The loess area is located in the middle and upper reaches of the Yellow River Basin. This area has a large area of ecologically sensitive areas and fragile areas, and it is the region with the most serious soil erosion in the country. A lot of loess is attached to the surface of the loess area, the vegetation is relatively sparse, and the seasonal rainfall is obvious. Therefore, the amount of soil erosion is large, which has a significant impact on the soil fertility of the loess area. At the same time, a large amount of soil erosion poses a huge challenge to environmental protection in the middle and lower reaches. Therefore, the problem of soil erosion is a key phenomenon that needs attention in the loess area. This paper takes the loess area of Tongwei-Zhuanglang area in Gansu Province as the research object, uses the multi-year remote sensing image classification data as the background (2000, 2005, 2010, 2015), combined with meteorological data (this data is released according to CRU The global 0.5° climate data set and the high-resolution climate data set for China released by CNERN were generated by the Delta spatial downscaling scheme in the Loess Plateau area), soil data, and soil parameter data (source 1 from the second soil census: 1 million Chinese soil maps), topographic data (DEM), vegetation coverage data, and the use of an improved universal soil loss equation (RULSE) model to carry out soil erosion in the region for many years (2000, 2005, 2010, 2015) Strength information extraction and classification. Contrast and analyze the degree of soil erosion in the area for many years, and evaluate the local soil erosion prevention measures. Studies have shown that from 2000, 2010, and 2015, the degree of soil loss gradually decreased, and the total amount of soil loss gradually decreased. However, due to the abnormally reduced precipitation in 2005, the soil erosion was generally low, which was an abnormal situation. Overall, soil erosion has continued to decrease in recent years, and the effects of soil and water conservation have been remarkable.
As a new multi-sensor satellite, GaoFen-5 (GF-5) has gradually attracted more attention. Especially, the GF-5 hyperspectral sensor has shown good prospects in geological applications, such as mineral mapping, geological body identification, and mining environment analysis. Therefore, there is an urgent need to evaluate the effectiveness of GF-5 hyperspectral data relative to airborne hyperspectral images (HSI) in geological applications. In this paper, the characteristics and preprocessing steps of GF-5 HSI were introduced. The HyMap data in the Subei area was employed for comparative experiments to evaluate the application performance of GF-5 in gossan identification. The experimental results show that the diagnostic spectral characteristics of limonite can be observed through GF-5 data. The distribution trends of limonite in both hyperspectral data are consistent, and the concentration of the limonite area directly indicated the gossan information, indicating that GF-5 HSI has promising potential for mineral mapping and may have important significance in large-scale geological applications.
Hyperspectral Images (HSI) contains hundreds of spectral information, which provides detailed spectral information, has an inherent advantage in land cover classification. Benefiting from the previous studies on hyperspectral mechanisms, hyperspectral technology has achieved significant progress in classification. Deep learning technology, with remarkable learning ability, can better extract the spatial and spectral information of HIS, which is essential for classification. However, the research and application of deep learning in HIS classification are still insufficient, especially in terms of combining with prior knowledge, which has an advantage in data optimization. In this paper, a novel CNN network, name IUNet, is proposed for airborne hyperspectral classification. Besides, Besides, a series of knowledge-guided methods such as Radiation Consistency Correction (RCC) and Minimum Noise Fraction (MNF) were introduced to optimize the HIS data. Selected spectral indexes are employed to improve the classification accuracy according to the characteristics of the target. The HyMap images from Gongzhuling area of Jilin Province are used for experiments, and the experimental results show that the application of prior knowledge in data optimization can significantly improve the classification performance of hyperspectral classification based on deep learning.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.