Land cover mapping based on time‐series MODIS‐NDVI using a dynamic time warping approach: A casestudy of the agricultural pastoral ecotone of northern China

Abstract

To curb land degradation, a series of ecological restoration projects have been carried out since 1999, leading to dramatic land cover change (LCC) in the agricultural pastoral ecotone of northern China (APENC). To date, there is still lack of timely and accurate land cover (LC) information for management and assessment actions. This paper presents a LC mapping scheme to map annual LC information based on dynamic time warping (DTW) approach and time‐series MODIS‐NDVI product for the APENC. The DTW approach was optimized firstly based on the change of vegetation phenology phase. Next, typical reference time‐series curves set of different LC types were established and pixel‐wise similarity was examined to identify the LC type. Before that, the reconstruction of time‐series MODIS‐NDVI was performed using harmonic analysis of time‐series and reconstruction accuracy was evaluated quantitatively at a regional scale. Results showed that the gap error was relatively large for the high vegetation cover areas while it might be ignored for the moderate and low vegetation cover areas. The overall accuracy of LC mapping in year 2010 (LC‐2010) was 77.89% and kappa coefficient reached 0.71, which suggested that LC mapping scheme could extract LC information with high accuracy. The producer's accuracy ranged between 69.83% (grasslands) and 100% (water body), while the user's accuracy changed from 58% (built‐up) to 86% (forest). The overall spatial agreement between LC‐2010 and GlobaLand30‐2010 was about 64.44%. The total area of forests, croplands, water body and built‐up exhibited an increasing trend while the contrary trend were found for the grasslands and bare land during the 2001–2017. These LC maps are valuable for research the land degradation investigation and monitoring, benefit evaluation of ecological restoration projects and effect of LCC on surface hydrothermal process in APENC.

Exploring the nexus between land use land cover (LULC) changes and population growth in a planned city of islamabad and unplanned city of Rawalpindi, Pakistan

“…The continuous rise in built-up class of the city was attributed to the growth/expansion of residential spaces, development of new housing societies/colonies, construction of industrial units, road and street pavement network, and business hub for commercial activities [ 29 , 95 ]. The development of built-up class put pressure mainly on bare land and vegetation classes, similar trend was reported by other studies [ 96 , 99 , 100 ]. The Built-up class showed a continuous positive increase from 5.7% (1990) to 25.7% (2021).The driving factors identified for increase in built-up class are population growth, migration, better economic opportunities and new housing societies (both public and private) [ 97 ] and industrial development.…”

“…Vegetation class shown a positive increment from 50.2% (1990) to 54.9% (2021), according to Ref. [ 96 ] grass land was increased by from 2010 to 2018. The increase in vegetation cover is due to the afforestation practices by both public and private communities.…”

Monitoring landcover change and desertification processes in northern China and Mongolia using historical written sources and vegetation indices

“…For the period MAM, four images/month were assigned to each point and plotted with a locally estimated scatterplot smoother to visualize trends in physical plant conditions during the growing season in Inner Mongolia. September images range from the 6 th to the 13 th and the 5 th to the 12 th of the month (Kawamura et al, 2005;Wang et al, 2019a;Wei et al, 2020;Zhou et al, 2017). The section covering the 45 regular points was cross validated with 127 regular points covering the entire extent of the MODIS scene over September 2000-2018.…”

“…Landsat-OLI-8 and MODIS hyperspectral imagery were used to monitor vegetation canopy changes and surface transformations linked to climate change and anthropogenic overstraining. Vegetation indices of subsequent months and years and on various spatial scales allow for temporal in-depth observations of physical plant behaviour or drought periods and are a common tool in remote sensing of ecological and climatic processes (Fensholt and Proud, 2012;Gu et al, 2009;Kempf and Glaser, 2020;Ren et al, 2018;Wei et al, 2020). A set of cloud-free Landsat-8 images spanning the period May-October 2013-2020 shows the monthly differentiation of vegetation cover in the study area (Fig.…”

Documentary Evidence of 17th Century Landcover and Climate Change in Northern China and Mongolia Compared to Modern Spectral Greening Trends

“…Modern NDVI time series were used to monitor vegetation canopy changes and surface transformations linked to climate change and anthropogenic overstraining. Vegetation indices of subsequent months and years and on various spatial scales allow for temporal in-depth observations of physical plant behavior or drought periods and are a common tool in remote sensing of ecological and climatic processes [92][93][94][95][96][97]. As derived from the Copernicus landcover data and the aridity index, the north-western parts of China and Mongolia reveal significantly low plant physiological activity and bare and sandy areas.…”