Bidirectional recurrent imputation and abundance estimation of LULC classes with MODIS multispectral time series and geo-topographic and climatic data
This work addresses the challenge of accurately estimating LULC abundances from mixed pixels in remote sensing, which is crucial for environmental monitoring and land management, but it is incremental as it builds on existing deep learning methods by adding temporal and ancillary data.
The paper tackles the problem of spectral unmixing for Land Use and Land Cover (LULC) types using MODIS multispectral time series, addressing missing data with an end-to-end deep learning model that incorporates geo-topographic and climatic information, resulting in significantly improved estimation of LULC abundances in mixed pixels.
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 (HS) or multispectral (MS) 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 (LSTM)-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 multispectral time series at 460m resolution for 2013. Named Andalusia MultiSpectral MultiTemporal Unmixing (Andalusia-MSMTU), this dataset provides pixel-level annotations of LULC abundances along with ancillary information. The dataset (https://zenodo.org/records/7752348) and code (https://github.com/jrodriguezortega/MSMTU) are available to the public.