Merge branch 'paper'

.github/workflows/paper-draft-pdf.yml

@@ -0,0 +1,24 @@
+name: Paper Draft PDF
+on: [push]
+
+jobs:
+  paper:
+    runs-on: ubuntu-latest
+    name: Paper Draft
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Build draft PDF
+        uses: openjournals/openjournals-draft-action@master
+        with:
+          journal: joss
+          # This should be the path to the paper within your repo.
+          paper-path: paper/paper.md
+      - name: Upload
+        uses: actions/upload-artifact@v4
+        with:
+          name: paper
+          # This is the output path where Pandoc will write the compiled
+          # PDF. Note, this should be the same directory as the input
+          # paper.md
+          path: paper/paper.pdf

paper/paper.bib

@@ -0,0 +1,299 @@
+@article{qcrunch,
+    title = {The Quant Crunch: How the demand for data science skills is
+            disrupting the job market},
+    author = {Miller, Steven and Hughes, Debbie},
+    journal = {Business Higher Education Forum},
+    year = {2017}
+}
+
+@article{see2024,
+    author = {See, Linda and Lesiv, Myroslava and Schepaschenko, Dmitry},
+    title = {Integrating Remote Sensing and Geospatial Big Data for Land Cover
+            and Land Use Mapping and Monitoring},
+    journal = {Land},
+    volume = {13},
+    year = {2024},
+    number = {6},
+    article-number = {769},
+    url = {https://www.mdpi.com/2073-445X/13/6/769},
+    issn = {2073-445X},
+    abstract = {The last few decades have seen an explosion in the availability
+               of remotely sensed and geospatial big data, which are defined by the 3 Vs:
+               a large volume of data; a variety of different forms of data; and the rapid
+               velocity of data arrival [...]},
+    doi = {10.3390/land13060769}
+}
+
+@article{era5,
+    author = {Hersbach, Hans and Bell, Bill and Berrisford, Paul and Hirahara,
+             Shoji and Horányi, András and Muñoz-Sabater, Joaquín and Nicolas, Julien
+             and Peubey, Carole and Radu, Raluca and Schepers, Dinand and Simmons,
+             Adrian and Soci, Cornel and Abdalla, Saleh and Abellan, Xavier and Balsamo,
+             Gianpaolo and Bechtold, Peter and Biavati, Gionata and Bidlot, Jean and
+             Bonavita, Massimo and De Chiara, Giovanna and Dahlgren, Per and Dee, Dick
+             and Diamantakis, Michail and Dragani, Rossana and Flemming, Johannes and
+             Forbes, Richard and Fuentes, Manuel and Geer, Alan and Haimberger, Leo and
+             Healy, Sean and Hogan, Robin J. and Hólm, Elías and Janisková, Marta and
+             Keeley, Sarah and Laloyaux, Patrick and Lopez, Philippe and Lupu, Cristina
+             and Radnoti, Gabor and de Rosnay, Patricia and Rozum, Iryna and Vamborg,
+             Freja and Villaume, Sebastien and Thépaut, Jean-Noël},
+    title = {The ERA5 global reanalysis},
+    journal = {Quarterly Journal of the Royal Meteorological Society},
+    volume = {146},
+    number = {730},
+    pages = {1999-2049},
+    keywords = {climate reanalysis, Copernicus Climate Change Service, data
+               assimilation, ERA5, historical observations},
+    doi = {https://doi.org/10.1002/qj.3803},
+    url = {https://rmets.onlinelibrary.wiley.com/doi/abs/10.1002/qj.3803},
+    eprint = {https://rmets.onlinelibrary.wiley.com/doi/pdf/10.1002/qj.3803},
+    abstract = {Abstract Within the Copernicus Climate Change Service (C3S),
+               ECMWF is producing the ERA5 reanalysis which, once completed, will embody a
+               detailed record of the global atmosphere, land surface and ocean waves from
+               1950 onwards. This new reanalysis replaces the ERA-Interim reanalysis
+               (spanning 1979 onwards) which was started in 2006. ERA5 is based on the
+               Integrated Forecasting System (IFS) Cy41r2 which was operational in 2016.
+               ERA5 thus benefits from a decade of developments in model physics, core
+               dynamics and data assimilation. In addition to a significantly enhanced
+               horizontal resolution of 31 km, compared to 80 km for ERA-Interim, ERA5 has
+               hourly output throughout, and an uncertainty estimate from an ensemble
+               (3-hourly at half the horizontal resolution). This paper describes the
+               general set-up of ERA5, as well as a basic evaluation of characteristics
+               and performance, with a focus on the dataset from 1979 onwards which is
+               currently publicly available. Re-forecasts from ERA5 analyses show a gain
+               of up to one day in skill with respect to ERA-Interim. Comparison with
+               radiosonde and PILOT data prior to assimilation shows an improved fit for
+               temperature, wind and humidity in the troposphere, but not the
+               stratosphere. A comparison with independent buoy data shows a much improved
+               fit for ocean wave height. The uncertainty estimate reflects the evolution
+               of the observing systems used in ERA5. The enhanced temporal and spatial
+               resolution allows for a detailed evolution of weather systems. For
+               precipitation, global-mean correlation with monthly-mean GPCP data is
+               increased from 67\% to 77\%. In general, low-frequency variability is found
+               to be well represented and from 10 hPa downwards general patterns of
+               anomalies in temperature match those from the ERA-Interim, MERRA-2 and
+               JRA-55 reanalyses.},
+    year = {2020}
+}
+
+@article{modis,
+    title = {An overview of MODIS Land data processing and product status},
+    journal = {Remote Sensing of Environment},
+    volume = {83},
+    number = {1},
+    pages = {3-15},
+    year = {2002},
+    note = {The Moderate Resolution Imaging Spectroradiometer (MODIS): a new
+           generation of Land Surface Monitoring},
+    issn = {0034-4257},
+    doi = {https://doi.org/10.1016/S0034-4257(02)00084-6},
+    url = {https://www.sciencedirect.com/science/article/pii/S0034425702000846},
+    author = {C.O Justice and J.R.G Townshend and E.F Vermote and E Masuoka and
+             R.E Wolfe and N Saleous and D.P Roy and J.T Morisette},
+    abstract = {Data from the first Moderate Resolution Imaging
+               Spectroradiometer (MODIS) instrument on the NASA Terra Platform are being
+               used to provide a new generation of land data products in support of the
+               National Aeronautics and Space Administration (NASA)'s Earth Science
+               Enterprise, global change research and natural resource management. The
+               MODIS products include global data sets heretofore unavailable, derived
+               from new moderate resolution spectral bands with spatial resolutions of 250
+               m to 1 km. A partnership between Science Team members and the MODIS Science
+               Data Support Team is producing data sets of unprecedented volume and number
+               for the land research and applications. This overview paper provides a
+               summary of the instrument performance and status, the data production
+               system, the products, their status and availability for land studies.}
+}
+
+@inproceedings{sentinel2,
+    author = {Spoto, Francois and Sy, Omar and Laberinti, Paolo and Martimort,
+             Philippe and Fernandez, Valerie and Colin, Olivier and Hoersch, Bianca and
+             Meygret, Aime},
+    booktitle = {2012 IEEE International Geoscience and Remote Sensing Symposium},
+    title = {Overview Of Sentinel-2},
+    year = {2012},
+    volume = {},
+    number = {},
+    pages = {1707-1710},
+    keywords = {Satellites;Europe;Spatial
+               resolution;Monitoring;Earth;Clouds;Satellite broadcasting;Earth
+               Observation;Land Monitoring;Multispectral Imaging},
+    doi = {10.1109/IGARSS.2012.6351195}
+}
+
+@article{numpy,
+    title = {Array programming with {NumPy}},
+    author = {Charles R. Harris and K. Jarrod Millman and St{\'{e}}fan J.
+             van der Walt and Ralf Gommers and Pauli Virtanen and David
+             Cournapeau and Eric Wieser and Julian Taylor and Sebastian
+             Berg and Nathaniel J. Smith and Robert Kern and Matti Picus
+             and Stephan Hoyer and Marten H. van Kerkwijk and Matthew
+             Brett and Allan Haldane and Jaime Fern{\'{a}}ndez del
+             R{\'{i}}o and Mark Wiebe and Pearu Peterson and Pierre
+             G{\'{e}}rard-Marchant and Kevin Sheppard and Tyler Reddy and
+             Warren Weckesser and Hameer Abbasi and Christoph Gohlke and
+             Travis E. Oliphant},
+    year = {2020},
+    month = sep,
+    journal = {Nature},
+    volume = {585},
+    number = {7825},
+    pages = {357--362},
+    doi = {10.1038/s41586-020-2649-2},
+    publisher = {Springer Science and Business Media {LLC}},
+    url = {https://doi.org/10.1038/s41586-020-2649-2}
+}
+
+@article{scipy,
+    author  = {Virtanen, Pauli and Gommers, Ralf and Oliphant, Travis E. and
+              Haberland, Matt and Reddy, Tyler and Cournapeau, David and
+              Burovski, Evgeni and Peterson, Pearu and Weckesser, Warren and
+              Bright, Jonathan and {van der Walt}, St{\'e}fan J. and
+              Brett, Matthew and Wilson, Joshua and Millman, K. Jarrod and
+              Mayorov, Nikolay and Nelson, Andrew R. J. and Jones, Eric and
+              Kern, Robert and Larson, Eric and Carey, C J and
+              Polat, {\.I}lhan and Feng, Yu and Moore, Eric W. and
+              {VanderPlas}, Jake and Laxalde, Denis and Perktold, Josef and
+              Cimrman, Robert and Henriksen, Ian and Quintero, E. A. and
+              Harris, Charles R. and Archibald, Anne M. and
+              Ribeiro, Ant{\^o}nio H. and Pedregosa, Fabian and
+              {van Mulbregt}, Paul and {SciPy 1.0 Contributors}},
+    title = {{{SciPy} 1.0: Fundamental Algorithms for Scientific Computing in Python}},
+    journal = {Nature Methods},
+    year = {2020},
+    volume = {17},
+    pages = {261--272},
+    adsurl = {https://rdcu.be/b08Wh},
+    doi = {10.1038/s41592-019-0686-2},
+}
+
+@article{xarray,
+    title = {xarray: {N-D} labeled arrays and datasets in {Python}},
+    author = {Hoyer, S. and J. Hamman},
+    journal = {Journal of Open Research Software},
+    volume = {5},
+    number = {1},
+    year = {2017},
+    publisher = {Ubiquity Press},
+    doi = {10.5334/jors.148},
+    url = {https://doi.org/10.5334/jors.148}
+}
+
+@manual{dask,
+    title = {Dask: Library for dynamic task scheduling},
+    author = {{Dask Development Team}},
+    year = {2016},
+    url = {http://dask.pydata.org},
+}
+
+@manual{gdal,
+    title = {{GDAL/OGR} Geospatial Data Abstraction software Library},
+    author = {{GDAL/OGR contributors}},
+    organization = {Open Source Geospatial Foundation},
+    year = {2024},
+    url = {https://gdal.org},
+    doi = {10.5281/zenodo.5884351},
+}
+
+@manual{rasterio,
+    title = {Rasterio: geospatial raster I/O for {Python} programmers},
+    author = {Sean Gillies and others},
+    organization = {Mapbox},
+    year = {2013--},
+    url = "https://github.com/rasterio/rasterio"
+}
+
+@manual{rioxarray,
+    title = {rioxarray: Geospatial xarray extension powered by rasterio},
+    author = {{rioxarray Development Team}},
+    organization = {Corteva, Inc.},
+    year = {2019},
+    url = {https://github.com/corteva/rioxarray},
+}
+
+@article{sklearn,
+    title={Scikit-learn: Machine Learning in {P}ython},
+    author={Pedregosa, F. and Varoquaux, G. and Gramfort, A. and Michel, V.
+            and Thirion, B. and Grisel, O. and Blondel, M. and Prettenhofer, P.
+            and Weiss, R. and Dubourg, V. and Vanderplas, J. and Passos, A. and
+            Cournapeau, D. and Brucher, M. and Perrot, M. and Duchesnay, E.},
+    journal={Journal of Machine Learning Research},
+    volume={12},
+    pages={2825--2830},
+    year={2011}
+}
+
+@inproceedings{xgboost,
+    author = {Chen, Tianqi and Guestrin, Carlos},
+    title = {XGBoost: A Scalable Tree Boosting System},
+    year = {2016},
+    isbn = {9781450342322},
+    publisher = {Association for Computing Machinery},
+    address = {New York, NY, USA},
+    url = {https://doi.org/10.1145/2939672.2939785},
+    doi = {10.1145/2939672.2939785},
+    abstract = {Tree boosting is a highly effective and widely used machine
+               learning method. In this paper, we describe a scalable end-to-end tree
+               boosting system called XGBoost, which is used widely by data scientists to
+               achieve state-of-the-art results on many machine learning challenges. We
+               propose a novel sparsity-aware algorithm for sparse data and weighted
+               quantile sketch for approximate tree learning. More importantly, we provide
+               insights on cache access patterns, data compression and sharding to build a
+               scalable tree boosting system. By combining these insights, XGBoost scales
+               beyond billions of examples using far fewer resources than existing
+               systems.},
+    booktitle = {Proceedings of the 22nd ACM SIGKDD International Conference on
+                Knowledge Discovery and Data Mining},
+    pages = {785–794},
+    numpages = {10},
+    keywords = {large-scale machine learning},
+    location = {San Francisco, California, USA},
+    series = {KDD '16}
+}
+
+@inproceedings{pytorch,
+    author = {Ansel, Jason and Yang, Edward and He, Horace and Gimelshein,
+             Natalia and Jain, Animesh and Voznesensky, Michael and Bao, Bin and Bell,
+             Peter and Berard, David and Burovski, Evgeni and Chauhan, Geeta and
+             Chourdia, Anjali and Constable, Will and Desmaison, Alban and DeVito,
+             Zachary and Ellison, Elias and Feng, Will and Gong, Jiong and Gschwind,
+             Michael and Hirsh, Brian and Huang, Sherlock and Kalambarkar, Kshiteej and
+             Kirsch, Laurent and Lazos, Michael and Lezcano, Mario and Liang, Yanbo and
+             Liang, Jason and Lu, Yinghai and Luk, C. K. and Maher, Bert and Pan, Yunjie
+             and Puhrsch, Christian and Reso, Matthias and Saroufim, Mark and Siraichi,
+             Marcos Yukio and Suk, Helen and Zhang, Shunting and Suo, Michael and
+             Tillet, Phil and Zhao, Xu and Wang, Eikan and Zhou, Keren and Zou, Richard
+             and Wang, Xiaodong and Mathews, Ajit and Wen, William and Chanan, Gregory
+             and Wu, Peng and Chintala, Soumith},
+    title = {PyTorch 2: Faster Machine Learning Through Dynamic Python Bytecode
+            Transformation and Graph Compilation},
+    year = {2024},
+    isbn = {9798400703850},
+    publisher = {Association for Computing Machinery},
+    address = {New York, NY, USA},
+    url = {https://doi.org/10.1145/3620665.3640366},
+    doi = {10.1145/3620665.3640366},
+    abstract = {This paper introduces two extensions to the popular PyTorch
+               machine learning framework, TorchDynamo and TorchInductor, which implement
+               the torch.compile feature released in PyTorch 2. TorchDynamo is a
+               Python-level just-in-time (JIT) compiler that enables graph compilation in
+               PyTorch programs without sacrificing the flexibility of Python. It achieves
+               this by dynamically modifying Python bytecode before execution and
+               extracting sequences of PyTorch operations into an FX graph, which is then
+               JIT compiled using one of many extensible backends. TorchInductor is the
+               default compiler backend for TorchDynamo, which translates PyTorch programs
+               into OpenAI's Triton for GPUs and C++ for CPUs. Results show that
+               TorchDynamo is able to capture graphs more robustly than prior approaches
+               while adding minimal overhead, and TorchInductor is able to provide a
+               2.27\texttimes{} inference and 1.41\texttimes{} training geometric mean
+               speedup on an NVIDIA A100 GPU across 180+ real-world models, which
+               outperforms six other compilers. These extensions provide a new way to
+               apply optimizations through compilers in eager mode frameworks like
+               PyTorch.},
+    booktitle = {Proceedings of the 29th ACM International Conference on
+                Architectural Support for Programming Languages and Operating Systems,
+                Volume 2},
+    pages = {929–947},
+    numpages = {19},
+    location = {La Jolla, CA, USA},
+    series = {ASPLOS '24}
+}