Remote Sensing, 6(1): 815-840 [DOI: 10.3390/rs6010815] [百度学术]
Shi X J, Chen Z R, Wang H, Yeung D Y, Wong W K and Woo W C. 2015. Convolutional LSTM network: a machine learning approach for precipitation nowcasting//Proceedings of the 28th International Conference on Neural Information Processing Systems. Montreal: MIT Press: 802-810[DOI:10.48550/arXiv.1506.04214] [百度学术]
Sun H B, Wang Z L, Zhu Z W, Huang F F, Gan X H and Zhang W Q. 2018. Stoichiometry characteristics of dominant tree species and soil in Heritiera littoralis community in Baguang Wetland Park in Shenzhen. Forestry and Environmental Science, 34(6): 15-20 [百度学术]
孙红斌, 王佐霖, 朱子维, 黄芳芳, 甘先华, 张卫强. 2018. 深圳市坝光湿地园银叶树群落优势树种与土壤生态化学计量特征分析. 林业与环境科学, 34(6): 15-20 [DOI: 10.3969/j.issn.1006-4427.2018.06.003] [百度学术]
Sun G F,Qin X L,Liu S C,et al. Potential analysis of typical vegetation index for identifying burned area[J].Remote Sensing for Land and Resources,2019,31( 1) : 204-211 [百度学术]
孙桂芬, 覃先林, 刘树超, 等. 2019.典型植被指数识别火烧迹地潜力分析. 国土资源遥感, 31(1):204-211 [DOI:10.6046 /gtzyyg.2019.01.27] [百度学术]
Verbesselt J, Zeileis A and Herold M. 2012. Near real-time disturbance detection using satellite image time series. Remote Sensing of Environment, 123: 98-108 [DOI: 10.1016/j.rse.2012.02.022] [百度学术]
Wang Z S, Wei S J, Xie J H, Zhong Y X, Li X C, Tang H H, Wu Z P, Zhou Y F and Li Q. 2019. Effect of forest fire combustion environment on forest fire suppression. Forestry and Environmental Science, 35(2): 84-88 [百度学术]
王振师, 魏书精, 谢继红, 钟映霞, 李小川, 唐洪辉, 吴泽鹏, 周宇飞, 李强. 2019. 林火燃烧环境对灭火效果的影响研究. 林业与环境科学, 35(2): 84-88 [DOI: 10.3969/j.issn.1006-4427.2019.02.014] [百度学术]
Wang Z X, Liu C and Huete A. 2003. From AVHRR-NDVI to MODIS-EVI: advances in vegetation index research. Acta Ecologica Sinica, 23(5): 979-987 [百度学术]
王正兴, 刘闯, Huete A. 2003. 植被指数研究进展: 从AVHRR-NDVI到MODIS-EVI. 生态学报, 23(5): 979-987 [DOI: 10.3321/j.issn:1000-0933.2003.05.020] [百度学术]
Wei S J, Luo S S, Luo B Z, Li X C, Wang Z S, Wu Z P, Zhou Y F, Zhong Y X and Li Q. 2020. Occurrence regularity of forest fire under the background of climate change. Forestry and Environmental Science, 36(2): 133-143 [百度学术]
魏书精, 罗斯生, 罗碧珍, 李小川, 王振师, 吴泽鹏, 周宇飞, 钟映霞, 李强. 2020. 气候变化背景下森林火灾发生规律研究. 林业与环境科学, 36(2): 133-143 [DOI: 10.3969/j.issn.1006-4427.2020.02.019] [百度学术]
Wu J W, Sun L Y, Ji R P, Feng R, Yu W Y and Zhang Y S. 2020. Research progress and prospect of remote sensing on extracting burned areas information. Journal of Catastrophology, 35(4): 151-156 [百度学术]
武晋雯, 孙龙彧, 纪瑞鹏, 冯锐, 于文颖, 张玉书. 2020. 火烧迹地信息遥感提取研究进展与展望. 灾害学, 35(4): 151-156 [DOI: 10.3969/j.issn.1000-811X.2020.04.028] [百度学术]
Yang C. 2013. Monitoring Regional Forest Disturbance by Remote Sensing: A Case Study of Wuning County. Nanjing: Nanjing University of Information Science and Technology [百度学术]
杨辰. 2013. 区域森林植被扰动遥感监测研究——以武宁县为例. 南京: 南京信息工程大学 [百度学术]
Yuan Y, Lin L, Huo L Z, Kong Y L, Zhou Z G, Wu B and Jia Y. 2020. Using an attention-based LSTM encoder-decoder network for near real-time disturbance detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13: 1819-1832 [DOI: 10.1109/JSTARS.2020.2988324] [百度学术]
Zhang X Y, Friedl M A, Schaaf C B, Strahler A H, Hodges J C F, Gao F, Reed B C and Huete A. 2003. Monitoring vegetation phenology using MODIS. Remote Sensing of Environment, 84(3): 471-475 [DOI: 10.1016/S0034-4257(02)00135-9] [百度学术]
Zhang Z M, Tang D, He G J, Long T F and Wei M Y. 2020. Global 30-meter resolution burned area products over the globe based on Landsat 8 images. China Scientific Data, 5(4): 91-96 [百度学术]
张兆明, 唐朝, 何国金, 龙腾飞, 魏明月. 2020. 全球30米分辨率火烧迹地产品. 中国科学数据(中英文网络版), 5(4): 91-96 [DOI:10.11922/sciencedb.976] [百度学术]
Zhao C J, Zhang P, Zhu J, Wu C R, Wang H M and Xu K L. 2019. Predicting tongue motion in unlabeled ultrasound videos using convolutional LSTM neural networks//2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP):5926-5930. IEEE, Piscataway, NJ.[DOI: 10.1109/ICASSP.2019.8683081] [百度学术]
Zhong X G, Mohamed A S and Florian M W. 2012. Testing the accuracy of query optimizers//Proceedings of the Fifth International Workshop on Testing Database Systems (DBTest '12. Association for Computing Machinery, 11:1-6[DOI:10.1145/2304510.2304525] [百度学术]
Zhu Z. 2017. Change detection using Landsat time series: a review of frequencies, preprocessing, algorithms, and applications. ISPRS Journal of Photogrammetry and Remote Sensing, 130: 370-384 [DOI: 10.1016/j.isprsjprs.2017.06.013] [百度学术]
Zhu Z, Fu Y C, Woodcock C E, Olofsson P, Vogelmann J E, Holden C, Wang M, Dai S and Yu Y. 2016. Including land cover change in analysis of greenness trends using all available Landsat 5, 7, and 8 images: a case study from Guangzhou, China (2000—2014). Remote Sensing of Environment, 185: 243-257 [DOI: 10.1016/j.rse.2016.03.036] [百度学术]
Zhu Z and Woodcock C E. 2014. Continuous change detection and classification of land cover using all available Landsat data. Remote Sensing of Environment, 144: 152-171 [DOI: 10.1016/j.rse.2014.01.011] [百度学术]
相关作者
相关机构