Evaluation of Landsat 8 time series image stacks for predicitng yield and yield components of winter wheat

Song, Renzhong; Cheng, Tao; Yao, Xia; Tian, Yongchao; Zhu, Yan; Cao, Weixing

doi:10.1109/igarss.2016.7730647

Cited by 9 publications

(8 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among the identified growth stages highest VIMP score was observed at the heading stage using RDVI1 and interferometric coherence at VH polarization (Table III). This result conforms with previous findings, which reveal the high sensitivity of optical indices for yield parameters at later growth stages though saturation still exists at this stage [50]. This study hypothesized that the interferometric coherence related to PWC and RDVI1, which can explain the aboveground biomass at each specific growth stage, can be related to yield.…”

Section: B Comparison Of Predictor Variablessupporting

confidence: 92%

“…Among the used metrics, the proposed sum of RDVI1 and Coherence at VH polarization outperforms with r 2 =0.81 and RMSE=0.56 t/ha and is followed by the product of interferometric coherence at VH polarization and RDVI1 with r 2 =0.71 and RMSE=0.71 t/ha. We contend that this accuracy level is parallel or better than the previous major findings that relied upon deep learning and machine learningtechniques [34,50]. The best statistical results from combined metrics suggest that interferometric coherence and RDVI1 metrices contain complementary information worth exploiting jointly.…”

Section: B Comparison Of Predictor Variablesmentioning

confidence: 54%

“…The optical indices suffer from a saturation problem, especially after the vegetative growth stage [34,50]. The synergetic metric from the two parameters has complementary information and can be effectively used to predict yield.…”

Section: B Comparison Of Predictor Variablesmentioning

confidence: 99%

See 2 more Smart Citations

Estimation of Crop Yield From Combined Optical and SAR Imagery Using Gaussian Kernel Regression

Alebele

Wang

Wei-guo

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

The synthetic aperture radar (SAR) interferometric coherence can complement optical data for the estimation of crop growth parameters, but it has not been yet investigated for predicting crop yield. Many studies have used machine learning methods, such as neural networks, random forest, and Gaussian process regression, to estimate crop yield from remotely sensed data. However, their performance depends on the amount of available ground truth data. This study proposed Gaussian kernel regression for rice yield estimation from optical and SAR imagery using a limited amount of ground truth data. The main objective was to investigate the synergetic use of Sentinel-2 vegetation indices and Sentinel-1 interferometric coherence data through Gaussian kernel regression for estimating rice grain yield. The prediction accuracy was assessed using in situ measured yield data collected in 2019 and 2020 over Xinghua county in Jiangsu Province, China. In all cases, Gaussian kernel regression outperformed the probabilistic Gaussian regression and Bayesian linear inference. With the independently used optical and SAR data, a better prediction accuracy was achieved with the optical red edge difference vegetation index (RDVI1) (r 2 = 0.65, RMSE = 0.61 t/ha) than with the interferometric coherence (r 2 = 0.52 and RMSE = 0.79 t/ha).The highest prediction accuracy can be achieved by combining RDVI1 with interferometric coherence at the heading stage (r 2 = 0.81 and RMSE = 0.55 t/ha). The results suggest the value of synergy between satellite interferometric coherence and optical indices for crop yield mapping with Gaussian kernel regression.

show abstract

Section: B Comparison Of Predictor Variablessupporting

confidence: 92%

Section: B Comparison Of Predictor Variablesmentioning

confidence: 54%

See 1 more Smart Citation

Estimation of Crop Yield From Combined Optical and SAR Imagery Using Gaussian Kernel Regression

Alebele

Wang

Wei-guo

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…They generated a linear regression equation per index per sensor per field and concluded that higher resolution imagery yielded better regression models where the Landsat-8 imagery resulted in an R 2 range between 0.39 and 0.65 compared to 0.47 and 0.65 for the Sentinel-2 dataset. While previous studies on modelling yield prediction used Landsat (Song et al 2016) and Sentinel-2 (Al-Gaadi et al 2016), this paper offers a new approach utilizing high spatial and temporal resolution PlanetScope (3 m, daily) analytical scenes in comparison with Sentinel-2A (20 m, 10 days) to monitor potato crop health over the 2017 growing season and predict crop yield. The most common vegetation indices used for forecasting crop yield status are NDVI, Green Normalized Difference Vegetation Index (GNDVI), SAVI and Modified Soil Adjusted Vegetation Index 2 (MSAVI2).…”

Section: __________________________________ * Corresponding Authormentioning

confidence: 99%

From Pixel to Yield: Forecasting Potato Productivity in Lebanon and Idaho

Ali

Delparte

Griffel

2020

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Idaho and Lebanon rely on potatoes as an economically important crop. NDVI (Normalized Difference Vegetation Index), GNDVI (Green Normalized Difference Vegetation Index), SAVI (Soil Adjusted Vegetation Index), and MSAVI2 (Modified Soil Adjusted Vegetation Index 2) indices were calculated from PlanetScope satellite imagery for the 2017 growing season cloud free days. Variations in vegetation health were tracked over time and correlated to yield data provided by growers in Idaho. Based on ordinary least squares regression an Idaho yield forecast model was developed. Vegetation response during the growth stage at which potato tubers were filling out was significant in predicting yield for both the Norkotah and Russet potato variety. This corresponded to a week with high recorded temperatures that impacted the health status of the crops. The yield forecasting model was validated with a cross validation approach and then applied to potato fields in Lebanon. The Idaho model successfully displayed yield variation in crops for Lebanon. Spectral indices along with field topography allow the prediction of yield based on the crop type and variety.

show abstract

“…They reported that the relative errors of the predicted yield were in the range of 4.62 -5.40 % and RMSE was 214.16 kg/ha. Song et al (2016) evaluated the performance of the time series of Landsat 8 images to barley yield prediction. They used NDVI.…”

Section: Introductionmentioning

confidence: 99%

Predicting Barley Harvest Time in Dryland Conditions Using Satellite Images

Adiban

Türkoğlu²,

Parchami-Araghi³

2021

Yüzüncü Yıl Üniversitesi Tarım Bilimleri Dergisi

View full text Add to dashboard Cite

Barley has an important role in livestock feed. Therefore, an accurate estimation of harvesting time is necessary to minimize the loss in barley farming. The aim of this study is to determine barley harvest time using satellite images accurately. Field data were sampled from the farms in the Dezaj region of the west of Iran. In addition, satellite remote sensing technique was applied during barley growing season in 2019 using Landsat 8 images. The vegetation indexes were used as input in the prediction model in this study. The results showed that satellite imaging has enough potential to predict the harvesting time of barley accurately. R-squared and RMSE values of the best-structured stepwise regression model in this study were 0.791 as well, and 1.34 respectively. This method can be beneficially employed by farm managers to have an accurate estimation of the most appropriate harvesting time and be able to manage the process, which is an important challenge for them.

show abstract

Evaluation of Landsat 8 time series image stacks for predicitng yield and yield components of winter wheat

Cited by 9 publications

References 4 publications

Estimation of Crop Yield From Combined Optical and SAR Imagery Using Gaussian Kernel Regression

Estimation of Crop Yield From Combined Optical and SAR Imagery Using Gaussian Kernel Regression

From Pixel to Yield: Forecasting Potato Productivity in Lebanon and Idaho

Predicting Barley Harvest Time in Dryland Conditions Using Satellite Images

Contact Info

Product

Resources

About