USGS Science⌕ Search
Home/Archive/USGS

USGS · 70225689

Random forest

Emil D. Attanasi·Timothy Coburn
View original source ↗Export metadata ↓

Abstract

This entry defines and discusses the random forest machine learning algorithm. The algorithm is used to predict class or quantities for target variables using values of a set of predictor variables. It uses decision trees that are generated from bootstrap sampling of the training data set to create a "forest". The entry discusses the algorithm steps, the interpretative tools of the resulting model, current areas of research, and its limitations. Applications to the quantitative geosciences are reviewed as well as availability of software to implement the algorithm.

Explore related subjects

Book chapter

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Emil D. Attanasi, Timothy Coburn. 2021-10-26. Random forest. https://doi.org/10.1007/978-3-030-26050-7_265-1

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related USGS reports

USGS2026

Loma salmonae and related species

Loma salmonae is a microsporidium that infects Pacific salmon and causes a gill inflammatory syndrome known as microsporidial gill disease of salmon. This disease has been mostly associated with netpen-farmed Chinook salmon ( Oncorhynchus tshawytscha ) in British Columbia, Canada. Clinical, diagnostic, pathological aspects of disease, as well as approaches for disease avoidance in salmon aquaculture are discussed. A laboratory infection model in rainbow trout was used to determine life cycle-stages, transmission dynamics, pathophysiology, influence of temperature, and to test therapeutics applicable to aquaculture. This experimental model has been informative on various approaches of disease control, including the development of a promising vaccine. In addition to improving fish health in salmon farming in North America, this L. salmonae model will be applicable to other microsporidial diseases that may be encountered in emerging aquaculture regions.

Book chapter↗
USGS2026

Cumulative effects of multiple stressors on marine mammals: Elephant seals as a model system

Noise exposure is a potential stressor for free-ranging marine mammals and is often studied in the absence of other environmental factors. Here, a multi-investigator, interdisciplinary effort was undertaken to examine the response of elephant seals to multiple stressors. An integrated physiological and ecological approach was taken, including immunology, stress physiology, toxicology, animal behavior, population biology, and life history theory, to examine the cumulative effects of exposure to multiple stressors in elephant seals. While we measured the response of individual animals, a population response can be predicted by incorporating these results into the long-term data on elephant seal demographics.

Book chapter↗
USGS2026

When is a parasite a problem?

A parasite’s perceived societal impact depends on the disease it causes and the perception of the affected host species. For instance, doctors and veterinarians have a mission to treat parasites that infect humans or that impact host species that have some utilitarian or aesthetic value for society. Marine scientists have different concerns than doctors. Although the number of parasites that marine scientists should be concerned about may vary, only 13% of parasites and 6% of host–parasite links might be considered “problematic” in a kelp forest food web. With regard to the many threats to marine ecosystems, these percentages suggest that most parasites and infectious diseases are inconsequential. A related issue is the common expectation that parasites and the impacts that they cause are increasing under stress as ocean environments across the globe degrade. Yet, reports of disease have not increased due to human impacts on the marine environment, where the factors that influence parasitism are more complex. Thus, the expectation that marine parasites create problems, and that the diseases they cause are getting worse, is more likely the exception than the rule.

Book chapter↗