Spatio-Temporal Transformers for Long-Term NDVI Forecasting

• URL: http://arxiv.org/abs/2602.01799v1
• Date: Mon, 02 Feb 2026 08:29:45 GMT
• Title: Spatio-Temporal Transformers for Long-Term NDVI Forecasting
• Authors: Ido Faran, Nathan S. Netanyahu, Maxim Shoshany,
• Abstract summary: STT-LTF processes multi-scale spatial patches alongside temporal sequences (up to 20 years) through a unified transformer architecture.<n>The framework employs comprehensive self-supervised learning with spatial masking, temporal masking, and horizon sampling strategies.<n>It directly predicts arbitrary future time points without error accumulation, incorporating spatial patch embeddings, cyclical temporal encoding, and geographic coordinates.
• Score: 0.5097809301149342
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Long-term satellite image time series (SITS) analysis in heterogeneous landscapes faces significant challenges, particularly in Mediterranean regions where complex spatial patterns, seasonal variations, and multi-decade environmental changes interact across different scales. This paper presents the Spatio-Temporal Transformer for Long Term Forecasting (STT-LTF ), an extended framework that advances beyond purely temporal analysis to integrate spatial context modeling with temporal sequence prediction. STT-LTF processes multi-scale spatial patches alongside temporal sequences (up to 20 years) through a unified transformer architecture, capturing both local neighborhood relationships and regional climate influences. The framework employs comprehensive self-supervised learning with spatial masking, temporal masking, and horizon sampling strategies, enabling robust model training from 40 years of unlabeled Landsat imagery. Unlike autoregressive approaches, STT-LTF directly predicts arbitrary future time points without error accumulation, incorporating spatial patch embeddings, cyclical temporal encoding, and geographic coordinates to learn complex dependencies across heterogeneous Mediterranean ecosystems. Experimental evaluation on Landsat data (1984-2024) demonstrates that STT-LTF achieves a Mean Absolute Error (MAE) of 0.0328 and R^2 of 0.8412 for next-year predictions, outperforming traditional statistical methods, CNN-based approaches, LSTM networks, and standard transformers. The framework's ability to handle irregular temporal sampling and variable prediction horizons makes it particularly suitable for analysis of heterogeneous landscapes experiencing rapid ecological transitions.

Related papers

• Continuous Exposure-Time Modeling for Realistic Atmospheric Turbulence Synthesis [65.19146708498346]
  Atmospheric turbulence significantly degrades long-range imaging by introducing geometric warping and exposure-timedependent blur.<n>Existing methods for turbulence effects often oversimplify the relationship between blur and exposure-time.<n>We construct ET-Turb, a large-scale synthetic turbulence dataset that explicitly incorporates continuous exposure-time modeling.
  arXiv  Detail & Related papers  (2026-03-02T02:58:44Z)
• A multimodal Transformer for InSAR-based ground deformation forecasting with cross-site generalization across Europe [3.3295066998131637]
  We propose a patch-based Transformer for single-step, fixed-interval next-epoch nowcasting of displacement maps from EGMS time series.<n>The model ingests recent displacement snapshots together with (i) static kinematic indicators (mean velocity, acceleration, seasonal amplitude) computed in a leakage-safe manner from the training window only.<n>On the eastern Ireland tile (E32N34), the STGCN is strongest in the displacement-only setting, whereas the multimodal Transformer clearly outperforms CNN-LSTM, CNN-LSTM+Attn, and multimodal STGCN.
  arXiv  Detail & Related papers  (2025-12-30T00:07:36Z)
• B-TGAT: A Bi-directional Temporal Graph Attention Transformer for Clustering Multivariate Spatiotemporal Data [0.15763762230817438]
  We present a time-distributed hybrid U-Net autocoder that integrates a Bi-multidimensional Graph Attention Transformer (B-TGAT) to guide efficient temporal clustering.<n>The encoder and decoder are equipped with ConvLSTM2D modules that extract joint spatial-temporal features.<n> experiments show superior cluster separability, temporal stability, and alignment with known climate transitions compared to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-09-16T16:08:21Z)
• XFMNet: Decoding Cross-Site and Nonstationary Water Patterns via Stepwise Multimodal Fusion for Long-Term Water Quality Forecasting [8.412056996021962]
  XFMNet is a stepwise multimodal fusion network that integrates remote sensing precipitation imagery.<n>XFMNet captures both long-term trends and short-term fluctuations.<n>Experiments on real-world datasets demonstrate substantial improvements over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-08-01T04:11:36Z)
• Transformer with Koopman-Enhanced Graph Convolutional Network for Spatiotemporal Dynamics Forecasting [12.301897782320967]
  TK-GCN is a two-stage framework that integrates geometry-aware spatial encoding with long-range temporal modeling.<n>We show that TK-GCN consistently delivers superior predictive accuracy across a range of forecast horizons.
  arXiv  Detail & Related papers  (2025-07-05T01:26:03Z)
• Interpretable Time Series Autoregression for Periodicity Quantification [18.6300875919604]
  Time series autoregression (AR) is a classical tool for auto-correlations and periodic structures in real-world systems.<n>We revisit this model by introducing sparse autoregression (SAR), where $ell$-norm constraints are used to isolate dominant periodicities.<n>We validate our framework on large-scale mobility and climate time series.
  arXiv  Detail & Related papers  (2025-06-28T14:17:11Z)
• Multivariate Long-term Time Series Forecasting with Fourier Neural Filter [42.60778405812048]
  We introduce FNF as the backbone and DBD as architecture to provide excellent learning capabilities and optimal learning pathways for spatial-temporal modeling.<n>We show that FNF unifies local time-domain and global frequency-domain information processing within a single backbone that extends naturally to spatial modeling.
  arXiv  Detail & Related papers  (2025-06-10T18:40:20Z)
• Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective [63.60312929416228]
  textbftextitAttraos incorporates chaos theory into long-term time series forecasting. We show that Attraos outperforms various LTSF methods on mainstream datasets and chaotic datasets with only one-twelfth of the parameters compared to PatchTST.
  arXiv  Detail & Related papers  (2024-02-18T05:35:01Z)
• Rethinking Urban Mobility Prediction: A Super-Multivariate Time Series Forecasting Approach [71.67506068703314]
  Long-term urban mobility predictions play a crucial role in the effective management of urban facilities and services. Traditionally, urban mobility data has been structured as videos, treating longitude and latitude as fundamental pixels. In our research, we introduce a fresh perspective on urban mobility prediction. Instead of oversimplifying urban mobility data as traditional video data, we regard it as a complex time series.
  arXiv  Detail & Related papers  (2023-12-04T07:39:05Z)
• Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation [53.04781510348416]
  Video-based 3D human pose and shape estimations are evaluated by intra-frame accuracy and inter-frame smoothness. We propose to structurally decouple the modeling of long-term and short-term correlations in an end-to-end framework, Global-to-Local Transformer (GLoT) Our GLoT surpasses previous state-of-the-art methods with the lowest model parameters on popular benchmarks, i.e., 3DPW, MPI-INF-3DHP, and Human3.6M.
  arXiv  Detail & Related papers  (2023-03-26T14:57:49Z)
• Supporting Optimal Phase Space Reconstructions Using Neural Network Architecture for Time Series Modeling [68.8204255655161]
  We propose an artificial neural network with a mechanism to implicitly learn the phase spaces properties. Our approach is either as competitive as or better than most state-of-the-art strategies.
  arXiv  Detail & Related papers  (2020-06-19T21:04:47Z)
• Spatial-Temporal Transformer Networks for Traffic Flow Forecasting [74.76852538940746]
  We propose a novel paradigm of Spatial-Temporal Transformer Networks (STTNs) to improve the accuracy of long-term traffic forecasting. Specifically, we present a new variant of graph neural networks, named spatial transformer, by dynamically modeling directed spatial dependencies. The proposed model enables fast and scalable training over a long range spatial-temporal dependencies.
  arXiv  Detail & Related papers  (2020-01-09T10:21:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.