% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@ARTICLE{Patnala:1041779,
      author       = {Patnala, Ankit and Schultz, Martin and Gall, Juergen},
      title        = {{BERT} {B}i-modal self-supervised learning for crop
                      classification using {S}entinel-2 and {P}lanetscope},
      journal      = {Frontiers in remote sensing},
      volume       = {6},
      issn         = {2673-6187},
      address      = {Lausanne},
      publisher    = {Frontiers Media},
      reportid     = {FZJ-2025-02419},
      pages        = {1555887},
      year         = {2025},
      abstract     = {Crop identification and monitoring of crop dynamics are
                      essential for agricultural planning, environmental
                      monitoring, and ensuring food security. Recent advancements
                      in remote sensing technology and state-of-the-art machine
                      learning have enabled large-scale automated crop
                      classification. However, these methods rely on labeled
                      training data, which requires skilled human annotators or
                      extensive field campaigns, making the process expensive and
                      time-consuming. Self-supervised learning techniques have
                      demonstrated promising results in leveraging large unlabeled
                      datasets across domains. Yet, self-supervised representation
                      learning for crop classification from remote sensing time
                      series remains under-explored due to challenges in curating
                      suitable pretext tasks. While bimodal self-supervised
                      approaches combining data from Sentinel-2 and Planetscope
                      sensors have facilitated pre-training, existing methods
                      primarily exploit the distinct spectral properties of these
                      complementary data sources. In this work, we propose novel
                      self-supervised pre-training strategies inspired from BERT
                      that leverage both the spectral and temporal resolution of
                      Sentinel-2 and Planetscope imagery. We carry out extensive
                      experiments comparing our approach to existing baseline
                      setups across nine test cases, in which our method
                      outperforms the baselines in eight instances. This
                      pre-training thus offers an effective representation of
                      crops for tasks such as crop classification.},
      cin          = {JSC},
      ddc          = {600},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {5111 - Domain-Specific Simulation $\&$ Data Life Cycle Labs
                      (SDLs) and Research Groups (POF4-511) / Earth System Data
                      Exploration (ESDE) / AI Strategy for Earth system data
                      $(kiste_20200501)$},
      pid          = {G:(DE-HGF)POF4-5111 / G:(DE-Juel-1)ESDE /
                      $G:(DE-Juel1)kiste_20200501$},
      typ          = {PUB:(DE-HGF)16},
      UT           = {WOS:001488134000001},
      doi          = {10.3389/frsen.2025.1555887},
      url          = {https://juser.fz-juelich.de/record/1041779},
}