SIMSOYA3D: A DATA-DRIVEN'S SIMULATOR OF SOYBEAN'S GROWTH MODELING USING TRAINABLE PARAMETRIC L-SYSTEM AND ANFIS ALGORITHM

  • Wiwiet Herulambang Universitas Bhayangkara Surabaya
Keywords: Parametric L-system, ANFIS, Plant growth simulation, Data driven modeling, 3D Plant growth animation

Abstract

The purpose of this study was to design and build a system that is able to predict plant's growth patterns as a function of the nutrients obtained from fertilization pattern. The simulator is represented in 3-dimentional to perform animated models. As the object of research is Soybean (Glycine max (L.) Merrill). The output parameters are long growth trunk / branches (L), a wide cross section of the leaf (W), and branch growth (B), as a function of changes in the fertilizing elements Nitrogen (N), Phosphate (P) and potassium (K), as input parameters of the system. Modeling done on the vegetative phase of the soybean crop. The training phase of ANFIS are to obtain the values of Parametric L-system's constantas as a change of N-P-K you L-W-B values. In the implementation phase, using obtained constantas, the user's inputed datas could processed bythe Trained Parametric L-system to perform simulation of growth's function, and finally to perform 3- dimentional's animated models. The test results on the system to grow plants pattern proves that ANFIS method is quite adaptive to variation of N-PK values changes, and able to predict the output values of L-W-B. The visualization of 3D-animated models as the results of Trainable Parametric L-system has proven to be influenced by variations in the composition of input parameters(N-P-K values). Overall, the system has been running as expected. column as it is here, below the author information.

Published
2017-08-29
Section
Articles