The advancement of deep learning (DL) technology and Unmanned Aerial Vehicles (UAV) remote sensing has made it feasible to monitor coastal wetlands efficiently and precisely. However, studies have rarely compared the performance of DL with traditional machine learning (Pixel-Based (PB) and Object-Based Image Analysis (OBIA) methods) in UAV-based coastal wetland monitoring. We constructed a dataset based on RGB-based UAV data and compared the performance of PB, OBIA, and DL methods in the classification of vegetation communities in coastal wetlands. In addition, to our knowledge, the OBIA method was used for the UAV data for the first time in this paper based on Google Earth Engine (GEE), and the ability of GEE to process UAV data was confirmed. The results showed that in comparison with the PB and OBIA methods, the DL method achieved the most promising classification results, which was capable of reflecting the realistic distribution of the vegetation. Furthermore, the paradigm shifts from PB and OBIA to the DL method in terms of feature engineering, training methods, and reference data explained the considerable results achieved by the DL method. The results suggested that a combination of UAV, DL, and cloud computing platforms can facilitate long-term, accurate monitoring of coastal wetland vegetation at the local scale.

As an important driving force, introgression plays an essential role in shaping the evolution of plant species. However, knowledge concerning how introgression affects plant evolution in agroecosystems with strong human influences is still limited. To generate such knowledge, we used InDel (insertion/deletion) molecular fingerprints to determine the level of introgression from japonica rice cultivars into the indica type of weedy rice. We also analyzed the impact of crop-to-weed introgression on the genetic differentiation and diversity of weedy rice, using InDel (insertion/deletion) and SSR (simple sequence repeat) molecular fingerprints. Results based on the STRUCTURE analysis indicated an evident admixture of some weedy rice samples with indica and japonica components, suggesting different levels of introgression from japonica rice cultivars to the indica type of weedy rice. The principal coordinate analyses indicated indica–japonica genetic differentiation among weedy rice samples, which was positively correlated with the introgression of japonica-specific alleles from the rice cultivars. In addition, increased crop-to-weed introgression formed a parabola pattern of dynamic genetic diversity in weedy rice. Our findings based on this case study provide evidence that human activities, such as the frequent change in crop varieties, can strongly influence weed evolution by altering genetic differentiation and genetic diversity through crop–weed introgression in agroecosystems.

Naked barley (Hordeum vulgare var. nudum) is a staple food crop, contributing significantly to global food security. Understanding genetic diversity will facilitate its effective conservation and utilization. To determine genetic diversity and its distribution within and among varieties, we characterized 30 naked barley varieties from Tibet, representing the traditional, modern, and germplasm-resources-bank gene pools, by analyzing SSR molecular fingerprints. The results demonstrate abundant genetic diversity in Tibetan naked barley varieties, particularly those in the traditional gene pool that holds much more private (unique) alleles. Principal coordinates and STRUCTURE analyses indicate substantial deviation of the modern varieties from the traditional and germplasm-resources-bank varieties. A considerable amount of seed mixture is detected in the modern varieties, suggesting the practices of using mixed seeds in modern-variety cultivation. Cluster analyses further indicate the narrow genetic background of the modern varieties, likely due to the limited number of traditional/germplasm-resources-bank varieties applied in breeding. Relationships between increases in genetic diversity and sample sizes within naked barley varieties highlight the importance of effective sampling strategies for field collections. The findings from this study have important implications for the sustainable utilization and effective conservation of different types of naked barley germplasm, both in Tibet and in other regions around the world.

Naked barley (Hordeum vulgare var. nudum) is a staple food crop contributing significantly to the global food security. Understanding genetic diversity will facilitate its effective conservation and utilization. To determine genetic diversity and its distribution within and among varieties, we characterized 30 naked barley varieties representing the traditional, modern, and germplasm-resources-bank gene-pools from Tibet, using the SSR molecular fingerprints. Results demonstrate abundant genetic diversity in Tibetan naked barley varieties, particularly those in the traditional gene-pool that holds much more private alleles. Principal coordinates and STRUCTURE analyses indicate substantial deviation of the modern varieties from the traditional and germplasm-resources-bank varieties. A considerable amount of seed mixture is detected in the modern varieties, suggesting the practices of using mixed seeds in modern-variety cultivation. Cluster analyses indicate the narrow genetic background of the modern varieties because of a few traditional/germplasm-resources-bank varieties used in breeding. Relationships between variation of genetic diversity and increases in sample sizes within naked barley varieties suggest effective sampling strategies for field collections. Knowledge generated from this study has important implications for the sustainable utilization and effective conservation of different types of naked barley germplasm in Tibet and in other regions of the world.