摘要：
The development of remote sensing technology has accumulated a large number of remote sensing image time series data for human monitoring of surface vegetation change, which provides a basis for vegetation change prediction. In order to improve the prediction accuracy of vegetation change, this paper uses discrete wavelet to decompose remote sensing image sequences at multiple scales, to explore the difference of influence of different temporal scale change characteristics on vegetation spatio-temporal change prediction, and find the best decomposition scale for vegetation change prediction. In this paper, the research object is the MODIS 13Q1 EVI image data of Hunan Province from 2001 to 2021. The discrete wavelet is adopted to obtain multi-scale vegetation trend components and detailed component sequences, and then complete the LSTM modeling prediction and comparison. The following are the experimental findings: the predictive ability of the discrete wavelet decomposition sequence group is better than that of the original EVI time series to varying degrees. The order of prediction accuracy is: monthly scale > seasonal scale > annual scale > original EVI time series. Thus, it is of reference significance to the research of application scenarios of change prediction of other regionalized variables with multi-scale characteristics.
作者机构：
[Long, Yue-hong; Zhu, Lei; Xue, Yun; Zhou, Song-lin] Hunan City Univ, Design Inst Co Ltd, Sch Municipal & Surveying Engn, Yiyang 413000, Peoples R China.;[Xue, Yun; Zou, Bin] Cent South Univ, Sch Geosci & Infophys, Key Lab Metallogen Predict Nonferrous Met & Geol, Changsha 410083, Peoples R China.;[Zhu, Lei] Jiangxi Univ Sci & Technol, Sch Civil & Surveying Engn, Ganzhou 341000, Peoples R China.;[Wen, Yi-min] Guilin Univ Elect Technol, Sch Comp Sci & Informat Secur, Guilin 541004, Peoples R China.
通讯机构：
[Zou, Bin] C;Cent South Univ, Sch Geosci & Infophys, Key Lab Metallogen Predict Nonferrous Met & Geol, Changsha 410083, Peoples R China.
关键词：
convolutional neural network;chlorophyll-a;Dongting Lake
摘要：
For Case-II water bodies with relatively complex water qualities, it is challenging to establish a chlorophyll-a concentration (Chl-a concentration) inversion model with strong applicability and high accuracy. Convolutional Neural Network (CNN) shows excellent performance in image target recognition and natural language processing. However, there little research exists on the inversion of Chl-a concentration in water using convolutional neural networks. Taking China's Dongting Lake as an example, 90 water samples and their spectra were collected in this study. Using eight combinations as independent variables and Chl-a concentration as the dependent variable, a CNN model was constructed to invert Chl-a concentration. The results showed that: (1) The CNN model of the original spectrum has a worse inversion effect than the CNN model of the preprocessed spectrum. The determination coefficient (R-P(2)) of the predicted sample is increased from 0.79 to 0.88, and the root mean square error (RMSEP) of the predicted sample is reduced from 0.61 to 0.49, indicating that preprocessing can significantly improve the inversion effect of the model.; (2) among the combined models, the CNN model with Baseline1_SC (strong correlation factor of 500-750 nm baseline) has the best effect, with R-P(2) reaching 0.90 and RMSEP only 0.45. The average inversion effect of the eight CNN models is better. The average R-P(2) reaches 0.86 and the RMSEP is only 0.52, indicating the feasibility of applying CNN to Chl-a concentration inversion modeling; (3) the performance of the CNN model (Baseline1_SC (R-P(2) = 0.90, RMSEP = 0.45)) was far better than the traditional model of the same combination, i.e., the linear regression model (R-P(2) = 0.61, RMSEP = 0.72) and partial least squares regression model (Baseline1_SC (R-P(2) = 0.58. RMSEP = 0.95)), indicating the superiority of the convolutional neural network inversion modeling of water body Chl-a concentration.
摘要：
三维城市规划信息系统可提供城市立体直观的表现形式,可为规划相关人员进行规划决策提供技术支持,提高规划管理水平和工作效率。Skyline软件体系下的Terra Explorer Pro在三维显示、浏览及开发等方面具有明显优势。文章以该软件为平台,以本校区为例,设计和开发了基本满足辅助城市规划需求的三维城市规划信息系统,能够为城市规划决策者进行决策提供一定的技术支持。
作者机构：
[杨准; 秦建新; 贺新光] College of Resources and Environmental Science, Hunan Normal University, Changsha, 410081, China;College of Municipal and Surveying and Mapping Engineering, Hunan City University, Yiyang, Hunan 413000, China;[龙岳红] College of Resources and Environmental Science, Hunan Normal University, Changsha, 410081, China, College of Municipal and Surveying and Mapping Engineering, Hunan City University, Yiyang, Hunan 413000, China
通讯机构：
[Qin, J.] C;College of Resources and Environmental Science, China
