A methodology to reconstruct LAI time series data based on generative adversarial network and improved Savitzky-Golay filter

Huang, Anqi; Shen, Runping; Di, Wenli; Han, Huimin

doi:10.1016/j.jag.2021.102633

Cited by 12 publications

(10 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Within more heterogeneous environments such as the Frasassi gorge, the boxplot function performs better for certain indices when compared to the tsclean function. In literature, different techniques have been used to carry out the smoothing and correction phase of time-series satellite data, such as the curve fitting (Pickers and Manning, 2015), the Fourier decomposition (Mingwei et al, 2008), the asymmetric Gaussian function (Jonsson and Eklundh, 2002), the double logistic functions (Atkinson et al, 2012, Eklundh andJönsson, 2015), the Whittaker smoother (Shao et al, 2016, Kandasamy et al, 2013, the Savitzky-Golay filter (Huang et al, 2021), the high order spline with roughness damping (Hermance et al, 2007), the spatio-temporal tensor completion method (Chu et al, 2021) and other spatio-temporal combination methods such as the adaptive spatio-temporal weighted method (Li et al, 2017) and hybrid Generalised Additive Model (GAM)geostatistical space-time model (Poggio et al, 2012) wich are even useful to fill temporal gaps. GAM utilization for regression model fitting widely demonstrated in literature (Hua et al, 2021).…”

Section: Discussionmentioning

confidence: 99%

A Comparison of Pre-Processing Approaches for Remotely Sensed Time Series Classification Based on Functional Analysis

Balestra,

Pierdicca,

Cesaretti

et al. 2023

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Satellite remote sensing has gained a key role for vegetation mapping distribution. Given the availability of multi-temporal satellite data, seasonal variations in vegetation dynamics can be used trough time series analysis for vegetation distribution mapping. These types of data have a very high variability within them and are subjected by artifacts. Therefore, a pre-processing phase must be performed to properly detect outliers, for data smoothing process and to correctly interpolate the data. In this work, we compare four pre-processing approaches for functional analysis on 4-years of remotely sensed images, resulting in four time series datasets. The methodologies presented are the results of the combination of two outlier detection methods, namely tsclean and boxplot functions in R and two discrete data smoothing approaches (Generalized Additive Model ”GAM” on daily and aggregated data). The approaches proposed are: tsclean-GAM on aggregated data (M01), boxplot-GAM on aggregated data (M02), tsclean-GAM on daily data (M03), boxplot-GAM on daily data (M04). Our results prove that the approach which involves tsclean function and GAM applied to daily data (M03) is ameliorative to the logic of the procedure and leads to better model performance in terms of Overall Accuracy (OA) which is always among the highest when compared with the others obtained from the other three different approaches.

show abstract

Section: Discussionmentioning

confidence: 99%

A Comparison of Pre-Processing Approaches for Remotely Sensed Time Series Classification Based on Functional Analysis

Balestra,

Pierdicca,

Cesaretti

et al. 2023

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…A atrous GAN architecture with atrous convolutions and spatial pyramid pooling has improved the generated optical image in SAR to optical data translation 32 . GAN, along with the Savitzky–Golay filter, has been used for effective MODIS LAI time series reconstruction 24 . Pix2pix GAN has been used to generate near-infrared band from RGB images acquired by unmanned aerial vehicle much more efficiently than the endmembers method 33 .…”

Section: Related Workmentioning

confidence: 99%

“…32 GAN, along with the Savitzky-Golay filter, has been used for effective MODIS LAI time series reconstruction. 24 Pix2pix GAN has been used to generate near-infrared band from RGB images acquired by unmanned aerial vehicle much more efficiently than the endmembers method. 33 Time series soil moisture content was estimated using Sentinel-1 images using the CycleGAN model.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

SAR2NDVI: a pix2pix generative adversarial network for reconstructing field-level normalized difference vegetation index time series using Sentinel-1 synthetic aperture radar data

Ramathilagam

Natarajan

Kumar

2023

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

The normalized difference vegetation index (NDVI) is essential for monitoring urban green space, forest cover, and crop growth from sowing to harvesting. High-resolution images from Sentinel-2 and Landsat-8 satellites are available nowadays to get field-level phenological information at short intervals. However, cloud cover is one of the biggest hindrances in vegetation monitoring using NDVI, resulting in data gaps. To address this issue, we propose an NDVI gap-filling methodology to generate cloud-free NDVI time series from Sentinel-1 SAR data using the pix2pix generative adversarial network (GAN) model. Pix2pix GANs with generators based on U-Net and ResNet were designed, and the performance of the models was compared for both the VV and VH polarizations. The generalization capability of the models was studied using synthetic aperture radar (SAR) and NDVI image pairs with different vegetation, field sizes, and shapes. Experimental results show that the generated synthetic NDVI images can effectively substitute the cloudy images for gap-filling. Compared to ResNet, the U-Net generator has given the best results with PSNR ¼ 29.447 dB, RMSE ¼ 0.055, and Pearson correlation coefficient ρ ¼ þ0.909 for VH polarization.

show abstract

“…The S-G filter is characterized by the ability to filter out noise and interference while ensuring that the shape and width of the original signal does not change, thus the change trend of the original signal can be more effectively preserved and analyzed [26]. The principle of the S-G filter is to convolve a certain length of filter with the data to be processed using a weighted average algorithm of moving windows , while fitting a weighted polynomial to the data to be processed that minimizes the root mean square error of the fitted target, thereby discarding some edge points far from the majority of points [27].…”

Section: B Savitzky-golay Filermentioning

confidence: 99%

Short-Term Power Load Prediction Based on VMD-SG-LSTM

Sun

Cai

2022

IEEE Access

View full text Add to dashboard Cite

Power load prediction plays an important role in the safety and stability of national power system. However, due to the nonlinear and multi-frequency characteristics of the power system itself, power load prediction is difficult. To address this problem, we propose a short-term power load prediction model based on variational mode decomposition (VMD). First, original data are decomposed into intrinsic mode function (IMF) of different frequencies using the VMD algorithm, and the decomposed sub-functions are reconstructed. After smoothing the reconstructed data by Savitzky-Golay (S-G) filtering algorithm, the change trend of raw data (CTRD) is obtained. Then, IMF, CTRD and raw data are used as inputs to predict short-term power load by long short-term memory network (LSTM). Finally, the proposed prediction model is compared with the other two groups of prediction models. The results show that the proposed VMD-SG-LSTM prediction model has high fitting ability and high prediction accuracy, and is an effective method for short-term power load prediction.

show abstract

A methodology to reconstruct LAI time series data based on generative adversarial network and improved Savitzky-Golay filter

Cited by 12 publications

References 36 publications

A Comparison of Pre-Processing Approaches for Remotely Sensed Time Series Classification Based on Functional Analysis

A Comparison of Pre-Processing Approaches for Remotely Sensed Time Series Classification Based on Functional Analysis

SAR2NDVI: a pix2pix generative adversarial network for reconstructing field-level normalized difference vegetation index time series using Sentinel-1 synthetic aperture radar data

Short-Term Power Load Prediction Based on VMD-SG-LSTM

Contact Info

Product

Resources

About