AUTHOR=Katal Negin , Rzanny Michael , Mäder Patrick , Wäldchen Jana 

TITLE=Deep Learning in Plant Phenological Research: A Systematic Literature Review

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2022.805738

DOI=10.3389/fpls.2022.805738

ISSN=1664-462X

ABSTRACT=
2 ABSTRACT
3 Climate change represents one of the most critical threats to biodiversity with far-reaching
4 consequences for species interactions, the functioning of ecosystems, or the assembly of
5 biotic communities. Plant phenology research has gained increasing attention as the timing
6 of periodic events in plants is strongly affected by seasonal and interannual climate variation.
7 Recent technological development allowed us to gather invaluable data at a variety of spatial
8 and ecological scales. The feasibility of phenological monitoring today and in the future depends
9 heavily on developing tools capable of efficiently analyzing these enormous amounts of data.
10 Deep Neural Networks learn representations from data with impressive accuracy and lead to
11 significant breakthroughs in, e.g., image processing. This paper is the first systematic literature
12 review aiming to thoroughly analyze all primary studies on deep learning approaches in plant
13 phenology research. In a multi-stage process, we selected 24 peer-reviewed studies published in
14 the last five years (2016–2021). After carefully analyzing these studies, we describe the applied
15 methods categorized according to the studied phenological stages, vegetation type, spatial scale,
16 data acquisition- and deep learning methods. Furthermore, we identify and discuss research
17 trends and highlight promising future directions. We present a systematic overview of previously
18 applied methods on different tasks that can guide this emerging complex research field.