Version 1
: Received: 1 October 2024 / Approved: 1 October 2024 / Online: 1 October 2024 (20:06:56 CEST)
How to cite:
Wu, Y.; Sun, X.; Jiang, D.; Zhang, H.; Li, C.; Gao, D. Integrating Forestry Knowledge into Research on Mountain Top and Water System Recognition Technology Using Deep Learning. Preprints2024, 2024100100. https://doi.org/10.20944/preprints202410.0100.v1
Wu, Y.; Sun, X.; Jiang, D.; Zhang, H.; Li, C.; Gao, D. Integrating Forestry Knowledge into Research on Mountain Top and Water System Recognition Technology Using Deep Learning. Preprints 2024, 2024100100. https://doi.org/10.20944/preprints202410.0100.v1
Wu, Y.; Sun, X.; Jiang, D.; Zhang, H.; Li, C.; Gao, D. Integrating Forestry Knowledge into Research on Mountain Top and Water System Recognition Technology Using Deep Learning. Preprints2024, 2024100100. https://doi.org/10.20944/preprints202410.0100.v1
APA Style
Wu, Y., Sun, X., Jiang, D., Zhang, H., Li, C., & Gao, D. (2024). Integrating Forestry Knowledge into Research on Mountain Top and Water System Recognition Technology Using Deep Learning. Preprints. https://doi.org/10.20944/preprints202410.0100.v1
Chicago/Turabian Style
Wu, Y., Chunpeng Li and Demin Gao. 2024 "Integrating Forestry Knowledge into Research on Mountain Top and Water System Recognition Technology Using Deep Learning" Preprints. https://doi.org/10.20944/preprints202410.0100.v1
Abstract
In the study of mountainous areas, mountain peaks play a vital role as geomorphic features that have significant influence on hydrological processes, vegetation distribution, and other important topographic characteristics. From the perspectives of geomorphology and hydrology, the river network water system is an interconnected entity that serves as a crucial component in describing regional topography, geomorphology, and hydrological features. The primary objective of this article is to extract water system information and mountain peak data in Chongli District, Hebei Province. To extract mountain peaks, coarse-resolution Digital Elevation Model (DEM) data is utilized to estimate their positions and initiate data sampling based on DEM elevations. Deep learning models are employed to avoid explicit feature extraction and instead implicitly learn from training data. By using weight sharing techniques, the training parameters of the network are reduced, achieving more accurate extraction and recognition of mountain peaks in Chongli District, along with their classification. For the extraction of the water system, the fast regional convolutional neural network algorithm from target detection is introduced to enhance the efficiency and accuracy of extracting water system information through image processing. This algorithm rapidly identifies the type, location, and width of the water systems. Additionally, the AlexNet transfer learning method is applied to locate the river skeleton within the extracted water system area. Morphological methods are then used to extract river morphology and calculate its length and width. Finally, a developed algorithm for water system information extraction detects the presence of water system coverage areas in Chongli District. Through experiments, a total of 2792 mountain peak data points were successfully extracted. In terms of water system information extraction, the Faster R-CNN and CNN-based methods demonstrate high efficiency and low detection rates. This study provides information services and data support for the operation and maintenance of the Chongli Winter Olympics. Furthermore, it serves as a reference for future research conducted by scholars in the Chongli area, offering insights into various fields such as environmental changes, vegetation classification, and geomorphic features.
Keywords
peak point; Water System; DEM; Spatial Analysis; GIS; terrain characteristics; Landform; Error Analysis; Deep Learning
Subject
Biology and Life Sciences, Forestry
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
