Extracting check dam areas from high‐resolution imagery based on the integration of object‐based image analysis and deep learning. (18th February 2021)

• Record Type: Journal Article
• Authors: Li, Sijin; Xiong, Liyang; Hu, Guanghui; Dang, Weiqin; Tang, Guoan; Strobl, Josef
• Is Part Of: Land degradation & development. Volume 32:Number 7(2021)
• Page Start: 2303
• Page End: 2317
• Publication Date: 2021-02-18
• Subjects: check dam -- deep learning -- method integration -- object‐based image analysis -- soil and water conservation -- soil loss; Land degradation -- Periodicals; Soil conservation -- Periodicals; Reclamation of land -- Periodicals; Land use -- Periodicals; Economic development -- Environmental aspects -- Periodicals; 333.7315
• DOI: 10.1002/ldr.3908
• Languages: English
• ISSNs: 1085-3278

Abstract

Abstract: Soil loss is a global environmental problem that can intensively damage surrounding ecosystems. To control soil loss and secure agricultural activities, check dams are constructed for soil conservation. However, due to ineffective management, many check dams are abandoned and are highly prone to be damaged due to rainstorms. Such a phenomenon would cause more serious damage to surrounding environments than that associated with common soil loss. The similar basic signatures of check dam areas and their surroundings can blur the boundaries of these structures in images and negatively affect boundary identification, thereby limiting the effectiveness of traditional check dam area extraction techniques based on the pixel level or visual inspection. To facilitate the extraction of check dams, we propose a method that integrates deep learning and object‐based image analysis. We select the Loess Plateau, on which several effective check dam systems have been constructed in recent years to address intense soil loss, as the study area on which to perform high‐resolution imagery experiments to determine the influences of different sample combinations. The parameters influencing the segmentation algorithm are also examined to determine the best parameter combination for the extraction of check dams. Four test areas comprising 12 check dams across different environments were selected with which to test the accuracy of the proposed method. In addition, we compared the check dam extraction capabilities of our proposed method with those of the random forest and deep learning approaches. The results show that the proposed method can achieve a classification accuracy and kappa coefficient that signify good performance in detecting the boundaries and areas of check dams. The proposed method generally outperforms the random forest and deep learning techniques. The extraction results can support the efficient soil management and guide future studies on gully erosion.