A data fusion and spatial data analysis approach for the estimation of wheat grain nitrogen uptake from satellite data

Castaldi, Fabio; Castrignanò, Annamaria; Casa, Raffaele

doi:10.1080/01431161.2016.1212423

Cited by 28 publications

(12 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A composite topsoil sample was collected for the LUCAS survey within a circular area of 2 m radius, while the ground sampling distance (GSD) for S2 is 10 m for the visible band, and 20 m in the NIR and SWIR bands. The discrepancy between soil sampling area and GSD is even more marked for L8: All the L8 bands have a resolution of 30 m. This incongruity could lead to not reliable soil estimation models if the measured values do not represent the actual situation within the pixel area [27,[44][45]; this issue may become more pronounced according to the magnitude of the geometric error and if the investigated soil property has a large short-range spatial variability. The Pearson's correlation coefficient between reflectance measured on LUCAS soil samples in the laboratory and satellite data (Figure 3) highlighted how the S2 SBSIs are closer to lab spectra than L8 SBSIs, probably due to the lower spatial resolution of the NASA sensor.…”

Section: Discussionmentioning

confidence: 99%

Sentinel-2 and Landsat-8 Multi-Temporal Series to Estimate Topsoil Properties on Croplands

Castaldi

2021

Remote Sensing

Self Cite

View full text Add to dashboard Cite

The spatial and temporal monitoring of soil organic carbon (SOC), and other soil properties related to soil erosion, is extremely important, both from the environmental and economic perspectives. Sentinel-2 (S2) and Landsat-8 (L8) time series increase the probability to observe bare soil fields in croplands, and thus, monitor soil properties over large regions. In this regard, this work suggests an automated pixel-based approach to select only pure soil pixels in S2 and L8 time series, and to make a synthetic bare soil image (SBSI). The SBSIs and the soil properties measured in the framework of the European LUCAS survey were used to calibrate SOC, clay, and CaCO3 prediction models. The results highlight a high correlation between laboratory soil spectra and the SBSIs median spectra, especially for the SBSI obtained by a three-year S2 collection, which provides satisfactory results in terms of SOC prediction accuracy (RPD: 1.74). The comparison between S2 and L8 results demonstrated the higher capability of the S2 sensor in terms of SOC prediction accuracy, mainly due to the greater spatial resolution of the bands in the visible region. Whereas, neither S2 nor L8 could accurately predict the clay and CaCO3 content. This is because of the low spectral and spatial resolution of their SWIR bands that prevent the exploitation of the narrow spectral features related to these two soil attributes. The results of this study prove that large S2 time series can estimate and monitor SOC in croplands using an automated pixel-based approach that selects pure soil pixels and retrieves reliable synthetic soil spectra.

show abstract

Section: Discussionmentioning

confidence: 99%

Sentinel-2 and Landsat-8 Multi-Temporal Series to Estimate Topsoil Properties on Croplands

Castaldi

2021

Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…Unfortunately, changing the support (the geometrical size),is unavoidablein order to enable the comparison of two variables with different supports. Nevertheless, if the ground sampling area is much smaller than the pixel size of the remote image there is a risk of weakening the link between target soil property and spectral data [38]. Although block kriging allowed to properly link SOC values and EnMAP data,this resulted in smoothing the SOC variability.…”

Section: Discussionmentioning

confidence: 99%

Sampling Strategies for Soil Property Mapping Using Multispectral Sentinel-2 and Hyperspectral EnMAP Satellite Data

2019

Self Cite

View full text Add to dashboard Cite

Designing a sampling strategy for soil property mapping from remote sensing imagery entails making decisions about sampling pattern and number of samples. A consistent number of ancillary data strongly related to the target variable allows applying a sampling strategy that optimally covers the feature space. This study aims at evaluating the capability of multispectral (Sentinel-2) and hyperspectral (EnMAP) satellite data to select the sampling locations in order to collect a calibration dataset for multivariate statistical modelling of the Soil Organic Carbon (SOC) content in the topsoil of croplands. We tested different sampling strategies based on the feature space, where the ancillary data are the spectral bands of the Sentinel-2 and of simulated EnMAP satellite data acquired in Demmin (north-east Germany). Some selection algorithms require setting the number of samples in advance (random, Kennard-Stones and conditioned Latin Hypercube algorithms) where others automatically provide the ideal number of samples (Puchwein, SELECT and Puchwein+SELECT algorithm). The SOC content and the spectra extracted at the sampling locations were used to build random forest (RF) models. We evaluated the accuracy of the RF estimation models on an independent dataset. The lowest Sentinel-2 normalized root mean square error (nRMSE) for the validation set was obtained using Puchwein (nRMSE: 8.7%), and Kennard-Stones (9.2%) algorithms. The most efficient sampling strategies, expressed as the ratio between accuracy and number of samples per hectare, were obtained using Puchwein with EnMAP and Puchwein+SELECT algorithm with Sentinel-2 data. Hence, Sentinel-2 and EnMAP data can be exploited to build a reliable calibration dataset for SOC mapping. For EnMAP, the different selection algorithms provided very similar results. On the other hand, using Puchwein and Kennard-Stones algorithms, Sentinel-2 provided a more accurate estimation than the EnMAP. The calibration datasets provided by EnMAP data provided lower SOC variability and lower prediction accuracy compared to Sentinel-2. This was probably due to EnMAP coarser spatial resolution (30 m) less adequate for linkage to the sampling performed at 10 m scale.

show abstract

“…For instance, [36] employed a filter feature-selection algorithm based on minimizing a tight bound on the Vapnik-Chervonenkis (VC) dimension [37]. Ranking-based methods are one of the most common filter-based feature selection methods; these methods estimate the importance of each spectral band using such metrics as the variance inflation factor (VIF) [38] in order to select the top-ranked bands. We will use the idea of calculating the VIF value to measure collinearity, but the spectral bands will not be ranked based on this simple measure alone.…”

Section: Related Workmentioning

confidence: 99%

“…In the literature, the recommended values of θ are between 5 and 10 [57,58], so we test different values of θ ∈ [5,12] to observe how the classification performance is affected by this threshold and to choose the best θ for a given classification task. Some methods, such as that proposed by Castaldi et al [38], use the VIF metric to perform a stepwise selection process where the bands that show a VIF value greater than a threshold θ (i.e., bands that show a high risk of multicollinearity) are removed from the selection. Our approach is novel and distinct in that we use the VIF metric as part of a preselection step, assessing the collinearity degree between each band and its local neighbors iteratively in order to find independent salient bands that are suitable cluster centers.…”

Section: Interband Redundancy Analysismentioning

confidence: 99%

Hyperspectral Dimensionality Reduction Based on Inter-Band Redundancy Analysis and Greedy Spectral Selection

et al. 2021

View full text Add to dashboard Cite

Hyperspectral imaging systems are becoming widely used due to their increasing accessibility and their ability to provide detailed spectral responses based on hundreds of spectral bands. However, the resulting hyperspectral images (HSIs) come at the cost of increased storage requirements, increased computational time to process, and highly redundant data. Thus, dimensionality reduction techniques are necessary to decrease the number of spectral bands while retaining the most useful information. Our contribution is two-fold: First, we propose a filter-based method called interband redundancy analysis (IBRA) based on a collinearity analysis between a band and its neighbors. This analysis helps to remove redundant bands and dramatically reduces the search space. Second, we apply a wrapper-based approach called greedy spectral selection (GSS) to the results of IBRA to select bands based on their information entropy values and train a compact convolutional neural network to evaluate the performance of the current selection. We also propose a feature extraction framework that consists of two main steps: first, it reduces the total number of bands using IBRA; then, it can use any feature extraction method to obtain the desired number of feature channels. We present classification results obtained from our methods and compare them to other dimensionality reduction methods on three hyperspectral image datasets. Additionally, we used the original hyperspectral data cube to simulate the process of using actual filters in a multispectral imager.

show abstract

A data fusion and spatial data analysis approach for the estimation of wheat grain nitrogen uptake from satellite data

Cited by 28 publications

References 46 publications

Sentinel-2 and Landsat-8 Multi-Temporal Series to Estimate Topsoil Properties on Croplands

Sentinel-2 and Landsat-8 Multi-Temporal Series to Estimate Topsoil Properties on Croplands

Sampling Strategies for Soil Property Mapping Using Multispectral Sentinel-2 and Hyperspectral EnMAP Satellite Data

Hyperspectral Dimensionality Reduction Based on Inter-Band Redundancy Analysis and Greedy Spectral Selection

Contact Info

Product

Resources

About