Extracting check dam areas from high‐resolution imagery based on the integration of object‐based image analysis and deep learning

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.

Terraces mapping by using deep learning approach from remote sensing images and digital elevation models

“…In this study, remote sensing images were acquired from Google Earth images, taken on October 3, 2020. Actually, these images have been widely used in object identification, which is suitable for terrace mapping in this research (Dai et al., 2020; Li et al., 2021; Li, Xiong, Tang, Hu, & Strobl, 2020). DEMs were collected by means of unmanned aerial vehicle photogrammetry on July 21, 2020 in the field (Table 1).…”

Past rainfall-driven erosion on the Chinese loess plateau inferred from archaeological evidence from Wucheng City, Shanxi

“…During this period, human activities had a remarkable impact on the landform evolution process in this area. Terraces and other anthropogenic facilities have been widely constructed here in the last 100 years 36 , which suggests that current human activities negatively influence and slow erosion on the Loess Plateau.…”

Priority setting for restoration in surrounding savannic areas of the Brazilian Pantanal based on soil loss risk and agrarian structure

“…We emphasize that the zoning of interventions within erosions was only possible with the vectorization of the drainage lines through visual inspection. Although the current trend of applying machine learning algorithms dominates publications on the spatialization of erosive processes (Ghorbanzadeh et al, 2020) or the detection of ravine edges (Li et al, 2021), here we highlight the importance of human expertise on RS images analysis. In this sense, our algebra of selection and exclusion of false positives can be useful as an attribute for achieving more robust models (Minella et al, 2010), or even for integrating variables in GIS, such as distance to roads, lithology, slope curvatures, and topographic indices (Zabihi et al, 2018;Pourghasemi et al, 2020;Amiri and Pourghasemi, 2020), especially regarding the locations suitable for palisades, whose studies are still scarce.…”