Generalized Classification of Satellite Image Time Series with Thermal Positional Encoding

• URL: http://arxiv.org/abs/2203.09175v1
• Date: Thu, 17 Mar 2022 08:53:22 GMT
• Title: Generalized Classification of Satellite Image Time Series with Thermal Positional Encoding
• Authors: Joachim Nyborg, Charlotte Pelletier, Ira Assent
• Abstract summary: We propose Thermal Positional generalization (TPE) for attention-based crop classification. TPE is based on thermal time, which is obtained by accumulating daily average temperatures over the growing season. We demonstrate our approach on a crop classification task across four different European regions, where we obtain state-of-the-art results.
• Score: 3.5773108446345034
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large-scale crop type classification is a task at the core of remote sensing efforts with applications of both economic and ecological importance. Current state-of-the-art deep learning methods are based on self-attention and use satellite image time series (SITS) to discriminate crop types based on their unique growth patterns. However, existing methods generalize poorly to regions not seen during training mainly due to not being robust to temporal shifts of the growing season caused by variations in climate. To this end, we propose Thermal Positional Encoding (TPE) for attention-based crop classifiers. Unlike previous positional encoding based on calendar time (e.g. day-of-year), TPE is based on thermal time, which is obtained by accumulating daily average temperatures over the growing season. Since crop growth is directly related to thermal time, but not calendar time, TPE addresses the temporal shifts between different regions to improve generalization. We propose multiple TPE strategies, including learnable methods, to further improve results compared to the common fixed positional encodings. We demonstrate our approach on a crop classification task across four different European regions, where we obtain state-of-the-art generalization results.

Related papers

• MambaDS: Near-Surface Meteorological Field Downscaling with Topography Constrained Selective State Space Modeling [68.69647625472464]
  Downscaling, a crucial task in meteorological forecasting, enables the reconstruction of high-resolution meteorological states for target regions. Previous downscaling methods lacked tailored designs for meteorology and encountered structural limitations. We propose a novel model called MambaDS, which enhances the utilization of multivariable correlations and topography information.
  arXiv  Detail & Related papers  (2024-08-20T13:45:49Z)
• Generalization Enhancement Strategies to Enable Cross-year Cropland Mapping with Convolutional Neural Networks Trained Using Historical Samples [5.703107376077042]
  The accuracy of mapping agricultural fields across large areas is steadily improving with high-resolution satellite imagery and deep learning (DL) models. However, developing effective DL models often requires large, expensive label datasets, typically available only for specific years or locations. This limits the ability to create annual maps essential for agricultural monitoring, as domain shifts occur between years and regions due to changes in farming practices and environmental conditions.
  arXiv  Detail & Related papers  (2024-08-12T19:42:09Z)
• Detecting Abnormal Operations in Concentrated Solar Power Plants from Irregular Sequences of Thermal Images [2.048226951354646]
  Concentrated Solar Power (CSP) plants store energy by heating a storage medium with an array of mirrors that focus sunlight onto solar receivers atop a central tower. operating at high temperatures these receivers face risks such as freezing, deformation, and corrosion, leading to operational failures, downtime, or costly equipment damage. We study the problem of anomaly detection (AD) in sequences of thermal images collected over a year from an operational CSP plant.
  arXiv  Detail & Related papers  (2024-06-23T11:09:21Z)
• PeFAD: A Parameter-Efficient Federated Framework for Time Series Anomaly Detection [51.20479454379662]
  We propose a. Federated Anomaly Detection framework named PeFAD with the increasing privacy concerns. We conduct extensive evaluations on four real datasets, where PeFAD outperforms existing state-of-the-art baselines by up to 28.74%.
  arXiv  Detail & Related papers  (2024-06-04T13:51:08Z)
• Combining Satellite and Weather Data for Crop Type Mapping: An Inverse Modelling Approach [23.23933321161625]
  We propose a deep learning model that combines weather (Daymet) and satellite imagery (Sentinel-2) to generate accurate crop maps. We show that our approach provides significant improvements over existing algorithms that solely rely on spectral imagery. We conclude by correlating our results with crop phenology to show that WSTATT is able to capture physical properties of crop growth.
  arXiv  Detail & Related papers  (2024-01-29T04:15:22Z)
• Long-Term Invariant Local Features via Implicit Cross-Domain Correspondences [79.21515035128832]
  We conduct a thorough analysis of the performance of current state-of-the-art feature extraction networks under various domain changes. We propose a novel data-centric method, Implicit Cross-Domain Correspondences (iCDC) iCDC represents the same environment with multiple Neural Radiance Fields, each fitting the scene under individual visual domains.
  arXiv  Detail & Related papers  (2023-11-06T18:53:01Z)
• ClimaX: A foundation model for weather and climate [51.208269971019504]
  ClimaX is a deep learning model for weather and climate science. It can be pre-trained with a self-supervised learning objective on climate datasets. It can be fine-tuned to address a breadth of climate and weather tasks.
  arXiv  Detail & Related papers  (2023-01-24T23:19:01Z)
• PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer [55.936527926778695]
  Recent deep learning approaches focus on mining subtle r clues using convolutional neural networks with limited-temporal receptive fields. In this paper, we propose the PhysFormer, an end-to-end video transformer based architecture.
  arXiv  Detail & Related papers  (2021-11-23T18:57:11Z)
• TimeMatch: Unsupervised Cross-Region Adaptation by Temporal Shift Estimation [5.027714423258537]
  TimeMatch is a new unsupervised domain adaptation method for SITS that directly accounts for the temporal shift. TimeMatch outperforms all competing methods by 11% in F1-score across five different adaptation scenarios. We introduce an open-access dataset for cross-region adaptation with SITS from four different regions in Europe.
  arXiv  Detail & Related papers  (2021-11-04T08:32:59Z)
• Resilient In-Season Crop Type Classification in Multispectral Satellite Observations using Growth Stage Normalization [2.4186361602373823]
  We present an approach for within-season crop type classification using moderate spatial resolution (30 m) satellite data. We use a neural network leveraging both convolutional and recurrent layers to predict if a pixel contains corn, soybeans, or another crop or land cover type. We show that our approach using growth stage-normalized time series outperforms fixed-date time series.
  arXiv  Detail & Related papers  (2020-09-21T21:55:32Z)
• A Transfer Learning approach to Heatmap Regression for Action Unit intensity estimation [50.261472059743845]
  Action Units (AUs) are geometrically-based atomic facial muscle movements. We propose a novel AU modelling problem that consists of jointly estimating their localisation and intensity. A Heatmap models whether an AU occurs or not at a given spatial location.
  arXiv  Detail & Related papers  (2020-04-14T16:51:13Z)

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.