Vis-NIR spectroscopy coupled with PLSR and multivariate regression models to predict soil salinity under different types of land use

Wang, Zixiao; Miao, Zhonghua; Yu, Xiaoyou; He, Feng

doi:10.1016/j.infrared.2023.104826

Cited by 5 publications

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multiple regression modeling is a well-established statistical method for predicting the values of dependent variables by modeling the relationships between multiple independent (explanatory) variables and a single dependent (response) variable [28]. To predict the MRA, we performed a multiple regression analysis using the number, area, and brightness of stars as independent variables and the corresponding MRA data as dependent variables.…”

Section: Different Mra Prediction Modelsmentioning

confidence: 99%

Automation in Middle- and Upper-Atmosphere LIDAR Operations: A Maximum Rayleigh Altitude Prediction System Based on Night Sky Imagery

Wei,

Liu,

Cheng

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

A prediction system was developed to determine the maximum Rayleigh altitude (MRA) by improving the automated detection of LIDAR power-on conditions and adapting to advancements in middle- and upper-atmosphere LIDAR technology. The proposed system was developed using observational data and nighttime sky imagery collected from multiple LIDAR stations. To assess the accuracy of predictions, three key parameters were employed: mean square error, root mean square error, and mean absolute error. Among the three prediction models created through multivariate regression and autoregressive integrated moving average (ARIMA) analyses, the most suitable model was selected for predicting the MRA. One-month predictions demonstrated the accuracy of the MRA with a maximum error of no more than 5 km and an average error of less than 2 km. This technology has been successfully implemented in numerous LIDAR stations, enhancing their automation capabilities and providing key technical support for large-scale, unmanned, and operational deployments in the middle- and upper-atmosphere LIDAR systems.

show abstract

Section: Different Mra Prediction Modelsmentioning

confidence: 99%