%0 Journal Article %1 perry_outlook_2022 %A Perry, George L. W. %A Seidl, Rupert %A Bellvé, André M. %A Rammer, Werner %D 2022 %J Ecosystems %K ecomodelling ecostudy %N 8 %P 1700--1718 %R 10.1007/s10021-022-00789-y %T An Outlook for Deep Learning in Ecosystem Science %U https://doi.org/10.1007/s10021-022-00789-y %V 25 %X Rapid advances in hardware and software, accompanied by public- and private-sector investment, have led to a new generation of data-driven computational tools. Recently, there has been a particular focus on deep learning—a class of machine learning algorithms that uses deep neural networks to identify patterns in large and heterogeneous datasets. These developments have been accompanied by both hype and scepticism by ecologists and others. This review describes the context in which deep learning methods have emerged, the deep learning methods most relevant to ecosystem ecologists, and some of the problem domains they have been applied to. Deep learning methods have high predictive performance in a range of ecological contexts, leveraging the large data resources now available. Furthermore, deep learning tools offer ecosystem ecologists new ways to learn about ecosystem dynamics. In particular, recent advances in interpretable machine learning and in developing hybrid approaches combining deep learning and mechanistic models provide a bridge between pure prediction and causal explanation. We conclude by looking at the opportunities that deep learning tools offer ecosystem ecologists and assess the challenges in interpretability that deep learning applications pose.

@article{perry_outlook_2022, abstract = {Rapid advances in hardware and software, accompanied by public- and private-sector investment, have led to a new generation of data-driven computational tools. Recently, there has been a particular focus on deep learning—a class of machine learning algorithms that uses deep neural networks to identify patterns in large and heterogeneous datasets. These developments have been accompanied by both hype and scepticism by ecologists and others. This review describes the context in which deep learning methods have emerged, the deep learning methods most relevant to ecosystem ecologists, and some of the problem domains they have been applied to. Deep learning methods have high predictive performance in a range of ecological contexts, leveraging the large data resources now available. Furthermore, deep learning tools offer ecosystem ecologists new ways to learn about ecosystem dynamics. In particular, recent advances in interpretable machine learning and in developing hybrid approaches combining deep learning and mechanistic models provide a bridge between pure prediction and causal explanation. We conclude by looking at the opportunities that deep learning tools offer ecosystem ecologists and assess the challenges in interpretability that deep learning applications pose.}, added-at = {2023-07-31T08:05:54.000+0200}, author = {Perry, George L. W. and Seidl, Rupert and Bellvé, André M. and Rammer, Werner}, biburl = {https://www.bibsonomy.org/bibtex/2e575575187e9b0b962057415993baf31/jascal_panetzky}, doi = {10.1007/s10021-022-00789-y}, file = {Full Text PDF:/Users/pascal/Zotero/storage/G3G88WN2/Perry et al. - 2022 - An Outlook for Deep Learning in Ecosystem Science.pdf:application/pdf}, interhash = {76823d8f8511c1b2fe1147033b10dcf7}, intrahash = {e575575187e9b0b962057415993baf31}, issn = {1435-0629}, journal = {Ecosystems}, keywords = {ecomodelling ecostudy}, language = {en}, month = dec, number = 8, pages = {1700--1718}, timestamp = {2023-07-31T08:46:01.000+0200}, title = {An {Outlook} for {Deep} {Learning} in {Ecosystem} {Science}}, url = {https://doi.org/10.1007/s10021-022-00789-y}, urldate = {2023-07-10}, volume = 25, year = 2022 }