The dataset contains geographic location estimates of Adelie penguins (Pygoscelis adeliae) tracked via Argos satellite telemetry in the Southern Ocean for the U.S. Antarctic Marine Living Resources project from 1996-10-29 to 2013-02-19. Birds were instrumented with back-mounted Argos satellite transmitters at the Copacabana Colony (62.21S, 58.42W) on King George Island during the austral summer breeding seasons (October - February) from 1996 to 2013. Typical deployments during the breeding season lasted 5 to 8 days, while some winter deployments lasted several months. The data set identifies the sex of the bird tracked (male, female, or unknown) and the age of the bird (adult). The data also identify the breeding stage of the bird during the summer tracking period (incubation, brood/guard, or creche) or is noted as 'winter' if tracked outside the summer breeding season. The data include the date (DD/MM/YYYY) and time (GMT) of the location estimate. Finally, a categorical estimate of uncertainty in the location estimate is provided by Argos quality codes (3,2,1,0,A,B).

The Antarctic Penguin Biogeography Project is an effort to collate all known information about the distribution and abundance of Antarctic penguins through time and to make such data available to the scientific and management community. The core data product involves a series of structured tables with information on known breeding sites and surveys conducted at those sites from the earliest days of Antarctic exploration through to the present. This database, which is continuously updated as new information becomes available, provides a unified and comprehensive repository of information on Antarctic penguin biogeography that contributes to a growing suite of applications of value to the Antarctic community. One such application is the Mapping Application for Antarctic Penguins and Projected Dynamics (MAPPPD; www.penguinmap.com) - a browser-based search and visualization tool designed primarily for policymakers and other non-specialists (Humphries et al., 2017), and ‘mapppdr’, an R package developed to assist the Antarctic science community. The Antarctic Penguin Biogeography Project has been funded by the National Aeronautics and Space Administration (NASA), the Pew Fellowship for Marine Conservation, and the Institute for Advanced Computational Sciences at Stony Brook University. Antarctic Penguin Biogeography Project: Database of abundance and distribution for the Adélie, chinstrap, gentoo, emperor, macaroni, and king penguin south of 60 S is an occurrence and sampling event type dataset published by SCAR-AntBIOS. This dataset contains records of Pygoscelis adeliae, Pygoscelis antarctica, Pygoscelis papua, Eudyptes chrysolophus, Aptenodytes patagonicus, and Aptenodytes forsteri annual nest, adult, and/or chick counts conducted during field expeditions or collected using remote sensing imagery, that were subsequently gathered by the Antarctic Penguin Biogeography Project from published and unpublished sources, at all known Antarctic penguin breeding colonies south of 60 S from 1892-11-01 to 2022-02-12. The data is published as a standardized Darwin Core Archive and includes an event core and occurrence and eMoF extensions. This dataset is published by SCAR-AntOBIS under the license CC-BY 4.0. Please follow the guidelines from the SCAR Data Policy (SCAR, 2023) when using the data. If you have any questions regarding this dataset, please contact us via the contact information provided in the metadata or via data-biodiversity-aq@naturalsciences.be. Issues with dataset can be reported at https://github.com/biodiversity-aq/data-publication/ This dataset is part of the Antarctic Penguin Biogeography Project project funded by National Aeronautics and Space Administration (NASA), the Pew Fellowship for Marine Conservation, and the Institute for Advanced Computational Sciences at Stony Brook University.

Measurements for three penguin species observed in the Palmer Archipelago, Antarctica.

These data were collected from 2007 - 2009 by Dr. Kristen Gorman with the Palmer Station Long Term Ecological Research Program, part of the US Long Term Ecological Research Network. The data were originally imported from the Environmental Data Initiative (EDI) Data Portal, and are available for use by CC0 license ("No Rights Reserved") in accordance with the Palmer Station Data Policy. This copy was imported from Allison Horst's GitHub repository.

To use this dataset:

import tensorflow_datasets as tfds

ds = tfds.load('penguins', split='train')
for ex in ds.take(4):
 print(ex)

See the guide for more informations on tensorflow_datasets.

Context :

This dataset has information about three penguin species. It includes their bill size, flipper length, and body weight. You can use it to see how species and sexes are different. It’s good for practicing data analysis and visualization

Feature Distribution :

Bill Measurements – Bill length and depth differences among penguins

Flipper Length – How flipper size varies across species

Body Weight – Distribution of body mass in males and females

Species Comparison – Comparing all features between penguin species

1. id................................................................................................................................................................

Description: Unique identifier for each penguin. Type: Integer or String. Use: Useful for uniquely identifying each observation.

1. species................................................................................................................................................................

Description: Species of the penguin. Type: Categorical (String). Possible Values: "Adelie", "Chinstrap", "Gentoo". Use: Often used as the target variable for classification tasks.

1. island................................................................................................................................................................

Description: Island in the Palmer Archipelago (Antarctica) where the penguin was observed. Type: Categorical (String). Possible Values: "Biscoe", "Dream", "Torgersen". Use: Used to analyze the geographical distribution of different penguin species.

1. bill_length_mm..................................................................................................................................................................

Description: Length of the penguin's bill (beak) in millimeters. Type: Continuous (Float). Use: Important feature for differentiating between species, often used in scatter plots to visualize relationships with other variables.

1. bill_depth_mm....................................................................................................................................................................

Description: Depth of the penguin's bill (beak) in millimeters. Type: Continuous (Float). Use: Another important feature for species differentiation, often used in combination with bill length.

1. flipper_length_mm...............................................................................................................................................................

Description: Length of the penguin's flipper in millimeters. Type: Continuous (Float). Use: Useful for understanding the physical characteristics of different species.

1. body_mass_g..........................................................................................................................................................................

Description: Body mass of the penguin in grams. Type: Continuous (Float). Use: Used to study the size and health of the penguins, and as a feature in predictive models.

1. sex..................................................................................................................................................................................

Description: Sex of the penguin. Type: Categorical (String). Possible Values: "Male", "Female", "NA" (missing values). Use: Useful for analyzing differences in physical characteristics and behaviors between male and female penguins.

1. year...................................................................................................................................................................................

Description: Year in which the observation was made. Type: Integer. Possible Values: Usually years like 2007, 2008, 2009. Use: Can be used to analyze trends over time and understand temporal patterns in the data.

This data is a publicly available dataset; I have made it a little simple to predict species using the bio-markers of the penguins. All credits go to the original owners: Palmer Archipelago (Antarctica) penguin data Gorman KB, Williams TD, Fraser WR (2014) Ecological Sexual Dimorphism and Environmental Variability within a Community of Antarctic Penguins (Genus Pygoscelis). PLoS ONE 9(3): e90081. doi:10.1371/journal.pone.0090081

Data were collected from two penguin monitoring sites in the Antarctic peninsula region between 1977 and 2015 using traditional census methods. Seabirds observed in this study are Adélie (Pygoscelis adeliae), chinstrap (P. antarctica), and gentoo (P. papua) penguins. The two study sites are the US AMLR Program sites at Cape Shirreff (Livingston Island) and Copacabana (King George Island).

Aerial reconnaissance and photography are used in the Ross Sea sector of Antarctica to determine the breeding locations of Adélie penguins and to count the numbers of nests occupied during the early incubation period. From 1981 to present (two-year embargo), all islands and sea coasts between 158°E and 175°E have been searched, and 11 previously unreported breeding colonies discovered. The aim is to census Adélie (Pygoscelis adeliae) populations to provide basic data against which future population levels can be compared in order to monitor environmental change of the Antarctic Ocean ecosystem, both natural and man-induced.

Context

This dataset, which focuses on penguins found in Antarctica, was first gathered by researchers to investigate the ways in which biological and environmental variables affect the morphological characteristics of these animals. Observations from three famous penguin species—Adelie, Gentoo, and Chinstrap—across several Palmer Archipelago islands are included. Students, analysts, and data scientists frequently use this data to practice data exploration, visualization, and machine learning techniques because it was gathered with the intention of supporting ecological study, species comparison, and educational analysis.

Content

Data about species, sex, and habitat island are included in the collection, along with specifics about each individual penguin, such as body mass, flipper length, bill length, and bill depth. A single penguin is represented by each row, which includes its physical characteristics and fundamental demographic information. This dataset's organization and cleanliness facilitate pattern analysis, species comparison, gender analysis, and the development of biological feature-based visualizations and prediction algorithms.

This dataset, derived from the Palmer's Penguins dataset, is intended to be a valuable resource for beginners in logistic regression.

The idea is to classify Gentoo and Adelie penguins using lgistic regression but you can learn something about them too!! 🙂:

Gentoo Penguins (Pygoscelis papua)

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F3880940%2F544281eed175e6f70787192cdf2c90ac%2Fgentoo.jpeg?generation=1701019777180956&alt=media" alt=""> - Habitat: Predominantly found on the Antarctic Peninsula and nearby islands. - Physical Characteristics: Recognizable by their bright orange-red bills and white stripe extending across the top of their heads. They are among the larger penguin species. - Diet: Primarily feed on krill, though their diet also includes fish and squid. - Behavior: Known for their fast swimming ability and long, deep dives while foraging.

Adelie Penguins (Pygoscelis adeliae)

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F3880940%2Faddfdad600743788f1cd44d3f474a5f3%2Fa-pair-of-adelie-penguins-photo-from-june-1984-all-hands-magazine-d14147-1024.jpeg?generation=1701019849646979&alt=media" alt=""> - Habitat: Widely distributed along the entire Antarctic coast. - Physical Characteristics: Smaller than Gentoo penguins, with distinctive black and white plumage and a blue-black bill. - Diet: Mainly eat krill, along with some fish and squid. - Behavior: Highly social and known for their loud calls and aggressive behavior during the breeding season.

The dataset was collected in Palmer Archipelago: A group of islands off the northwestern coast of the Antarctic Peninsula. Home to a diverse range of wildlife, including several species of penguins, seals, and seabirds. This archipielago is characterized by cold temperatures, strong winds, and significant ice cover, although it's one of the most rapidly warming areas on Earth.

Usage Scenarios for the Dataset

Educational Use: Ideal for teaching logistic regression in data science and statistics courses. Students can learn how to handle categorical and numerical data, as well as binary classification.

Ecological Research: Researchers can use the dataset to study penguin population dynamics, diet preferences, and the impact of climate change on habitat and species distribution.

Conservation Efforts: Conservationists could analyze trends in penguin populations and health indicators (like body mass) to inform protection strategies.

Data Visualization Projects: The dataset is suitable for creating visual representations of data, such as scatter plots or heat maps, to illustrate differences between species or changes over time.

Machine Learning Model Development: Beginners in machine learning can use this dataset to build and validate logistic regression models, before moving on to more complex algorithms.

Statistical Analysis: The dataset can be used to perform statistical tests to understand correlations between different physical characteristics of penguins and their environment or diet.

This dataset provides a unique opportunity for a wide range of users, from educators and students to researchers and conservationists, to explore and understand the fascinating world of these Antarctic penguins.

PENGUIn-1, Antarctica, Ground-based Vector Magnetic Field Level 2 Data, 1.0 s Time Resolution, Station Code: (PG1), Station Location: (GEO Latitude -84.5, Longitude 77.2), Antarctic Network

PENGUIn-1, Antarctica, Ground-based Vector Magnetic Field Level 2 Data, 1.0 s Time Resolution, Station Code: (PG1), Station Location: (GEO Latitude -84.5, Longitude 77.2), Antarctic Network

Get the latest USA Penguin import data with importer names, shipment details, buyers list, product description, price, quantity, and major US ports.

Data were collected and made available by Dr. Kristen Gorman and the Palmer Station, Antarctica LTER, a member of the Long Term Ecological Research Network.

This dataset contains data on the habitats, distribution and numbers of Adelie Penguins (Pygoscellis adeliae) along the Vestfold Hills coast (including colonies on the mainland and offshore islands) during November 1973. The data are obtained from counts at the colonies and black and white photographs. Some aerial photographs were taken at Davis in 1981-82 and 1987-88, and will be compared to the results of this survey. The results are listed in the documentation. A total of 174178 26127 breeding pairs were counted. An increase in Adelie penguin population was found at most locations in East Antarctica.

Data from this record has been incorporated into a larger Adelie penguin dataset described by the metadata record - Annual population counts at selected Adelie Penguin colonies within the AAT (SOE_seabird_candidate_sp_AP). It also falls under ASAC project 1219 (ASAC_1219).

This dataset contains data on the habitats, distribution and numbers of Adelie Penguins (Pygoscellis adeliae) in the Mawson area, Antarctica during 1981 and 1988. The data are obtained from aerial photographs obtained at various times, during the 1981-82 and 1988-89 seasons. The results are listed in the documentation. Comparisons are made with census data collected in the 1971-72 summer.

Data from this record has been incorporated into a larger Adelie penguin dataset described by the metadata record - Annual population counts at selected Adelie Penguin colonies within the AAT (SOE_seabird_candidate_sp_AP). It also falls under ASAC project 1219 (ASAC_1219).

The version of the Palmer Penguins dataset used in the ggEDA manuscript.Also accessible via the palmerpenguins R package.If you use please cite:Horst AM, Hill AP, Gorman KB (2020). palmerpenguins: Palmer Archipelago (Antarctica) penguin data. R package version 0.1.0. https://allisonhorst.github.io/palmerpenguins/. doi:10.5281/zenodo.3960218.Gorman KB, Williams TD, Fraser WR (2014) Ecological Sexual Dimorphism and Environmental Variability within a Community of Antarctic Penguins (Genus Pygoscelis). PLoS ONE 9(3): e90081. doi:10.1371/journal.pone.0090081

PENGUIn-5, Antarctica, Ground-based Vector Magnetic Field Level 2 Data, 1.0 s Time Resolution, Station Code: (PG5), Station Location: (GEO Latitude -82.0, Longitude 5.7), Antarctic Network

Dataset

This dataset was created by Martin Nguyen

Contents

This project is an international collaborative investigation of geographic structuring, founding of new colonies, and population change of Adelie penguins (Pygoscelis adelia) nesting on Ross and Beaufort islands, Antarctica. This ongoing study will continue to consider the relative importance of resources that constrain or enhance colony growth (nesting habitat, access to food); the aspects of natural history that are affected by exploitative or interference competition among neighboring colonies (breeding success, foraging effort); climatic factors that influence the latter, especially sea ice patterns; and behavioral mechanisms that influence colony growth as a function of initial size and location (emigration, immigration). The research includes a census of known-age penguins, studies of foraging effort and overlap among colonies; and identification of the location of molting and wintering areas.