A lot of hype has recently been generated around deep learning, a novel group of artificial intelligence approaches able to break accuracy records in pattern recognition. Over the course of just a few years, deep learning has revolutionized several research fields such as bioinformatics and medicine with its flexibility and ability to process large and complex datasets. As ecological datasets are becoming larger and more complex, we believe these methods can be useful to ecologists as well. In this paper, we review existing implementations and show that deep learning has been used successfully to identify species, classify animal behaviour and estimate biodiversity in large datasets like camera‐trap images, audio recordings and videos. We demonstrate that deep learning can be beneficial to most ecological disciplines, including applied contexts, such as management and conservation. We also identify common questions about how and when to use deep learning, such as what are the steps required to create a deep learning network, which tools are available to help, and what are the requirements in terms of data and computer power. We provide guidelines, recommendations and useful resources, including a reference flowchart to help ecologists get started with deep learning. We argue that at a time when automatic monitoring of populations and ecosystems generates a vast amount of data that cannot be effectively processed by humans anymore, deep learning could become a powerful reference tool for ecologists.
Long-term forest productivity decline in boreal forests has been extensively studied in the last decades, yet its causes are still unclear. Soil conditions associated with soil organic matter accumulation are thought to be responsible for site productivity decline. The objectives of this study were to determine if paludification of boreal soils resulted in reduced forest productivity, and to identify changes in the physical and chemical properties of soils associated with reduction in productivity. We used a chronosequence of 23 black spruce stands ranging in postfire age from 50 to 2350 years and calculated three different stand productivity indices, including site index. We assessed changes in forest productivity with time using two complementary approaches: (1) by comparing productivity among the chronosequence stands and (2) by comparing the productivity of successive cohorts of trees within the same stands to determine the influence of time independently of other site factors. Charcoal stratigraphy indicates that the forest stands differ in their fire history and originated either from high- or low-severity soil burns. Both chronosequence and cohort approaches demonstrate declines in black spruce productivity of 50-80% with increased paludification, particularly during the first centuries after fire. Paludification alters bryophyte abundance and succession, increases soil moisture, reduces soil temperature and nutrient availability, and alters the vertical distribution of roots. Low-severity soil burns significantly accelerate rates of paludification and productivity decline compared with high-severity fires and ultimately reduce nutrient content in black spruce needles. The two combined approaches indicate that paludification can be driven by forest succession only, independently of site factors such as position on slope. This successional paludification contrasts with edaphic paludification, where topography and drainage primarily control the extent and rate of paludification. At the landscape scale, the fire regime (frequency and severity) controls paludification and forest productivity through its effect on soil organic layers. Implications for global carbon budgets and sustainable forestry are discussed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.