% 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:1037598,
      author       = {Patnala, Ankit and Stadtler, Scarlet and Schultz, Martin G.
                      and Gall, Juergen},
      title        = {{B}i-modal contrastive learning for crop classification
                      using {S}entinel-2 and {P}lanetscope},
      journal      = {Frontiers in remote sensing},
      volume       = {5},
      issn         = {2673-6187},
      address      = {Lausanne},
      publisher    = {Frontiers Media},
      reportid     = {FZJ-2025-00769},
      pages        = {1480101},
      year         = {2024},
      abstract     = {Remote sensing has enabled large-scale crop classification
                      for understanding agricultural ecosystems and estimating
                      production yields. In recent years, machine learning has
                      become increasingly relevant for automated crop
                      classification. However, the existing algorithms require a
                      huge amount of annotated data. Self-supervised learning,
                      which enables training on unlabeled data, has great
                      potential to overcome the problem of annotation. Contrastive
                      learning, a self-supervised approach based on instance
                      discrimination, has shown promising results in the field of
                      natural as well as remote sensing images. Crop data often
                      consists of field parcels or sets of pixels from small
                      spatial regions. Additionally, one needs to account for
                      temporal patterns to correctly label crops. Hence, the
                      standard approaches for landcover classification cannot be
                      applied. In this work, we propose two contrastive
                      self-supervised learning approaches to obtain a pre-trained
                      model for crop classification without the need for labeled
                      data. First, we adopt the uni-modal contrastive method
                      (SCARF) and, second, we use a bi-modal approach based on
                      Sentinel-2 and Planetscope data instead of standard
                      transformations developed for natural images to accommodate
                      the spectral characteristics of crop pixels. Evaluation in
                      three regions of Germany and France shows that crop
                      classification with the pre-trained multi-modal model is
                      superior to the pre-trained uni-modal method as well as the
                      supervised baseline models in the majority of test cases.},
      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)},
      pid          = {G:(DE-HGF)POF4-5111},
      typ          = {PUB:(DE-HGF)16},
      UT           = {WOS:001380631400001},
      doi          = {10.3389/frsen.2024.1480101},
      url          = {https://juser.fz-juelich.de/record/1037598},
}