| Summary: | This study explores the potential of using smartphone cameras to estimate soil attributes as a field-based alternative to traditional sampling and lab analyses that are time-consuming, expensive, and non-friendly to the environment. It aims to investigate whether the color information captured by smartphone cameras could provide spectral information that can be utilized for soil attribute estimation using regression techniques. The DN values from smartphone camera photos were transformed into reflectance using colored plastic plated marker (PPM) reference panels. The spectral information of the PPM keys, obtained using a laboratory spectrometer, was convolved into 3 RGB smartphone bands. Using the legacy soil spectral library (SSL) of Israel on the 3-reflectance calibrated RGB smartphone bands, a good agreement with the reflectance of the laboratory spectrometer was obtained. The soil properties were modeled with the converted reflectance using the multiple linear regression (MLR), partial least square regression (PLSR), and ridge regression (RR) algorithms. The models created using the smartphone data (RGB and 6 synthetic bands) predicted six soil properties: i.e., soil organic matter (OM%), CaCO3, free iron oxides (Fe-dithionite), Al2O3, soil surface area (SSA), and hygroscopic moisture with the coefficient of determination (R2) values of 0.58, 0.54, 0.60, 0.55, 0.55 and 0.64, respectively. The quality of predictions was also evaluated using root mean square error (RMSE) and the ratio of prediction to interquartile distance (RPIQ). This research provides the results of an experiment to convert a personal smartphone camera to a spectrometer with the help of SSL. Despite the low spectral resolution of smartphone cameras, the models achieved fair results in predicting six soil properties. These findings could promote the adoption of citizen science methodologies for sustainable soil management as smartphone devices that are available to all can be simply calibrated to reflectance and used for proximal sensing of soils.
|
|---|