Forest-Fires-Data-Set-Portugal
OpenML43807MaRDI QIDQ6036900FDOQ6036900RO-CrateQ6036900
OpenML dataset with id 43807
Author name not available (Why is that?)
Full work available at URL: https://api.openml.org/data/v1/download/22102632/Forest-Fires-Data-Set-Portugal.arff
Upload date: 24 March 2022
Dataset Characteristics
Number of features: 13 (numeric: 11, symbolic: 0 and in total binary: 0 )
Number of instances: 517
Number of instances with missing values: 0
Number of missing values: 0
ABSTRACT
This is a difficult regression task, where the aim is to predict the burned area of forest fires, in the northeast region of Portugal, by using meteorological and other data (see details at: [Web Link]).
Data Set Information:
Data Set Characteristics: Multivariate
Number of Instances: 517
Area: Physical
Attribute Characteristics: Real
Number of Attributes: 13
Date Donated: 2008-02-29
Associated Tasks: Regression
Missing Values? N/A
Number of Web Hits: 871088
In [Cortez and Morais, 2007], the output 'area' was first transformed with a ln(x+1) function.
Then, several Data Mining methods were applied. After fitting the models, the outputs were
post-processed with the inverse of the ln(x+1) transform. Four different input setups were
used. The experiments were conducted using a 10-fold (cross-validation) x 30 runs. Two
regression metrics were measured: MAD and RMSE. A Gaussian support vector machine (SVM) fed
with only 4 direct weather conditions (temp, RH, wind and rain) obtained the best MAD value:
12.71 +- 0.01 (mean and confidence interval within 95 using a t-student distribution). The
best RMSE was attained by the naive mean predictor. An analysis to the regression error curve
(REC) shows that the SVM model predicts more examples within a lower admitted error. In effect,
the SVM model predicts better small fires, which are the majority.
Source:
Paulo Cortez, pcortez dsi.uminho.pt, Department of Information Systems, University of Minho, Portugal.
Anbal Morais, araimorais gmail.com, Department of Information Systems, University of Minho, Portugal.
Relevant Papers:
[Cortez and Morais, 2007] P. Cortez and A. Morais. A Data Mining Approach to Predict Forest Fires using Meteorological Data. In J. Neves, M. F. Santos and J. Machado Eds., New Trends in Artificial Intelligence, Proceedings of the 13th EPIA 2007 - Portuguese Conference on Artificial Intelligence, December, Guimares, Portugal, pp. 512-523, 2007. APPIA, ISBN-13 978-989-95618-0-9. Available at: [Web Link]
Cited In (1)
ROCrate
What is a RO-Crate?
A RO-Crate is a standardized research object package used to bundle data together with rich machine-readable metadata. Each RO-Crate contains:
- the files belonging to the dataset (e.g. CSVs, images, code, documentation)
- a ro-crate-metadata.json file describing the content, provenance, and context
- persistent identifiers and references to related research objects (e.g. software, publications)
This ensures that the dataset can be easily reused, cited, validated, and interpreted in a reproducible manner. More information can be found here.
Download
You can download a RO-Crate for this dataset here: Download RO-Crate
HINT: The RO-Crate is created dynamically, so it could take up to 30 seconds until the downloads starts.
This page was built for dataset: Forest-Fires-Data-Set-Portugal
