Selecting appropriate variables for detecting grassland to cropland changes using high resolution satellite data.

Tomáš Klouček,Přemysl Štych,Jan Komárek,David Moravec,Ondřej Lagner

doi:10.7717/peerj.5487

Tomáš Klouček, Přemysl Štych + Show 3 more

Open Access

https://doi.org/10.7717/peerj.5487

Copy DOI

Abstract

Grassland is one of the most represented, while at the same time, ecologically endangered, land cover categories in the European Union. In view of the global climate change, detecting its change is growing in importance from both an environmental and a socio-economic point of view. A well-recognised tool for Land Use and Land Cover (LULC) Change Detection (CD), including grassland changes, is Remote Sensing (RS). An important aspect affecting the accuracy of change detection is finding the optimal indicators of LULC changes (i.e., variables). Inappropriately selected variables can produce inaccurate results burdened with a number of uncertainties. The aim of our study is to find the most suitable variables for the detection of grassland to cropland change, based on a pair of high resolution images acquired by the Landsat 8 satellite and from the vector database Land Parcel Identification System (LPIS). In total, 59 variables were used to create models using Generalised Linear Models (GLM), the quality of which was verified through multi-temporal object-based change detection. Satisfactory accuracy for the detection of grassland to cropland change was achieved using all of the statistically identified models. However, a three-variable model can be recommended for practical use, namely by combining the Normalised Difference Vegetation Index (NDVI), Wetness and Fifth components of Tasselled Cap. Increasing number of variables did not significantly improve the accuracy of detection, but rather complicated the interpretation of the results and was less accurate than detection based on the original Landsat 8 images. The results obtained using these three variables are applicable in landscape management, agriculture, subsidy policy, or in updating existing LULC databases. Further research implementing these variables in combination with spatial data obtained by other RS techniques is needed.

Highlights

Land Use and Land Cover (LULC) techniques form an integral part of many studies (Kindu et al, 2013; Gupta & Shukla, 2016; Chaudhuri & Mishra, 2016) overlapping with other research fields (Cardinale et al, 2012)
This study provides an analysis of the utilisation of selected remote sensing variables for grassland to cropland change detection based on a pair of Landsat 8 OLI images and the Land Parcel Identification System (LPIS) vector database
The results confirm the principal hypotheses that (1) there are suitable variables usable for grassland to cropland change detection; (2) increasing the number of variables used in a model leads to increased accuracy of the change detection, but to achieve the highest accuracy, it is necessary to use original Landsat 8 bands; (3) spectral variables play a more important role than textural variables in the change detection; (4) the appropriate time of the acquisition satellite images is important for grassland to cropland change detection

Summary

Introduction

Land Use and Land Cover (LULC) techniques form an integral part of many studies (Kindu et al, 2013; Gupta & Shukla, 2016; Chaudhuri & Mishra, 2016) overlapping with other research fields (Cardinale et al, 2012). Grassland plays an irreplaceable role as a natural habitat of many organisms, helps with the accumulation of greenhouse gases, prevents erosion, keeps water in the landscape and reduces pollution (European Union, 2016) These benefits are disrupted by ploughing the grassland, turning it into cropland. The occurrence of new cropland at the expense of grassland is especially prominent in post-communist states that have recently joined the EU and started to receive agricultural subsidies (Pazúr et al, 2014) This process is affected by a number of national and European agricultural policies and initiatives (Sklenicka et al, 2014), such as the Good Agricultural and Environmental Conditions (GAEC) (Sklenicka et al, 2015). Change data acquired from remote sensing based models can, serve both as a basis for decision-making in the landscape management and have a socio-economic application in agriculture and its subsidy policy (Esch et al, 2014)

Objectives

Methods

Results

Discussion

Conclusion