Table of Content

Artificial Intelligence and Deep Learning Techniques in Smart Agriculture

Submission Deadline: 31 December 2022 (closed)

Guest Editors

Dr. U. Vignesh, Manipal Institute of Technology, Manipal Academy of Higher Education, India.
Prof. R. Parvathi, Vellore Institute of Technology, India.
Dr. Ruchi Doshi, Universidad Azteca, Mexico.


Agriculture yield depends on the climate and geological factors. Choosing the right crop at the right time is the most important factor in obtaining a higher yield. There- fore, any information associated with climatic factors will ensure farmers’ foreordained farming. The proposed issue puts forward a prediction and analysis model, which is built to predict climatic factors for a long range based on Artificial intelligence, IoT, Decision Science, Bioiformatics methodologies, etc. Different attributes that include cloud cover, diurnal temperature range, maximum and minimum temperatures, vapour pressure, potential evapotranspiration, precipitation, wet day frequency, relative humidity, reference crop evapotranspiration and ground frost frequency can be used for the development of models. Deep learning algorithms like Recurrent Neural Network (RNN), Gated Recurrrent Unit (GRU), and Long Short-Term Memory (LSTM)are used to build the forecast model in preliminary work and the errors of all three models are outside of the intended error range. Comparatively, the error of the LSTM model is closer to the expected range. The proposed issue provides an statistical weather forecasting models, which can be used in future for crop mining, Seasonal Auto-Regressive Integrated Moving Average with eXogenous factors (SARIMAX) and Holt Winter Exponential Smoothing, etc.


Crop mining, Deep learning, Machine Learning, Artificial Intelligence, Agriculture, Prediction, etc.

Share Link

WeChat scan