Semi-Arid Region Soil Moisture Prediction using Multivariate Regression
Roohul Abad Khan1, Javed Mallick2, Rachida El Morabet3
1Roohul Abad Khan*, Faculty of Science and Engineering, Himalayan University, Arunachal Pradesh, India.
2Javed Mallick, Department of Civil Engineering. King Khalid University, Abha, Saudi Arabia.
3Rachida El Morabet, Department of Geography, University Hassan II Casablanca Morocco.

Manuscript received on November 17., 2019. | Revised Manuscript received on November 24 2019. | Manuscript published on 30 November, 2019. | PP: 12457-12460 | Volume-8 Issue-4, November 2019. | Retrieval Number: D9284118419/2019©BEIESP | DOI: 10.35940/ijrte.D9284.118419

Open Access | Ethics and Policies | Cite  | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: The Water Scarcity is a prominent feature in Arid and Semi-Arid region. Soil moisture content is significant factor in deciding vegetation growth and also affects the performance of any water harvesting system in place. This paper evaluates the interrelationship of Soil properties with Soil Moisture content. The study covers about 13 soil Samples from Single Watershed. The soil properties covered in the study are Conductivity, pH, Bulk Density, Dry Density, Specific gravity, organic content, void ratio, and Moisture Content. Multiple linear regression analysis was done to determine significance of each soil properties for soil moisture content as individual and as whole. Modelling was done based on soil characteristics to predict Soil Moisture. Principal Component Analysis was performed to identify most significant soil properties responsible for variation of prediction of Soil Moisture content. The Correlation between location topography and Moisture Content was obtained through Cluster Analysis.
Keywords: Moisture Content, Regression Analysis, Principal Component Analysis, Cluster Analysis.
Scope of the Article: Regression and Prediction.