A Machine Learning Approach for NDVI Forecasting based on Sentinel-2 Data

Stefano Cavalli, Gabriele Penzotti, Michele Amoretti, Stefano Caselli

2021

Abstract

The Normalized Difference Vegetation Index (NDVI) is a well-known indicator of the greenness of the biomes. NDVI data are typically derived from satellites (such as Landsat, Sentinel-2, SPOT, Plèiades) that provide images in visible red and near-infrared bands. However, there are two main complications in satellite image acquisition: 1) orbits take several days to be completed, which implies that NDVI data are not daily updated; 2) the usability of satellite images to compute the NDVI value of a given area depends on the local meteorological conditions during satellite transit. Indeed, the discontinuous availability of up to date NDVI data is detrimental to the usability of NDVI as an indicator supporting agricultural decisions, e.g., whether to irrigate crops or not, as well as for alerting purposes. In this work, we propose a multivariate multi-step NDVI forecasting method based on Long Short-Term Memory (LSTM) networks. By careful selection of publicly available but relevant input data, the proposed method has been able to predict with high accuracy NDVI values for the next 1, 2 and 3 days considering regional data of interest.

Paper Citation

in Harvard Style

Cavalli S., Penzotti G., Amoretti M. and Caselli S. (2021). A Machine Learning Approach for NDVI Forecasting based on Sentinel-2 Data. In Proceedings of the 16th International Conference on Software Technologies - Volume 1: ICSOFT, ISBN 978-989-758-523-4, pages 473-480. DOI: 10.5220/0010544504730480

in Bibtex Style

@conference{icsoft21,
author={Stefano Cavalli and Gabriele Penzotti and Michele Amoretti and Stefano Caselli},
title={A Machine Learning Approach for NDVI Forecasting based on Sentinel-2 Data},
booktitle={Proceedings of the 16th International Conference on Software Technologies - Volume 1: ICSOFT,},
year={2021},
pages={473-480},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010544504730480},
isbn={978-989-758-523-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Software Technologies - Volume 1: ICSOFT,
TI - A Machine Learning Approach for NDVI Forecasting based on Sentinel-2 Data
SN - 978-989-758-523-4
AU - Cavalli S.
AU - Penzotti G.
AU - Amoretti M.
AU - Caselli S.
PY - 2021
SP - 473
EP - 480
DO - 10.5220/0010544504730480