Deep learning and citizen science enable automated plant trait predictions from photographs.

Plant functional traits ('traits') are essential for assessing biodiversity and ecosystem processes, but cumbersome to measure. To facilitate trait measurements, we test if traits can be predicted through visible morphological features by coupling heterogeneous photographs from citizen science (iNaturalist) with trait observations (TRY database) through Convolutional Neural Networks (CNN). Our results show that image features suffice to predict several traits representing the main axes of plant functioning. The accuracy is enhanced when using CNN ensembles and incorporating prior knowledge on trait plasticity and climate. Our results suggest that these models generalise across growth forms, taxa and biomes around the globe. We highlight the applicability of this approach by producing global trait maps that reflect known macroecological patterns. These findings demonstrate the potential of Big Data derived from professional and citizen science in concert with CNN as powerful tools for an efficient and automated assessment of Earth's plant functional diversity.

A Landsat-based vegetation trend product of the Tibetan Plateau for the time-period 1990-2018.

The Tibetan Plateau is a unique, biodiverse ecosystem with an important role in the climate and hydrological system of Asia. Its vegetation supports important functions including fodder provision, erosion prevention and water retention. Assessing vegetation trends of the Tibetan Plateau is crucial to understand effects of recent climate and land-use changes. Most existing vegetation trend products covering the entire Tibetan Plateau have a coarse spatial grain and cover short temporal ranges. This hampers their applicability in studies conducted at local scales where land-use decisions take place and at time scales where climate changes become apparent. Here, we present vegetation trend products for the entire Tibetan Plateau at a spatial resolution of 30 m for the time period 1990-2018. These products include results of a modified Mann-Kendall trend test applied to annual Landsat-based NDVI mosaics, composed from all satellite observations acquired during the vegetation periods as well as NDVI difference images. These data can be valuable to many researchers including for example wildlife ecologists, rangeland experts and climate change researchers.