Mobile and benchtop MIR spectrometer comparison for soil salinity indicators prediction in arid and semi-arid areas

: Soil salinity and alkalinity pose critical challenges to soil health, especially in arid and semi-arid regions, leading to reduced crop productivity and ecosystem degradation. Soil salinity, resulting from excessive soluble salt accumulation, is exacerbated by factors such as high temperatures, low rainfall, poor irrigation water quality, and unrestricted use of soluble fertilizers. Controlling the parameters that determine soil quality in terms of salinity and alkalinity is essential. Soil spectroscopy modeling may also offer a rapid and effective alternative for assessing these parameters, providing reliable estimates with an acceptable level of error. This study compares the predictive performance of a mobile mid-infrared (MIR) spectrometer (Alpha II) and a benchtop instrument (Tensor II) in assessing soil salinity through key indicators: pH, electrical conductivity (EC), sodium adsorption ratio (SAR), and exchangeable sodium percentage (ESP) in southern Morocco. A total of 492 soil samples were used, split into calibration (80%) and test (20%) sets using the Kennard-Stone algorithm, with 5-fold cross-validation applied on the calibration set to optimize model hyperparameters. Three predictive algorithms including partial least squares regression (PLSR), random forest (RF), and memory-based learning (MBL) were applied alongside various spectral preprocessing techniques to optimize prediction accuracy. Model performance was evaluated using R 2 , RMSE, and RPD. The best results showed high accuracy for EC, SAR, and ESP, with R 2 values generally exceeding 0.80 (RPD > 2.0), and acceptable prediction performance for pH, with R 2 values not exceeding 0.65 (RPD 1.4 - 1.7). MBL and PLSR consistently delivered competitive and strong predictions for all properties across both spectrometers. MBL outperformed other tested models, particularly for EC, SAR, and ESP using the benchtop instrument (R 2 = 0.87, 0.85, and 0.84; RPIQ = 2.90, 2.17, and 2.66, respectively) and for pH using the mobile spectrometer (R 2 = 0.64, RMSE = 0.25, RPIQ = 2.82). Meanwhile, the performance of RF improved significantly by using preprocessing techniques. These findings highlight the promising potential of the mobile MIR spectrometer for rapid salinity assessment, with performance comparable to the benchtop instrument under laboratory conditions, though field validation is needed to confirm its practical viability.