Algorithm 2: yield estimation
1:	Inputs: Preprocessed feature vector F
2:	Outputs: Estimation outcome E
3:		Let us take a collection P = {P1, P2, P3, Pi} of field sensors data, where i ≤ N
4:			Let us apply preprocessing filters to n sensed data items from collection P∀ n ≤ N
5:			Let us extract the features of sensed data as vector F = {F1, F2, F3, Fi}∀ i ≤ N
6:				Analyze Pi instances with features F using Linear Regressor where each Pi in P
7:				Analyze Pi instances with features F using GradientBoosting where each Pi in P
8:				Analyze Pi instances with features F using Tree Regressor where each Pi in P
9:				Analyze Pi instances with features F using Random Forest regressor, each Pi in P
10:				Analyze the individual performance of all estimators on Pi attributes of P for i ≤ N
11:				Output the estimation as an estimation vector E
12:			End
13:		End