Efficiency assessment of using satellite data for crop area estimation in Ukraine

Gallego, Francisco Javier; Kussul, Nataliia; Skakun, Sergii; Kravchenko, Oleksii; Shelestov, Andrii

doi:10.1016/j.jag.2013.12.013

Cited by 93 publications

(56 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many papers report better performance of SVM, DT and RF comparing to other techniques, including MLP (McNairn et al, 2009). However, some other studies show MLP to outperform SVM and DT (Gallego et al, 2012(Gallego et al, , 2014. Though the MLP training phase might be resource and time consuming (but this is becoming less problematic with the use of high-performance computations (Kravchenko et al, 2008;Kussul et al, 2009Kussul et al, , 2010aKussul et al, , 2010bKussul et al, , 2012Shelestov et al, 2006;Shelestov and Kussul, 2008)), and might require experience from the user, it has several advantages over SVM and DT.…”

Section: Committee Of Neural Network For Image Classificationmentioning

confidence: 99%

“…A remark should be made considering vegetables. In the region, vegetables are mainly (approximately 96%) produced by small farmers and people living in villages for self-consumption purposes (so called family gardens (Gallego et al, 2014)). The fields are mainly located next to the houses and, as a rule, are very small in size (less than 0.1 ha).…”

Section: Study Area Descriptionmentioning

confidence: 99%

“…Reliable crop maps can be used for more accurate agriculture statistics estimation (Gallego et al, 2010(Gallego et al, , 2013(Gallego et al, , 2014, stratification purposes (Boryan and Zhengwei, 2013), better crop yield prediction Kogan et al, 2013aKogan et al, , 2013b.…”

Section: Introductionmentioning

confidence: 99%

“…The approach combines different neural networks (NNs) architectures to restore missing values in a time-series of satellite imagery and provide supervised classification for crop discrimination. Results are presented for the Joint Experiment of Crop Assessment and Monitoring (JECAM) test site in Ukraine with the area of more than 28,000 km 2 (Gallego et al, 2014;Shelestov et al, 2013). The resulting classification map from Landsat-8 imagery is produced, and derived crop area estimates are compared to official statistics.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Regional scale crop mapping using multi-temporal satellite imagery

Kussul

Skakun

Shelestov

et al. 2015

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

View full text Add to dashboard Cite

ABSTRACT:One of the problems in dealing with optical images for large territories (more than 10,000 sq. km) is the presence of clouds and shadows that result in having missing values in data sets. In this paper, a new approach to classification of multi-temporal optical satellite imagery with missing data due to clouds and shadows is proposed. First, self-organizing Kohonen maps (SOMs) are used to restore missing pixel values in a time series of satellite imagery. SOMs are trained for each spectral band separately using nonmissing values. Missing values are restored through a special procedure that substitutes input sample's missing components with neuron's weight coefficients. After missing data restoration, a supervised classification is performed for multi-temporal satellite images. An ensemble of neural networks, in particular multilayer perceptrons (MLPs), is proposed. Ensembling of neural networks is done by the technique of average committee, i.e. to calculate the average class probability over classifiers and select the class with the highest average posterior probability for the given input sample. The proposed approach is applied for regional scale crop classification using multi temporal Landsat-8 images for the JECAM test site in Ukraine in 2013. It is shown that ensemble of MLPs provides better performance than a single neural network in terms of overall classification accuracy, kappa coefficient, and producer's and user's accuracies for separate classes. The overall accuracy more than 85% is achieved. The obtained classification map is also validated through estimated crop areas and comparison to official statistics.

show abstract

Section: Committee Of Neural Network For Image Classificationmentioning

confidence: 99%

Section: Study Area Descriptionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Regional scale crop mapping using multi-temporal satellite imagery

Kussul

Skakun

Shelestov

et al. 2015

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

View full text Add to dashboard Cite

show abstract

“…A 30-meter crop mask was derived from land cover map that was created within SIGMA project from Landsat-7 images (Gallego et al, 2014;Lavreniuk et al, 2015;Shelestov et al, 2013;.…”

Section: Satellite Products Descriptionmentioning

confidence: 99%

Comparison of biophysical and satellite predictors for wheat yield forecasting in Ukraine

Kolotii

Kussul

Shelestov

et al. 2015

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

View full text Add to dashboard Cite

ABSTRACT:Winter wheat crop yield forecasting at national, regional and local scales is an extremely important task. This paper aims at assessing the efficiency (in terms of prediction error minimization) of satellite and biophysical model based predictors assimilation into winter wheat crop yield forecasting models at different scales (region, county and field) for one of the regions in central part of Ukraine. Vegetation index NDVI, as well as different biophysical parameters (LAI and fAPAR) derived from satellite data and WOFOST crop growth model are considered as predictors of winter wheat crop yield forecasting model. Due to very short time series of reliable statistics (since 2000) we consider single factor linear regression. It is shown that biophysical parameters (fAPAR and LAI) are more preferable to be used as predictors in crop yield forecasting regression models at each scale. Correspondent models possess much better statistical properties and are more reliable than NDVI based model. The most accurate result in current study has been obtained for LAI values derived from SPOT-VGT (at 1 km resolution) on county level. At field level, a regression model based on satellite derived LAI significantly outperforms the one based on LAI simulated with WOFOST.

show abstract