Digital Mapping Algorithms to Estimate Soil Salinity in Indira Gandhi Nahar Pariyojana (IGNP) Command area of India

Abstract

In the present study, the distribution of salinity was investigated usingdigital soil mapping (DSM) algorithms in the 5 km buffer zone of both sides of theIndira Gandhi Nahar Pariyojana (IGNP) canal system of Suratgarh tehsil inRajasthan. To achieve this goal, 64 soil samples were used with 21 environmentalcovariates and 3 DSM algorithms. The result from the study showed that the-1difference between the minimum and maximum EC is very high (35.55dS m ) in theedifferent irrigation zone of the IGNP canal system. The EC ranged from 0.50 to 36.05e-1dSm . Results indicated that the most important environmental covariates wereannual precipitation, elevation and valley depth. Among the DSM algorithms, RFmodel showed the best performance in predicting EC at the regional level. Resultse2showed that the RF algorithm could predict EC with an R , RMSE and MAE ofe0.701, 3.367 and 1.722, respectively. RF and QRF showed similar performance inpredicting EC , while SVM showed lower efficiency than the other models in terms ofe2R and prediction errors. The salinity prediction map shows that the vulnerability tosoil salinity is high in theAnupgarh branch of the canal, and low in the IGNP main andBikaner canal area. Furthermore, the model developed in this study providescomprehensive guidance for the land planners and decision-makers to developamicable strategies for the management of the IGNP canal system.