Abstract
This paper develops and applies a novel method for inferring land cover/land use (LCLU) change that combines direct multi-date classification with measures from a change vector analysis. The model predicts change directly rather than the land cover at either time, although these could be inferred. Unsupervised classifications of bi-temporal imagery were manually labeled and used to generate reference data for class-to-class changes. These were used to train a Random Forest model with inputs from the bi-temporal image bands and change vector measures (change vector direction, angle and the spectral angle) and used to generate a predicted surface of land cover change for a case study in the Pearl River Delta, China. The overall accuracy of LCLU change prediction was 96% and specific class-to-class changes had errors rates of 0–12.8%. Some errors were related the semi-automated labeling of the training data. The spectral angle variables and Near Infra-Red image bands for both years were found to be strong predictors of change. Odd ratios were used to quantify regional differences in land cover change rates in urban and peri-urban areas. The regional differences and origins of the observed errors are discussed, along with some areas of further work. The key contributions of this paper are the focus on change rather than LCLU through the construction of a model to predict changes directly and the development of an approach that provides quick, effective and informative analysis of LCLU change in support of policy and planning in rapidly urbanizing areas.
Highlights
Understanding land cover and land use (LCLU) change is important [1,2]
Overall accuracy was found to be 96% which corresponds to the model out of bag (OOB) classification error (4%)
Errors were associated with changes between Vegetation to Fishing Ponds (VG and Fishing ponds (FP)) and Crops (CP) with low and high intensity Impervious Surface (LIS and High-albedo Impervious Surface (HIS))
Summary
Understanding land cover and land use (LCLU) change is important [1,2]. LCLU changes are caused by human activity and natural processes [2,3]. This paper proposes and applies a change vector analysis (CVA) of land cover and land use change It combines direct multi-date classification [5] with CVA measures (magnitude, spectral direction and spectral angle) and with image band reflectance values. This paper reflects a shift in emphasis in current approaches to LCLU monitoring away from a focus of LCLU states towards one of LCLU change processes, inevitably the former are associated with the latter It seeks to quantify change processes and, in so doing, build on approaches and philosophies being applied in large scale land cover inventories [6,7]. The approach is to generate and manually label bi-temporal unsupervised LCLU layers from which reference data are sampled These are used to calculate class-to-class change vectors and image characteristics which are used as inputs to train a classification model. The model is used to predict and label land cover change directly and to quantify rates of urbanization
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
