Votre recherche
Résultats 3 ressources
-
Abstract Vegetation restoration has been proposed as an effective measure for rehabilitating degraded land and slowing desertification in arid regions. However, the spatial variation in soil quality and plant diversity following vegetation restoration remains unclear. This study was designed to explore soil nutrient dynamics and how soil nutrients affect plant diversity and spatial heterogeneity after shrub restoration. We assessed the effect of Haloxylon ammodendron (C.A.Mey.) Bunge (which has been planted over 30 years) on the soil nutrients and plant diversity in a desert–oasis ecotone in Minqin County, Gansu, China, using geostatistics, beta diversity and rarefaction analyses, and Hill number extrapolation. Soil nutrients, including soil organic matter, total nitrogen, and alkali nitrogen, increased significantly after H. ammodendron planting. Species richness gradually increased from 1–5 years to 10–20 years after H. ammodendron was planted but then decreased at 20–30 years. The largest differences in plant composition were observed at 15 and 20 years. Plant diversity increased in the whole 30 years after shrub planting, increasing in the first 25 years and then decreasing at 26–30 year stage. The maximum coefficient of determination for the spatial heterogeneity model fit was 0.84 (25 years). The spatial heterogeneity in vegetation decreased with increasing soil available K content at 1–10 years. Our results suggest that planting shrubs can improve soil conditions and plant species diversity in desert–oasis ecotones and soil nutrients have a strong influence on plant diversity patterns and spatial heterogeneity following vegetation restoration.
-
Abstract Background The accurate estimation of soil nutrient content is particularly important in view of its impact on plant growth and forest regeneration. In order to investigate soil nutrient content and quality for the natural regeneration of Dacrydium pectinatum communities in China, designing advanced and accurate estimation methods is necessary. Methods This study uses machine learning techniques created a series of comprehensive and novel models from which to evaluate soil nutrient content. Soil nutrient evaluation methods were built by using six support vector machines and four artificial neural networks. Results The generalized regression neural network model was the best artificial neural network evaluation model with the smallest root mean square error (5.1), mean error (− 0.85), and mean square prediction error (29). The accuracy rate of the combined k -nearest neighbors ( k -NN) local support vector machines model (i.e. k -nearest neighbors -support vector machine (KNNSVM)) for soil nutrient evaluation was high, comparing to the other five partial support vector machines models investigated. The area under curve value of generalized regression neural network (0.6572) was the highest, and the cross-validation result showed that the generalized regression neural network reached 92.5%. Conclusions Both the KNNSVM and generalized regression neural network models can be effectively used to evaluate soil nutrient content and quality grades in conjunction with appropriate model variables. Developing a new feasible evaluation method to assess soil nutrient quality for Dacrydium pectinatum , results from this study can be used as a reference for the adaptive management of rare and endangered tree species. This study, however, found some uncertainties in data acquisition and model simulations, which will be investigated in upcoming studies.