Publication Date:
2020-02-12
Description:
The sampling strategy for mapping soil properties from remote sensing imagery entails making decisions aboutsampling pattern, size and location. The availability of a consistent number of ancillary data strongly related to thetarget variable allows applying sampling strategies that optimally cover the feature space. This study aims at eval-uating the capability of multispectral (Sentinel-2) and hyperspectral (EnMAP) satellite data to select the samplinglocations in order to collect a calibration dataset as basis for multivariate statistical modelling of the Soil OrganicCarbon (SOC) content. Remote sensing spectra can be exploited first to set the sampling strategy and then as inde-pendent variables for the prediction models of the target variables. We tested different sampling strategies based onthe feature space, where the ancillary data are the spectral bands of the Sentinel-2 and of simulated EnMAP satellitedata acquired in Demmin (north-Est Germany). Some selection algorithms require to set the number of samples inadvance (random, Kennard-Stones and conditioned Latin Hypercube algorithm) and others automatically providethe ideal number of sampling units (Puchwein, SELECT and Puchwein+SELECT algorithm). The SOC contentand the spectra extracted at the sampling locations were used to build random forest (RF) models. The accuracyof the RF estimation models was evaluated on an independent dataset. The highest Sentinel-2 ratio of performanceto deviation (RPD) for the validation set was obtained using Puchwein (RPD: 2.5), and Kennard-Stones (RPD:2.4) algorithm. A strong positive correlation was detected between the standard deviation of the calibration datasetand the validation accuracy. The efficiency of the sampling strategies, as ratio between accuracy and number ofsamples per hectare, is highest using Puchwein with EnMAP and Puchwein+SELECT algorithm with Sentinel-2 data. The achieved results demonstrated that Sentinel-2 and EnMAP data can be exploited to build a reliablecalibration dataset for SOC mapping; moreover the efficiency of the sampling strategy selection can be improvedusing algorithms that provide the number of sampling units. For EnMAP, the different selection algorithms pro-vided very similar results. On the other hand, using Puchwein and Kennard-Stones algorithms, Sentinel-2 provideda more accurate estimation than the EnMAP. The calibration datasets provided by EnMAP data provided in thiscase lower SOC variability and lower prediction accuracy than compared to Sentinel-2. This was probably due toEnMAP coarser spatial resolution (30 m) less adequate for linkage to the sampling performed at 10 m scale.
Language:
English
Type:
info:eu-repo/semantics/conferenceObject
Permalink