Deep learning and process understanding for data-driven Earth system science. Reichstein, M., Camps-Valls, G., Stevens, B., Jung, M., Denzler, J., Carvalhais, N., & Prabhat Nature, 566(7743):195–204, February, 2019.
Deep learning and process understanding for data-driven Earth system science [link]Paper  doi  abstract   bibtex   
Complex Earth system challenges can be addressed by incorporating spatial and temporal context into machine learning, especially via deep learning, and further by combining with physical models into hybrid models.
@article{reichstein_deep_2019,
	title = {Deep learning and process understanding for data-driven {Earth} system science},
	volume = {566},
	copyright = {2019 Springer Nature Limited},
	issn = {1476-4687},
	url = {https://www.nature.com/articles/s41586-019-0912-1},
	doi = {10.1038/s41586-019-0912-1},
	abstract = {Complex Earth system challenges can be addressed by incorporating spatial and temporal context into machine learning, especially via deep learning, and further by combining with physical models into hybrid models.},
	language = {en},
	number = {7743},
	urldate = {2019-11-07},
	journal = {Nature},
	author = {Reichstein, Markus and Camps-Valls, Gustau and Stevens, Bjorn and Jung, Martin and Denzler, Joachim and Carvalhais, Nuno and {Prabhat}},
	month = feb,
	year = {2019},
	keywords = {***},
	pages = {195--204}
}

Downloads: 0