Accurate digital mapping of farmland soil organic carbon (SOC) contributes to sustainable agricultural development and climate change mitigation. Farmland landscape pattern has changed greatly under anthropogenic influence, which should be considered an environmental variable to characterize the impact of human activities on SOC. In this study, we verified the feasibility of integrating landscape patterns in SOC prediction on Lower Liaohe Plain. Specifically, ten variables (climate, topographic, and landscape pattern variables) were selected for prediction with Random Forest (RF) and Support Vector Machines (SVMs). The effectiveness of landscape metrics was verified by establishing different variable combinations: (1) natural variables, and (2) natural and landscape pattern variables. The results confirmed that landscape variables improved mapping accuracy compared with natural variables. R2 of RF and SVM increased by 20.63% and 20.75%, respectively. RF performed better than SVM with smaller prediction error. Ranking of importance of variables showed that temperature and precipitation were the most important variables. The Aggregation Index (AI) contributed more than elevation, becoming the most important landscape variable. The Mean Contiguity Index (CONTIG-MN) and Landscape Contagion Index (CONTAG) also contributed more than other topographic variables. We conclude that landscape patterns can improve mapping accuracy and support SOC sequestration by optimizing farmland landscape management policies.

Providing food security to meet the growing human demand while improving the biodiversity of arable land is a global challenge. Although semi-natural field margins are known to enhance biodiversity in arable land systems globally, the role that abundant artificial field margins play in maintaining epigeic arthropod diversity within arable land remains unclear. Here, we compared epigeic arthropods within adjacent arable land with an artificial field margin (paved and dirt roads) and a semi-natural field margin (ditch, woodland, or grassland), as well as vegetation community characteristics at a field scale for identifying the ecological effects of different field margin types. Our results indicated the following: (i) Compared with semi-natural field margins, there is less epigeic arthropod diversity and less stable ecological networks within adjacent arable land with artificial field margins, with more herbivores within adjacent arable land with artificial field margins and more natural enemies within adjacent arable land with semi-natural field margins. (ii) Arable land adjacent to a dirt road (DR) maintained more resilient ecological networks than that adjacent to a paved road (PR), and there are more flowering plants at DRs, which attracts natural enemies, whereas Orthoptera is more active at PRs with abundant weeds. (iii) The main factors affecting epigeic arthropod functional groups were the tree layer cover (TC), herb layer abundance (HA), and herb layer height (HH) of the artificial and semi-natural field margins. We concluded that increasing the number of flowering plants and removing noxious weeds can eliminate negative effects on epigeic arthropod functional groups within adjacent arable land with artificial field margins. Delineating a certain percentage of vegetation strips to be a buffer zone in artificial field margins or creating a suitable vegetation community in semi-natural field margins can maintain and protect natural enemies and strengthen the ecological network stability between functional groups.