Refine
Language
- English (3)
Is part of the Bibliography
- yes (3)
Keywords
- artificial intelligence (2)
- hierarchy-of-hypotheses approach (2)
- machine learning (2)
- meta-analysis (2)
- synthesis (2)
- systematic review (2)
- Anthropocene (1)
- eco-evolutionary experience (1)
- global change (1)
- novel ecosystems (1)
Institute
Global change has complex eco-evolutionary consequences for organisms and ecosystems, but related concepts (e.g., novel ecosystems) do not cover their full range. Here we propose an umbrella concept of "ecological novelty" comprising (1) a site-specific and (2) an organism-centered, eco-evolutionary perspective. Under this umbrella, complementary options for studying and communicating effects of global change on organisms, ecosystems, and landscapes can be included in a toolbox. This allows researchers to address ecological novelty from different perspectives, e.g., by defining it based on (a) categorical or continuous measures, (b) reference conditions related to sites or organisms, and (c) types of human activities. We suggest striving for a descriptive, non-normative usage of the term "ecological novelty" in science. Normative evaluations and decisions about conservation policies or management are important, but require additional societal processes and engagement with multiple stakeholders.
Research synthesis on simple yet general hypotheses and ideas is challenging in scientific disciplines studying highly context-dependent systems such as medical, social, and biological sciences. This study shows that machine learning, equation-free statistical modeling of artificial intelligence, is a promising synthesis tool for discovering novel patterns and the source of controversy in a general hypothesis. We apply a decision tree algorithm, assuming that evidence from various contexts can be adequately integrated in a hierarchically nested structure. As a case study, we analyzed 163 articles that studied a prominent hypothesis in invasion biology, the enemy release hypothesis. We explored if any of the nine attributes that classify each study can differentiate conclusions as classification problem. Results corroborated that machine learning can be useful for research synthesis, as the algorithm could detect patterns that had been already focused in previous narrative reviews. Compared with the previous synthesis study that assessed the same evidence collection based on experts' judgement, the algorithm has newly proposed that the studies focusing on Asian regions mostly supported the hypothesis, suggesting that more detailed investigations in these regions can enhance our understanding of the hypothesis. We suggest that machine learning algorithms can be a promising synthesis tool especially where studies (a) reformulate a general hypothesis from different perspectives, (b) use different methods or variables, or (c) report insufficient information for conducting meta-analyses.
Research synthesis on simple yet general hypotheses and ideas is challenging in scientific disciplines studying highly context-dependent systems such as medical, social, and biological sciences. This study shows that machine learning, equation-free statistical modeling of artificial intelligence, is a promising synthesis tool for discovering novel patterns and the source of controversy in a general hypothesis. We apply a decision tree algorithm, assuming that evidence from various contexts can be adequately integrated in a hierarchically nested structure. As a case study, we analyzed 163 articles that studied a prominent hypothesis in invasion biology, the enemy release hypothesis. We explored if any of the nine attributes that classify each study can differentiate conclusions as classification problem. Results corroborated that machine learning can be useful for research synthesis, as the algorithm could detect patterns that had been already focused in previous narrative reviews. Compared with the previous synthesis study that assessed the same evidence collection based on experts' judgement, the algorithm has newly proposed that the studies focusing on Asian regions mostly supported the hypothesis, suggesting that more detailed investigations in these regions can enhance our understanding of the hypothesis. We suggest that machine learning algorithms can be a promising synthesis tool especially where studies (a) reformulate a general hypothesis from different perspectives, (b) use different methods or variables, or (c) report insufficient information for conducting meta-analyses.