AUTHOR=Wu Chien-Hung , Lu Chun-Yi , Zhan Jun-We , Wu Hsin-Te 

TITLE=Using Long Short-Term Memory for Building Outdoor Agricultural Machinery

JOURNAL=Frontiers in Neurorobotics

VOLUME=Volume 14 - 2020

YEAR=2020

URL=https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2020.00027

DOI=10.3389/fnbot.2020.00027

ISSN=1662-5218

ABSTRACT=Today, climate change has caused the decrease of agricultural output or the overall yield was not as expected; however, with the progress of population explosion, many undeveloped countries have transferred into emerging countries, which also transferred farmland for other types of applications. Regarding the declining agriculture output, it further causes the severity of the food crisis. Based on the context, this study proposes an outdoor agricultural robot by using Long Short-Term Memory (LSTM). The key features of this research include: 1. the robot is portable, and it uses green power to reduce the installation cost. 2. The system combines the current environment with weather forecasts through LSTM to predict the timing for watering. 3. Detecting the environment and utilizing the information of weather forecasts can help the system to ensure the growing conditions are suitable for the crops. 4. The robot of this study is mainly for outdoor applications because such kind of farms lacks sufficient electricity and water resources, which makes the robot critical for environmental control and resource allocation. From the experiment results, the robot developed in this study can detect the environment effectively to control electricity and water resources. Additionally, because the system is planned to increase agricultural output significantly, the study predicts the variables by LSTM through multivariate, which controls the power supply by the solar power system.