Data prediction is carried out according to the model trained based on forest classification or the existing model, such as the prediction of suitable areas for animals and plants, areas prone to natural disasters, etc. The result returns to the element Dataset (FeatureRDD). The prediction result will automatically generate a column of predicted fields and add the probability field to represent the probability of each predicted value. The value with the highest probability is the final prediction result (predicted).

When you create a forest-based classification prediction task, you need to set the following parameters: