Change detection work-flow for mapping changes from arable lands to permanent grasslands with advanced boosting methods

Šandera, Jiří; Štych, Přemysl

doi:10.15292/geodetski-vestnik.2019.03.379-394

Cited by 2 publications

(3 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The correct selection of the bitemporal images that replicate the phenological phases of vegetation may seem to be a suitable alternative, as recommended by Šandera and Štych [71], who, in their study, used a pair of Landsat images to detect changes similar to the above case [51] using boosting methods to classify changes from arable land to permanent grassland. The highest overall accuracy of 89.51% was achieved.…”

Section: Discussionmentioning

confidence: 99%

“…Subsequently, 20 m bands were resampled by the nearest neighbor method to the same pixel size as the bands of the visible band and near infrared (NIR) (8), i.e., 10 m. Then, all the biological predictors [67] were calculated, which are standardly implemented in the freely available software SNAP [66], including the vegetation index NDVI. Biological predictors were selected on the basis of several elaborated studies focused on plant physiology or biomass monitoring [91][92][93][94] or precision agriculture [95,96] as well as based on our previous experiences and testing [71]. The original spectral bands from the red edge bands (spectral bands 5, 6, and 7), were chosen as further input predictors.…”

Section: Methods Usedmentioning

confidence: 99%

“…An important methodological aspect of change detection is the selection of predictors that best describe and detect the observed phenomena [68][69][70]. This is mainly the effect of the time acquisition of a satellite image within a time series and a specific biological predictor or spectral band as many predictors are correlated and bring redundant information to the identification of the observed phenomena [51,71,72]. To date, various methods have been developed and tested to determine suitable predictors.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Selecting Relevant Biological Variables Derived from Sentinel-2 Data for Mapping Changes from Grassland to Arable Land Using Random Forest Classifier

Šandera

Štych

2020

Land

Self Cite

View full text Add to dashboard Cite

Permanent grassland is one of the monitored categories of land use, land use change, and forestry (LULUCF) within the climate concept and greenhouse gas reduction policy (Regulation (EU) 2018/841). Mapping the conditions and changes of permanent grasslands is thus very important. The area of permanent grassland is strongly influenced by agricultural subsidy policies. Over the course of history, it is possible to trace different shares of permanent grassland within agricultural land and areas with significant changes from grassland to arable land. The need for monitoring permanent grassland and arable land has been growing in recent years. New subsidy policies determining farm management are beginning to affect land use, especially in countries that have joined the EU in recent waves. The large amount of freely available satellite data enables this monitoring to take place, mainly owing to data products of the Copernicus program. There are a large number of parameters (predictors) that can be calculated from satellite data, but finding the right combination is very difficult. This study presents a methodical, systematic procedure using the random forest classifier and its internal metric of mean decrease accuracy (MDA) to select the most suitable predictors to detect changes from permanent grassland to arable land. The relevance of suitable predictors takes into account the date of the satellite image, the overall accuracy of change detection, and the time required for calculations. Biological predictors, such as leaf area index (LAI), fraction absorbed photosynthetically active radiation (FAPAR), normalized difference vegetation index (NDVI), etc. were tested in the form of a time series from the Sentinel-2 satellite, and the most suitable ones were selected. FAPAR, canopy water content (CWC), and LAI seemed to be the most suitable. The proposed change detection procedure achieved a very high accuracy of more than 95% within the study site with an area of 8766 km2.

show abstract

Section: Discussionmentioning

confidence: 99%