Water-absorption-trough dewatering machine for estimation of organic carbon in moist soil
2021
Lin, Lixin | Wang, Yunjia | Liu, Xixi | Zhang, Xinyu
Quantitative estimation of soil organic carbon (SOC) is essential for the study of the C cycle and global C storage. Soil spectroscopic technology provides a cost-effective and time-efficient method for SOC quantification and has been successfully used to determine SOC storage. However, the SOC estimation accuracy remains limited by other soil properties, particularly soil water. In this study, we proposed a new deep learning algorithm named the Water Absorption Trough Dewatering Machine (WATDM) to improve estimations of SOC from soil reflectance spectra and reduce the effect of soil water. Soil water and reflectance spectral data of soil samples were measured using spectrometry. Based on the soil water contents derived from the water absorption troughs around 1900 nm, the optimal WATDM model was obtained and treated as the final model of the WATDM method, which performed better than a multiple linear regression model based on moist soil samples. The findings of this study indicate that the WATDM method can improve the estimation accuracy of SOC content by reducing the effect of soil water and can be used as a valuable new methodology within the spectroscopic estimation of soil properties.
Показать больше [+] Меньше [-]Ключевые слова АГРОВОК
Библиографическая информация
Эту запись предоставил National Agricultural Library