Search

The black soil region experiences complex erosion due to natural processes and intense human activities, leading to soil degradation and adverse ecological and agricultural impacts. However, the complexities involved in quantifying regional erosion poses remarkable challenges in accurately assessing the current status of regional soil erosion for effective soil conservation. To solve this issue, we proposed a new method for monitoring soil erosion using Interferometric synthetic aperture radar (InSAR) technology and machine learning algorithms within the Google Earth Engine platform. The new method not only enables regional-scale monitoring, but also ensures high accuracy in measurement (millimeter-level). The erosion susceptibility of the study area (Yanshou County, Heilongjiang Province, Northeastern China) was also classified using random forest algorithms to refine the monitored and predicted soil erosion. The results indicate that the five-year (2016–2021) deformation in Yanshou County was −11.08 mm, with a significant mean cumulative deformation of −8.08 mm yr−1 occurring in 2017. The driving factor analysis shows that the region was subject to the compound effect of water and freeze–thaw erosion, closely related to crop phenological stages. The susceptibility analysis indicates that 73.3% of the region was susceptible to erosion, with a higher probability in river areas, at high altitudes, and on steep slopes. However, good vegetation cover can reduce the risk of soil erosion to some extent. This study offers a new perspective on monitoring regional soil erosion in the black soil region of China. The proposed method holds potential for future expansion to monitor soil erosion in a larger areas, thereby guiding the strategies development for protection of the agriculturally important black soil. [ABSTRACT FROM AUTHOR]

A simple nonlinear control strategy using sparse kernel learning (SKL) with a polynomial kernel form is presented and applied to chemical processes. The nonlinear process is first identified by SKL with a polynomial kernel, and then a predictive control performance index is formulated. This index is characterized as an even-degree polynomial function of the manipulated input and has the benefit that the input can be separated from the index because of its special structure. Consequently, the optimal manipulated input can be efficiently obtained by solving a simple root problem of an odd-degree polynomial equation. Moreover, the control parameter directly relates to its performance and can be tuned in a guided manner. All these attributes result in a practicable solution for real-time process control. The novel controller is applied to two chemical processes to evaluate its performance. The obtained results show the superiority of the proposed method compared to a well-tuned proportional−integral−derivative controller in different situations. [ABSTRACT FROM AUTHOR]