Rahmawati, Winda and Suharyatun, Siti and sugianti, cicih Model Jaringan Syaraf Tiruan untuk Memprediksi Indeks Plastisitas Tanah. Prosiding Seminar Nasional Lahan Suboptimal 2019, Palembang 4-5 September 2019 “Smart Farming yang Berwawasan Lingkungan untuk Kesejahteraan Petani”.

[img] Text
Makalah-Seminar Palembang-2019 Winda Rahmawati1.doc - Presentation
Restricted to Registered users only until 18 December 2020.

Download (135kB) | Request a copy

Abstract

Soil index plasticity is an important soil physical property of the soil related to the tillage intensity , especially if it is done by machine such as a tractor. This study aim is to build an artificial neural network (ANN) model that connects the soil texture with the soil index plasticity. The research was conducted in several stages, namely: (1) soil texture determination, plastic limit and liquid limit in the laboratory, (2) plasticity index calculation, (3) Soil texture-soil plasticity index ANN model built. ANN models are created using 3 input variables, namely x1: clay content, x2: silt content and x3: sand content. The model uses 2 layers, with a logsig-tangig-purelin activation function. The results of the model training resulted in a RMSE (Root Mean Square Error) value of 1.6542 and an R2 value of 0.9570. Model validation produces a correlation value of predictive data and R2 observation data of 0.9332 Keywords: artificial neural network models, soil consistency, soil physical properties, soil texture

Item Type: Article
Subjects: S Agriculture > S Agriculture (General)
Divisions: Fakultas Pertanian (FP) > Prodi Teknik Pertanian
Depositing User: WINDA RAHMAWATI
Date Deposited: 18 Nov 2019 07:14
Last Modified: 18 Nov 2019 07:14
URI: http://repository.lppm.unila.ac.id/id/eprint/16883

Actions (login required)

View Item View Item