Crop Identification Using Deep Learning on LUCAS Crop Cover Photos.

Massive and high-quality in situ data are essential for Earth-observation-based agricultural monitoring. However, field surveying requires considerable organizational effort and money. Using computer vision to recognize crop types on geo-tagged photos could be a game changer allowing for the provision of timely and accurate crop-specific information. This study presents the first use of the largest multi-year set of labelled close-up in situ photos systematically collected across the European Union from the Land Use Cover Area frame Survey (LUCAS). Benefiting from this unique in situ dataset, this study aims to benchmark and test computer vision models to recognize major crops on close-up photos statistically distributed spatially and through time between 2006 and 2018 in a practical agricultural policy relevant context. The methodology makes use of crop calendars from various sources to ascertain the mature stage of the crop, of an extensive paradigm for the hyper-parameterization of MobileNet from random parameter initialization, and of various techniques from information theory in order to carry out more accurate post-processing filtering on results. The work has produced a dataset of 169,460 images of mature crops for the 12 classes, out of which 15,876 were manually selected as representing a clean sample without any foreign objects or unfavorable conditions. The best-performing model achieved a macro F1 (M-F1) of 0.75 on an imbalanced test dataset of 8642 photos. Using metrics from information theory, namely the equivalence reference probability, resulted in an increase of 6%. The most unfavorable conditions for taking such images, across all crop classes, were found to be too early or late in the season. The proposed methodology shows the possibility of using minimal auxiliary data outside the images themselves in order to achieve an M-F1 of 0.82 for labelling between 12 major European crops.

Cognitive Keys in Psychophysical Estimation of Chemosensory Perception in University Students.

Psychophysical methods allow us to measure the relationship between stimuli and sensory perception. Of these, Detection Threshold (DT) allows us to know the minimum concentration to produce taste identification. Given this, we wonder whether, for example, wine tasting experts are more capable of perceiving their sensory properties than other people, or whether they can distinguish them because they are better able to "describe" them. To verify this, this study analyses the influence of having prior knowledge of the name astringency and, failing that, to detect it and distinguish it between the four basic tastes. One-hundred-and-sixty-two university students with an average age of 19.43 (SD = 2.55) years were assigned to three experimental conditions: an experimental group (G.2) without previous knowledge of the name astringency and with alimentary satiety, and two control groups, both with previous knowledge of the name, these being G.1, with satiety, and G.3, with hunger. DT was collected for the four basic tastes and astringencies. Results showed significant differences in the identification of astringency, being the least identified experimental group with respect to the control groups. It is striking that G.2, without prior knowledge of the name, identified astringency as a bitter taste in most cases. This supports our hypothesis of the importance of attending to linguistic cognitive processes when psychophysically estimating taste in humans.

Harmonised LUCAS in-situ land cover and use database for field surveys from 2006 to 2018 in the European Union.

Accurately characterizing land surface changes with Earth Observation requires geo-located ground truth. In the European Union (EU), a tri-annual surveyed sample of land cover and land use has been collected since 2006 under the Land Use/Cover Area frame Survey (LUCAS). A total of 1351293 observations at 651780 unique locations for 106 variables along with 5.4 million photos were collected during five LUCAS surveys. Until now, these data have never been harmonised into one database, limiting full exploitation of the information. This paper describes the LUCAS point sampling/surveying methodology, including collection of standard variables such as land cover, environmental parameters, and full resolution landscape and point photos, and then describes the harmonisation process. The resulting harmonised database is the most comprehensive in-situ dataset on land cover and use in the EU. The database is valuable for geo-spatial and statistical analysis of land use and land cover change. Furthermore, its potential to provide multi-temporal in-situ data will be enhanced by recent computational advances such as deep learning.