Papers › Multi-Modal Temporal Attention Models for Crop Mapping from Satellite Time Series

Multi-Modal Temporal Attention Models for Crop Mapping from Satellite Time Series

14 Dec 2021arXiv:2112.07558archive 2025-07-28

Vivien Sainte Fare Garnot, Loic Landrieu, Nesrine Chehata

Optical and radar satellite time series are synergetic: optical images contain rich spectral information, while C-band radar captures useful geometrical information and is immune to cloud cover. Motivated by the recent success of temporal attention-based methods across multiple crop mapping tasks, we propose to investigate how these models can be adapted to operate on several modalities. We implement and evaluate multiple fusion schemes, including a novel approach and simple adjustments to the training procedure, significantly improving performance and efficiency with little added complexity. We show that most fusion schemes have advantages and drawbacks, making them relevant for specific settings. We then evaluate the benefit of multimodality across several tasks: parcel classification, pixel-based segmentation, and panoptic parcel segmentation. We show that by leveraging both optical and radar time series, multimodal temporal attention-based models can outmatch single-modality models in terms of performance and resilience to cloud cover. To conduct these experiments, we augment the PASTIS dataset with spatially aligned radar image time series. The resulting dataset, PASTIS-R, constitutes the first large-scale, multimodal, and open-access satellite time series dataset with semantic and instance annotations.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

VSainteuf/pastis-benchmark officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Panoptic SegmentationSemantic SegmentationTime SeriesTime Series Analysis

Datasets

Introduced by this paper, per the archive.

PASTIS-R

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Panoptic Segmentation PASTIS-R Early Fusion PQ 42 #1 of 1 Archive leaderboard report
Panoptic Segmentation PASTIS-R Early Fusion RQ 50.6 #1 of 1 Archive leaderboard report
Panoptic Segmentation PASTIS-R Early Fusion SQ 82.2 #1 of 1 Archive leaderboard report
Semantic Segmentation PASTIS-R Late Fusion IoU 66.3 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Temporal Dropout

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections