DEEP LEARNING MODELS PERFORMANCE FOR NDVI TIME SERIES PREDICTION: A CASE STUDY ON NORTH WEST TUNISIA

被引：0

作者：

Rhif, Manel ^{[1
]}

Ben Abbes, Ali ^{[1
,2
]}

Martinez, Beatriz ^{[3
]}

Farah, Imed Riadh ^{[1
]}

机构：

[1] Ecole Natl Sci Informat, Lab RIADI, Manouba, Tunisia

[2] Univ Sherbrooke, Ctr Applicat & Rech Teledetect CARTEL, Sherbrooke, PQ J1K 2R1, Canada

[3] Univ Valencia, Dept Fis Terra & Termodinam, Valencia, Spain

来源：

2020 MEDITERRANEAN AND MIDDLE-EAST GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (M2GARSS) | 2020年

关键词：

time series; prediction; LSTM; BiLSTM; NDVI; vegetation;

D O I：

10.1109/m2garss47143.2020.9105149

中图分类号：

S [农业科学];

学科分类号：

09 ;

摘要：

The main goal of this paper is to analyze the performance of two deep learning models Long Short-Term Memory (LSTM) and bidirectional LSTM (BiLSTM) network for non-stationary Normalized Difference Vegetation Index (NDVI) time-series prediction. Both methods have provided good performances in the different time series. The BiLSTM has shown the best agreement with the lowest root mean square error (RMSE) and the highest Pearson correlation coefficient (R) of 0.034 and 0.93, respectively.

引用

页码：9 / 12

页数：4

共 9 条

[1] Performance Assessment of the Linear, Nonlinear and Nonparametric Data Driven Models in River Flow Forecasting [J].