The extraction of urban cognizable synergistic features could be regarded as a form of dimensionality reduction in 23 X factors. Therefore, we compared urban cognizable features with the results of a principal component analysis, which is a widely used technique in machine learning (Monedero et al. 2019). There were 6 principal components, which all contained no more than 2 factors (Table S3). However, we could not give definite practical meaning to the principal components, which meant that the extraction of urban cognizable features has unique advantages as a new dimensionality reduction method.
Conclusion
The study proposed deep learning as a new, more effective approach to understanding the patterns, dynamics, and driving factors of ESV that are crucial for coping with sustainability challenges. The findings of the model analysis suggested that underlying social and economic conditions presumably influence regional ecological functions through ESV.
Regarding Nanjing City, although the outputs of the 1st, 2nd and 3rdindustries all showed a decreasing trend in ESV, the “2nd industry output value” had the highest influence intensity, indicating the urgency and necessity of controlling its proportion. We propose that economic development, urbanization, and tourism should be further accelerated and enhanced in Nanjing, because “GDP”, “light index”, “tourism output” and “residential electricity consumption” all have positive influences on ESV. In addition, there should be singleness in the urban function, which means that city space needs to be separated to serve different functions. The extraction of high-level urban cognizable factors related to ESV in the penultimate layer may be a new dimensionality reduction method, and the analysis suggested that the city scale of Nanjing can truly affect the ESV. As a result, it is possible for decision-makers to provide policy guidance and adjust urban features to realize the coordinated development of the regional economy and ecological functions. For instance, the most suitable city scale can be found that is within the regional ecological carrying capacity.
In this work, the relationship between human socioeconomic development and ESV on the urban scale is at the heart of our research. We built a deep learning model based on the limited socioeconomic factors (X) to cognize it and obtained interesting and meaningful results. Furthermore, our point of view is that there are likely to be obvious differences in the driving mechanisms under diverse regional and scale contexts. Therefore, an important direction for further research is the investigation of more influence patterns and mechanisms on diverse spatial scales and levels of socioeconomic development affecting the change in regional ESV.
Acknowledge
This work was supported by the Environmental Protection Research Project of Jiangsu Province(No. 2018008)and the Environmental Science and Technology Project of Nanjing(No.201904). The authors thank Prof. Jiangang Xu for valuable comments and discussion.
References
Alcamo, J. (2003). Ecosystems and human well-being: A framework for assessment. Ecosystems and human well-being: A framework for assessment . Island Press, Washington, DC, USA.
Barbier, E.B., Hacker, S.D., Kennedy, C., Koch, C., Stier, A. & Silliman, B.R. (2011). The value of estuarine and coastal ecosystem services. Ecol Monogr 81 : 169-193.
Billé, R., Laurans, Y., Mermet, L., Priard, R. & Rankovic, A. (2012). Valuation without action? On the use of economic valuations of ecosystem services. IDDRI Policy Brief 7 : 1-4.
Braden, J.B., Feng, X., Freitas, L. & Won, D.H. (2010). Meta-functional transfer of hedonic property values: Application to great lakes areas of concern. ARER 39 : 101-113.
Costanza, R, d’Arge, R., De Groot, R., Farber, S., Hannon, B., Limburg, K., et al. (1997). The value of the world’s ecosystem services and natural capital. Nature 387 : 253.
Harrington, W. & Portney, P.R. (1987). Valuing the benefits of health and safety regulation. J Urban Econ 22 : 101-112.
Hodgkinson, T. & Andresen, M.A. (2019). Changing spatial patterns of residential burglary and the crime drop: The need for spatial data signatures. J Crim Just 61 : 90-100.
Ji, Q., Li, C. & Jones P. (2017). New green theories of urban development in china. Sustain Citie Soc 30 : 248-253.
LeCun, Y., Bengio, Y. & Hinton, G. (2015). Deep learning. Nature521 : 436-444.
Li, B.J., Chen, D.X., Wu, S.H., Zhou, S.L., Wang, T. & Chen, H. (2016). Spatio-temporal assessment of urbanization impacts on ecosystem services: Case study of nanjing city, china. Ecol Indic71 : 416-427.
Meacham, M., Queiroz, C., Norström, A.V. & Peterson, G.D. (2016). Social-ecological drivers of multiple ecosystem services: What variables explain patterns of ecosystem services across the norrström drainage basin? Ecol Soc 21 :14.
Mendelsohn, R. & Olmstead, S. (2009). The economic valuation of environmental amenities and disamenities: Methods and applications.Annu Rev Env Resour 34 : 325-347.
Monedero, D.R., Mezher, A.M., Colomé, X.C., Forné, J. & Soriano, M. (2019). Efficient k-anonymous micro-aggregation of multivariate numerical data via principal component analysis. Inform Sciences503 : 417-443.
Moore, D.W., Booth, P., Alix, A., Apitz, S.E., Forrow, D., Huber-Sannwald, E., et al. (2017). Application of ecosystem services in natural resource management decision making. Integr Environ Assess 13 : 74-84.
Openshaw, S. (1984). Ecological fallacies and the analysis of areal census data. Environ Plann A 16 : 17-31.
Perkins, C. (2017). Reflections on ‘map design for census mapping’. In: Landmarks in mapping. London; New York: Routledge.
Phaneuf, D.J., Smith, V.K., Palmquist, R.B., Pope, J.C. (2008). Integrating property value and local recreation models to value ecosystem services in urban watersheds. Land Econ 84 : 361-381.
Reichstein, M., Camps-Valls, G., Stevens, B., Jung, M., Denzler, J. & Carvalhais, N. (2019). Deep learning and process understanding for data-driven earth system science. Nature 566 : 195-204.
Shi, G., Shan, J., Ding, L., Ye, P., Li, Y. & Jiang, N. (2019). Urban road network expansion and its driving variables: A case study of nanjing city. Int J Env Res Pub He 16 : 2318.
Shiferaw, H., Bewket, W., Alamirew, T., Zeleke, G., Teketay, D., Bekele, K., et al. (2019). Implications of land use/land cover dynamics and prosopis invasion on ecosystem service values in afar region, Ethiopia.Sci Total Environ 675 : 354-366.
Spake, R., Lasseur, R., Crouzat, E., Bullock, J,M., Lavorel, S., Parks, K.E., et al. (2017). Unpacking ecosystem service bundles: Towards predictive mapping of synergies and trade-offs between ecosystem services. Global Environ Chang 47 : 37-50.
Sze, V., Chen, Y.H., Yang, T.J. & Emer, J.S. (2017). Efficient processing of deep neural networks: A tutorial and survey. P IEEE105 : 2295-2329.
Tamayo, N.C.A., Anticamara, J.A. & Acosta-Michlik, L. (2018). National estimates of values of Philippine reefs’ ecosystem services. Ecol Econ 146 : 633-644.
Wei, F., Costanza, R., Dai, Q., Stoeckl, N., Gu, X.D., Farber, S, et al. (2018). The value of ecosystem services from giant panda reserves.Curr Biol 28 : 2174-2180. e7.
Wu, K.Y., Ye, X.Y., Qi, Z.F. & Zhang, H. (2013). Impacts of land use/land cover change and socioeconomic development on regional ecosystem services: The case of fast-growing Hangzhou metropolitan area, china Cities 31 : 276-284.
Yang, Y.Y., Zheng, H., Kong, L.Q., Huang, B.B., Xu, W.H. & Ouyang, Z.Y. (2019). Mapping ecosystem services bundles to detect high-and low-value ecosystem services areas for land use management. J Clean Prod225 : 11-17.
Yu, D. & Seltzer, M.L. (2011). Improved bottleneck features using pretrained deep neural networks. Proceedings of the 12th annual conference of the international speech communication association; 27-31 Aug 2011; Florence.
Yuan, Y.J., Wu, S.H., Yu, Y.N., Tong, G.J., Mo, L.J., Yan, D.H., et al. (2018). Spatiotemporal interaction between ecosystem services and urbanization: Case study of nanjing city, china. Ecol Indic95 : 917-929.