Saved in:
Bibliographic Details
Main Authors: Sabo, Filip, Claverie, Martin, Meroni, Michele, Essenfelder, Arthur Hrast
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.06684
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929240516067328
author Sabo, Filip
Claverie, Martin
Meroni, Michele
Essenfelder, Arthur Hrast
author_facet Sabo, Filip
Claverie, Martin
Meroni, Michele
Essenfelder, Arthur Hrast
contents This paper investigated the potential of a multivariate Transformer model to forecast the temporal trajectory of the Fraction of Absorbed Photosynthetically Active Radiation (FAPAR) for short (1 month) and long horizon (more than 1 month) periods at the regional level in Europe and North Africa. The input data covers the period from 2002 to 2022 and includes remote sensing and weather data for modelling FAPAR predictions. The model was evaluated using a leave one year out cross-validation and compared with the climatological benchmark. Results show that the transformer model outperforms the benchmark model for one month forecasting horizon, after which the climatological benchmark is better. The RMSE values of the transformer model ranged from 0.02 to 0.04 FAPAR units for the first 2 months of predictions. Overall, the tested Transformer model is a valid method for FAPAR forecasting, especially when combined with weather data and used for short-term predictions.
format Preprint
id arxiv_https___arxiv_org_abs_2402_06684
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Ai4Fapar: How artificial intelligence can help to forecast the seasonal earth observation signal
Sabo, Filip
Claverie, Martin
Meroni, Michele
Essenfelder, Arthur Hrast
Atmospheric and Oceanic Physics
Machine Learning
This paper investigated the potential of a multivariate Transformer model to forecast the temporal trajectory of the Fraction of Absorbed Photosynthetically Active Radiation (FAPAR) for short (1 month) and long horizon (more than 1 month) periods at the regional level in Europe and North Africa. The input data covers the period from 2002 to 2022 and includes remote sensing and weather data for modelling FAPAR predictions. The model was evaluated using a leave one year out cross-validation and compared with the climatological benchmark. Results show that the transformer model outperforms the benchmark model for one month forecasting horizon, after which the climatological benchmark is better. The RMSE values of the transformer model ranged from 0.02 to 0.04 FAPAR units for the first 2 months of predictions. Overall, the tested Transformer model is a valid method for FAPAR forecasting, especially when combined with weather data and used for short-term predictions.
title Ai4Fapar: How artificial intelligence can help to forecast the seasonal earth observation signal
topic Atmospheric and Oceanic Physics
Machine Learning
url https://arxiv.org/abs/2402.06684