A Case Study on a Combination NDVI Forecasting Model Based on the Entropy Weight Method

Huang, Shengzhi; Ming, Bo; Huang, Qiang; Leng, Guoyong; Hou, Beibei

doi:10.1007/s11269-017-1692-8

Cited by 81 publications

(47 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Some scholars hope to predict NDVI accurately in order to explore the vegetation changes. For example, Iwasaki () used GSmaP precipitation and JRA25/JCDAS temperature to predict NDVI of Mongolian grassland; Wang, Chang, Shi, Ma, and Liang () used Markov model to predict the vegetation coverage changes in arid areas of north‐west China; Pringle () predicted the time‐integrated normalized difference vegetation index (iNDVI) of Queensland, Australia; Huang et al () predicted the NDVI of the Yellow River Basin using the entropy weight method and the combination forecasting model (CFM).…”

Section: Introductionmentioning

confidence: 99%

Study on NDVI changes in Weihe Watershed based on CA–Markov model

Wang

Liu

et al. 2018

Geological Journal

View full text Add to dashboard Cite

The simulation and prediction of the NDVI are conducive to regional ecological restoration. In this research, the Weihe Watershed is selected as the study area, which is located on the eastern edge of the Tianshan tectonic belt. Firstly, according to NDVI characters, we divide the values into five grades, including very low (<0.3), lower (0.3–0.4), medium (0.4–0.5), higher (0.5–0.6), and very high (>0.6), and analyse the NDVI tempo‐spatial variations in Weihe Watershed from 2006 to 2015. Then, we use CA–Markov model with parameters adjustment to simulate and predict the NDVI distributions in 2015 and 2020, respectively. The results show that (a) at temporal scales, the NDVI in Weihe Watershed increase year by year from 2006 to 2015, indicating a better vegetation recovery. At spatial scales, the NDVI increase from north‐west to south‐east gradually, which is related with the main climate factors such as temperature and precipitation. (b) By adjusting the parameters of state transition suitability atlas in the Markov model, we get the model with higher accuracy to simulate NDVI changes. And the Kappa coefficient between the simulation results and the true values is 0.6123. (c) According to the predictions in 2020, the regions with very high NDVI and higher NDVI mainly locate in Qinling Mountains, Guanzhong Plain, Ziwu Mountains, Jinghe Valley, and Luohe Valley. And these regional area percentages occupying the whole watershed increased by 13.62% and 2.64%, respectively, compared with the area percentages in 2015. The regions with medium NDVI, lower NDVI, and very low NDVI mainly distribute at the north Loess Plateau of the watershed. And these regional area percentages occupying the whole watershed decreased by 7.40%, 6.59%, and 2.28%, respectively, compared with the area percentages in 2015. The above results illustrate that the ecological environment of Weihe Watershed is improving, which can provide scientific reference for assessing the regional ecological risk and formulating ecological protection measures.

show abstract

Section: Introductionmentioning

confidence: 99%

Study on NDVI changes in Weihe Watershed based on CA–Markov model

Wang

Liu

et al. 2018

Geological Journal

View full text Add to dashboard Cite

show abstract

“…Consequently, the grazing pressure index I p from 2016 to 2020 can be predicted using the proposed method as shown in Table 3. Several studies have been presented to predict the NDVI with respect to the precipitation such as multiple linear regression (Iwasaki, 2009), SVM (Huang et al, 2017) and BPNN (Wu et al, 2019). This paper has proposed to introduce the NARX network to predict the temporal variations of the NDVI with respect to the precipitation.…”

Section: Prediction Results Of Precipitation Ndvi and Grazing Presmentioning

confidence: 99%

“…Studies have been presented to predict the temporal variations of the NDVI with respect to the precipitation, such as the statistical regression methods (Huang et al, 2017), back-propagation neural network (BPNN) (Wu et al, 2019;Yang, Zhu, Zhao, Liu, & Tong, 2011), support vector machine (SVM) (Huang et al, 2017) and so on. The BPNN can accurately predict the NDVI through a certain amount of the time series of the precipitation.…”

mentioning

confidence: 99%

See 1 more Smart Citation

A new temporal prediction method of grazing pressure based on normalized difference vegetation index and precipitation using nonlinear autoregressive with exogenous input networks

Feng

Lin

et al. 2019

Grassland Science

View full text Add to dashboard Cite

Restoration of natural vegetation in arid and semi‐arid grasslands is facing severe challenges. The vegetation is easy to lose their vitality, resulting in the loss of the cover in natural grasslands under the high grazing pressure. To address this situation, this paper proposes a novel method for accurately predicting the grazing pressure using the nonlinear autoregressive with exogenous input (NARX) network based on the remote sensing data of normalized difference vegetation index (NDVI) and precipitation. The proposed method uses the NARX networks to predict the temporal variations of the NDVI with respect to the precipitation. The grazing pressure can be thus calculated using the predicted values of the NDVI. For practical application, this study investigated an arid and semi‐arid grassland with heavy grazing pressure in Hulunbuir, China. The results demonstrate that the proposed method can provide an accurate prediction of the grazing pressure (mean absolute error 0.103, root‐mean‐square error 0.122, mean absolute percentage error 8.36% and coefficient of determination 0.899 at the confidence interval of 95%). In addition, the predicted values of the grazing pressure in the study area during the years from 2016 to 2020 can be obtained using the proposed method. The proposed method can obtain a good prediction of the grazing pressure, which can be further used as a guidance for the rangeland managers to reduce the occurrence of the overgrazing.

show abstract

“…Machine learning has a wide spectrum of applications in different science disciplines [1][2][3][4][5][6][7][8][9]. Advanced computational methods, including artificial neural networks (ANN), process input data in the context of previous training history on a defined sample database to produce relevant output [7].…”

Section: Introductionmentioning

confidence: 99%

Entropy Ensemble Filter: A Modified Bootstrap Aggregating (Bagging) Procedure to Improve Efficiency in Ensemble Model Simulation

Foroozand

Weijs

2017

Entropy

View full text Add to dashboard Cite

Over the past two decades, the Bootstrap AGGregatING (bagging) method has been widely used for improving simulation. The computational cost of this method scales with the size of the ensemble, but excessively reducing the ensemble size comes at the cost of reduced predictive performance. The novel procedure proposed in this study is the Entropy Ensemble Filter (EEF), which uses the most informative training data sets in the ensemble rather than all ensemble members created by the bagging method. The results of this study indicate efficiency of the proposed method in application to synthetic data simulation on a sinusoidal signal, a sawtooth signal, and a composite signal. The EEF method can reduce the computational time of simulation by around 50% on average while maintaining predictive performance at the same level of the conventional method, where all of the ensemble models are used for simulation. The analysis of the error gradient (root mean square error of ensemble averages) shows that using the 40% most informative ensemble members of the set initially defined by the user appears to be most effective.

show abstract

A Case Study on a Combination NDVI Forecasting Model Based on the Entropy Weight Method

Cited by 81 publications

References 39 publications

Study on NDVI changes in Weihe Watershed based on CA–Markov model

Study on NDVI changes in Weihe Watershed based on CA–Markov model

A new temporal prediction method of grazing pressure based on normalized difference vegetation index and precipitation using nonlinear autoregressive with exogenous input networks

Entropy Ensemble Filter: A Modified Bootstrap Aggregating (Bagging) Procedure to Improve Efficiency in Ensemble Model Simulation

Contact Info

Product

Resources

About