We used near infrared reflectance spectroscopy (NIR) combined with chemometric methods to predict the sorption of lindane and linuron to 27 agricultural soils from Sweden. The NIR predictions were calibrated by principal component analysis (PCA) of the NIR spectra and sorption data obtained using the batch equilibrium technique. Partial least square regression PLSR of the NIR data could predict 85% of the soil sorption (K (d)) for lindane and 84% for linuron, respectively. The results indicate that NIR can be used as a rapid and simple method to predict pesticide sorption to and leaching from soils.