Various geological factors shape drainage patterns. Identifying drainage patterns is a classic problem in topographical knowledge mining and map generalization. Existing rule-based methods rely heavily on the parameter settings of cartographers for drainage-pattern recognition. These methods effectively identify drainage patterns in specific areas but require manual parameter tuning to identify drainage patterns in other areas. Owing to the complexity of topological and geometric characteristics, drainage pattern recognition involves nonlinear problems, and it is difficult to build mapping relationships between characteristics and patterns using rule-based methods. Therefore, we proposed a data-driven method based on a graph convolutional neural network to avoid heavy reliance on human experience and automatically mine implicit relationships between characteristics and drainage patterns. First, six typical drainage patterns (dendritic, rectangular, parallel, trellis, reticulate, and fanned) were listed based on map specifications, and the unique characteristics of each drainage pattern were illustrated. Subsequently, the drainage graphs were constructed. The characteristics of the whole, local, and individual units in the drainage networks were quantified based on drainage vector data. Finally, an identification model was developed using graph convolution, self-attention pooling, and multiple fully connected layers for drainage pattern recognition. After training and testing, the accuracy of our model (0.801 ± 0.014) was better than that of the rule-based method (0.572 ± 0.000) and the traditional machine learning methods (less than 0.733 ± 0.016). The results demonstrate that the ability of our model to identify drainage patterns surpasses that of other methods. 相似文献
This study presents a detailed analysis of geochemical and biotic proxies in a lake sediment profile to assess the effects of local and regional environmental drivers on the Holocene development of Lake Loitsana, situated in the northern boreal forest of NE Finland. Multi-proxy studies, in particular those that include a detailed plant macrofossil record, from the part of the northern boreal zone of Fennoscandia which has not been affected by treeline fluctuations, are scarce and few of these records date back to the earliest part of the Holocene. A 9-m sediment sequence of gyttja overlying silts representing the last c. 10,700 cal year, allowed for a high-resolution study with emphasis on the early to mid-Holocene lake history. The lacustrine sediments were studied using lithology, loss-on-ignition and C/N ratios, micro- and macro-fossils of aquatic and wetland taxa, diatoms, chironomids and accelerator mass spectrometry 14C dating on terrestrial plant macrofossils. Our study shows that the local development at Loitsana was complex and included a distinct glacial lake phase and subsequent drainage, a history of fluvial input affected by nearby wetland expansion, and lake infilling in an eventual esker-fed shallow lake. Enhanced trophic conditions, due to morphometric eutrophication, are recorded as Glacial Lake Sokli drained and open water conditions became restricted to a relatively small Lake Loitsana depression. pH appears to have been stable throughout the Holocene with a well-buffered lake due to the local carbonatite bedrock (Sokli Carbonatite Massif). The fossil assemblage changes are best explained by a complex mixture of drivers, including water-body conditions (i.e. depth, turbidity and turbulence), rate of sediment input, and the general infilling of the lake, highlighting the need to carefully evaluate the possible influence of such local factors as palaeoenvironmental conditions are reconstructed based on aquatic proxies. 相似文献
A generalized, efficient, and practical approach based on the travel‐time modeling framework is developed to estimate in situ reaction rate coefficients for groundwater remediation in heterogeneous aquifers. The required information for this approach can be obtained by conducting tracer tests with injection of a mixture of conservative and reactive tracers and measurements of both breakthrough curves (BTCs). The conservative BTC is used to infer the travel‐time distribution from the injection point to the observation point. For advection‐dominant reactive transport with well‐mixed reactive species and a constant travel‐time distribution, the reactive BTC is obtained by integrating the solutions to advective‐reactive transport over the entire travel‐time distribution, and then is used in optimization to determine the in situ reaction rate coefficients. By directly working on the conservative and reactive BTCs, this approach avoids costly aquifer characterization and improves the estimation for transport in heterogeneous aquifers which may not be sufficiently described by traditional mechanistic transport models with constant transport parameters. Simplified schemes are proposed for reactive transport with zero‐, first‐, nth‐order, and Michaelis‐Menten reactions. The proposed approach is validated by a reactive transport case in a two‐dimensional synthetic heterogeneous aquifer and a field‐scale bioremediation experiment conducted at Oak Ridge, Tennessee. The field application indicates that ethanol degradation for U(VI)‐bioremediation is better approximated by zero‐order reaction kinetics than first‐order reaction kinetics. 相似文献
Satellite images are used extensively in studying the urban heat island (UHI) phenomenon. We evaluated the suitability of thermal infrared (TIR) data from the HJ-1B satellite for detecting UHI using a case study in Beijing. Two modified algorithms for retrieving the land surface temperature (LST) from HJ-1B data were tested. The results were compared with LST images derived from a Landsat TM thermal band and the MODIS LST output. The spatial pattern of UHI generated using HJ-1B data matched well with that produced using TM and MODIS data. Of the two algorithms, the mono-window algorithm performed better but further tests are necessary. With more frequent coverage than TM and higher spatial resolution than MODIS, the HJ-1B TIR data present a unique opportunity to study thermal environments in cities in China and neighboring countries.