Please use this identifier to cite or link to this item:
|Title:||Forecasting Soil moisture based on evaluation of Time Series Analysis|
|Keywords:||Soil Moisture;Precision Agriculture;ARIMA;LSTM|
|Abstract:||Precision agriculture is a technique that is incorporated to produce high crop yield with the best utilization of available resources. Traditional farming is adversely affected due to improper resource management. In order to overcome the efforts of a farmer, a model for the soil moisture forecasting has been proposed to deliver better results of farming. The proposed model uses the Auto-Regressive Integrated Moving Average (ARIMA) and Long short-term memory (LSTM) to predict soil moisture. The models are trained on a dataset acquired from IIT Kanpur agricultural site. For analyzing the performance of the model Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Mean Squared Error (MSE) and Root Mean Squared Error (RMSE) have been used as performance metrics. This study reveals that the LSTM model performs better in contrast with the ARIMA model. It paving way for the early prediction of the soil moisture that can be used with other advanced innovative irrigation techniques.|
|Appears in Collections:||Masters Theses@CSED|
Files in This Item:
|801732052_ME_Sukhwinder.pdf||2.97 MB||Adobe PDF|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.