Soil Moisture Modelling Using Remote Sensing and Artificial Neural Networks: A Study of Devbhumi Dwarka Region, Gujarat, India
K. M. Gojiya *
Agriculture Research Station (Fruit Crops), Junagadh Agricultural University, Mahuva, India.
B. A. Karangiya
College of Agricultural Engineering and Technology, Junagadh Agricultural University, Junagadh, India.
S. K. Chavda
Chimanbhai Patel College of Agriculture, Sardarkrushinagar Dantiwada Agricultural University, Dantiwada, India.
S. K. Gaadhe
College of Agricultural Engineering and Technology, Junagadh Agricultural University, Junagadh, India.
D. K. Gojiya
Polytecnic in Agro-Processing, Junagadh Agricultural University, Junagadh, India.
H. D. Rank
Department of SWCE, College of Agricultural Engineering and Technology, Junagadh Agricultural University, Junagadh, India.
*Author to whom correspondence should be addressed.
Abstract
For the arid and semi-arid region of Devbhumi Dwarka in Gujarat, where soil moisture issue is prominent, a GIS-based approach is needed to develop models for estimation of soil moisture. In this study, Landsat and Sentinel data were used to develop multiple soil moisture indices. Using these spectral indices, artificial neural network (ANN) models were developed using actual recorded soil moisture data. Total of 174 samples were collected in the study area of 3,77,731 ha. Values of soil moisture ranged from 3.40 % to 12.50 % with an average value of 8.42 %. The maps of soil moisture indices i.e. LST, NDVI, NDWI, NSDSI3, MI and VSWI were generated on 1:550000 scale using ArcMap software. Moisture index NSDSI3 was highest correlating index. Best ANN model for soil moisture content (SMC) estimation was developed using Sentinel data (8-14-1) with RMSE, R2 and NRMSE values of 0.85 %, 0.73 and 0.10 for training and 1.11 %, 0.54 and 0.13 for testing respectively.
Keywords: Soil moisture modelling, remote sensing, GIS, ANN, spectral indices