About this Dataset

Asteroid Dataset

Story Behind This Dataset

I am an Astronomy and Astrophysics Researcher. As a Mathematics background I am a data science, machine learning, and deep learning enthusiast. Nowadays Machine Learning is solving so many problems in Astronomy and Astrophysics fields. Asteroid is nice topic for Machine Learning projects like classification and regression problems.

Data Source And Method of Collection

I have collected this Dataset from which is officially maintained by Jet Propulsion Laboratory of California Institute of Technology which is an organization under NASA. In this Dataset all kinds of Data related to Asteroid is included. This Dataset is publicly available in their website. The Basic Definitions of the Columns have been given below.
Website Link- JPL Small-Body Database Search Engine

Basic Column Definition

SPK-ID: Object primary SPK-ID
Object ID: Object internal database ID
Object fullname: Object full name/designation
pdes: Object primary designation
name: Object IAU name
NEO: Near-Earth Object (NEO) flag
PHA: Potentially Hazardous Asteroid (PHA) flag
H: Absolute magnitude parameter
Diameter: object diameter (from equivalent sphere) km Unit
Albedo: Geometric albedo
Diameter_sigma: 1-sigma uncertainty in object diameter km Unit
Orbit_id: Orbit solution ID
Epoch: Epoch of osculation in modified Julian day form
Equinox: Equinox of reference frame
e: Eccentricity
a: Semi-major axis au Unit
q: perihelion distance au Unit
i: inclination; angle with respect to x-y ecliptic plane
tp: Time of perihelion passage TDB Unit
moid_ld: Earth Minimum Orbit Intersection Distance au Unit

Acknowledgements

I wouldn't be here without the help of NASA. I heartily thank NASA and JPL for maintaining such an wonderful database which is user friendly. JPL-authored documents are sponsored by NASA under Contract NAS7-030010. All documents available from this server may be protected under the U.S. and Foreign Copyright Laws. Permission to reproduce may be required.

Cite this paper

Hossain, M.S., Zabed, M.A. (2023). Machine Learning Approaches for Classification and Diameter Prediction of Asteroids. In: Ahmad, M., Uddin, M.S., Jang, Y.M. (eds) Proceedings of International Conference on Information and Communication Technology for Development. Studies in Autonomic, Data-driven and Industrial Computing. Springer, Singapore.
DOI

Bibtex

@InProceedings{10.1007/978-981-19-7528-8_4,
author="Hossain, Mir Sakhawat
and Zabed, Md. Akib",
editor="Ahmad, Mohiuddin
and Uddin, Mohammad Shorif
and Jang, Yeong Min",
title="Machine Learning Approaches for Classification and Diameter Prediction of Asteroids",
booktitle="Proceedings of International Conference on Information and Communication Technology for Development",
year="2023",
publisher="Springer Nature Singapore",
address="Singapore",
pages="43--55",
abstract="In Astronomy, the size of data is increasing day by day and is becoming more complex than in previous years. Even it is also found in the study of asteroids. There are millions of asteroids to study its classification and calculating its diameter to determine their characteristics. These will help us to know which are potentially hazardous asteroids for Earth. We have applied machine learning methods to classify the asteroids and predict their diameter. For classification task, we have implemented kNN classifier, logistic regression classifier, SGD classifier, and XGBoost classifier algorithms. For the prediction of diameter, we have used linear regression, decision tree, random forest, logistic regression, XGBoost regression, kNN, and neural network models. We have depicted a comparative analysis of our results. Applying these approaches, we have gained significant 99.99{%} percent accuracy for asteroid classification task.",
isbn="978-981-19-7528-8"
}

If you use this dataset in your research please cite the paper

Inspiration

I have been Inspired by Astronomers and Astro Community who are working hard to reveal the Unsolved Questions.

Tables

Dataset

@kaggle.sakhawat18_asteroid_dataset.dataset

238.39 MB
958524 rows
45 columns


CREATE TABLE dataset (
  "id" VARCHAR,
  "spkid" BIGINT,
  "full_name" VARCHAR,
  "pdes" VARCHAR,
  "name" VARCHAR,
  "prefix" VARCHAR,
  "neo" VARCHAR,
  "pha" VARCHAR,
  "h" DOUBLE,
  "diameter" DOUBLE,
  "albedo" DOUBLE,
  "diameter_sigma" DOUBLE,
  "orbit_id" VARCHAR,
  "epoch" DOUBLE,
  "epoch_mjd" BIGINT,
  "epoch_cal" DOUBLE,
  "equinox" VARCHAR,
  "e" DOUBLE,
  "a" DOUBLE,
  "q" DOUBLE,
  "i" DOUBLE,
  "om" DOUBLE,
  "w" DOUBLE,
  "ma" DOUBLE,
  "ad" DOUBLE,
  "n" DOUBLE,
  "tp" DOUBLE,
  "tp_cal" DOUBLE,
  "per" DOUBLE,
  "per_y" DOUBLE,
  "moid" DOUBLE,
  "moid_ld" DOUBLE,
  "sigma_e" DOUBLE,
  "sigma_a" DOUBLE,
  "sigma_q" DOUBLE,
  "sigma_i" DOUBLE,
  "sigma_om" DOUBLE,
  "sigma_w" DOUBLE,
  "sigma_ma" DOUBLE,
  "sigma_ad" DOUBLE,
  "sigma_n" DOUBLE,
  "sigma_tp" DOUBLE,
  "sigma_per" DOUBLE,
  "class" VARCHAR,
  "rms" DOUBLE
);