Improvement of mapping vegetation cover for arid and semiarid areas using a local nonlinear modelling method and landsat images
H. Sun A B C , Q. Wang D , G. X. Wang D F , P. Luo E and F. G. Jiang A B C
+ Author Affiliations
- Author Affiliations
A Research Centre of Forestry Remote Sensing and Information Engineering, Central South University of Forestry and Technology, Changsha 410004, Hunan, China.
B Key Laboratory of Forestry Remote Sensing Based Big Data and Ecological Security for Hunan Province, Changsha 410004, Hunan, China.
C Key Laboratory of National Forestry and Grassland Administration on Forest Resources Management and Monitoring in Southern Area, Changsha 410004, China.
D Department of Geography and Environmental Resources, Southern Illinois University, Carbondale, IL, USA.
E Research Institute of Forest Resources Information Technique, Chinese Academy of Forestry, Beijing, 100091, China.
F Corresponding author. Email: gxwang@siu.edu
The Rangeland Journal 42(3) 161-169 https://doi.org/10.1071/RJ19081
Submitted: 21 November 2019 Accepted: 15 September 2020 Published: 29 October 2020
Abstract
Accurately estimating and mapping vegetation cover for monitoring land degradation and desertification of arid and semiarid areas using remotely sensed images is promising but challenging in remote, sparsely vegetated and large areas. In this study, a novel method – geographically weighted logistic regression (GWLR – integrating geographically weighted regression (GWR) and a logistic model) was proposed to improve vegetation cover mapping of Kangbao County, Hebei of China using Landsat 8 image and field data. Additionally, a new method to determine the bandwidth of GWLR is presented. Using cross-validation, GWLR was compared with a globally linear stepwise regression (LSR), a local linear modelling method GWR and a nonparametric method, k-nearest neighbours (kNN) with varying numbers of nearest plots. Results demonstrated (1) the red and near infrared relevant band ratios and vegetation indices significantly improved mapping; (2) the GWLR, GWR and kNN methods led to more accurate predictions than LSR; (3) GWLR reduced overestimations and underestimations compared with LSR, kNN and GWR, and also eliminated negative and very large estimates caused by GWR and LSR; and (4) The maximum distance of spatial autocorrelation could be used to determine the bandwidth for GWLR. Overall, GWLR proved more promising for mapping vegetation cover of arid and semiarid areas.
Keywords: accurate estimation, desertification, geographically weighted logistic regression, Kangbao County, land degradation, northern China, remote sensing, spatial variability, vegetation cover.
References
Archibald, S., Roy, D. P., Wilgen, B. W. V., and Scholes, R. J. (2009). What limits fire? An examination of drivers of burnt area in southern Africa. Global Change Biology 15, 613–630.| What limits fire? An examination of drivers of burnt area in southern Africa.Crossref | GoogleScholarGoogle Scholar |
Atkinson, P. M., German, S. E., Sear, D. A., and Clark, M. J. (2003). Exploring the relations between riverbank erosion and geomorphological controls using geographically weighted logistic regression. Geographical Analysis 35, 58–82.
| Exploring the relations between riverbank erosion and geomorphological controls using geographically weighted logistic regression.Crossref | GoogleScholarGoogle Scholar |
Diouf, A., and Lambin, E. F. (2001). Monitoring land-cover changes in semi-arid regions: remote sensing data and field observations in the Ferlo, Senegal. Journal of Arid Environments 48, 129–148.
| Monitoring land-cover changes in semi-arid regions: remote sensing data and field observations in the Ferlo, Senegal.Crossref | GoogleScholarGoogle Scholar |
Dubovyk, O., Menz, G., Conrad, C., Kan, E., Machwitz, M., and Khamzina, A. (2013). Spatio-temporal analyses of cropland degradation in the irrigated lowlands of Uzbekistan using remote-sensing and logistic regression modelling. Environmental Monitoring and Assessment 185, 4775–4790.
| Spatio-temporal analyses of cropland degradation in the irrigated lowlands of Uzbekistan using remote-sensing and logistic regression modelling.Crossref | GoogleScholarGoogle Scholar | 23054271PubMed |
Dymond, J. R., Stephens, P. R., Newsome, P. F., and Wilde, R. H. (1992). Percentage vegetation cover of a degrading rangeland from SPOT. International Journal of Remote Sensing 13, 1999–2007.
| Percentage vegetation cover of a degrading rangeland from SPOT.Crossref | GoogleScholarGoogle Scholar |
Fleming, A. L., Wang, G., and Mcroberts, R. E. (2015). Comparison of methods toward multi-scale forest carbon mapping and spatial uncertainty analysis: combining national forest inventory plot data and landsat TM images. European Journal of Forest Research 134, 125–137.
| Comparison of methods toward multi-scale forest carbon mapping and spatial uncertainty analysis: combining national forest inventory plot data and landsat TM images.Crossref | GoogleScholarGoogle Scholar |
Halperin, J., Lemay, V., Coops, N., Verchot, L., Marshall, P., and Lochhead, K. (2016). Canopy cover estimation in miombo woodlands of Zambia: comparison of landsat 8 OLI versus RapidEye imagery using parametric, nonparametric, and semiparametric methods. Remote Sensing of Environment 179, 170–182.
| Canopy cover estimation in miombo woodlands of Zambia: comparison of landsat 8 OLI versus RapidEye imagery using parametric, nonparametric, and semiparametric methods.Crossref | GoogleScholarGoogle Scholar |
Ishiyama, T., Nakajima, Y., Kajiwara, K., and Tsuchiya, K. (1997). Extraction of vegetation cover in an arid area based on satellite data. Advances in Space Research 19, 1375–1378.
| Extraction of vegetation cover in an arid area based on satellite data.Crossref | GoogleScholarGoogle Scholar |
Jenson, J. R. (2016). ‘Introductory Digital Image Processing: A Remote Sensing Perspective,’ 4th edn. (Pearson: Upper Saddle River, NJ, USA.)
Jia, K., Liang, S., Gu, X., Baret, F., Wei, X., Wang, X., and Li, Y. (2016). Fractional vegetation cover estimation algorithm for Chinese GF-1 wide field view data. Remote Sensing of Environment 177, 184–191.
| Fractional vegetation cover estimation algorithm for Chinese GF-1 wide field view data.Crossref | GoogleScholarGoogle Scholar |
Jiang, M., Zhang, X., and Tong, Q. (2009). Monitoring and Evaluation of Desertification in Shihezi Area Using Landsat TM Imagery. In: ‘Proceedings SPIE 7471, Second International Conference on Earth Observation for Global Changes, 74710Q’. 9 October 2009, Chengdu China. https://doi.org/10.1117/12.836605.
Karnieli, A., Gilad, U., Ponzet, M., Svoray, T., Mirzadinov, R., and Fedorina, O. (2008). Assessing land-cover change and degradation in the central Asian deserts using satellite image processing and geostatistical methods. Journal of Arid Environments 72, 2093–2105.
| Assessing land-cover change and degradation in the central Asian deserts using satellite image processing and geostatistical methods.Crossref | GoogleScholarGoogle Scholar |
Keshkamat, S. S., Tsendbazar, N. E., Zuidgeest, M. H. P., Shiirev-Adiya, S., Van, V. A., and Van Maarseveen, M. F. A. M. (2013). Understanding transportation-caused rangeland damage in Mongolia. Journal of Environmental Management 114, 433–444.
| Understanding transportation-caused rangeland damage in Mongolia.Crossref | GoogleScholarGoogle Scholar | 23192175PubMed |
McRoberts, R. E., Næsset, E., and Gobakken, T. (2015). Optimizing the k-nearest neighbors technique for estimating forest aboveground biomass using airborne laser scanning data. Remote Sensing of Environment 163, 13–22.
| Optimizing the k-nearest neighbors technique for estimating forest aboveground biomass using airborne laser scanning data.Crossref | GoogleScholarGoogle Scholar |
Nicholson, S. E., Davenport, M. L., and Malo, A. R. (1990). A comparison of the vegetation response to rainfall in the Sahel and East Africa, using normalized difference vegetation index from NOAA AVHRR. Climatic Change 17, 209–241.
| A comparison of the vegetation response to rainfall in the Sahel and East Africa, using normalized difference vegetation index from NOAA AVHRR.Crossref | GoogleScholarGoogle Scholar |
Nordberg, M. L., and Evertson, J. (2005). Vegetation index differencing and linear regression for change detection in a Swedish mountain range using landsat TM® and ETM+® imagery. Land Degradation & Development 16, 139–149.
| Vegetation index differencing and linear regression for change detection in a Swedish mountain range using landsat TM® and ETM+® imagery.Crossref | GoogleScholarGoogle Scholar |
Ogneva-Himmelberger, Y., Pearsall, H., and Rakshit, R. (2009). Concrete evidence and geographically weighted regression: a regional analysis of wealth and the land cover in Massachusetts. Applied Geography 29, 478–487.
| Concrete evidence and geographically weighted regression: a regional analysis of wealth and the land cover in Massachusetts.Crossref | GoogleScholarGoogle Scholar |
Paz-Kagan, T., Ohana-Levi, N., Herrmann, I., Zaady, E., Henkin, Z., and Karnieli, A. (2016). Grazing intensity effects on soil quality: a spatial analysis of a Mediterranean grassland. Catena 146, 100–110.
| Grazing intensity effects on soil quality: a spatial analysis of a Mediterranean grassland.Crossref | GoogleScholarGoogle Scholar |
Qi, J. G., Chehbouni, A. R., Huete, A. R., Kerr, Y. H., and Sorooshian, S. (1994). A modified soil adjusted vegetation index. Remote Sensing of Environment 48, 119–126.
| A modified soil adjusted vegetation index.Crossref | GoogleScholarGoogle Scholar |
Rayegani, B., Barati, S., Sohrabi, T. A., and Sonboli, B. (2016). Remotely sensed data capacities to assess soil degradation. The Egyptian Journal of Remote Sensing and Space Sciences 19, 207–222.
| Remotely sensed data capacities to assess soil degradation.Crossref | GoogleScholarGoogle Scholar |
Reynolds, J. F., Smith, D. M. S., Lambin, E. F., Turner, B. L., Mortimore, M., Batterbury, S. P., and Huber-Sannwald, E. (2007). Global desertification: building a science for dryland development. Science 316, 847–851.
| Global desertification: building a science for dryland development.Crossref | GoogleScholarGoogle Scholar | 17495163PubMed |
Saefuddin, A., Setiabudi, N. A., and Fitrianto, A. (2012). On comparison between logistic regression and geographically weighted logistic regression: with application to Indonesian poverty data. World Applied Sciences Journal 19, 205–210.
Schucknecht, A., Erasmi, S., Niemeyer, I., and Matschullat, J. (2013). Assessing vegetation variability and trends in north-eastern Brazil using AVHRR and MODIS NDVI time series. European Journal of Remote Sensing 46, 40–59.
| Assessing vegetation variability and trends in north-eastern Brazil using AVHRR and MODIS NDVI time series.Crossref | GoogleScholarGoogle Scholar |
Shao, J. (1993). Linear model selection by cross-validation. Journal of the American Statistical Association 88, 486–494.
| Linear model selection by cross-validation.Crossref | GoogleScholarGoogle Scholar |
Sun, D., Dawson, R., Li, H., and Li, B. (2005). Modelling desertification change in Minqin county, China. Environmental Monitoring and Assessment 108, 169–188.
| Modelling desertification change in Minqin county, China.Crossref | GoogleScholarGoogle Scholar | 16160785PubMed |
Sun, H., Qie, G., Wang, G., Tan, Y., Li, J., Peng, Y., and Luo, C. (2015). Increasing the accuracy of mapping urban forest carbon density by combining spatial modelling and spectral unmixing analysis. Remote Sensing 7, 15114–15139.
| Increasing the accuracy of mapping urban forest carbon density by combining spatial modelling and spectral unmixing analysis.Crossref | GoogleScholarGoogle Scholar |
Tomppo, E. O., Gagliano, C., Natale, F. D., Katila, M., and Mcroberts, R. E. (2009). Predicting categorical forest variables using an improved k-nearest neighbour estimator and landsat imagery. Remote Sensing of Environment 113, 500–517.
| Predicting categorical forest variables using an improved k-nearest neighbour estimator and landsat imagery.Crossref | GoogleScholarGoogle Scholar |
Wang, G., Murphy, D., Oller, A., Howard, H. R., Anderson, A. B., Rijal, S., and Woodford, P. (2014). Spatial and temporal assessment of cumulative disturbance impacts due to military training, burning, haying, and their interactions on land condition of fort riley. Environmental Management 54, 51–66.
| Spatial and temporal assessment of cumulative disturbance impacts due to military training, burning, haying, and their interactions on land condition of fort riley.Crossref | GoogleScholarGoogle Scholar | 24817335PubMed |
White, K., Pontius, J., and Schaberg, P. (2014). Remote sensing of spring phenology in northeastern forests: a comparison of methods, field metrics and sources of uncertainty. Remote Sensing of Environment 148, 97–107.
| Remote sensing of spring phenology in northeastern forests: a comparison of methods, field metrics and sources of uncertainty.Crossref | GoogleScholarGoogle Scholar |
Zhou, J., Zhang, N., and Li, T. (2015). Monitoring Dynamics of Forest Land for the Ba-Shang Area of Hebei Using MODIS Images and Random Forest. Available at: http://xbna.pku.edu.cn/fileup/0479-8023/HTML/2018-4-792.html (accessed 23 July 2020).
