Forest Fires dataset 1: Description. 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. 2: Type. Regression 3: Origin. Real world 4: Instances. 517 5: Features. 12 6: Classes. - 7: Missing values. No 8: Header. @relation forestFires @attribute X integer [1, 9] @attribute Y integer [2, 9] @attribute Month integer [1, 12] @attribute Day integer [1, 7] @attribute FFMC real [18.7, 96.2] @attribute DMC real [1.1, 291.3] @attribute DC real [7.9, 860.6] @attribute ISI real [0.0, 56.1] @attribute Temp real [2.2, 33.3] @attribute RH integer [15, 100] @attribute Wind real [0.4, 9.4] @attribute Rain real [0.0, 6.4] @attribute Area real [0.0, 1090.84] @inputs X, Y, Month, Day, FFMC, DMC, DC, ISI, Temp, RH, Wind, Rain @outputs Area