Assessing soil salinity dynamics using time-lapse electromagnetic conductivity imaging

Leziria Grande de Vila Franca de Xira, located in Portugal, is an important agricultural system where soil faces the risk of salinization due to climate change, as the level and salinity of groundwater are likely to increase as a result of the rise of the sea water level and consequently of the estuary. These changes can also affect the salinity of the irrigation water which is collected upstream of the estuary. Soil salinity can be assessed over large areas by the following rationale: (1) use of electromagnetic induction (EMI) to measure the soil apparent electrical conductivity (ECa, mSm(-1)); (2) inversion of ECa to obtain electromagnetic conductivity imaging (EMCI) which provides the spatial distribution of the soil electrical conductivity (sigma, mSm(-1)); (3) calibration process consisting of a regression between sigma and the electrical conductivity of the saturated soil paste extract (ECe, dSm(-1)), used as a proxy for soil salinity; and (4) conversion of EMCI into salinity cross sections using the obtained calibration equation. In this study, EMI surveys and soil sampling were carried out between May 2017 and October 2018 at four locations with different salinity levels across the study area of Leziria de Vila Franca. A previously developed regional calibration was used for predicting ECe from EMCI. Using time-lapse EMCI data, this study aims (1) to evaluate the ability of the regional calibration to predict soil salinity and (2) to perform a preliminary qualitative analysis of soil salinity dynamics in the study area. The validation analysis showed that ECe was predicted with a root mean square error (RMSE) of 3.14 dSm(-1) in a range of 52.35 dSm(-1), slightly overestimated (-1.23 dSm(-1)), with a strong Lin's concordance correlation coefficient (CCC) of 0.94 and high linearity between measured and predicted data (R-2 = 0 :88). It was also observed that the prediction ability of the regional calibration is more influenced by spatial variability of data than temporal variability of data. Soil salinity cross sections were generated for each date and location of data collection, revealing qualitative salinity fluctuations related to the input of salts and water either through irrigation, precipitation, or level and salinity of groundwater. Time-lapse EMCI is developing into a valid methodology for evaluating the risk of soil salinization, so it can further support the evaluation and adoption of proper agricultural management strategies, especially in irrigated areas, where continuous monitoring of soil salinity dynamics is required.