RT Journal Article
T1 ResNeTS: A ResNet for Time Series Analysis of Sentinel-2 Data Applied to Grassland Plant-Biodiversity Prediction
A1 Goldar Dieste, Álvaro
A1 Argüello Pedreira, Francisco
A1 Blanco Heras, Dora
A1 Magdon, Paul
A1 Linstädter, Anja
A1 Dubovyk, Olena
A1 Muro, Javier
K1 Time series analysis
K1 Biodiversity
K1 Remote sensing
K1 Grasslands
K1 Long short term memory
K1 Europe
K1 Deep learning
K1 Multispectral imaging
K1 Residual neural networks
AB Analyzing time series from remote sensing data can aid in understanding spectral-temporal phenomena in ecosystems, such as the seasonal variation of plant components. Lately, deep learning has emerged as a strong method for mapping environmental variables from this data due to its exceptional predictive capabilities. This work studies the adaptation of the ResNet computer vision architecture for time series analysis of Sentinel-2 data. The resulting deep learning architecture, ResNeTS, stacks sequential convolutions to build a deep and narrow network, aligning with the design principles of leading convolutional architectures in computer vision. Experiments were carried out for predicting different plant-biodiversity indices, namely, species richness, and Shannon and Simpson indices, for temperate grassland ecosystems. The results show that ResNeTS can achieve moderate improvements in terms of accuracy compared to other state-of-the-art architectures, such as InceptionTime (up to +0.021 r2), with reduced computational costs owing to its streamlined architecture.
PB IEEE
SN 1939-1404
YR 2024
FD 2024-09-03
LK https://hdl.handle.net/10347/41154
UL https://hdl.handle.net/10347/41154
LA eng
NO Dieste, Á. G., Argüello, F., Heras, D. B., Magdon, P., Linstädter, A., Dubovyk, O., & Muro, J. (2024). ResNeTS: A ResNet for Time Series Analysis of Sentinel-2 Data Applied to Grassland Plant-Biodiversity Prediction. "IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing", 17, 17349-17370.
NO The authors would like to thank the managers of the three exploratories, Kirsten Reichel-Jung, Iris Steitz, Sandra Weithmann, Juliane Vogt, Miriam Teuscher, and all former managers, for their work in maintaining the plot and project infrastructure; Victoria Grießmeier for giving support through the central office; Andreas Ostrowski for managing the central database; and Markus Fischer, Eduard Linsenmair, Dominik Hessenmöller, Daniel Prati, Ingo Schöning, François Buscot, Ernst-Detlef Schulze, Wolfgang W. Weisser, and the late Elisabeth Kalko, for their role in setting up the Biodiversity Exploratories project. The authors would like to thank the administration of the Hainich National Park, the UNESCO Biosphere Reserve of Schwäbische Alb, and the UNESCO Biosphere Reserve Schorfheide-Chorin, as well as all landowners, for the excellent collaboration. The authors would also like to thank Ralph Bolliger for providing and maintaining the species inventory datasets, Stephan Wollawer for maintaining the remote sensing database, Florian Männer for processing the biodiversity indices, and Lisa Schwarz for the photos of plant species provided.
DS Minerva
RD 28 abr 2026