vonLaszewski-cloudmask.bib

@misc{unkown,
  title =	 {???},
  howpublished = {???},
  year =	 2023,
  month =	 jun,
  note =	 {unkown},
}


@misc{www-fair,
  title =	 {{FAIR Principles}},
  howpublished = {Web Page},
  year =	 2022,
  month =	 jan,
  note =	 {[Online; accessed 23. Jun. 2023]},
  url =		 {https://www.go-fair.org/fair-principles}
}

@misc{www-sentinal-3,
  title =	 {{Sentinel-3}},
  howpublished = {Web Page},
  year =	 2023,
  month =	 jun,
  note =	 {[Online; accessed 22. Jun. 2023]},
  url =
                  {https://sentinels.copernicus.eu/web/sentinel/missions/sentinel-3}
}

@misc{las23-insights-mlcommons-education,
  title =	 {Insights in High-Performance Big Data Systems Gained
                  from Educational MLCommons Earthquake Benchmarks
                  Efforts},
  author =	 { von Laszewski, Gregor and J.P. Fleischer and Robert
                  Knuuti and Fox, Geoffrey. C. and Jake Kolessar and
                  Thomas Butler and Judy Fox },
  howpublished = {Technical report, under review},
  month =	 may,
  year =	 2023
}

@misc{www-rivanna,
  title =	 {{Rivanna at University of Virginia}},
  year =	 2023,
  month =	 jun,
  note =	 {[Online; accessed 21. Jun. 2023]},
  url =
                  {https://www.rc.virginia.edu/userinfo/rivanna/overview}
}

@misc{www-mlcommons,
  title =	 {{MLCommons}},
  howpublished = {Web Page},
  year =	 2023,
  month =	 jun,
  note =	 {[Online; accessed 21. Jun. 2023]},
  url =		 {https://mlcommons.org/en}
}

@misc{www-greene-hw,
  title =	 {{NYU High Performance Computing - Hardware specs}},
  year =	 2023,
  month =	 jun,
  howpublished = {Web Page},
  note =	 {[Online; accessed 21. Jun. 2023]},
  url =
                  {https://sites.google.com/nyu.edu/nyu-hpc/hpc-systems/greene/hardware-specs?authuser=0}
}

@misc{www-cudnn-seed,
  title =	 {{Reproducibility -- PyTorch 2.0 documentation}},
  year =	 2023,
  month =	 jun,
  howpublished = {Web Page},
  note =	 {[Online; accessed 20. Jun. 2023]},
  url =
                  {https://pytorch.org/docs/stable/notes/randomness.html#cuda-convolution-benchmarking}
}

@article{arxiv-mlperf,
  author =	 {Mattson, Peter and Cheng, Christine and Coleman,
                  Cody and Diamos, Greg and Micikevicius, Paulius and
                  Patterson, David and Tang, Hanlin and Wei, Gu-Yeon
                  and Bailis, Peter and Bittorf, Victor and Brooks,
                  David and Chen, Dehao and Dutta, Debojyoti and
                  Gupta, Udit and Hazelwood, Kim and Hock, Andrew and
                  Huang, Xinyuan and Ike, Atsushi and Jia, Bill and
                  Kang, Daniel and Kanter, David and Kumar, Naveen and
                  Liao, Jeffery and Ma, Guokai and Narayanan, Deepak
                  and Oguntebi, Tayo and Pekhimenko, Gennady and
                  Pentecost, Lillian and Reddi, Vijay Janapa and
                  Robie, Taylor and John, Tom {\relax St}. and Tabaru,
                  Tsuguchika and Wu, Carole-Jean and Xu, Lingjie and
                  Yamazaki, Masafumi and Young, Cliff and Zaharia,
                  Matei},
  title =	 {{MLPerf Training Benchmark}},
  journal =	 {arXiv},
  year =	 2019,
  month =	 oct,
  eprint =	 {1910.01500},
  doi =		 {10.48550/arXiv.1910.01500}
}

@article{Farrell2021MLPerfHA,
  title =	 {MLPerf{\texttrademark} HPC: A Holistic Benchmark
                  Suite for Scientific Machine Learning on HPC
                  Systems},
  author =	 {Steven Andrew Farrell and Murali Krishna Emani and
                  Jacob Balma and Lukas Drescher and Aleksandr Drozd
                  and Andreas Fink and Geoffrey Fox and David Kanter
                  and Thorsten Kurth and Peter Mattson and Dawei Mu
                  and Amit Ruhela and Kento Sato and Koichi Shirahata
                  and Tsuguchika Tabaru and Aristeidis Tsaris and Jan
                  Balewski and Benjamin Cumming and Takumi Danjo and
                  Jens Domke and Takaaki Fukai and Naoto Fukumoto and
                  Tatsuya Fukushi and Balazs Gerofi and Takumi Honda
                  and Toshiyuki Imamura and Akihiko Kasagi and Kentaro
                  Kawakami and Shuhei Kudo and Akiyoshi Kuroda and
                  Maxime Martinasso and Satoshi Matsuoka and Henrique
                  Mendonc and Kazuki Minami and Prabhat Ram and
                  Takashi Sawada and Mallikarjun (Arjun) Shankar and
                  Tom St. John and Akihiro Tabuchi and Venkatram
                  Vishwanath and Mohamed Wahib and Masafumi Yamazaki
                  and Junqi Yin},
  journal =	 {2021 IEEE/ACM Workshop on Machine Learning in High
                  Performance Computing Environments (MLHPC)},
  year =	 2021,
  pages =	 {33-45}
}

@article{Yan2018CloudAC,
  title =	 {Cloud and Cloud Shadow Detection Using Multilevel
                  Feature Fused Segmentation Network},
  author =	 {Zhiyuan Yan and Menglong Yan and Hao Sun and Kun Fu
                  and Jun Hong and Jun Sun and Yi Zhang and Xian Sun},
  journal =	 {IEEE Geoscience and Remote Sensing Letters},
  year =	 2018,
  volume =	 15,
  pages =	 {1600-1604}
}

@inproceedings{Thiyagalingam2022AIBF,
  title =	 {AI Benchmarking for Science: Efforts from the
                  MLCommons Science Working Group},
  author =	 {Jeyan Thiyagalingam and G. Laszewski and Junqi Yin
                  and Murali Krishna Emani and Juri Papay and Gregg
                  Barrett and Piotr Luszczek and Aristeidis Tsaris and
                  Christine R. Kirkpatrick and Feiyi Wang and Tom
                  Gibbs and Venkatram Vishwanath and Mallikarjun
                  (Arjun) Shankar and Geoffrey C. Fox and Anthony
                  J. G. Hey},
  booktitle =	 {ISC Workshops},
  year =	 2022
}

@article{Saunders1986AnAS,
  title =	 {An automated scheme for the removal of cloud
                  contamination from AVHRR radiances over western
                  Europe},
  author =	 {Roger W. Saunders},
  journal =	 {International Journal of Remote Sensing},
  year =	 1986,
  volume =	 7,
  pages =	 {867-886}
}

@article{Saunders1988AnIM,
  title =	 {An improved method for detecting clear sky and
                  cloudy radiances from AVHRR data},
  author =	 {Roger W. Saunders and Karl Theodor Kriebel},
  journal =	 {International Journal of Remote Sensing},
  year =	 1988,
  volume =	 9,
  pages =	 {123-150}
}

@article{Ronneberger2015UNetCN,
  title =	 {U-Net: Convolutional Networks for Biomedical Image
                  Segmentation},
  author =	 {Olaf Ronneberger and Philipp Fischer and Thomas
                  Brox},
  journal =	 {ArXiv},
  year =	 2015,
  volume =	 {abs/1505.04597}
}

@misc{www-mlcommons-science,
  author =	 {Fox, G. and Hey, T. and Thiyagalingam, J},
  title =	 {Science data working group of MLCommons
                  research. Web Page.},
  url =		 {https://mlcommons.org/en/groups/research-science/},
  month =	 apr,
  howpublished = {Web Page},
  year =	 2023,
  urldate =	 {04/20/2023}
}

@misc{www-lsf,
  author =	 {{IBM}},
  title =	 {Introduction to IBM Spectrum LSF},
  howpublished = {Web Page},
  url =
                  {https://www.ibm.com/docs/en/spectrum-lsf/10.1.0?topic=overview-lsf-introduction},
  month =	 apr,
  year =	 2023
}

@misc{www-slurm,
  journal =	 {Web page},
  key =		 {SLURM},
  month =	 apr,
  howpublished = {Web page},
  url =		 {https://slurm.schedmd.com},
  title =	 {Homepage},
  year =	 2003,
  month =	 apr
}

@misc{github-laszewsk-mlcommons,
  author =	 {von Laszewski, Gregor and {et.al.}},
  title =	 {laszewsk/mlcommons:
                  https://laszewsk.github.io/mlcommons/},
  url =		 {https://github.com/laszewsk/mlcommons},
  month =	 apr,
  howpublished = {Web Page},
  year =	 2023,
  urldate =	 {04/20/2023}
}

@misc{www-greene,
  author =	 {{New York University}},
  title =	 {NYU Greene Supercomputer},
  url =
                  {https://www.nyu.edu/life/information-technology/research-computing-services/high-performance-computing/high-performance-computing-nyu-it/hpc-supercomputer-clusters/greene.html},
  month =	 apr,
  year =	 2023,
  urldate =	 {04/20/2023},
  howpublished = {Web Page},
}

@misc{top500-greene,
  author =	 {{Top500}},
  title =	 {Greene - ThinkSystem SR650, Xeon Gold 6240 18C
                  2.6GHz, Infiniband HDR},
  howpublished = {Web Page},
  url =		 {https://www.top500.org/system/179851/},
  month =	 apr,
  year =	 2023
}

@InCollection{las22-cloudmesh-cc-reu,
  author =	 {von Laszewski, Gregor and Fleischer, J.P.},
  title =	 {{Hybrid Multi-Cloud Analytics Services Framework}},
  booktitle =	 {Computing for Global Challenges Symposium},
  publisher =	 {Online},
  year =	 2022,
  type =	 {Poster},
  edition =	 {Oct. 2022},
  month =	 jul,
  address =	 {University of Virginia, Charlottesville, VA},
  note =	 {corrected and updated Oct. 2022},
  url =
                  {https://raw.githubusercontent.com/cloudmesh/cloudmesh-cc/main/documents/analytics-service.pdf}
}

@misc{github-cloudmesh-cc,
  author =	 {Gregor von Laszewski and J.P. Fleischer},
  title =	 {{Hybrid Multi-Cloud Analytics Services Framework}},
  howpublished = {GitHub},
  year =	 2022,
  month =	 oct,
  note =	 {[Online; accessed 14. Oct. 2022]},
  url =		 {https://github.com/cloudmesh/cloudmesh-cc}
}

@misc{github-mlcommons-logging,
  author =	 {MLCommons},
  title =	 {GitHub MLCommons Logging},
  year =	 2022,
  url =		 {https://github.com/mlcommons/logging},
}

@misc{github-cloudmesh-sbatch,
  author =	 {Gregor von Laszewski},
  title =	 {{Hyperparameter Search Batch Job Generator}},
  howpublished = {GitHub},
  year =	 2022,
  month =	 oct,
  note =	 {[Online; accessed 14. Oct. 2022]},
  url =		 {https://github.com/cloudmesh/cloudmesh-sbatch}
}

@article{las-2021-covid,
  author =	 {Geoffrey C. Fox and Gregor von Laszewski and Fugang
                  Wang and Saumyadipta Pyne},
  title =	 {AICov: An Integrative Deep Learning Framework for
                  COVID-19 Forecasting with Population Covariates},
  journal =	 {Journal of Data Science},
  volume =	 19,
  number =	 2,
  year =	 2021,
  pages =	 {293--313},
  doi =		 {10.6339/21-JDS1007},
  issn =	 {1680-743X},
  publisher =	 {School of Statistics, Renmin University of China}
}

@misc{google-meeting-notes,
  author =	 {Varshitha Chennamsetti and Alex Tang and Rouchen Gu
                  and von Laszewski, Gregor},
  title =	 {{NYU-MLCommons Meeting Notes}},
  howpublished = {Google Drive},
  year =	 2022,
  month =	 oct,
  note =	 {[Online; accessed 25. Mar. 2023]},
  url =
                  {https://docs.google.com/document/d/1LUuVSeLYv-717TJxtyikihLmuyf6at50FNBn57Doo_4/edit#heading=h.7p7jjuq4vbsm}
}

@inbook{mlcommons-benchmark-2023,
  author =	 {Thiyagalingam, Jeyan and von Laszewski, Gregor and
                  Yin, Junqi and Emani, Murali and Papay, Juri and
                  Barrett, Gregg and Luszczek, Piotr and Tsaris,
                  Aristeidis and Kirkpatrick, Christine and Wang,
                  Feiyi and Gibbs, Tom and Vishwanath, Venkatram and
                  Shankar, Mallikarjun and Fox, Geoffrey and Hey,
                  Tony},
  year =	 2023,
  month =	 01,
  pages =	 {47-64},
  title =	 {AI Benchmarking for Science: Efforts from the
                  MLCommons Science Working Group},
  isbn =	 {978-3-031-23219-0},
  doi =		 {10.1007/978-3-031-23220-6_4}
}

@article{Merchant2005ProbabilisticPB,
  title =	 {Probabilistic physically based cloud screening of
                  satellite infrared imagery for operational sea
                  surface temperature retrieval},
  author =	 {Christopher J. Merchant and Andrew R. Harris and
                  Eileen Maturi and S. Maccallum},
  journal =	 {Quarterly Journal of the Royal Meteorological
                  Society},
  year =	 2005,
  volume =	 131
}

@article{WIELAND2019111203,
  title =	 {Multi-sensor cloud and cloud shadow segmentation
                  with a convolutional neural network},
  journal =	 {Remote Sensing of Environment},
  volume =	 230,
  pages =	 111203,
  year =	 2019,
  issn =	 {0034-4257},
  doi =		 {https://doi.org/10.1016/j.rse.2019.05.022},
  url =
                  {https://www.sciencedirect.com/science/article/pii/S0034425719302159},
  author =	 {Marc Wieland and Yu Li and Sandro Martinis},
  keywords =	 {Cloud, Cloud shadow, Convolutional neural network,
                  Landsat, Sentinel-2},
  abstract =	 {Cloud and cloud shadow segmentation is a crucial
                  pre-processing step for any application that uses
                  multi-spectral satellite images. In particular,
                  disaster related applications (e.g., flood
                  monitoring or rapid damage mapping), which are
                  highly time- and data-critical, require methods that
                  produce accurate cloud and cloud shadow masks in
                  short time while being able to adapt to large
                  variations in the target domain (induced by
                  atmospheric conditions, different sensors, scene
                  properties, etc.). In this study, we propose a
                  data-driven approach to semantic segmentation of
                  cloud and cloud shadow in single date images based
                  on a modified U-Net convolutional neural network
                  that aims to fulfil these requirements. We train the
                  network on a global database of Landsat OLI images
                  for the segmentation of five classes (“shadow”,
                  “cloud”, “water”, “land” and “snow/ice”). We compare
                  the results to state-of-the-art methods, proof the
                  model's generalization ability across multiple
                  satellite sensors (Landsat TM, Landsat ETM+, Landsat
                  OLI and Sentinel-2) and show the influence of
                  different training strategies and spectral band
                  combinations on the performance of the
                  segmentation. Our method consistently outperforms
                  Fmask and a traditional Random Forest classifier on
                  a globally distributed multi-sensor test dataset in
                  terms of accuracy, Cohen's Kappa coefficient, Dice
                  coefficient and inference speed. The results
                  indicate that a reduced feature space composed
                  solely of red, green, blue and near-infrared bands
                  already produces good results for all tested
                  sensors. If available, adding shortwave-infrared
                  bands can increase the accuracy. Contrast and
                  brightness augmentations of the training data
                  further improve the segmentation performance. The
                  best performing U-Net model achieves an accuracy of
                  0.89, Kappa of 0.82 and Dice coefficient of 0.85,
                  while running the inference over 896 test image
                  tiles with 44.8 s/megapixel (2.8 s/megapixel on
                  GPU). The Random Forest classifier reaches an
                  accuracy of 0.79, Kappa of 0.65 and Dice coefficient
                  of 0.74 with 3.9 s/megapixel inference time (on CPU)
                  on the same training and testing data. The
                  rule-based Fmask method takes significantly longer
                  (277.8 s/megapixel) and produces results with an
                  accuracy of 0.75, Kappa of 0.60 and Dice coefficient
                  of 0.72.}
}

@InProceedings{RFB15a,
  author =	 "O. Ronneberger and P.Fischer and T. Brox",
  title =	 "U-Net: Convolutional Networks for Biomedical Image
                  Segmentation",
  booktitle =	 "Medical Image Computing and Computer-Assisted
                  Intervention (MICCAI)",
  series =	 "LNCS",
  volume =	 9351,
  pages =	 "234--241",
  year =	 2015,
  publisher =	 "Springer",
  note =	 "(available on arXiv:1505.04597 [cs.CV])",
  url =
                  "http://lmb.informatik.uni-freiburg.de/Publications/2015/RFB15a"
}

@ARTICLE{8401847,
  author =	 {Yan, Zhiyuan and Yan, Menglong and Sun, Hao and Fu,
                  Kun and Hong, Jun and Sun, Jun and Zhang, Yi and
                  Sun, Xian},
  journal =	 {IEEE Geoscience and Remote Sensing Letters},
  title =	 {Cloud and cloud shadow detection using multilevel
                  feature fused segmentation network},
  year =	 2018,
  volume =	 15,
  number =	 10,
  pages =	 {1600-1604},
  doi =		 {10.1109/LGRS.2018.2846802}
}