Combining Machine Learning and Remote Sensing for Online Environmental Quality Monitoring and Cause Analysis in Xiamen, China

Honghui Yang; Weizhen Xu; Zhengyan Chen; Jiao Yu

doi:10.62051/eytk3z12

Authors

Honghui Yang
Weizhen Xu
Zhengyan Chen
Jiao Yu

DOI:

https://doi.org/10.62051/eytk3z12

Keywords:

Machine learning; remote sensing; environmental monitoring; RSEI; SHAP.

Abstract

This study focuses on Xiamen, China, and uses the Google Earth Engine (GEE) platform to calculate the city's Remote Sensing Ecological Index (RSEI) from 2000 to 2020, analyzing the temporal and spatial changes in environmental quality. Additionally, it integrates the eXtreme Gradient Boosting (XGBoost) model and SHapley Additive exPlanations (SHAP) algorithms to analyze the driving factors affecting changes in the environmental quality of Xiamen. The results of the study show that: (1) From 2000 to 2020, the environmental quality in Xiamen City showed a trend of "first increase and then decrease", with the average value of RSEI increasing from 0.55 to 0.57 and then slightly decreasing to 0.56. (2) During 2000 to 2020, the majority of Xiamen's environment quality improved, covering 44.75% of the area. However, regions where the environment deteriorated were primarily located along the coast in Jimei district and Xiang'an district, accounting for 32.58% of the total area. (3) Elevation, slope, percentage of construction area, annual average precipitation, and percentage of cropland area are the five factors with the greatest impact on environmental quality. The effects of elevation and slope on environmental quality exhibit a quadratic function relationship, while percentage of construction area, annual average precipitation, and percentage of cropland area show linear relationships.

Downloads

Download data is not yet available.

References

[1] Y. Xu, Q. Dai, Y. Lu, C. Zhao, W. Huang, M. Xu, and Y. Feng, "Identification of ecologically sensitive zones affected by climate change and anthropogenic activities in Southwest China through a NDVI-based spatial-temporal model," Ecological Indicators, vol. 158, Art. no. 111482, January 2024.

[2] W. Xu, J. Song, Y. Long, R. Mao, B. Tang, and B. Li, "Analysis and simulation of the driving mechanism and ecological effects of land cover change in the Weihe River basin, China," Journal of Environmental Management, vol. 344, Art. no. 118320, October 2023.

[3] J. C. Jimenez-Munoz, J. Cristobal, J. A. Sobrino, G. Sòria, M. Ninyerola, and X. Pons, "Revision of the single-channel algorithm for land surface temperature retrieval from Landsat thermal-infrared data," IEEE Transactions on geoscience and remote sensing, vol. 47, pp. 339-349, January 2008.

[4] J. Teng, S. Xia, Y. Liu, X. Yu, H. Duan, H. Xiao, and C. Zhao, "Assessing habitat suitability for wintering geese by using Normalized Difference Water Index (NDWI) in a large floodplain wetland, China," Ecological Indicators, vol. 122, Art. no. 107260, March 2021.

[5] H. Yang, J. Yu, W. Xu, Y. Wu, X. Lei, J. Ye, J. Geng, and Z. Ding, "Long-time series ecological environment quality monitoring and cause analysis in the Dianchi Lake Basin, China," Ecological Indicators, vol. 148, Art. no. 110084, April 2023.

[6] S. Li, C. Liu, C. Ge, J. Yang, Z. Liang, X. Li, and X. Cao, "Ecosystem health assessment using PSR model and obstacle factor diagnosis for Haizhou Bay, China," Ocean & Coastal Management, vol. 250, Art. no. 107024, April 2024.

[7] X. Hu, C. Ma, P. Huang, and X. Guo, "Ecological vulnerability assessment based on AHP-PSR method and analysis of its single parameter sensitivity and spatial autocorrelation for ecological protection–A case of Weifang City, China," Ecological Indicators, vol. 125, Art. no. 107464, June 2021.

[8] P. Zhang, H. Xu, Q. Du, H. Ling, P. Zhang, and X. Zhao, "Ecological environment assessment of Tarim River main stream based on RS and GIS," Arid Zone Research, vol. 34, pp. 416-422, April 2017.

[9] Z. Zheng, Z. Wu, Y. Chen, C. Guo, and F. Marinello, "Instability of remote sensing based ecological index (RSEI) and its improvement for time series analysis," Science of the Total Environment, vol. 814, Art. no. 152595, March 2022.

[10] H. Xu, "A remote sensing index for assessment of regional ecological changes," China Environmental Science, vol. 33, pp. 889-897, May 2013.

[11] H. Yang, W. Xu, J. Yu, X. Xie, Z. Xie, X. Lei, Z. Wu, and Z. Ding, "Exploring the impact of changing landscape patterns on ecological quality in different cities: A comparative study among three megacities in eastern and western China," Ecological Informatics, vol. 77, Art. no. 102255, November 2023.

[12] Y. Zhang, J. She, X. Long, and M. Zhang, "Spatio-temporal evolution and driving factors of eco-environmental quality based on RSEI in Chang-Zhu-Tan metropolitan circle, central China," Ecological Indicators, vol. 144, Art. no. 109436, November 2022.

[13] C. Gong, F. Lyu and Y. Wang, "Spatiotemporal change and drivers of ecosystem quality in the Loess Plateau based on RSEI: A case study of Shanxi, China," Ecological Indicators, vol. 155, Art. no. 111060, November 2023.

[14] Z. Cao, M. Wu, D. Wang, B. Wan, H. Jiang, X. Tan, and Q. Zhang, "Space-time cube uncovers spatiotemporal patterns of basin ecological quality and their relationship with water eutrophication," Science of The Total Environment, vol. 916, Art. no.170195, March 2024.

[15] Z. Cai, Z. Zhang, F. Zhao, X. Guo, J. Zhao, Y. Xu, and X. Liu, "Assessment of eco-environmental quality changes and spatial heterogeneity in the Yellow River Delta based on the remote sensing ecological index and geo-detector model," Ecological Informatics, vol. 77, Art. no. 102203, November 2023.

[16] Y. Lv, L. Xiu, X. Yao, Z. Yu, and X. Huang, "Spatiotemporal evolution and driving factors analysis of the eco-quality in the Lanxi urban agglomeration," Ecological Indicators, vol. 156, Art. no. 111114, December 2023.

[17] X. Zhang, W. Jia and J. He, "Spatial and temporal variation of ecological quality in northeastern China and analysis of influencing factors," Journal of Cleaner Production, vol. 423, Art. no. 138650, October 2023.

[18] F. Wang, F. Wang, H. Yang, J. Yu, and R. Ni, "Ecological risk assessment based on soil adsorption capacity for heavy metals in Taihu basin, China," Environmental Pollution, vol. 316, Art. no. 120608, January 2023.

[19] Y. Yang, M. Shi, B. Liu, Y. Yi, J. Wang, and H. Zhao, "Contribution of ecological restoration projects to long-term changes in PM2. 5," Ecological Indicators, vol. 159, Art. no. 111630, February 2024.

[20] X. Ma, J. Zhang, P. Wang, L. Zhou, and Y. Sun, "Estimating the nonlinear response of landscape patterns to ecological resilience using a random forest algorithm: Evidence from the Yangtze River Delta," Ecological Indicators, vol. 153, Art. no. 110409, September 2023.

[21] J. Wan and T. Fei, "Production-Living-Ecological Spaces" Recognition Methods based on Street View Images," Journal of Geo-information Science, vol. 25, pp. 838-851, April 2023.

[22] S. M. Lundberg and S. Lee, "A unified approach to interpreting model predictions," in Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA, 2017, pp. 4768-4777.

[23] S. Wang, and H. Peng, " Multiple spatio-temporal scale runoff forecasting and driving mechanism exploration by K-means optimized XGBoost and SHAP," Journal of Hydrology, vol. 630, Art. no. 130650, January 2024.

[24] X. Liu, J. Zeng and P. Zeng, "Construction and Optimization of the Green Space Ecological Network in Xiamen City," Chinese Landscape Architecture, vol. 36, pp. 76-81, July 2020.

[25] J. Yang and X. Huang, "30 m annual land cover and its dynamics in China from 1990 to 2019," Earth System Science Data Discussions, vol. 2021, pp. 1-29, Augest 2021.

[26] C. Song, B. Huang and S. You, "Comparison of three time-series NDVI reconstruction methods based on TIMESAT," in Geoscience and Remote Sensing Symposium (IGARSS), 2012 IEEE International. IEEE, 2012, pp. 2225-2228.

[27] E. P. Crist, "A TM tasseled cap equivalent transformation for reflectance factor data," Remote sensing of Environment, vol. 17, pp. 301-306, June 1985.

[28] H. Xu, "A new index for delineating built‐up land features in satellite imagery," International journal of remote sensing, vol. 29, pp. 4269-4276, October 2008.

[29] J. A. Sobrino, J. C. Jiménez-Muñoz and L. Paolini, "Land surface temperature retrieval from LANDSAT TM 5," Remote Sensing of environment, vol. 90, pp. 434-440, April 2004.

[30] S. M. Lundberg, G. Erion, H. Chen, A. DeGrave, J. M. Prutkin, B. Nair, R. Katz, J. Himmelfarb, N. Bansal, and S. Lee, "From local explanations to global understanding with explainable AI for trees," Nature machine intelligence, vol. 2, pp. 56-67, January 2020.

[31] Z. Chen, H. Yang, Y. Lin, J. Xie, Y. Xie, and Z. Ding, "Exploring the association between the built environment and positive sentiments of tourists in traditional villages in Fuzhou, China," Ecological Informatics, vol. 80, Art. no. 102465, May 2024.

[32] A. Mohammat, X. Wang, X. Xu, L. Peng, Y. Yang, X. Zhang, R. B. Myneni, and S. Piao, "Drought and spring cooling induced recent decrease in vegetation growth in Inner Asia," Agricultural and Forest Meteorology, vol. 178, pp. 21-30, September 2013.

[33] B. Yuan, L. Fu, Y. Zou, S. Zhang, X. Chen, F. Li, Z. Deng, and Y. Xie, "Spatiotemporal change detection of ecological quality and the associated affecting factors in Dongting Lake Basin, based on RSEI," Journal of Cleaner Production, vol. 302, Art. no. 126995, June 2021.