Selection of characteristic wavebands to minimize soil moisture effects with in-situ soil spectroscopy

Authors: ZHOU, PENG - China Agricultural University; Sudduth, Kenneth - Ken; Veum, Kristen; LI, MINZAN - China Agricultural University

Submitted to: Proceedings of the American Society of Agricultural and Biological Engineers International (ASABE)
Publication Type: Proceedings
Publication Acceptance Date: 6/12/2020
Publication Date: 7/13/2020
Citation: Zhou, P., Sudduth, K.A., Veum, K.S., Li, M. 2020. Selection of characteristic wavebands to minimize soil moisture effects with in-situ soil spectroscopy. Proceedings of the American Society of Agricultural and Biological Engineers International (ASABE). Paper No. 2000191. https://doi.org/10.13031/aim.202000191.
DOI: https://doi.org/10.13031/aim.202000191

Interpretive Summary: Collection of in-situ data using visible and near-infrared spectroscopy (VNIRS) soil sensors has the potential to provide rapid, high-resolution estimates of soil properties for precision agriculture, soil health assessment, and other applications related to environmental protection and agronomic sustainability. Most previous research has focused on laboratory-based VNIRS, where drying and sieving of samples is typically used to eliminate soil moisture effects. In contrast, this research investigated methods to reduce or eliminate soil moisture effects without the need for drying and sieving. Mathematical pretreatment of the spectral data was able to partially reduce soil moisture effects; however, the reduction was not enough to provide useful results. Because of this, other soil moisture reduction approaches will need to be evaluated to further improve the prediction accuracy of in-situ VNIRS.

Technical Abstract: Visible and near-infrared spectroscopy (VNIRS) has been used to supply fast, nondestructive and environmentally-friendly estimation of profile soil properties, but most of the previous research has been limited to VNIRS of air-dried and sieved soil. The need to air-dry and sieve the soil slows the estimation process and increases labor requirements, so real-time, in-situ measurements of moist soil would be preferable. Soil moisture is recognized as a major factor reducing the utility and accuracy of soil property estimation by real-time VNIRS. Therefore, the objective of this paper is to explore pretreatment methods of soil spectra to improve the estimation of soil total nitrogen (TN) based on real-time, in-situ measurements without the need for artificial drying and sieving of soil cores. A commercial soil profile sensing instrument, the Veris P4000, was used to acquire real-time VNIRS data to a 1m depth in 22 fields across Missouri and Indiana, USA. Simultaneously, soil cores were obtained and TN content was measured in the laboratory with standard methods. The derivative method was used to reduce the interference of soil moisture. The correlation coefficients between VNIRS and TN content demonstrated that the derivative method was effective at decreasing the effect of soil moisture at some moisture levels. Seven sensitive wavebands were selected using the particle swarm optimization algorithm. Finally, two modeling approaches were compared. Partial least squares regression models were calibrated based on the full spectrum, and back-propagation neural network models were calibrated based on sensitive wavebands. Both approaches reduced the effect of soil moisture, suggesting an improvement in prediction accuracy could be achieved. These results demonstrate that other soil moisture reduction approaches should be evaluated to further improve the prediction accuracy of VNIRS.