As environment-friendly recreational facilities, greenways can bring ecological, social, and economic benefits to the residents of agricultural heritage sites (AHS). Zengcheng District of Guangzhou City first implemented the recreational greenway in China in 2008. Liantang Village is the tourist center of the Liantang Spring segment of Zeng River Greenway system. This village has always been an important planting region of black olive and lychee from ancient times, with more than 1800 large old trees until today. Taking Liantang as a case, participant observations, in-depth interviews, and questionnaires (n = 140) are performed to collect relevant data. This study explores the economic and sociocultural influences of greenway implementation on AHS. Findings reveal that greenway tourism and agricultural heritage conservation form a mutually beneficial relationship. The greenway implementation successfully prompts the emergence and rapid development of tourism which significantly improves the economy of the heritage area and effectively increases the income of the villagers in AHS. The sources of their income mainly include agritainment businesses, agricultural product sales, tourist-related business wages, land leases, and house rentals. Most villagers greatly improve their quality of life because of the continuous infrastructure improvements. However, the daily lives and production orders of villagers are disturbed to some extent. The villagers have a highly sober cognition of the value of old trees, and their protection consciousness is enhanced. The difference in the source of economic income affects the judgment of the villagers, and three groups of villagers exhibit some cognitive differences with the influence of tourism. Results indicate that multi-dimensional values of agricultural heritage can be achieved, and a mutually beneficial relationship will then be formed between tourism and agricultural heritage conservation as soon as the correct eco-tourism is developed in AHS.
Urbanization is one of the major threats to the dynamic inheritance of the agricultural heritage system (AHS). The ability to achieve sustainable development in intra-urban areas is an essential proposition related to the innovation of AHS conservation principles. The Haizhu high bed-low ditch agroecosystem (HHBLDA), a China-Nationally Important Agricultural Heritage System site located at the center of Guangzhou City, is taken as an example in this study. The effect of implementing the Land Acquisition to Keep Agricultural Use (LAKAU) on intra-urban AHS conservation is assessed through literature collection and review, field survey, and in-depth interviews. The results show that the LAKAU was implemented because of a three-decades-long struggle between ecological conservation and urban sprawl. Because of the important functions of ecosystem services, the AHS can coexist with urban land use in the course of rapid urbanization. The LAKAU mode can ensure that the nature of farmland remains unchanged, which is an effective strategy for the conservation of an urban AHS. The resulting problems, such as high operating costs, insufficient agricultural outputs, and insufficient local farmers in the AHS site because of off-farm opportunities, should be addressed by establishing an effective self-sustaining mechanism. Realizing the compatibility of management concepts between the AHS and nature reserves, adapting to the changing role of farmers, and strengthening the acceptance of the AHS by urban managers should attract the attention of decision-makers.
For the past decade, Important Agricultural Heritage Systems (IAHSs) have become research hotspots because of their rapidly increasing number. The non-use value is an important part of the value of an IAHS, and if ignored, the total value of an IAHS may be underestimated in part. Litchi is native to southern China, and its farming system is an important agricultural heritage with Chinese characteristics and global influence. In this context, the present study attempts to investigate the willingness to pay (WTP) of local residents and assess the non-use value of the Lingnan Litchi Cultivation System (Zengcheng) in Guangdong, China. To this aim, a survey was implemented on four sites in Zengcheng with the application of the contingent valuation method (CVM). Based on the analysis of 458 questionnaires, the WTP rate of residents in the heritage site is 66.6%, and the mean WTP is 62.5 Chinese yuan (CNY) per year. The total non-use value of the Lingnan Litchi Cultivation System (Zengcheng) is 49.9 million CNY. The option, bequest, and existence values in 2018 are estimated to be 20.1, 13.7, and 16.1 million CNY, respectively. Results of the logistic regression analysis indicate that variables of age, education level, financial burden, and heritage value cognition are significant factors of WTP for protecting litchi heritage. Compared with similar studies in China, the mean WTP and positive payment rate in this study are at a medium level. Resource attributes and local cultures may have significant impacts on the composition and estimate of the non-use value of an IAHS. The results of this study can be beneficial to the dynamic conservation and adaptive management of IAHSs.
Employing the multi-scale strategy in hyperspectral image (HSI) classification enables the exploration of complex land-cover structures with diverse shapes. However, existing multi-scale methods still have limitations for fine feature extraction and deep feature fusion, which hinder the further improvement of classification performance. In this paper, we propose a multi-scale dual-aggregated feature fusion network (MDFFN) for both balanced and imbalanced environments. The network comprises two main core modules: a multi-scale convolutional information embedding (MCIE) module and a dual aggregated cross-attention (DACA) module. The proposed MCIE module introduces a multi-scale pooling operation to aggregate local features, which efficiently highlights discriminative spectral–spatial information and especially learns key features in small target samples in the imbalanced environment. Furthermore, the proposed DACA module employs a cross-scale interaction strategy to realize the deep fusion of multi-scale features and designs a dual aggregation mechanism to mitigate the loss of information, which facilitates further spatial–spectral feature enhancement. The experimental results demonstrate that the proposed method outperforms state-of-the-art methods on three classical HSI datasets, proving the superiority of the proposed MDFFN.
Urbanization severely threatens the dynamic conservation of Agricultural Heritage Systems (AHS). Focusing on the Haizhu High Bed-Low Ditch Agroecosystem (HHBLDA) in Guangzhou, China—a rare urban AHS facing rapid encroachment—this study integrates the Semantic Differential (SD) method with VR eye-tracking to quantify the public’s subjective evaluations and objective visual preferences. The findings reveal a critical perceptual discrepancy: despite expressing subjective interest in the AHS, participants’ objective visual attention heavily gravitates toward designed garden landscapes, exposing an intrinsic inadequacy in the agricultural site’s aesthetic appeal. Analysis identifies “uniqueness” and “sense of order” as core perceptual drivers, especially among younger demographics exhibiting high visual exploration. Consequently, this study proposes a perception-driven, hierarchical zoning conservation strategy. By prioritizing these core drivers and enriching the site’s cultural-artistic ambiance, this strategy provides a scientific framework to transform urban AHS from traditional productive systems into engaging experiential spaces, ensuring their sustainable conservation.