Evaluation of soil rocky desertification in Karst region based on deep belief network

• Autorzy: Lu Guan-Yao , Xu Dan , Meng Yue

Identyfikatory

DOI

10.2478/eces-2023-0016

• Języki publikacji: EN

Abstrakty

EN

Dynamic features from remote sensing photos may be successfully extracted using deep learning and symmetric network structure, which can then be used to direct them to carry out accurate classification. The DBN model can more effectively extract features from photos since it uses unsupervised learning. It can be reduced to the many symmetric Restricted Boltmann Machines (RBM) training problem. In this paper, a soil rocky desertification (RD) assessment model based on a deep belief network (DBN) is created in light of the complicated influencing aspects of Karst RD risk assessment encompassing several geographical elements. The model builds upon the conventional RBM framework and incorporates the influence layer of related elements as an auxiliary requirement for retrieving Geographic Information System (GIS) score data. Then, in order to forecast the level of soil rocky desertification, it learns the features of many elements. The experimental results show that the proposed model proposed in this paper has better prediction performance and faster convergence speed, and its classification results for different degrees of RD are more consistent with the actual risk assessment results.

Słowa kluczowe

EN

karst regions; rocky desertification; deep belief network; DBN; geographic information system; GIS

PL

regiony krasowe; pustynnienie; skały; DBN; system informacji geograficznej; GIS

• Wydawca: Towarzystwo Chemii i Inżynierii Ekologicznej
• Czasopismo: Ecological Chemistry and Engineering. S
• Rocznik: 2023
• Tom: Vol. 30, nr 2
• Strony: 167--173
• Opis fizyczny: Bibliogr. 13 poz., tab.

Twórcy

autor

Lu Guan-Yao

• School of Environmental and Chemical Engineering, Foshan University, Foshan, 528000, Guangdong, China

• https://orcid.org/0000-0002-4559-2156

autor

Xu Dan

• School of Environmental and Chemical Engineering, Foshan University, Foshan, 528000, Guangdong, China

• https://orcid.org/0000-0002-9948-7917

autor

Meng Yue

• School of Environmental and Chemical Engineering, Foshan University, Foshan, 528000, Guangdong, China

• https://orcid.org/0000-0003-2623-3657

Bibliografia

• [1] Wu CH, Tsai SB, Liu W, Shao XF, Sun R, Wacławek M. Eco-technology and eco-innovation for green sustainable growth. Ecol Chem Eng S. 2021;28(1):7-10. DOI: 10.2478/eces-2021-0001.
• [2] Wu CH. An empirical study on discussion and evaluation of green university. Ecol Chem Eng S. 2021;28(1):75-87. DOI: 10.2478/eces-2021-0007.
• [3] Liao SJ, Wu Y, Wong SW, Shen LY. Provincial perspective analysis on the coordination between urbanization growth and resource environment carrying capacity (RECC) in China. Sci Total Environ. 2020;730:138964. DOI: 10.1016/j.scitotenv.2020.138964.
• [4] Dharumarajan S, Veeramani S, Suputhra A, Parmar M, Kalaiselvi B, Lalitha M, et al. Remote sensing sensors and recent techniques in desertification and land degradation mapping - a review. Adv Understanding Soil Degradation. 2022;701-16. DOI: 10.1007/978-3-030-85682-3_32.
• [5] Wang HF, Liu YL, Zhang GX, Wang YH, Zhao J. Multi-scenario simulation of urban growth under integrated urban spatial planning: a case study of Wuhan, China. Sustainability. 2021;13(20):11279. DOI: 10.3390/su132011279.
• [6] Wu XP, Zhou ZF, Zhu M, Huang DH, Zhu CL, Feng Q, et al. Study on the coupling relationship between relocation for poverty alleviation and spatiotemporal evolution of rocky desertification in karst areas of Southwest China. Sustainability. 2022;14(13):8037. DOI: 10.3390/su14138037.
• [7] Peng XD, Dai QH, Ding GJ, Li CL. Role of underground leakage in soil, water and nutrient loss from a rock-mantled slope in the karst rocky desertification area. J Hydrology. 2019;578:124086. DOI: 10.1016/j.jhydrol.2019.124086.
• [8] Hou WJ, Gao J. Spatially variable relationships between Karst landscape pattern and vegetation activities. Remote Sensing. 2020;12(7):1134. DOI: 10.3390/rs12071134.
• [9] He SY, Xiong KN, Song SZ, Chi YK, Fang JZ, He C. Research progress of grassland ecosystem structure and stability and inspiration for improving its service capacity in the Karst desertification control. Plants. 2023;12(4):770. DOI: 10.3390/plants12040770.
• [10] Liao SB, Cai H, Tian PJ, Zhang BB, Li YP. Combined impacts of the abnormal and urban heat island effect in Guiyang, a typical Karst Mountain City in China. Urban Climate. 2022;41:101014. DOI: 10.1016/j.uclim.2021.101014.
• [11] Pu JW, Zhao XQ, Huang P, Gu ZX, Shi XQ, Chen YJ, et al. Ecological risk changes and their relationship with exposed surface fraction in the karst region of southern China from 1990 to 2020. J Environ Manage. 2022;323:116206. DOI: 10.1016/j.jenvman.2022.116206.
• [12] Liu QW, Xiang XQ, Wang YF, Luo ZW, Fang F. Aircraft detection in remote sensing image based on corner clustering and deep learning. Eng Applications Artificial Intelligence. 2020;87:103333. DOI: 10.1016/j.engappai.2019.103333.
• [13] Zhao ZC, Li JQ, Luo Z, Li J, Chen C. Remote sensing image scene classification based on an enhanced attention module. IEEE Geosci Remote Sensing Lett. 2020;18(11):1926-30. DOI: 10.1109/LGRS.2020.3011405.

Uwagi

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).