English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Missing data is a recurrent problem in remote sensing, mainly due to cloudcoverage for multispectral images and acquisition problems. This can be acritical issue for crop monitoring, especially for applications relying onmachine learning techniques, which generally assume that the feature matrixdoes not have missing values. This paper proposes a Gaussian Mixture Model(GMM) for the reconstruction of parcel-level features extracted frommultispectral images. A robust version of the GMM is also investigated, sincedatasets can be contaminated by inaccurate samples or features (e.g., wrongcrop type reported, inaccurate boundaries, undetected clouds, etc). Additionalfeatures extracted from Synthetic Aperture Radar (SAR) images using Sentinel-1data are also used to provide complementary information and improve theimputations. The robust GMM investigated in this work assigns reduced weightsto the outliers during the estimation of the GMM parameters, which improves thefinal reconstruction. These weights are computed at each step of anExpectation-Maximization (EM) algorithm by using outlier scores provided by theisolation forest algorithm. Experimental validation is conducted on rapeseedand wheat parcels located in the Beauce region (France). Overall, we show thatthe GMM imputation method outperforms other reconstruction strategies. A meanabsolute error (MAE) of 0.013 (resp. 0.019) is obtained for the imputation ofthe median Normalized Difference Index (NDVI) of the rapeseed (resp. wheat)parcels. Other indicators (e.g., Normalized Difference Water Index) andstatistics (for instance the interquartile range, which captures heterogeneityamong the parcel indicator) are reconstructed at the same time with goodaccuracy. In a dataset contaminated by irrelevant samples, using the robust GMMis recommended since the standard GMM imputation can lead to inaccurate imputedvalues.

computers and electronics in agriculture

Reconstruction of Sentinel-2 Time Series Using Robust Gaussian Mixture  Models -- Application to the Detection of Anomalous Crop Development in wheat  and rapeseed crops