Forest landscape preference studies have an important role and significance for forest landscape conservation, quality improvement and utilization. However, there are few studies on objective forest landscape preferences from the perspective of plants and using photos. This study relies on Deep Learning technology to select six case sites in China and uses geotagged photos of forest landscapes posted by the forest recreationists on the “2BULU” app as research objects. The preferences of eight forest landscape scenes, including look down landscape, look forward landscape, look up landscape, single-tree-composed landscape, detailed landscape, overall landscape, forest trail landscape and intra-forest landscape, were explored. It also uses Deepsentibank to perform sentiment analysis on forest landscape photos to better understand Chinese forest recreationists’ forest landscape preferences. The research results show that: (1) From the aesthetic spatial angle, people prefer the flat view, while the attention of the elevated view is relatively low. (2) From the perspective of forest scale and level, forest trail landscape has a high preference, implying that trail landscape plays an important role in forest landscape recreation. The landscape within the forest has a certain preference, while the preference of individual, detailed and overall landscape is low. (3) Although forest landscape photographs are extremely high in positive emotions and emotional states, there are also negative emotions, thus, illustrating that people’s preferences can be both positive and negative.

In the study of protected areas, the "Fences & fines" approach is increasingly becoming acknowledged as obsolete and ineffectual, and there is mounting evidence suggesting that the "Community-based conservation" approach is acquiring consideration. It is significant to identify which protection model or factors perform a definitive part in China. Taking the East Dongting Lake National Nature Reserve in China as a survey site, this paper utilizes semi-structured interviews and random questionnaires surveyed 431 households to investigate the relationship between "community-based conservation" approaches such aslegal system, ecological compensation, environmental education, community participation, concessions, livelihoods, job provision, intrinsic motivation and pro-environmental behavior. The regression results declare that intrinsic motivation (β = 0.390) and legal system (β = 0.212) are the most effective factors impacting on pro-environmental behavior; concessions has a negative conflict on preservation;but other "community-based conservation" approaches had insignificant positive impacts on pro-environmental behavior. Further mediating effects analysis indicated that intrinsic motivation (B = 0.3899, t = 11.9694, p < 0.01) mediates between legal system and pro-environmental behavior of community residents, legal system promotes pro-environmental behavior by promoting intrinsic motivation, which is more effective than legal system promoting pro-environmental behavior directly. This demonstrates that “Fence and fine approach" still is an effective management tool which can shape community residents' positive attitude towards conservation and pro-environmental behavior especially protected areas with large communities. And appropriate "community-based conservation" approaches can mitigate conflicts between special groups with the combination of these two approaches, the management of protected areas can be successful. This supplies a valuable real-world case for the current debate on conservation and improved human livelihoods.

In the study of protected areas, the " Fences & fines " approach is increasingly becoming acknowledged as obsolete and ineffectual, and there is mounting evidence suggesting that the "Community-based conservation" approach is acquiring consideration. It is significant to identify which protection model or factors perform a definitive part in China. Taking the East Dongting Lake National Nature Reserve in China as a survey site, this paper utilizes a random sampling method to interview 431 households to investigate the relationship between legal system, ecological compensation, environmental education, community participation, concessions, livelihoods, job provision, intrinsic motivation and pro-environmental behavior. The regression results declare that intrinsic motivation and legal system are the most effective factors impacting on pro-environmental behavior; concessions has a critical adverse consequence on pro-environmental behavior; ecological compensation, community participation, environmental education, livelihoods, and job provision had insignificant positive impacts on pro-environmental behavior. Further mediating effects analysis and SEM model construction indicated that intrinsic motivation mediates between legal system and pro-environmental behavior of community residents, legal system promotes pro-environmental behavior by promoting intrinsic motivation, which is more effective than legal system promoting pro-environmental behavior directly. This demonstrates that in communal protected areas, long-term strict legal constraints can shape community residents' positive attitude towards conservation and pro-environmental behavior, and appropriate "community-based conservation" approaches can mitigate conflicts between special groups represented by hunters and protected areas. With the combination of these two approaches, the management of protected areas can be successful. This supplies a valuable real-world case for the current debate on biodiversity conservation.