A Perspective on Plant Phenomics: Coupling Deep Learning and Near-Infrared Spectroscopy.

The trait-based approach in plant ecology aims at understanding and classifying the diversity of ecological strategies by comparing plant morphology and physiology across organisms. The major drawback of the approach is that the time and financial cost of measuring the traits on many individuals and environments can be prohibitive. We show that combining near-infrared spectroscopy (NIRS) with deep learning resolves this limitation by quickly, non-destructively, and accurately measuring a suite of traits, including plant morphology, chemistry, and metabolism. Such an approach also allows to position plants within the well-known CSR triangle that depicts the diversity of plant ecological strategies. The processing of NIRS through deep learning identifies the effect of growth conditions on trait values, an issue that plagues traditional statistical approaches. Together, the coupling of NIRS and deep learning is a promising high-throughput approach to capture a range of ecological information on plant diversity and functioning and can accelerate the creation of extensive trait databases.

Shifts in soil and plant functional diversity along an altitudinal gradient in the French Alps.

OBJECTIVES: Altitude integrates changes in environmental conditions that determine shifts in vegetation, including temperature, precipitation, solar radiation and edaphogenetic processes. In turn, vegetation alters soil biophysical properties through litter input, root growth, microbial and macrofaunal interactions. The belowground traits of plant communities modify soil processes in different ways, but it is not known how root traits influence soil biota at the community level. We collected data to investigate how elevation affects belowground community traits and soil microbial and faunal communities. This dataset comprises data from a temperate climate in France and a twin study was performed in a tropical zone in Mexico. DATA DESCRIPTION: The paper describes soil physical and chemical properties, climatic variables, plant community composition and species abundance, plant community traits, soil microbial functional diversity and macrofaunal abundance and diversity. Data are provided for six elevations (1400-2400 m) ranging from montane forest to alpine prairie. We focused on soil biophysical properties beneath three dominant plant species that structure local vegetation. These data are useful for understanding how shifts in vegetation communities affect belowground processes, such as water infiltration, soil aggregation and carbon storage. Data will also help researchers understand how plant communities adjust to a changing climate/environment.