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/

Global: Zendy Plus annual

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

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Accurate, detailed, and timely crop type mapping is a very valuableinformation for the institutions in order to create more accurate policiesaccording to the needs of the citizens. In the last decade, the amount ofavailable data dramatically increased, whether it can come from Remote Sensing(using Copernicus Sentinel-2 data) or directly from the farmers (providingin-situ crop information throughout the years and information on croprotation). Nevertheless, the majority of the studies are restricted to the useof one modality (Remote Sensing data or crop rotation) and never fuse the EarthObservation data with domain knowledge like crop rotations. Moreover, when theyuse Earth Observation data they are mainly restrained to one year of data, nottaking into account the past years. In this context, we propose to tackle aland use and crop type classification task using three data types, by using aHierarchical Deep Learning algorithm modeling the crop rotations like alanguage model, the satellite signals like a speech signal and using the cropdistribution as additional context vector. We obtained very promising resultscompared to classical approaches with significant performances, increasing theAccuracy by 5.1 points in a 28-class setting (.948), and the micro-F1 by 9.6points in a 10-class setting (.887) using only a set of crop of interestsselected by an expert. We finally proposed a data-augmentation technique toallow the model to classify the crop before the end of the season, which workssurprisingly well in a multimodal setting.

Multimodal Crop Type Classification Fusing Multi-Spectral Satellite Time Series with Farmers Crop Rotations and Local Crop Distribution