An IoT-Big Data Based Machine Learning Technique for Forecasting Water Requirement in Irrigation Field - Research and Practical Issues of Enterprise Information Systems
Conference Papers Year : 2018

An IoT-Big Data Based Machine Learning Technique for Forecasting Water Requirement in Irrigation Field

Fizar Ahmed
  • Function : Author
  • PersonId : 1037155

Abstract

Efficient water management is a major concern in rice cropping. Controlling the use of excessive water in irrigation field is essential for the protection of underground water that will also be the part of climate change adaptation. The sustainable use of water resources is the prior task in Bangladesh. Imbalances between demand and supply are the main region for degradation of surface and groundwater. The human readability of checking the water level on irrigation field is considerable for these circumstances. In this paper I discussed the procedure for monitoring of surface water level in irrigation field, continuous monitoring of weather condition like temperature, air pressure, sunlight, rainfall etc. by using sensor network. The aim is to create a machine learning mechanism for farmers that can be given a forecast of water demand of irrigation field by the collection of IoT based data. In turn, this will help the farmer to prepare them to give water and on the other hand it will be helpful to use appropriate ground water and also it can be used for predict energy utilization. In this research Multiple linear regression algorithm is used for this prediction. Data from the irrigation field of North-West part in Bangladesh is used here to find the result of prediction.
Fichier principal
Vignette du fichier
470174_1_En_7_Chapter.pdf (582.46 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01888626 , version 1 (05-10-2018)

Licence

Identifiers

Cite

Fizar Ahmed. An IoT-Big Data Based Machine Learning Technique for Forecasting Water Requirement in Irrigation Field. 11th International Conference on Research and Practical Issues of Enterprise Information Systems (CONFENIS), Oct 2017, Shanghai, China. pp.67-77, ⟨10.1007/978-3-319-94845-4_7⟩. ⟨hal-01888626⟩
121 View
122 Download

Altmetric

Share

More