Forecasting Soil Moisture Based on Evaluation of Time Series Analysis
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 in this manuscript to deliver better after-effects of farming. The proposed model uses long short-term memory (LSTM) to predict soil moisture. The model is 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) has been used as performance metrics. This paper is paving way for the early prediction of the soil moisture that can be used with other advanced innovative irrigation techniques.
KeywordsSmart irrigation Time series Soil moisture LSTM MAE MSE
The author would like to thanks Dr. Rajib Maity of IIT Kanpur, India for providing dataset based on the different depths of the soil moisture and also acknowledge to Council of Scientific and Industrial Research (CSIR) for funding grants vide No. 38(1464)/18/EMIR-II for carrying out research work.
- 1.Shinde D, Siddiqui N (2018) IOT based environment change monitoring and controlling in greenhouse using WSN. In: 2018 international conference on information, communication, engineering and technology (ICICET), IEEE, Aug 2018, pp 1–5Google Scholar
- 2.Calla OPN et al (2008) Measurement of soil moisture using microwave radiometer. In: Proceedings of the IEEE international conference on microwave ′08, 2008, pp 621–624Google Scholar
- 3.Zhang P, Zhang Q, Liu F, Li J, Cao N, Song C (2017) The construction of the integration of water and fertilizer smart water saving irrigation system based on big data. In: 2017 IEEE international conference on computational science and engineering (CSE) and IEEE international conference on embedded and ubiquitous computing (EUC), vol 2, pp 392–397. IEEE, July 2018Google Scholar
- 4.Lenka SK, Mohapatra AG (2015 December). Gradient descent with momentum based neural network pattern classification for the prediction of soil moisture content in precision agriculture. In: 2015 IEEE International Symposium on Nanoelectronic and Information Systems (pp. 63–66). IEEEGoogle Scholar
- 8.Priya R, Ramesh D, Khosla E (2018) Crop prediction on the region belts of India: a Naïve Bayes MapReduce precision agricultural model. In: 2018 international conference on advances in computing, communications and informatics (ICACCI), pp 99–104. IEEE, Sept 2018Google Scholar
- 9.Ponce-Guevara KL, Palacios-Echeverría JA, Maya-Olalla E, Domínguez-Limaico HM, Suárez-Zambrano LE, Rosero-Montalvo PD, Peluffo-Ordóñez DH, Alvarado-Pérez JC (2017) GreenFarm-DM: a tool for analyzing vegetable crops data from a greenhouse using data mining techniques (First trial). In: 2017 IEEE second ecuador technical chapters meeting (ETCM), pp 1–6. IEEE, Oct 2017Google Scholar