Salix psammophila, classified under the Salicaceae family, is a deciduous, densely branched, and erect shrub. As a leading pioneer tree species in windbreak and sand stabilization, it has played a crucial role in combating desertification in northwestern China. However, different genetic sources of Salix psammophila exhibit significant variations in their effectiveness for windbreak and sand stabilization. Therefore, it is essential to establish a rapid and reliable method for identifying different Salix psammophila varieties. Visible and near-infrared (Vis-NIR) spectroscopy is currently a reliable non-destructive solution for origin traceability. This study introduced a novel feature selection strategy, called qualitative percentile weighted sampling (QPWS), based on the principle of the long tail effect for Vis-NIR spectroscopy. The core idea of QPWS combines weighted sampling and percentage wavelength selection to identify key wavelengths. By employing a multi-threaded parallel execution of multiple QPWS instances, we aimed to search for the optimal feature bands to address the instability issues that can arise during the feature selection process. To address the problem of reduced prediction performance in one-dimensional convolutional neural network (1D-CNN) models after feature selection, we have introduced convolutional autoencoders (CAEs) to reduce the dimensions of wavelengths that are discarded during feature selection. Subsequently, these reduced dimensions are fused with the selected wavelengths, thereby enhancing the model’s performance. With our completed model, we selected outstanding models for model fusion and established a decision system for Salix psammophila. It is worth noting that all 1D-CNN models in this study were developed using Bayesian optimization methods. In comparison with principal component analysis (PCA) and full spectrum methods, QPWS exhibits superior predictive performance in the field of machine learning. In the realm of deep learning, the fusion of data combining QPWS with CAE demonstrated even greater potential with an improvement of average accuracy of approximately 2.13% when compared to QPWS alone and a 228% increase in operational speed compared to a model with full spectra. These results indicated that the combination of CAE with QPWS can be an effective tool for identifying the origin of Salix psammophila.

To conduct ecological restoration in the Kubuqi sandy land and to select suitable superior Salix psammophila provenances, four provenances were selected from Dalate Banner, Ordos (DLT), Wushen Banner, Ordos (WSQ), Yulin, Shaanxi (YL), and Yanchi, Ningxia (YC). All cuttings were interplanted and established at an experimental site, and stumping was conducted five years after establishment. Six months after stumping, 11 parameters, including growth characteristics, gas exchange parameters, and photosynthetic pigments, were systematically measured. There were significant differences in plant height and branch number among Salix psammophila from different provenances, while there was no significance in the number of branches among different provenances. The daily variation in net photosynthetic rate (Pn) was significantly different among various Salix psammophila from different provenances, with highest in that from WSQ. The daily variations in stomatal conductance (Gs) and transpiration rate (Tr) from various provenances are relatively consistent, showing a unimodal trend. In terms of pigment content, the WSQ provenance exhibited the highest chlorophyll a content, while the YC provenance showed the highest carotenoid content. The variation coefficients of each parameters ranged 2.607–40.619%, with the highest for branch number, while the lowest for intercellular CO₂ concentration. Cluster analysis divided the Salix psammophila from four provenances into two groups, with DLT and YL being one group, and WSQ and YC being the other one. The results of entropy weight TOPSIS showed that the comprehensive ranking of various provenances was: WSQ > YC > YL > DLT, indicating the physiological properties of WSQ being superior to others, indicating its relatively high ecological adaptability in the semi-arid environment of the Kubuqi sandy land, and it can be used as a preferred provenance for ecological restoration and promotion applications.