Open AccessWeather prediction system and recommendation of plant varieties as an effort to minimize harvest failure with android-based Backpropagation Artificial Neural Networks
Author(s) -
Md. Saikat Ahsan,
Wiji Setiyaningsih Wiji Setiyaningsih,
B Rinanto,
M Susilowati,
Indah Sulistiyowati
Publication year - 2021
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/1098/3/032027
Subject(s) - hectare , backpropagation , wind speed , artificial neural network , sowing , agricultural engineering , agriculture , environmental science , meteorology , humidity , mathematics , engineering , geography , computer science , agronomy , machine learning , archaeology , biology
Based on Malang Regency agriculture data in 2017 presented by the Head of the Agriculture and Food Crops and Horticulture Office (DPTPH), there was a 2.5% decrease in yields. One hectare of paddy land can produce 7.71 tons during normal weather, but currently only produces 6.9 tons per hectare. Three farmers’ groups in Malang Regency (2018), are of the opinion that the current weather greatly influences crop failure. Weather prediction used so far using conventional benchmarks for planting, is no longer relevant to current reality. These estimates are often incorrect, resulting in crop failures, which have an impact on the farmer’s economy. This study aims to make the application of weather prediction systems and recommendations for suitable planting varieties based on data on temperature, humidity, time of sun exposure, wind speed, and rainfall using Backpropagation ANN method. Data used for Karangploso District weather prediction from 2009-2018. While the variables used in the application of Backpropagation ANN: temperature, humidity, time of sun exposure, wind speed, and rainfall. For output, the prediction of rainfall in the next 12 months and planting of varieties in accordance with the predicted rainfall, OPT and land type. From the calculation results of this application the MSE error value of 0.0299 is obtained.