Bidirectional Recurrent Imputation and Abundance Estimation of LULC Classes With MODIS Multispectral Time-Series and Geo-Topographic and Climatic Data
Metadatos
Mostrar el registro completo del ítemEditorial
Institute of Electrical and Electronics Engineers
Materia
Abundance estimation Bidirectional long-short term memory (LSTM) Climatic data
Fecha
2024-01-29Referencia bibliográfica
J. Rodríguez-Ortega, R. Khaldi, D. Alcaraz-Segura and S. Tabik, "Bidirectional Recurrent Imputation and Abundance Estimation of LULC Classes With MODIS Multispectral Time-Series and Geo-Topographic and Climatic Data," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 17, pp. 4626-4645, 2024, doi: 10.1109/JSTARS.2024.3359647
Patrocinador
Project EarthCul PID2020-118041GB-I00 within the Spanish Research Projects Plan supported by MCIN/AEI/10.13039/501100011033 and by FEDER funds “Una manera de hacer Europa”; Project ECOPOTENTIAL, supported by the European Union’s Horizon 2020 Research and Innovation Programme under Grant 641762; TED project under Grant TED2021-129690B-I00, supported by the Ministry of Science and Innovation; Project “Thematic Center on Mountain Ecosystem and Remote sensing, Deep learning-AI e-Services University of Granada-Sierra Nevada” under Grant LifeWatch-2019-10-UGR-01, which has been cofunded by the Ministry of Science and Innovation through the FEDER funds from the Spanish Pluriregional Operational Program 2014-2020 (POPE), LifeWatch-ERIC action lineResumen
Remotely sensed data are dominated by mixed land
use and land cover (LULC) types. Spectral unmixing (SU) is a key
technique that disentangles mixed pixels into constituent LULC
types and their abundance fractions.While existing studies on deep
learning (DL) for SU typically focus on single time-step hyperspectral
or multispectral data, our work pioneers SU using MODIS MS
time series, addressing missing data with end-to-end DL models.
Our approach enhances a long-short-term-memory-based model
by incorporating geographic, topographic (geo-topographic), and
climatic ancillary information. Notably, our method eliminates the
need for explicit endmember extraction, instead learning the input–output relationship between mixed spectra and LULC abundances
through supervised learning. Experimental results demonstrate
that integrating spectral-temporal input data with geo-topographic
and climatic information significantly improves the estimation of
LULC abundances in mixed pixels. To facilitate this study, we
curated a novel labeled dataset for Andalusia (Spain) with monthly
MODIS MS time series at 460-m resolution for 2013. Named Andalusia MultiSpectral MultiTemporal Unmixing, this dataset
provides pixel-level annotations of LULC abundances along with
ancillary information.