Geo-Object-Based Vegetation Mapping via Machine Learning Methods with an Intelligent Sample Collection Scheme: A Case Study of Taibai Mountain, China

Precise vegetation maps of mountainous areas are of great significance to grasp the situation of an ecological environment and forest resources. In this paper, while multi-source geospatial data can generally be quickly obtained at present, to realize effective vegetation mapping in mountainous areas when samples are difficult to collect due to their perilous terrain and inaccessible deep forest, we propose a novel and intelligent method of sample collection for machine-learning (ML)-based vegetation mapping. First, we employ geo-objects (i.e., polygons) from topographic partitioning and constrained segmentation as basic mapping units and formalize the problem as a supervised classification process using ML algorithms. Second, a previously available vegetation map with rough-scale label information is overlaid on the geo-object-level polygons, and candidate geo-object-based samples can be identified when all the grids’ labels of vegetation types within the geo-objects are the same. Third, various kinds of geo-object-level features are extracted according to high-spatial-resolution remote sensing (HSR-RS) images and multi-source geospatial data. Some unreliable geo-object-based samples are rejected in the candidate set by comparing their features and the rules based on local expert knowledge. Finally, based on these automatically collected samples, we train the model using a random forest (RF)-based algorithm and classify all the geo-objects with labels of vegetation types. A case experiment of Taibai Mountain in China shows that the methodology has the ability to achieve good vegetation mapping results with the rapid and convenient sample collection scheme. The map with a finer geographic distribution pattern of vegetation could clearly promote the vegetation resources investigation and monitoring of the study area; thus, the methodological framework is worth popularizing in the mapping areas such as mountainous regions where the field survey sampling is difficult to implement.

Sensitivity of Vegetation on Alpine and Subalpine Timberline in Qinling Mountains to Temperature Change

Alpine timberline is a great place for monitoring climate change. The study of alpine and subalpine timberline in Qinling Mountains has led to early warning that reveals the response and adaptation of terrestrial vegetation ecosystem to climate change. Based on the remote sensing image classification method, the typical timberline area in Qinling Mountains was determined. Temperature and normalized difference vegetation index (NDVI) data were extracted from the typical timberline area based on spatial interpolation and NDVI data. The relationship between NDVI and temperature change and the critical temperature value affecting vegetation response in the timberline area in Qinling Mountains were analyzed. Correlation between NDVI and air temperature in the alpine and subalpine timberline areas of Qinling Mountains exhibited an upward trend, which implied that temperature promotes vegetation activity. A strong correlation between temperature and NDVI in typical timberline areas of Qinling Mountains, and a significant correlation between temperature and NDVI in the early growing season. A phenomenon of NDVI lagging behind air temperature was observed. Temperature response showed synchronization and hysteresis. The correlation between cumulative temperature and vegetation was similar between Taibai Mountain and Niubeiliang timberline, and the correlation between NDVI in April and cumulative temperature in the first 12 months was the strongest. Temperature threshold range of Taibai Mountain timberline played a dominant role in vegetation growth. Our results provide insights and basis for future studies of early warning signs of climate change, specifically between 0.34 and 1.34 °C. The threshold ranges of temperature response of different vegetation types vary. Compared with alpine shrub meadow, the threshold ranges of temperature effect of Coniferous forest and Larix chinensis Beissn. are smaller, implying that these vegetation types are more sensitive to temperature change.